How We Know · Case 002False independence
When eight research agents agree, how many evidence roots are there?
The claim: Eight research agents agreed, so the answer looked independently corroborated.
Why care: A cited report can look rigorous while its runs, links, and source claims still share one capture program. Counting echoes as witnesses is a direct failure mode for agent-generated research.
encyclopedia finding
The bounded record contains empirical methods for URL resolution and claim-to-source support, but the eight reports reuse overlapping capture, source, method, and derivation lineages. Report agreement alone adds no independent warrant beyond the inspected source record.
If you use this claim
Use a polished cited report as a map into sources, not as a vote count. Check URL resolution and sentence-level support separately.
This bounded 2026 packet does not estimate current or universal agent reliability.
BoundaryEight context-isolated public-by-design reports captured under one frozen prompt, plus the public source editions and exact spans they cited. This historical pilot does not estimate current or universal agent behavior.
The evidence map
How the familiar claim changes under inspection
01 · What looked persuasive
Eight polished reports
The same frozen question produced eight separately captured, citation-rich answers.
02 · What the audit collapsed
Thirty URLs became eleven works
Repeated links and editions were grouped, and run multiplicity received zero automatic independence credit.
03 · What remains
Seven candidates, none confirmed
Thirty-four citation occurrences remain unresolved; the seven warrant candidates still require independent rooting.
Lineage accounting
The units count different things
8captured reportsObservations from one frozen capture program30distinct URL stringsA resolving link is not sentence support11source worksLogical works after edition collapse7candidate warrantsScoped candidates, not independent programs34unresolved citationsVisible and assigned no credit
Shared capture: Unknown provider and retrieval dependencies remain; all reports share the exact prompt and one bounded capture program, so run multiplicity gets zero automatic independence credit.
Warrant boundary: Unknown residual independence remains across task data, judge methods, retrieval, source, edition, span, derivation, and upstream-citation lineages.
Sentence x-ray
What the selected record actually supports
Read the statement first. Its exact work, edition, span, retrieval, digest, and license chain—plus dependence and calculations—remain one disclosure away.
01dependence
This report is a captured observation, not an independent evidence root.
EM-0026 deterministic agent-citation evidence ledger · Captured report V2-SOL-01EM-0026 deterministic agent-citation evidence ledger · Shared capture lineage
Trace this statement
- Relation
relation-v2-sol-01-e7797662c8em:dossier-evidence-relation:sha256:abcc4d174a23391ada839ade500ca01bc54bba21adb6f16b792623606c50cb39- Lineage
lineage-v2-sol-01-a73232acf8em:dossier-lineage:sha256:eaae15e292d35333b3ab5f2629d26645b56eb974d9b94c4be66394ea98adfc6b
02support
In one five-system dermatology-review audit, reference identifiability and metadata correctness did not establish sentence-level claim-citation concordance.
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype · Main text, paragraph beginning 'For their high performances in generating reference lists'Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype · Table 1, ChatGPT all-correct subtotalAssessment of Deep Research for dermatology literature reviews: Deep concern over the hype · main text, paragraph beginning 'For their high performances'; Figure 1Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype · Table 1, ChatGPT subtotalSupplementary materials of the article: Assessment of Deep Research for Dermatology Literature Reviews: Deep Concern Over the Hype · Dataset descriptionAssessment of Deep Research for dermatology literature reviews: Deep concern over the hype · Main text, paragraph beginning 'To address the gap' (search-indexed primary full text)Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype · Main text, following paragraph (search-indexed primary full text)Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype · body, paragraph immediately after Table 1Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype · Paragraph after Table 1
Trace this statement
- Relation
relation-keplinger-metadata-versus-support-c23e105c8bem:dossier-evidence-relation:sha256:cf9857ecb3c92201f72007257a23a62a68c8b655f551d3e62392baef87507e8a- Proposition
prop-keplinger-metadata-versus-support-73dfc141c5em:dossier-proposition:sha256:913134ebeedb4a61c33c6b4c7a61bebb59b5be78daf7424f26f5b14f56ba8283- Assertion
assertion-keplinger-metadata-versus-support-73dfc141c5em:dossier-assertion:sha256:dbab0bf3479337837fb7d341657082207174d8a39ff61d224eb2d5ac228fe8be- Lineage
lineage-keplinger-metadata-versus-support-73dfc141c5em:dossier-lineage:sha256:a46612a0397294b1e58fa90ce5cfacd98ff271164d2a49eb549ee40b26b23225
03support
DeepResearch Bench evaluated binary support for deduplicated statement-URL pairs; numeric values are edition-specific.
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · Evaluation methodology, lines 144-149DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · Table 1, lines 177-182DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · Section 3.2, lines 144-146DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · Table 1, Perplexity Deep Research citation-accuracy cellDeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · page 16, FACT judge validationDeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · Table 1, OpenAI Deep Research row; FACT columnsDeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · page 4, Section 3.2, Support JudgmentAyanami0730/deep_research_bench · README FACT, lines 240-248DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · Section 3.2, paragraphs 'Statement-URL Pair Extraction and Deduplication' and 'Support Judgment'DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · p. 4, lines 150-159DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · Appendix C, line 365DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · page 5, Section 4.1DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · pp.17-18, Appendix E, equations 4-6Ayanami0730/deep_research_bench · README News, 2026-05-11 evaluator migration noticeDeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · p.4, Section 3.2, lines 148-155Ayanami0730/deep_research_bench · README News, lines 176-188DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents · p.17, Appendix C, lines 704-708
Trace this statement
- Relation
relation-deepresearch-bench-fact-a3f61d7a3aem:dossier-evidence-relation:sha256:6adf0bc790adeb0f5b77cd93a3a1e1f7fbf3b4f2cd43d447246cd5c3a1d5afde- Proposition
prop-deepresearch-bench-fact-ab2a1c0fd8em:dossier-proposition:sha256:b476681a6c3ad4658a9fa593caeb6d01207a48f1b4a0fcfd4b9523dfd8dcf46d- Assertion
assertion-deepresearch-bench-fact-ab2a1c0fd8em:dossier-assertion:sha256:7a83bdb7d484e15702c9b201fd817128505788f16fbe8738b028fab0ee45a0f8- Lineage
lineage-deepresearch-bench-fact-ab2a1c0fd8em:dossier-lineage:sha256:e5dca8785a2cf9d98885a01cf163bc158cabd7a6b12008eccc6891009bf32391
04support
DeepTRACE measured statement-source support and found between-system variation; its Gemini value is internally inconsistent between table and prose.
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · page 14, Table 3DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · Abstract, line 46DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · pp.4-7, Sections 3.1.1 and 3.2DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · Section 3.2, lines 163-171DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · Official ICLR abstractDeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · page 4, source scrapingDeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · p.14, Table 3DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · Paper section 3.1.1, factual-support validationDeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · printed page 10; PDF page index 10/22; Section 4 Results; Deep Research Agents paragraphDeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence · printed page 9; PDF page index 9/22; Table 1; Gemini (DR) column; %Citation Accuracy row
Trace this statement
- Relation
relation-deeptrace-support-variation-1a84ef7c6fem:dossier-evidence-relation:sha256:6d44f25458001a3d2b303c223d05f31ec5d47f2a5870083593594141290a3a69- Proposition
prop-deeptrace-support-variation-de1dfdaff3em:dossier-proposition:sha256:06007bbafd55f21604b29a9b70bc781072fe39dfd6bd9078e539581ef49200bb- Assertion
assertion-deeptrace-support-variation-de1dfdaff3em:dossier-assertion:sha256:b041cab9ed6954b90c0160b9679e6b36a6048e41734b20e431c3875574dbaee9- Lineage
lineage-deeptrace-support-variation-de1dfdaff3em:dossier-lineage:sha256:76899e048e8624bdbc295f77eba9d647f354f8bc235d5052ed62e4356ae20a90
05support
Cited but Not Verified operationalized link access, topical relevance, and factual support separately and reported materially different rates.
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents · Section 3.3.1-3.3.3Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents · Abstract, lines 47-48Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents · Abstract and Table 1Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents · Abstract and Table 1Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents · Abstract, lines 45-49Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents · Section 4.4, line 217
Trace this statement
- Relation
relation-cnv-link-relevance-support-gap-165443d270em:dossier-evidence-relation:sha256:64e195a6456aebffbb478b57f1cefbe57b12973371ad65e8360feffcf08eae3d- Proposition
prop-cnv-link-relevance-support-gap-81b86b6d92em:dossier-proposition:sha256:e677a533523393e22cecf616372c9dc369ac1c4e455a851917672f69f59bb4ea- Assertion
assertion-cnv-link-relevance-support-gap-81b86b6d92em:dossier-assertion:sha256:6fa46782b3e3128aca1e97f75cba4846be90f31c236e01ed2968ef92ac7c1378- Lineage
lineage-cnv-link-relevance-support-gap-81b86b6d92em:dossier-lineage:sha256:ca155e4894daf1886d38f9d2e13d1757164295ffc0315af008cef7f895d71cbf
06support
The URL-health study measured HTTP resolution and Wayback presence, not semantic claim support, on outputs including reused DeepResearch Bench material.
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents · pp. 1-2, lines 64-95Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents · page 3, Section 3.3Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents · Section 3.3 'URL extraction and classification'Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents · Section 3 Experimental setup; Section 3.1 Datasets; section#S3.SS1; paragraph p#S3.SS1.p1.1
Trace this statement
- Relation
relation-url-health-resolution-0b26fb45c7em:dossier-evidence-relation:sha256:fd5741fb1196a75091a20a03b6e903c1fdc7e338c94d9f366d8cec6caf3613fe- Proposition
prop-url-health-resolution-9fcccc534aem:dossier-proposition:sha256:06ffd95abe646fb91cec30d455f3bbb9fb44f6b410d1536060e4051a3ddf6b0b- Assertion
assertion-url-health-resolution-9fcccc534aem:dossier-assertion:sha256:c1b99004fca0476c7c180f7ea829071b94278f2a2b5754678d316d098fe19c6b- Lineage
lineage-url-health-resolution-9fcccc534aem:dossier-lineage:sha256:92d2ecbee8e25a15eeb7a6c7fa6a54f79536633180a2740eda32d3b43027e580
07support
ReportBench compared cited statements with retrieved cited-page content and reported sub-100-percent semantic match rates in its bounded survey-task setting.
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · Limitations, lines 259-261ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · Section 4, line 186ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · Section 3.3, line 155ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · p. 5, lines 315-329ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · Section 2.2 'Cited statements'ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · Settings and metrics, lines 132-139ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · Section 3.1 'Setttings'ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · Table 1, OpenAI Deep Research row and cited-statements Match Rate column
Trace this statement
- Relation
relation-reportbench-match-rate-6964e41a69em:dossier-evidence-relation:sha256:ce23bc99cef3ca2b0b0e3597ada68536bf0813903e3468c894914c79a30c6d41- Proposition
prop-reportbench-match-rate-46ddf0a876em:dossier-proposition:sha256:9ad38ce48023866a877ebd02b5af9e70e587f22da770e87e0806d9f284351aab- Assertion
assertion-reportbench-match-rate-46ddf0a876em:dossier-assertion:sha256:2d0c2401cc47abfb1b09b0cd2facf39f6b0e5e9da4c2ff28f3d61679df670365- Lineage
lineage-reportbench-match-rate-46ddf0a876em:dossier-lineage:sha256:a7a4824a78a41b9491f399ac0fe498624111accf239f3d2cac5bd00c3fb8813c
56 exact passages · repeated display spans collapsed
This human register shows each exact accepted span once. The JSON, Markdown, relations, and ledgers retain every occurrence.
Used by evidence statement 01
EM-0026 deterministic agent-citation evidence ledger
Captured report V2-SOL-01
{ "answer_bytes": 40476, "answer_path": "research/how-we-know/agent-citation-lineage/answers-v2/V2-SOL-01.json", "answer_sha256": "17a7cf97b717d7b520026b9eb52a7da59ddb9b5f698c2aeadfab3f38c91008a0", "prompt_sha256": "d321a9cec7b5fe419157c0623e18ff0020cb0080fbe6dd9ed4fd20a0b896f670", "reported_model_identity": "unknown", "requested_model_profile": "gpt-5.6-sol", "retrieval_infrastructure": "unknown", "run_id": "V2-SOL-01", "status": "completed", "trace_path": "research/how-we-know/agent-citation-lineage/traces-v2/V2-SOL-01.json" }
Exact source identity
- Edition
- em:dossier-edition:sha256:f0111e28ede7d9e17c435927cba483d0d9a7acf3dc23b38322ee4677d8cb70c0
- Edition digest
- sha256:8400ea3bfe6c1e2516ab92710486eff3e62f5fee783a38859b383a561181533b
- Span
- em:dossier-span:sha256:ead238d33280cfd1dd252936d47fc1351950f8efb4105085d161ac7c1e51fa97
- Span digest
- sha256:ab05cfa54280c980dabd52b0d336f1dc65a5761925a54dad2d5c7b1cbfb094cb
- Retrieval
- Repository audit span; no external retrieval record
- License
- Repository metadata and derived audit relations under Apache-2.0; embedded source excerpts retain their recorded treatments · Repository metadata and derived audit relations under Apache-2.0; embedded source excerpts retain their recorded treatments
Used by evidence statement 01
EM-0026 deterministic agent-citation evidence ledger
Shared capture lineage
{ "automatic_independence_credit": 0, "prompt_sha256": "d321a9cec7b5fe419157c0623e18ff0020cb0080fbe6dd9ed4fd20a0b896f670", "reported_model_identity": "unknown", "requested_profiles": [ "gpt-5.6-sol", "gpt-5.6-terra" ], "retrieval_infrastructure": "unknown" }
Exact source identity
- Edition
- em:dossier-edition:sha256:f0111e28ede7d9e17c435927cba483d0d9a7acf3dc23b38322ee4677d8cb70c0
- Edition digest
- sha256:8400ea3bfe6c1e2516ab92710486eff3e62f5fee783a38859b383a561181533b
- Span
- em:dossier-span:sha256:e120064fee0bdabe15299cb865ff2f7df66473291a13b7a765a4a09d16223f5e
- Span digest
- sha256:92b558b23559a96a551de8acb2627b148688d21ede2ca3fb9966196c4675dab6
- Retrieval
- Repository audit span; no external retrieval record
- License
- Repository metadata and derived audit relations under Apache-2.0; embedded source excerpts retain their recorded treatments · Repository metadata and derived audit relations under Apache-2.0; embedded source excerpts retain their recorded treatments
Used by evidence statement 02
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype
Main text, paragraph beginning 'For their high performances in generating reference lists'
citation-bearing sentences exhibited high error rates: 51.3 ± 6.5% for ChatGPT and 57.8 ± 22.7% for Le Chat
Exact source identity
- Edition
- em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Edition digest
- sha256:98431c96e776a0502a6387574529817629ca50e164d8cd4e7f6997215ec7e097
- Span
- em:dossier-span:sha256:9f91508aa7be57f8e16c902e5399763ce349e7318b10d6085b65f0f53d5bdb56
- Span digest
- sha256:39f799b4bf1bcc50a74e5b019c585b970fa01779cf4b07bdeb27d71f35ea455b
- Retrieval
- retrieved https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ · inaccessible https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 · inaccessible https://pubmed.ncbi.nlm.nih.gov/40904191/
- License
- CC BY-NC 4.0 · quote-minimal attributed spans; no full-text redistribution
Used by evidence statement 02
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype
Table 1, ChatGPT all-correct subtotal
16 (69.6%)
Exact source identity
- Edition
- em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Edition digest
- sha256:98431c96e776a0502a6387574529817629ca50e164d8cd4e7f6997215ec7e097
- Span
- em:dossier-span:sha256:72a3edb3976aa397d38e9a7ccbc18b5e4af6f00c91540cd47aadcf9eddce2439
- Span digest
- sha256:b6c3ff6f2ff60f37ae1c6b773ba6aa5a6c01015b61e3cc6f2a06bfcef69b53ad
- Retrieval
- retrieved https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ · inaccessible https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 · inaccessible https://pubmed.ncbi.nlm.nih.gov/40904191/
- License
- CC BY-NC 4.0 · quote-minimal attributed spans; no full-text redistribution
Used by evidence statement 02
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype
main text, paragraph beginning 'For their high performances'; Figure 1
citation-bearing sentences exhibited high error rates: 51.3 ± 6.5% for ChatGPT and 57.8 ± 22.7% for Le Chat
Exact source identity
- Edition
- em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Edition digest
- sha256:98431c96e776a0502a6387574529817629ca50e164d8cd4e7f6997215ec7e097
- Span
- em:dossier-span:sha256:910f7758be3883fc0964cd1e5412b9c75a586e6c4c7c08e64ebda5b9f541a132
- Span digest
- sha256:39f799b4bf1bcc50a74e5b019c585b970fa01779cf4b07bdeb27d71f35ea455b
- Retrieval
- retrieved https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ · inaccessible https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 · inaccessible https://pubmed.ncbi.nlm.nih.gov/40904191/
- License
- CC BY-NC 4.0 · quote-minimal attributed spans; no full-text redistribution
Used by evidence statement 02
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype
Table 1, ChatGPT subtotal
23 (100.0%)
Exact source identity
- Edition
- em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Edition digest
- sha256:98431c96e776a0502a6387574529817629ca50e164d8cd4e7f6997215ec7e097
- Span
- em:dossier-span:sha256:d9dab2e8e8da55f5a5ddbe3e62c658a7f643cd05c36c117aa8a0dfc76a7b6d09
- Span digest
- sha256:5428bd1a04d5d2e332015107e915fe3a38f1d5e173e8c7246b743d98ecfd8618
- Retrieval
- retrieved https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ · inaccessible https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 · inaccessible https://pubmed.ncbi.nlm.nih.gov/40904191/
- License
- CC BY-NC 4.0 · quote-minimal attributed spans; no full-text redistribution
Used by evidence statement 02
Supplementary materials of the article: Assessment of Deep Research for Dermatology Literature Reviews: Deep Concern Over the Hype
Dataset description
sentence-level evaluation
Exact source identity
- Edition
- em:dossier-edition:sha256:8c80a50cd40cbb31bdaedb6730e8e173e3edc0f3440538dbcc4878eb0997ffd9
- Edition digest
- sha256:0a485e13dcc56e5f883213fde7e24bdcc4ffb810bda8ac95186f83f6325fafd1
- Span
- em:dossier-span:sha256:38bf64d13c4edef9c0aba131c84d42e0e08637a661d2552cbf2cb49536813488
- Span digest
- sha256:e3ec5c81f615c657f7c6b124c5b2150d86f18281384ca0bd24ebb43a3317796f
- Retrieval
- retrieved https://data.mendeley.com/datasets/3s73z9zf3c/1
- License
- CC BY 4.0 · metadata and quote-minimal landing-page spans
Used by evidence statement 02
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype
Main text, paragraph beginning 'To address the gap' (search-indexed primary full text)
We imposed a 1500-word limit, APA-style references and conducted three independent runs.
Exact source identity
- Edition
- em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Edition digest
- sha256:98431c96e776a0502a6387574529817629ca50e164d8cd4e7f6997215ec7e097
- Span
- em:dossier-span:sha256:54d8710861e7e1ee03c50697f1316c12138246e303a08c843fdadecfa99b8c5e
- Span digest
- sha256:1c94be957cfe750f445dc9143722905b5784b02f754a9b4071a3381e2bd493e9
- Retrieval
- retrieved https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ · inaccessible https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 · inaccessible https://pubmed.ncbi.nlm.nih.gov/40904191/
- License
- CC BY-NC 4.0 · quote-minimal attributed spans; no full-text redistribution
Used by evidence statement 02
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype
Main text, following paragraph (search-indexed primary full text)
ChatGPT Deep Research-generated references were mostly identifiable by their metadata (95.7%): 69.6% were entirely correct
Exact source identity
- Edition
- em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Edition digest
- sha256:98431c96e776a0502a6387574529817629ca50e164d8cd4e7f6997215ec7e097
- Span
- em:dossier-span:sha256:b9e4b58f255c32e2a9e5e6796e8d35f7f28d7481060d6b35f1e02a3c74d2b3d6
- Span digest
- sha256:28141fd1b0222658eb93a338783358926de770223eea24f8c5cbcf632d67f955
- Retrieval
- retrieved https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ · inaccessible https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 · inaccessible https://pubmed.ncbi.nlm.nih.gov/40904191/
- License
- CC BY-NC 4.0 · quote-minimal attributed spans; no full-text redistribution
Used by evidence statement 02
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype
body, paragraph immediately after Table 1
high error rates: 51.3 ± 6.5% for ChatGPT and 57.8 ± 22.7% for Le Chat
Exact source identity
- Edition
- em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Edition digest
- sha256:98431c96e776a0502a6387574529817629ca50e164d8cd4e7f6997215ec7e097
- Span
- em:dossier-span:sha256:f687ae7c3889980d4d3eea1b63b7bea25ae674ebc04caf8c59e7ae4f4fb77464
- Span digest
- sha256:2e43a0652065a6a1fb69de224082ac79d903cc71cac0664a1cb376cbfa09d0e8
- Retrieval
- retrieved https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ · inaccessible https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 · inaccessible https://pubmed.ncbi.nlm.nih.gov/40904191/
- License
- CC BY-NC 4.0 · quote-minimal attributed spans; no full-text redistribution
Used by evidence statement 02
Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype
Paragraph after Table 1
51.3 ± 6.5%
Exact source identity
- Edition
- em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Edition digest
- sha256:98431c96e776a0502a6387574529817629ca50e164d8cd4e7f6997215ec7e097
- Span
- em:dossier-span:sha256:2f331f1e2636907b0cab1000b0947e440fa5f24eec0edaf9498470522e1abe1a
- Span digest
- sha256:1f863c1f35c37af1fd2c3e4927ea0b289d94a9532fa5855e209ce98ea344d498
- Retrieval
- retrieved https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ · inaccessible https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 · inaccessible https://pubmed.ncbi.nlm.nih.gov/40904191/
- License
- CC BY-NC 4.0 · quote-minimal attributed spans; no full-text redistribution
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Evaluation methodology, lines 144-149
Each unique Statement-URL pair undergoes a support evaluation.
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:ed08815f4aabd455caf37f61a1e37a2dc35725098f2e9be5c6da6c9d5854d612
- Span digest
- sha256:1bde849b0f5df91e847e907dd763f27be01ffdc7eb0c7e61898c8a9731472c35
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Table 1, lines 177-182
Perplexity Deep Research | ... | 90.24 | 31.26 ... Gemini-2.5-Pro Deep Research | ... | 81.44 | 111.21 ... OpenAI Deep Research | ... | 77.96 | 40.79
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:fd8835d2aaa9358bd7dfbcf07848ed19001fa82f11e45ceff3374cdd4e882be3
- Span digest
- sha256:53d38f9cf0d0aedf28a77d7de32935372202fff78a0c02d98f8c269ef223906a
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Section 3.2, lines 144-146
‘support’ or ‘not support’
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:4648142e8019a2d54f201844685fbb87a921d93fc24b0f5c08f8124a82ffc374
- Span digest
- sha256:a49c200ea10833496ac73719992be09d5fd3fd021fdd51ccc587ac2592225f56
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Table 1, Perplexity Deep Research citation-accuracy cell
90.24
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:b118f44725ec505886f92a94123fe289be763523b8afb669757c72ccd0d8c352
- Span digest
- sha256:64c911242980826f92ffae6d0571646ecc3aceca73c213791c6d3a8d889b4cc7
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
page 16, FACT judge validation
aligned with human 'support' determinations in 96% of cases
Exact source identity
- Edition
- em:dossier-edition:sha256:47d8d33326a498097021dc5754365cbb8f5abfd3e628e90908d2342f0b6c7cf1
- Edition digest
- sha256:02f53bf5ae17ab2bffc25ba8dd5ca912d35b85ae6ae78a202cd79fe7f7efe25f
- Span
- em:dossier-span:sha256:a59ed2a9ea0e6972bc3f71d63feb1c361b76eb8d8fa5bb679c7beab61a32b713
- Span digest
- sha256:8be6257e74c3696813fb0079c27e93e8bec16c71d214b6da43811fbd9b406ba4
- Retrieval
- inaccessible https://openreview.net/pdf?id=hQ0K2Hhq7H · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf
- License
- CC BY 4.0; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Table 1, OpenAI Deep Research row; FACT columns
OpenAI Deep Research | 46.98 | 46.87 | 45.25 | 49.27 | 47.14 | 77.96 | 40.79
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:762ebe0afa7a2ddf8eb19d879c91f63d1de7d25192f10d248b65fefb0e113038
- Span digest
- sha256:dedd156999fa7d57ae9c22a166c56c263547eee3c37e6f41fe7644d980110986
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
page 4, Section 3.2, Support Judgment
This yields a binary judgment: 'support' or 'not support'.
Exact source identity
- Edition
- em:dossier-edition:sha256:47d8d33326a498097021dc5754365cbb8f5abfd3e628e90908d2342f0b6c7cf1
- Edition digest
- sha256:02f53bf5ae17ab2bffc25ba8dd5ca912d35b85ae6ae78a202cd79fe7f7efe25f
- Span
- em:dossier-span:sha256:d915faef70b54c6751577ba10f4057744b2b1b0b4d10613cdd8d74720a5da23b
- Span digest
- sha256:78f021c07980218ead835a986c84780444479e627dcfa9f2ea126b3604b89ad7
- Retrieval
- inaccessible https://openreview.net/pdf?id=hQ0K2Hhq7H · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf
- License
- CC BY 4.0; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 03
Ayanami0730/deep_research_bench
README FACT, lines 240-248
Support Verification: Uses web scraping and LLM judgment to verify whether cited sources actually support the claims
Exact source identity
- Edition
- em:dossier-edition:sha256:bf5c65b640b321fb75bf8b7f96854f151f834a7d31a2fc9d2bfb783852e7262b
- Edition digest
- sha256:35350075b3514f668c0deddb5bd4850ec31c7bfda2cf1e363995d68c580fe81b
- Span
- em:dossier-span:sha256:a28651fed7ffef6fdbbe7f322faa2482aa1e0f6b1e2a0a909eddef59a72740f2
- Span digest
- sha256:549018c6df261f27bd10133ad4e4f565e004f07710095259a7889cc79d149794
- Retrieval
- retrieved https://github.com/Ayanami0730/deep_research_bench
- License
- Apache-2.0 · metadata and quote-minimal README spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Section 3.2, paragraphs 'Statement-URL Pair Extraction and Deduplication' and 'Support Judgment'
"Each unique Statement-URL pair undergoes a support evaluation."
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:aba61c5b1685e20da29c0d6a42dd49b66f0b6c2f3ca08483716ae5c518562d4f
- Span digest
- sha256:3cca518ed14d7451346a35623b20e7f9e350e4cb5cbcec3d7f622cc6aac509ce
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
p. 4, lines 150-159
"Each unique Statement-URL pair undergoes a support evaluation... This results in a binary judgment ('support' or 'not support') for each pair, determining whether the citation accurately grounds the claim."
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:0b565d8281beb5c9b95d300108446049bc4c93de4dc3e80a501f41e85d0a98a5
- Span digest
- sha256:4edb75ec3f690eb2d15089923ba5e9c4e6174f55094d0919041bf10625901ceb
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Appendix C, line 365
96% of cases
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:d753bc9c860da325190141f3f78a0d031f2d6c7cf5e1a51f19f355f44cfb47db
- Span digest
- sha256:ae845f85955fa47d52d51f32803e6a26afa8b725c523e53d9ef30b2abca72d9b
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
page 5, Section 4.1
complete set of 100 tasks
Exact source identity
- Edition
- em:dossier-edition:sha256:47d8d33326a498097021dc5754365cbb8f5abfd3e628e90908d2342f0b6c7cf1
- Edition digest
- sha256:02f53bf5ae17ab2bffc25ba8dd5ca912d35b85ae6ae78a202cd79fe7f7efe25f
- Span
- em:dossier-span:sha256:4aa9441f93251fa969f1fe8cc8a4fb6cf728ec3f8879efae3ffff55fabae759d
- Span digest
- sha256:11034cf2238003f213bf87210c9017f57cc743910fa70754f3e61f875abe75e6
- Retrieval
- inaccessible https://openreview.net/pdf?id=hQ0K2Hhq7H · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf
- License
- CC BY 4.0; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
pp.17-18, Appendix E, equations 4-6
"the proportion of 'support' statement-URL pairs for each individual task"
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:c6710bb4b411353c7c600e449cc556e39a3530dc63c002a7b3973ef6bb1793bf
- Span digest
- sha256:82b9361b6e696a92b41fdfae500f56b05d48575c0d429f15b3a8d6786c83b8d7
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
Ayanami0730/deep_research_bench
README News, 2026-05-11 evaluator migration notice
Legacy code: the previous Gemini-2.5-Pro / Gemini-2.5-Flash evaluation code is preserved on the Gemini-2.5 branch.
Exact source identity
- Edition
- em:dossier-edition:sha256:bf5c65b640b321fb75bf8b7f96854f151f834a7d31a2fc9d2bfb783852e7262b
- Edition digest
- sha256:35350075b3514f668c0deddb5bd4850ec31c7bfda2cf1e363995d68c580fe81b
- Span
- em:dossier-span:sha256:abc4ab811e5c574575a0024557dda57a45d8d439ad4ff4ce08bef3753f7a86ef
- Span digest
- sha256:02cd1c04d6312fcda76549885095d9c9d971cc14709ae8f749cf47fc2c11bcee
- Retrieval
- retrieved https://github.com/Ayanami0730/deep_research_bench
- License
- Apache-2.0 · metadata and quote-minimal README spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
p.4, Section 3.2, lines 148-155
"Each unique Statement-URL pair undergoes a support evaluation."
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:27d667cb8cff21b646ec759c6c6fe79c5744a28079337d7a7fa9ac98abf8da9d
- Span digest
- sha256:3cca518ed14d7451346a35623b20e7f9e350e4cb5cbcec3d7f622cc6aac509ce
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 03
Ayanami0730/deep_research_bench
README News, lines 176-188
Official Evaluator Switched to GPT-5.5 ... Legacy code: the previous Gemini-2.5-Pro / Gemini-2.5-Flash evaluation code is preserved
Exact source identity
- Edition
- em:dossier-edition:sha256:bf5c65b640b321fb75bf8b7f96854f151f834a7d31a2fc9d2bfb783852e7262b
- Edition digest
- sha256:35350075b3514f668c0deddb5bd4850ec31c7bfda2cf1e363995d68c580fe81b
- Span
- em:dossier-span:sha256:fd761963efd1f957ebe8dae1eb76239c2d17ce1553109a4e0ac420525c73cfcb
- Span digest
- sha256:9c713be4fc872b46e66d812e033708b51b4e385c81aa45f7b1798459a677343d
- Retrieval
- retrieved https://github.com/Ayanami0730/deep_research_bench
- License
- Apache-2.0 · metadata and quote-minimal README spans
Used by evidence statement 03
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
p.17, Appendix C, lines 704-708
"aligned with human 'support' determinations in 96% of cases"
Exact source identity
- Edition
- em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Edition digest
- sha256:023aac7d22e7ca1230e2ffa237a4ea24c9f69f8b27653ddb6a494d4a30e4331c
- Span
- em:dossier-span:sha256:17193f2aab7106eece041bcabda963d9bd172d798792efc058b6a93c9bd4cb0c
- Span digest
- sha256:43c892b582d42a335c982009f97347b5bf2ae2799cc3e478c53504f4d01e4388
- Retrieval
- retrieved https://arxiv.org/html/2506.11763 · retrieved https://arxiv.org/html/2506.11763v1 · retrieved https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf
- License
- CC BY 4.0; unknown · quote-minimal attributed spans
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
page 14, Table 3
Factual support (statement-source) 0.62 binary
Exact source identity
- Edition
- em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Edition digest
- sha256:0e0c4dd57c80c2ab32707ec1b17eda3ea21fc75ec4ce5191875446912649b545
- Span
- em:dossier-span:sha256:6cf2883b02dd404844a662bae3367ab60d91f6847160a3df9c6ec6b287dc0858
- Span digest
- sha256:bb4f28cd0f4527c633bcfacf51b18ced7387c4a2f266c59d41de7ee899b24b85
- Retrieval
- retrieved https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
Abstract, line 46
citation accuracy ranging from 40–80% across systems
Exact source identity
- Edition
- em:dossier-edition:sha256:c7779c770aa24aa5925b5fe6e66f968c733e8522d30bcdc4290bc9409bbe8b5b
- Edition digest
- sha256:07a6f7e0282d888bc9157436b17fbde6286fb934b0efafd23399eebb7a22fa5d
- Span
- em:dossier-span:sha256:e748230bbc2f6b31433eaba4536917834c454cb73a7f18e8d9b975e2cac447b5
- Span digest
- sha256:a0eeca5c86f9c7aeda9167f626a8cb0ed56dc87ea1ac5ca8c4a7a0add76e7625
- Retrieval
- retrieved https://arxiv.org/html/2509.04499 · retrieved https://arxiv.org/html/2509.04499v1
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
pp.4-7, Sections 3.1.1 and 3.2
"The dataset comprises 303 questions"
Exact source identity
- Edition
- em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Edition digest
- sha256:0e0c4dd57c80c2ab32707ec1b17eda3ea21fc75ec4ce5191875446912649b545
- Span
- em:dossier-span:sha256:b9cbe6b1d35e74f3c8133d2be41a47d9361a26958e9f644dafd97e9e5acb516a
- Span digest
- sha256:2ce91759797b86455a478a9ced58ec59d032e1a32a1c964347f96be4ab9e2054
- Retrieval
- retrieved https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
Section 3.2, lines 163-171
303 queries x 9 models
Exact source identity
- Edition
- em:dossier-edition:sha256:c7779c770aa24aa5925b5fe6e66f968c733e8522d30bcdc4290bc9409bbe8b5b
- Edition digest
- sha256:07a6f7e0282d888bc9157436b17fbde6286fb934b0efafd23399eebb7a22fa5d
- Span
- em:dossier-span:sha256:8c1ac40e63a414c1a41cd0842632677269c8800967f22ef8247b6fb36f6242ea
- Span digest
- sha256:5cc83ab699cb1342475b407e34d33fc106d64b5d9270e5bb9445d80586ebabc2
- Retrieval
- retrieved https://arxiv.org/html/2509.04499 · retrieved https://arxiv.org/html/2509.04499v1
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
Official ICLR abstract
with citation accuracy ranging from 40–80% across systems
Exact source identity
- Edition
- em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Edition digest
- sha256:0e0c4dd57c80c2ab32707ec1b17eda3ea21fc75ec4ce5191875446912649b545
- Span
- em:dossier-span:sha256:06ea026aae360f700369f4b1f658c4ca85e8acce431923cd7978ff2358b1ec05
- Span digest
- sha256:af76864a50c641f8d693216d3b7ebe2a414eebf75467305c1e1a6946b6746590
- Retrieval
- retrieved https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
page 4, source scraping
For roughly 15% of the URLs, the Reader tool returns an error
Exact source identity
- Edition
- em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Edition digest
- sha256:0e0c4dd57c80c2ab32707ec1b17eda3ea21fc75ec4ce5191875446912649b545
- Span
- em:dossier-span:sha256:12ab62355d178256bbaed6cdf5cbf6ae150410d9364f98cced347b54161fa5e8
- Span digest
- sha256:a38c9ac275570f2b78dd1e1bf7663579e35f9037131e12d721dfb4c6f005683d
- Retrieval
- retrieved https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
p.14, Table 3
"Factual support (statement–source) 0.62"
Exact source identity
- Edition
- em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Edition digest
- sha256:0e0c4dd57c80c2ab32707ec1b17eda3ea21fc75ec4ce5191875446912649b545
- Span
- em:dossier-span:sha256:2aa386b3653a99db3b670f783272056371480ed287dc1f62a51d3d587d680996
- Span digest
- sha256:75a9212dc448c15ffc1e4a36bdf190728977470661bd9f45be534010704faa25
- Retrieval
- retrieved https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
Paper section 3.1.1, factual-support validation
Pearson correlation of 0.62 between the LLM judge and manual labels
Exact source identity
- Edition
- em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Edition digest
- sha256:0e0c4dd57c80c2ab32707ec1b17eda3ea21fc75ec4ce5191875446912649b545
- Span
- em:dossier-span:sha256:a575506a3cca26acda376aa922fdb0e269767f71b01f502a7c50f3d4492e6f03
- Span digest
- sha256:d2f6a4561a938ee913dadde2fc4a80c32c492fbcb3b47f236c9639375843ae8d
- Retrieval
- retrieved https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
printed page 10; PDF page index 10/22; Section 4 Results; Deep Research Agents paragraph
Gemini(DR) demonstrates weak citation performance: only 40.3% citation accuracy
Exact source identity
- Edition
- em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Edition digest
- sha256:0e0c4dd57c80c2ab32707ec1b17eda3ea21fc75ec4ce5191875446912649b545
- Span
- em:dossier-span:sha256:533550e262b8691ce9ed33aa0e89a7bf13d89c04c6002e1855ed1e767f556e3a
- Span digest
- sha256:cf32a686cec566152749e3a4c643fa29aa115099f9eba77c0ca113c48264f769
- Retrieval
- retrieved https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 04
DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
printed page 9; PDF page index 9/22; Table 1; Gemini (DR) column; %Citation Accuracy row
{ "cell": "50.3", "column": "Gemini (DR)", "row": "%Citation Accuracy" }
Exact source identity
- Edition
- em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Edition digest
- sha256:0e0c4dd57c80c2ab32707ec1b17eda3ea21fc75ec4ce5191875446912649b545
- Span
- em:dossier-span:sha256:cf4e063e6f297fe901b342752b67850d84cc3e8e21ace2ef8d5ea4f3fd93091c
- Span digest
- sha256:e020a09063eee7aa1eb70663cf3e8bd7a8162952f5ae65d959d57ef74ab855f6
- Retrieval
- retrieved https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html · retrieved https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf
- License
- arXiv non-exclusive distribution license; unknown · metadata, digest, and quote-minimal attributed spans only
Used by evidence statement 05
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Section 3.3.1-3.3.3
"Fact Check verifies whether specific factual claims are accurately supported by the source content."
Exact source identity
- Edition
- em:dossier-edition:sha256:601f0e4510819607265b94c8261884c072d559e63de9f71dbfc6bca5d33c5e29
- Edition digest
- sha256:90da1e5adccef8448150bd162daa5cdc08d01bfab5142d92de6aee947a79e58b
- Span
- em:dossier-span:sha256:d4e2f35392b064365ad867f33ead8636bb8bbf3af03c0141585e5ae56c868090
- Span digest
- sha256:a4386d56325583893d806fdd15ccd475d5096f0b445b1b9f52aeba253c910987
- Retrieval
- retrieved https://arxiv.org/html/2605.06635 · retrieved https://arxiv.org/html/2605.06635v1 · retrieved https://arxiv.org/pdf/2605.06635 · retrieved https://arxiv.org/abs/2605.06635
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 05
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Abstract, lines 47-48
yet achieve only 39–77% factual accuracy
Exact source identity
- Edition
- em:dossier-edition:sha256:601f0e4510819607265b94c8261884c072d559e63de9f71dbfc6bca5d33c5e29
- Edition digest
- sha256:90da1e5adccef8448150bd162daa5cdc08d01bfab5142d92de6aee947a79e58b
- Span
- em:dossier-span:sha256:ea33bc17365ed01ed68ab06f33c4fd2020dc8e6947659e4e9629b44af4aef635
- Span digest
- sha256:be05510d58cc0231bf968f29c70b3d669a82d5cd0c74a778a5f8c4e035bf45b4
- Retrieval
- retrieved https://arxiv.org/html/2605.06635 · retrieved https://arxiv.org/html/2605.06635v1 · retrieved https://arxiv.org/pdf/2605.06635 · retrieved https://arxiv.org/abs/2605.06635
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 05
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Abstract and Table 1
link validity above 94% and relevance above 80%, yet achieve only 39–77% factual accuracy
Exact source identity
- Edition
- em:dossier-edition:sha256:601f0e4510819607265b94c8261884c072d559e63de9f71dbfc6bca5d33c5e29
- Edition digest
- sha256:90da1e5adccef8448150bd162daa5cdc08d01bfab5142d92de6aee947a79e58b
- Span
- em:dossier-span:sha256:49ee66722d6d523dd485f05c796181af55736c3ceab2a235c5c3b40cca95e439
- Span digest
- sha256:44d4c6941f2920e907de1e4cd22aeb9a725f24cc19432723754e316bd6f5cc49
- Retrieval
- retrieved https://arxiv.org/html/2605.06635 · retrieved https://arxiv.org/html/2605.06635v1 · retrieved https://arxiv.org/pdf/2605.06635 · retrieved https://arxiv.org/abs/2605.06635
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 05
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Abstract and Table 1
maintain link validity above 94% and relevance above 80%, yet achieve only 39–77% factual accuracy
Exact source identity
- Edition
- em:dossier-edition:sha256:601f0e4510819607265b94c8261884c072d559e63de9f71dbfc6bca5d33c5e29
- Edition digest
- sha256:90da1e5adccef8448150bd162daa5cdc08d01bfab5142d92de6aee947a79e58b
- Span
- em:dossier-span:sha256:8cf2ff4c32b2dac6d6dfc7684dd2bf7dca9d40fe7b7b36d50dfdcddad067bff3
- Span digest
- sha256:e35ca66d12349d7290a6dbe7449bf6da173eb0671765644b581713528b316c74
- Retrieval
- retrieved https://arxiv.org/html/2605.06635 · retrieved https://arxiv.org/html/2605.06635v1 · retrieved https://arxiv.org/pdf/2605.06635 · retrieved https://arxiv.org/abs/2605.06635
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 05
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Abstract, lines 45-49
Citations are evaluated along three dimensions. (1) Link Works verifies URL accessibility, (2) Relevant Content measures topical alignment, and (3) Fact Check validates factual accuracy against source content.
Exact source identity
- Edition
- em:dossier-edition:sha256:601f0e4510819607265b94c8261884c072d559e63de9f71dbfc6bca5d33c5e29
- Edition digest
- sha256:90da1e5adccef8448150bd162daa5cdc08d01bfab5142d92de6aee947a79e58b
- Span
- em:dossier-span:sha256:237508b682de825711f61762deb5ce7661d5d197e9fde3aed5f5e80f05fdcdb5
- Span digest
- sha256:d34096a9d9b1fbb43ef50ba503c3894607c008b563e1e1a5d1643cbc23c5d447
- Retrieval
- retrieved https://arxiv.org/html/2605.06635 · retrieved https://arxiv.org/html/2605.06635v1 · retrieved https://arxiv.org/pdf/2605.06635 · retrieved https://arxiv.org/abs/2605.06635
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 05
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Section 4.4, line 217
only 1 failed link out of 2,159 evaluations
Exact source identity
- Edition
- em:dossier-edition:sha256:601f0e4510819607265b94c8261884c072d559e63de9f71dbfc6bca5d33c5e29
- Edition digest
- sha256:90da1e5adccef8448150bd162daa5cdc08d01bfab5142d92de6aee947a79e58b
- Span
- em:dossier-span:sha256:2bd67a5caa606894f4301ca1185c88a4dde02d3c5c4a2cf311463a0f39332443
- Span digest
- sha256:da34a8e2a1d4e190d3b2095d79886b3cbf7edb2c63874189aa381302d2c2924e
- Retrieval
- retrieved https://arxiv.org/html/2605.06635 · retrieved https://arxiv.org/html/2605.06635v1 · retrieved https://arxiv.org/pdf/2605.06635 · retrieved https://arxiv.org/abs/2605.06635
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 06
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
pp. 1-2, lines 64-95
"This study focuses on URL-based citation hallucinations"; "fabricated snippets ... and invented bibliographic entries ... require separate systematic study."
Exact source identity
- Edition
- em:dossier-edition:sha256:89224c483a2c88c51351393bd2ae482b8f2642a27b621c5a7a1401b05fe86b2f
- Edition digest
- sha256:37bffd052d581c627c32d65958b6037bebdc9a9c4cf1bef8376499fb0caa5bb7
- Span
- em:dossier-span:sha256:179697ec62048a6465fa50dda34ff54530e700430013a878201b9dadde405cc0
- Span digest
- sha256:ee1de7374c67e208aa5d1331c20a08c8c83418309f1bd768d380620bfdc27901
- Retrieval
- retrieved https://arxiv.org/html/2604.03173 · retrieved https://arxiv.org/html/2604.03173v1 · retrieved https://arxiv.org/pdf/2604.03173 · retrieved https://arxiv.org/abs/2604.03173
- License
- CC0 1.0 · quote-minimal attributed spans
Used by evidence statement 06
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
page 3, Section 3.3
no archived snapshot exists at any timestamp
Exact source identity
- Edition
- em:dossier-edition:sha256:89224c483a2c88c51351393bd2ae482b8f2642a27b621c5a7a1401b05fe86b2f
- Edition digest
- sha256:37bffd052d581c627c32d65958b6037bebdc9a9c4cf1bef8376499fb0caa5bb7
- Span
- em:dossier-span:sha256:73d72803976f4bb5529880a7185545e8b0ce5581409b9f64ba6ace3ac07c4e2c
- Span digest
- sha256:3a14d6f574bed17e76ef8b560bbca0aa27b3a50918e49461433e34ec7770a4c9
- Retrieval
- retrieved https://arxiv.org/html/2604.03173 · retrieved https://arxiv.org/html/2604.03173v1 · retrieved https://arxiv.org/pdf/2604.03173 · retrieved https://arxiv.org/abs/2604.03173
- License
- CC0 1.0 · quote-minimal attributed spans
Used by evidence statement 06
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
Section 3.3 'URL extraction and classification'
"URLs returning 4xx or 5xx status codes, connection errors, or timeouts are classified as non-resolving"
Exact source identity
- Edition
- em:dossier-edition:sha256:89224c483a2c88c51351393bd2ae482b8f2642a27b621c5a7a1401b05fe86b2f
- Edition digest
- sha256:37bffd052d581c627c32d65958b6037bebdc9a9c4cf1bef8376499fb0caa5bb7
- Span
- em:dossier-span:sha256:57bdc827daee408c0042ec10327966b2b898d525449bee7ecbce1e02330f7f5f
- Span digest
- sha256:b240bd208cb4c322f3c9c242d01e13da53b3fd2a64e41b8b0f26653032e0ee54
- Retrieval
- retrieved https://arxiv.org/html/2604.03173 · retrieved https://arxiv.org/html/2604.03173v1 · retrieved https://arxiv.org/pdf/2604.03173 · retrieved https://arxiv.org/abs/2604.03173
- License
- CC0 1.0 · quote-minimal attributed spans
Used by evidence statement 06
Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents
Section 3 Experimental setup; Section 3.1 Datasets; section#S3.SS1; paragraph p#S3.SS1.p1.1
DRBench (17) comprises 100 multilingual research queries (Chinese and English) covering finance, science, and technology, with pre-collected outputs from 23 models.
Exact source identity
- Edition
- em:dossier-edition:sha256:89224c483a2c88c51351393bd2ae482b8f2642a27b621c5a7a1401b05fe86b2f
- Edition digest
- sha256:37bffd052d581c627c32d65958b6037bebdc9a9c4cf1bef8376499fb0caa5bb7
- Span
- em:dossier-span:sha256:1adfd92244c349596074ef5bf78e7edf7297e8966c13f429410a0f5871d89e45
- Span digest
- sha256:9741316a5669b3b6e1e3022dfe4bfc23f53569a2839c46889423478a0b3c058f
- Retrieval
- retrieved https://arxiv.org/html/2604.03173 · retrieved https://arxiv.org/html/2604.03173v1 · retrieved https://arxiv.org/pdf/2604.03173 · retrieved https://arxiv.org/abs/2604.03173
- License
- CC0 1.0 · quote-minimal attributed spans
Used by evidence statement 07
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Limitations, lines 259-261
The benchmark primarily draws from peer-reviewed survey papers on arXiv, most of which are concentrated in STEM fields.
Exact source identity
- Edition
- em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Edition digest
- sha256:e13193419b2e087faabf99c51b27acf1a58919072019e4197c41c279354eb2f8
- Span
- em:dossier-span:sha256:bf94ce1ab912090b1db248bca0eae62fb77c0f4f12f2fffca9cafaf6524deadd
- Span digest
- sha256:4947edaf643bd0a234e0ca914d920a1a5b068d18b017dcfe6d6103c466d422ca
- Retrieval
- retrieved https://arxiv.org/html/2508.15804 · retrieved https://arxiv.org/html/2508.15804v1 · retrieved https://arxiv.org/pdf/2508.15804
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 07
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Section 4, line 186
the cited URL does not exist
Exact source identity
- Edition
- em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Edition digest
- sha256:e13193419b2e087faabf99c51b27acf1a58919072019e4197c41c279354eb2f8
- Span
- em:dossier-span:sha256:e896138fd05fe0904311d35606553601c77784112c448651ce822a85e31ed99c
- Span digest
- sha256:ac4714fdd34ead02999923441a133a798a67254f0449f293905ef5b1d1caffab
- Retrieval
- retrieved https://arxiv.org/html/2508.15804 · retrieved https://arxiv.org/html/2508.15804v1 · retrieved https://arxiv.org/pdf/2508.15804
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 07
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Section 3.3, line 155
78.87% vs. 72.94%
Exact source identity
- Edition
- em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Edition digest
- sha256:e13193419b2e087faabf99c51b27acf1a58919072019e4197c41c279354eb2f8
- Span
- em:dossier-span:sha256:d87df9d6e418184717863f7c621ddc6c16838dc569a1ab2a558421fbc20eeaa9
- Span digest
- sha256:4545fdd46cab2ffc151c9ddbfaab08b82862b68eebf5205cda180b5875a3aa81
- Retrieval
- retrieved https://arxiv.org/html/2508.15804 · retrieved https://arxiv.org/html/2508.15804v1 · retrieved https://arxiv.org/pdf/2508.15804
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 07
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
p. 5, lines 315-329
"we manually collected responses ... during the period from July 14 to July 25... OpenAI was using the standard version of Deep Research, powered by the o3 model."
Exact source identity
- Edition
- em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Edition digest
- sha256:e13193419b2e087faabf99c51b27acf1a58919072019e4197c41c279354eb2f8
- Span
- em:dossier-span:sha256:3c149d37c88677f94f1715b536ad1808c4e476392f7e02212adbc723e30d8e27
- Span digest
- sha256:e45fbf61feb38fc8de32433d439fdb8544133e905103b884c92327930a929b0a
- Retrieval
- retrieved https://arxiv.org/html/2508.15804 · retrieved https://arxiv.org/html/2508.15804v1 · retrieved https://arxiv.org/pdf/2508.15804
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 07
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Section 2.2 'Cited statements'
"retrieve the full content of each cited webpage"
Exact source identity
- Edition
- em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Edition digest
- sha256:e13193419b2e087faabf99c51b27acf1a58919072019e4197c41c279354eb2f8
- Span
- em:dossier-span:sha256:5da64a3b244d7aa2f4baebee7a32be87f2f4255de92db8287d1b11a2a396932d
- Span digest
- sha256:153b2f37a8662ac0dbbd7fe51bcbb291afd5d227c4da3f4c6463274c63a11fb2
- Retrieval
- retrieved https://arxiv.org/html/2508.15804 · retrieved https://arxiv.org/html/2508.15804v1 · retrieved https://arxiv.org/pdf/2508.15804
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 07
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Settings and metrics, lines 132-139
For statement extraction, supporting source extraction, and semantic consistency verification, we adopt gpt-4o.
Exact source identity
- Edition
- em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Edition digest
- sha256:e13193419b2e087faabf99c51b27acf1a58919072019e4197c41c279354eb2f8
- Span
- em:dossier-span:sha256:f3bc53b3bd401949fea37755e5943e417ceb79e044727a73f7219cfc824ab859
- Span digest
- sha256:397d217cf5022ad78aa1072c2e82bcf3197e5a87cf4ef96ea81a78e1ad39b384
- Retrieval
- retrieved https://arxiv.org/html/2508.15804 · retrieved https://arxiv.org/html/2508.15804v1 · retrieved https://arxiv.org/pdf/2508.15804
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 07
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Section 3.1 'Setttings'
"during the period from July 14 to July 25"
Exact source identity
- Edition
- em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Edition digest
- sha256:e13193419b2e087faabf99c51b27acf1a58919072019e4197c41c279354eb2f8
- Span
- em:dossier-span:sha256:abc076cdbec4977f668ce36fa6e5edcfebfd81c18c90a4f7913fbb0f8d5fe33a
- Span digest
- sha256:b55cc3d05dbba5d160b75515ce407128fe2e2cf8c2d679517e79309d6ed6ab40
- Retrieval
- retrieved https://arxiv.org/html/2508.15804 · retrieved https://arxiv.org/html/2508.15804v1 · retrieved https://arxiv.org/pdf/2508.15804
- License
- CC BY 4.0 · quote-minimal attributed spans
Used by evidence statement 07
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Table 1, OpenAI Deep Research row and cited-statements Match Rate column
OpenAI Deep Research ... Match Rate 78.87%
Exact source identity
- Edition
- em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Edition digest
- sha256:e13193419b2e087faabf99c51b27acf1a58919072019e4197c41c279354eb2f8
- Span
- em:dossier-span:sha256:5ea28918cbd966b0fc14072426f2b7132bfe47f03d327e0b6eaee0629c3740ca
- Span digest
- sha256:9b1bf034e823976ac267434e9c67ee7e4038da04f3d2582a0de7d6d729fc6916
- Retrieval
- retrieved https://arxiv.org/html/2508.15804 · retrieved https://arxiv.org/html/2508.15804v1 · retrieved https://arxiv.org/pdf/2508.15804
- License
- CC BY 4.0 · quote-minimal attributed spans
Verify every number
Complete count ledgers
Every displayed total is a view over these typed members; no total is maintained as marketing copy.
8 · Captured reports
- V2-SOL-01 — completed
Technical identity
- Member
V2-SOL-01- Object type
- captured report
- Object key
V2-SOL-01- Object ID
V2-SOL-01- Status
- completed
- V2-SOL-02 — completed
Technical identity
- Member
V2-SOL-02- Object type
- captured report
- Object key
V2-SOL-02- Object ID
V2-SOL-02- Status
- completed
- V2-SOL-03 — completed
Technical identity
- Member
V2-SOL-03- Object type
- captured report
- Object key
V2-SOL-03- Object ID
V2-SOL-03- Status
- completed
- V2-SOL-04 — completed
Technical identity
- Member
V2-SOL-04- Object type
- captured report
- Object key
V2-SOL-04- Object ID
V2-SOL-04- Status
- completed
- V2-TERRA-01 — completed
Technical identity
- Member
V2-TERRA-01- Object type
- captured report
- Object key
V2-TERRA-01- Object ID
V2-TERRA-01- Status
- completed
- V2-TERRA-02 — completed
Technical identity
- Member
V2-TERRA-02- Object type
- captured report
- Object key
V2-TERRA-02- Object ID
V2-TERRA-02- Status
- completed
- V2-TERRA-03 — completed
Technical identity
- Member
V2-TERRA-03- Object type
- captured report
- Object key
V2-TERRA-03- Object ID
V2-TERRA-03- Status
- completed
- V2-TERRA-04 — completed
Technical identity
- Member
V2-TERRA-04- Object type
- captured report
- Object key
V2-TERRA-04- Object ID
V2-TERRA-04- Status
- completed
30 · Distinct cited URL strings
- https://arxiv.org/abs/2604.03173 — retrieved
Technical identity
- Member
https://arxiv.org/abs/2604.03173- Object type
- cited url
- Object key
https://arxiv.org/abs/2604.03173- Object ID
https://arxiv.org/abs/2604.03173- Status
- retrieved
- https://arxiv.org/abs/2605.06635 — retrieved
Technical identity
- Member
https://arxiv.org/abs/2605.06635- Object type
- cited url
- Object key
https://arxiv.org/abs/2605.06635- Object ID
https://arxiv.org/abs/2605.06635- Status
- retrieved
- https://arxiv.org/abs/2607.08700 — retrieved
Technical identity
- Member
https://arxiv.org/abs/2607.08700- Object type
- cited url
- Object key
https://arxiv.org/abs/2607.08700- Object ID
https://arxiv.org/abs/2607.08700- Status
- retrieved
- https://arxiv.org/html/2506.11763 — retrieved
Technical identity
- Member
https://arxiv.org/html/2506.11763- Object type
- cited url
- Object key
https://arxiv.org/html/2506.11763- Object ID
https://arxiv.org/html/2506.11763- Status
- retrieved
- https://arxiv.org/html/2506.11763v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2506.11763v1- Object type
- cited url
- Object key
https://arxiv.org/html/2506.11763v1- Object ID
https://arxiv.org/html/2506.11763v1- Status
- retrieved
- https://arxiv.org/html/2507.16280 — retrieved
Technical identity
- Member
https://arxiv.org/html/2507.16280- Object type
- cited url
- Object key
https://arxiv.org/html/2507.16280- Object ID
https://arxiv.org/html/2507.16280- Status
- retrieved
- https://arxiv.org/html/2508.15804 — retrieved
Technical identity
- Member
https://arxiv.org/html/2508.15804- Object type
- cited url
- Object key
https://arxiv.org/html/2508.15804- Object ID
https://arxiv.org/html/2508.15804- Status
- retrieved
- https://arxiv.org/html/2508.15804v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2508.15804v1- Object type
- cited url
- Object key
https://arxiv.org/html/2508.15804v1- Object ID
https://arxiv.org/html/2508.15804v1- Status
- retrieved
- https://arxiv.org/html/2509.04499 — retrieved
Technical identity
- Member
https://arxiv.org/html/2509.04499- Object type
- cited url
- Object key
https://arxiv.org/html/2509.04499- Object ID
https://arxiv.org/html/2509.04499- Status
- retrieved
- https://arxiv.org/html/2509.04499v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2509.04499v1- Object type
- cited url
- Object key
https://arxiv.org/html/2509.04499v1- Object ID
https://arxiv.org/html/2509.04499v1- Status
- retrieved
- https://arxiv.org/html/2604.03173 — retrieved
Technical identity
- Member
https://arxiv.org/html/2604.03173- Object type
- cited url
- Object key
https://arxiv.org/html/2604.03173- Object ID
https://arxiv.org/html/2604.03173- Status
- retrieved
- https://arxiv.org/html/2604.03173v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2604.03173v1- Object type
- cited url
- Object key
https://arxiv.org/html/2604.03173v1- Object ID
https://arxiv.org/html/2604.03173v1- Status
- retrieved
- https://arxiv.org/html/2605.06635 — retrieved
Technical identity
- Member
https://arxiv.org/html/2605.06635- Object type
- cited url
- Object key
https://arxiv.org/html/2605.06635- Object ID
https://arxiv.org/html/2605.06635- Status
- retrieved
- https://arxiv.org/html/2605.06635v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2605.06635v1- Object type
- cited url
- Object key
https://arxiv.org/html/2605.06635v1- Object ID
https://arxiv.org/html/2605.06635v1- Status
- retrieved
- https://arxiv.org/pdf/2507.16280 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2507.16280- Object type
- cited url
- Object key
https://arxiv.org/pdf/2507.16280- Object ID
https://arxiv.org/pdf/2507.16280- Status
- retrieved
- https://arxiv.org/pdf/2508.15804 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2508.15804- Object type
- cited url
- Object key
https://arxiv.org/pdf/2508.15804- Object ID
https://arxiv.org/pdf/2508.15804- Status
- retrieved
- https://arxiv.org/pdf/2510.14240v5 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2510.14240v5- Object type
- cited url
- Object key
https://arxiv.org/pdf/2510.14240v5- Object ID
https://arxiv.org/pdf/2510.14240v5- Status
- retrieved
- https://arxiv.org/pdf/2604.03173 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2604.03173- Object type
- cited url
- Object key
https://arxiv.org/pdf/2604.03173- Object ID
https://arxiv.org/pdf/2604.03173- Status
- retrieved
- https://arxiv.org/pdf/2605.06635 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2605.06635- Object type
- cited url
- Object key
https://arxiv.org/pdf/2605.06635- Object ID
https://arxiv.org/pdf/2605.06635- Status
- retrieved
- https://data.mendeley.com/datasets/3s73z9zf3c/1 — retrieved
Technical identity
- Member
https://data.mendeley.com/datasets/3s73z9zf3c/1- Object type
- cited url
- Object key
https://data.mendeley.com/datasets/3s73z9zf3c/1- Object ID
https://data.mendeley.com/datasets/3s73z9zf3c/1- Status
- retrieved
- https://data.mendeley.com/datasets/3s73z9zf3c/2 — retrieved
Technical identity
- Member
https://data.mendeley.com/datasets/3s73z9zf3c/2- Object type
- cited url
- Object key
https://data.mendeley.com/datasets/3s73z9zf3c/2- Object ID
https://data.mendeley.com/datasets/3s73z9zf3c/2- Status
- retrieved
- https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf — retrieved
Technical identity
- Member
https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf- Object type
- cited url
- Object key
https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf- Object ID
https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf- Status
- retrieved
- https://github.com/Ayanami0730/deep_research_bench — retrieved
Technical identity
- Member
https://github.com/Ayanami0730/deep_research_bench- Object type
- cited url
- Object key
https://github.com/Ayanami0730/deep_research_bench- Object ID
https://github.com/Ayanami0730/deep_research_bench- Status
- retrieved
- https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035 — inaccessible
Technical identity
- Member
https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035- Object type
- cited url
- Object key
https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035- Object ID
https://onlinelibrary.wiley.com/doi/10.1111/jdv.70035- Status
- inaccessible
- https://openreview.net/pdf?id=hQ0K2Hhq7H — inaccessible
Technical identity
- Member
https://openreview.net/pdf?id=hQ0K2Hhq7H- Object type
- cited url
- Object key
https://openreview.net/pdf?id=hQ0K2Hhq7H- Object ID
https://openreview.net/pdf?id=hQ0K2Hhq7H- Status
- inaccessible
- https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ — retrieved
Technical identity
- Member
https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/- Object type
- cited url
- Object key
https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/- Object ID
https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/- Status
- retrieved
- https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf — retrieved
Technical identity
- Member
https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf- Object type
- cited url
- Object key
https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf- Object ID
https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf- Status
- retrieved
- https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf — retrieved
Technical identity
- Member
https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf- Object type
- cited url
- Object key
https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf- Object ID
https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf- Status
- retrieved
- https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html — retrieved
Technical identity
- Member
https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html- Object type
- cited url
- Object key
https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html- Object ID
https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html- Status
- retrieved
- https://pubmed.ncbi.nlm.nih.gov/40904191/ — inaccessible
Technical identity
- Member
https://pubmed.ncbi.nlm.nih.gov/40904191/- Object type
- cited url
- Object key
https://pubmed.ncbi.nlm.nih.gov/40904191/- Object ID
https://pubmed.ncbi.nlm.nih.gov/40904191/- Status
- inaccessible
11 · Source works
- Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution — examined-source-work
Technical identity
- Member
work-citation-verifier-benchmark-2d5e94336b- Object type
- source work
- Object key
work-citation-verifier-benchmark-2d5e94336b- Object ID
em:dossier-source-work:sha256:22b2290799937200bec1536c9c67de0f5642340c180e656e8ed687a1d566f8d9
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents — examined-source-work
Technical identity
- Member
work-cited-not-verified-3825b25622- Object type
- source work
- Object key
work-cited-not-verified-3825b25622- Object ID
em:dossier-source-work:sha256:19d52572cf9e426b68cba35f9dd627d014ff71a978756c5b50103c2aabe554ce
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents — examined-source-work
Technical identity
- Member
work-deepresearch-bench-paper-8ef36010d2- Object type
- source work
- Object key
work-deepresearch-bench-paper-8ef36010d2- Object ID
em:dossier-source-work:sha256:2a2c79463c9697b114728426edb183b5881f8b742ea6febfc272f73db58c1a14
- Ayanami0730/deep_research_bench — examined-source-work
Technical identity
- Member
work-deepresearch-bench-repository-1e475c7631- Object type
- source work
- Object key
work-deepresearch-bench-repository-1e475c7631- Object ID
em:dossier-source-work:sha256:433604e28e4a1ee90dfc7f2c5b2389d04e64a600930ad51cd9acf599b4df9f21
- DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence — examined-source-work
Technical identity
- Member
work-deeptrace-650d66cfcb- Object type
- source work
- Object key
work-deeptrace-650d66cfcb- Object ID
em:dossier-source-work:sha256:f58addec09e622c4c6457ae395e065ad2c0e9bc92035131100c8cb15e3a9d6d1
- Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype — examined-source-work
Technical identity
- Member
work-keplinger-dermatology-audit-639f9ea37a- Object type
- source work
- Object key
work-keplinger-dermatology-audit-639f9ea37a- Object ID
em:dossier-source-work:sha256:7e292f6ce412d254983ada9a5032ef5fac626876b16404d99ed1a99ce4e3ba05
- Supplementary materials of the article: Assessment of Deep Research for Dermatology Literature Reviews: Deep Concern Over the Hype — examined-source-work
Technical identity
- Member
work-keplinger-supplement-1a03034fb3- Object type
- source work
- Object key
work-keplinger-supplement-1a03034fb3- Object ID
em:dossier-source-work:sha256:daa2447b3107ce9818b1c435de19c6ea8ca0de07129761714bda29dc7a062eb4
- LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild — examined-source-work
Technical identity
- Member
work-liveresearchbench-61e7da557b- Object type
- source work
- Object key
work-liveresearchbench-61e7da557b- Object ID
em:dossier-source-work:sha256:f93da6e764e8998aec2b860736cdf95f0218d6144a5827faf13b95db0f5720fd
- ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks — examined-source-work
Technical identity
- Member
work-reportbench-dca823c910- Object type
- source work
- Object key
work-reportbench-dca823c910- Object ID
em:dossier-source-work:sha256:a3c37defe96fa413eeb6391ba84067bec7456d35921aaf1b38c7ad003078fb54
- ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry — examined-source-work
Technical identity
- Member
work-researcherbench-82729ab60f- Object type
- source work
- Object key
work-researcherbench-82729ab60f- Object ID
em:dossier-source-work:sha256:8ece2d6fcbf199ebb71533abd1448ccd8796f710bb7759b59557d9856a17a2a3
- Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents — examined-source-work
Technical identity
- Member
work-url-health-f64342d493- Object type
- source work
- Object key
work-url-health-f64342d493- Object ID
em:dossier-source-work:sha256:ebddaffccfcd23869d5dd243d9f4272b520252f96cd784ed4058bacef7f764aa
7 · Candidate warrant roots
- Cited but Not Verified operationalized link access, topical relevance, and factual support separately and reported materially different rates.
Technical identity
- Member
relation-cnv-link-relevance-support-gap-165443d270- Object type
- evidence relation
- Object key
relation-cnv-link-relevance-support-gap-165443d270- Object ID
em:dossier-evidence-relation:sha256:64e195a6456aebffbb478b57f1cefbe57b12973371ad65e8360feffcf08eae3d
- Within the Cited but Not Verified harness, the 2-to-150-call ablation reduced reported Fact Check scores for two setups without establishing a general causal law about search depth.
Technical identity
- Member
relation-cnv-search-depth-ablation-9c01321092- Object type
- evidence relation
- Object key
relation-cnv-search-depth-ablation-9c01321092- Object ID
em:dossier-evidence-relation:sha256:454a592bc79732fb100cc628b9b5c7caa7eef3358f0a3acefc85d7e55147fdba
- DeepResearch Bench evaluated binary support for deduplicated statement-URL pairs; numeric values are edition-specific.
Technical identity
- Member
relation-deepresearch-bench-fact-a3f61d7a3a- Object type
- evidence relation
- Object key
relation-deepresearch-bench-fact-a3f61d7a3a- Object ID
em:dossier-evidence-relation:sha256:6adf0bc790adeb0f5b77cd93a3a1e1f7fbf3b4f2cd43d447246cd5c3a1d5afde
- DeepTRACE measured statement-source support and found between-system variation; its Gemini value is internally inconsistent between table and prose.
Technical identity
- Member
relation-deeptrace-support-variation-1a84ef7c6f- Object type
- evidence relation
- Object key
relation-deeptrace-support-variation-1a84ef7c6f- Object ID
em:dossier-evidence-relation:sha256:6d44f25458001a3d2b303c223d05f31ec5d47f2a5870083593594141290a3a69
- In one five-system dermatology-review audit, reference identifiability and metadata correctness did not establish sentence-level claim-citation concordance.
Technical identity
- Member
relation-keplinger-metadata-versus-support-c23e105c8b- Object type
- evidence relation
- Object key
relation-keplinger-metadata-versus-support-c23e105c8b- Object ID
em:dossier-evidence-relation:sha256:cf9857ecb3c92201f72007257a23a62a68c8b655f551d3e62392baef87507e8a
- ReportBench compared cited statements with retrieved cited-page content and reported sub-100-percent semantic match rates in its bounded survey-task setting.
Technical identity
- Member
relation-reportbench-match-rate-6964e41a69- Object type
- evidence relation
- Object key
relation-reportbench-match-rate-6964e41a69- Object ID
em:dossier-evidence-relation:sha256:ce23bc99cef3ca2b0b0e3597ada68536bf0813903e3468c894914c79a30c6d41
- The URL-health study measured HTTP resolution and Wayback presence, not semantic claim support, on outputs including reused DeepResearch Bench material.
Technical identity
- Member
relation-url-health-resolution-0b26fb45c7- Object type
- evidence relation
- Object key
relation-url-health-resolution-0b26fb45c7- Object ID
em:dossier-evidence-relation:sha256:fd5741fb1196a75091a20a03b6e903c1fdc7e338c94d9f366d8cec6caf3613fe
34 · Unresolved citation occurrences
- Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype — unresolved
Technical identity
- Member
V2-SOL-01:s1_keplinger- Object type
- citation occurrence
- Object key
V2-SOL-01:s1_keplinger- Object ID
V2-SOL-01:s1_keplinger- Status
- unresolved
- Supplementary materials of the article: Assessment of Deep Research for Dermatology Literature Reviews: Deep Concern Over the Hype — unresolved
Technical identity
- Member
V2-SOL-01:s1a_keplinger_data- Object type
- citation occurrence
- Object key
V2-SOL-01:s1a_keplinger_data- Object ID
V2-SOL-01:s1a_keplinger_data- Status
- unresolved
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents — unresolved
Technical identity
- Member
V2-SOL-01:s2_drbench- Object type
- citation occurrence
- Object key
V2-SOL-01:s2_drbench- Object ID
V2-SOL-01:s2_drbench- Status
- unresolved
- DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence — unresolved
Technical identity
- Member
V2-SOL-01:s3_deeptrace- Object type
- citation occurrence
- Object key
V2-SOL-01:s3_deeptrace- Object ID
V2-SOL-01:s3_deeptrace- Status
- unresolved
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents — unresolved
Technical identity
- Member
V2-SOL-01:s4_cited_not_verified- Object type
- citation occurrence
- Object key
V2-SOL-01:s4_cited_not_verified- Object ID
V2-SOL-01:s4_cited_not_verified- Status
- unresolved
- Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents — unresolved
Technical identity
- Member
V2-SOL-01:s5_url_health- Object type
- citation occurrence
- Object key
V2-SOL-01:s5_url_health- Object ID
V2-SOL-01:s5_url_health- Status
- unresolved
- Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents — unresolved
Technical identity
- Member
V2-SOL-02:S1- Object type
- citation occurrence
- Object key
V2-SOL-02:S1- Object ID
V2-SOL-02:S1- Status
- unresolved
- Supplementary materials of the article: Assessment of Deep Research for Dermatology Literature Reviews: Deep Concern Over the Hype — unresolved
Technical identity
- Member
V2-SOL-02:S3- Object type
- citation occurrence
- Object key
V2-SOL-02:S3- Object ID
V2-SOL-02:S3- Status
- unresolved
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents — unresolved
Technical identity
- Member
V2-SOL-02:S4- Object type
- citation occurrence
- Object key
V2-SOL-02:S4- Object ID
V2-SOL-02:S4- Status
- unresolved
- ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks — unresolved
Technical identity
- Member
V2-SOL-02:S5- Object type
- citation occurrence
- Object key
V2-SOL-02:S5- Object ID
V2-SOL-02:S5- Status
- unresolved
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents — unresolved
Technical identity
- Member
V2-SOL-02:S7- Object type
- citation occurrence
- Object key
V2-SOL-02:S7- Object ID
V2-SOL-02:S7- Status
- unresolved
- Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype — unresolved
Technical identity
- Member
V2-SOL-03:s1- Object type
- citation occurrence
- Object key
V2-SOL-03:s1- Object ID
V2-SOL-03:s1- Status
- unresolved
- DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence — unresolved
Technical identity
- Member
V2-SOL-03:s3- Object type
- citation occurrence
- Object key
V2-SOL-03:s3- Object ID
V2-SOL-03:s3- Status
- unresolved
- Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents — unresolved
Technical identity
- Member
V2-SOL-03:s4- Object type
- citation occurrence
- Object key
V2-SOL-03:s4- Object ID
V2-SOL-03:s4- Status
- unresolved
- Supplementary materials of the article: Assessment of Deep Research for Dermatology Literature Reviews: Deep Concern Over the Hype — unresolved
Technical identity
- Member
V2-SOL-04:S6- Object type
- citation occurrence
- Object key
V2-SOL-04:S6- Object ID
V2-SOL-04:S6- Status
- unresolved
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-01:s1_deepresearchbench- Object type
- citation occurrence
- Object key
V2-TERRA-01:s1_deepresearchbench- Object ID
V2-TERRA-01:s1_deepresearchbench- Status
- unresolved
- ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks — unresolved
Technical identity
- Member
V2-TERRA-01:s2_reportbench- Object type
- citation occurrence
- Object key
V2-TERRA-01:s2_reportbench- Object ID
V2-TERRA-01:s2_reportbench- Status
- unresolved
- ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry — unresolved
Technical identity
- Member
V2-TERRA-01:s3_researcherbench- Object type
- citation occurrence
- Object key
V2-TERRA-01:s3_researcherbench- Object ID
V2-TERRA-01:s3_researcherbench- Status
- unresolved
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-01:s4_cited_not_verified- Object type
- citation occurrence
- Object key
V2-TERRA-01:s4_cited_not_verified- Object ID
V2-TERRA-01:s4_cited_not_verified- Status
- unresolved
- Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-01:s5_urlhealth- Object type
- citation occurrence
- Object key
V2-TERRA-01:s5_urlhealth- Object ID
V2-TERRA-01:s5_urlhealth- Status
- unresolved
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-02:s1_deepresearchbench- Object type
- citation occurrence
- Object key
V2-TERRA-02:s1_deepresearchbench- Object ID
V2-TERRA-02:s1_deepresearchbench- Status
- unresolved
- LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild — unresolved
Technical identity
- Member
V2-TERRA-02:s2_liveresearchbench- Object type
- citation occurrence
- Object key
V2-TERRA-02:s2_liveresearchbench- Object ID
V2-TERRA-02:s2_liveresearchbench- Status
- unresolved
- DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence — unresolved
Technical identity
- Member
V2-TERRA-02:s3_deeptrace- Object type
- citation occurrence
- Object key
V2-TERRA-02:s3_deeptrace- Object ID
V2-TERRA-02:s3_deeptrace- Status
- unresolved
- ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry — unresolved
Technical identity
- Member
V2-TERRA-02:s4_researcherbench- Object type
- citation occurrence
- Object key
V2-TERRA-02:s4_researcherbench- Object ID
V2-TERRA-02:s4_researcherbench- Status
- unresolved
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-03:S1- Object type
- citation occurrence
- Object key
V2-TERRA-03:S1- Object ID
V2-TERRA-03:S1- Status
- unresolved
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-03:S2- Object type
- citation occurrence
- Object key
V2-TERRA-03:S2- Object ID
V2-TERRA-03:S2- Status
- unresolved
- ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks — unresolved
Technical identity
- Member
V2-TERRA-03:S3- Object type
- citation occurrence
- Object key
V2-TERRA-03:S3- Object ID
V2-TERRA-03:S3- Status
- unresolved
- Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype — unresolved
Technical identity
- Member
V2-TERRA-03:S4- Object type
- citation occurrence
- Object key
V2-TERRA-03:S4- Object ID
V2-TERRA-03:S4- Status
- unresolved
- PubMed record and Figure 1 caption for Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype — unresolved
Technical identity
- Member
V2-TERRA-03:S6- Object type
- citation occurrence
- Object key
V2-TERRA-03:S6- Object ID
V2-TERRA-03:S6- Status
- unresolved
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-04:S1_deepresearchbench- Object type
- citation occurrence
- Object key
V2-TERRA-04:S1_deepresearchbench- Object ID
V2-TERRA-04:S1_deepresearchbench- Status
- unresolved
- ResearcherBench: Evaluating Deep AI Research Systems on the Frontiers of Scientific Inquiry — unresolved
Technical identity
- Member
V2-TERRA-04:S2_researcherbench- Object type
- citation occurrence
- Object key
V2-TERRA-04:S2_researcherbench- Object ID
V2-TERRA-04:S2_researcherbench- Status
- unresolved
- ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks — unresolved
Technical identity
- Member
V2-TERRA-04:S3_reportbench- Object type
- citation occurrence
- Object key
V2-TERRA-04:S3_reportbench- Object ID
V2-TERRA-04:S3_reportbench- Status
- unresolved
- Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-04:S4_urlhealth- Object type
- citation occurrence
- Object key
V2-TERRA-04:S4_urlhealth- Object ID
V2-TERRA-04:S4_urlhealth- Status
- unresolved
- Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents — unresolved
Technical identity
- Member
V2-TERRA-04:S5_cited_not_verified- Object type
- citation occurrence
- Object key
V2-TERRA-04:S5_cited_not_verified- Object ID
V2-TERRA-04:S5_cited_not_verified- Status
- unresolved
Open the full technical ledger · 9 additional groups
48 · Citation occurrences
- V2-SOL-01:s1_keplinger — unresolved
Technical identity
- Member
V2-SOL-01:s1_keplinger- Object type
- citation occurrence
- Object key
V2-SOL-01:s1_keplinger- Object ID
V2-SOL-01:s1_keplinger- Status
- unresolved
- V2-SOL-01:s1a_keplinger_data — unresolved
Technical identity
- Member
V2-SOL-01:s1a_keplinger_data- Object type
- citation occurrence
- Object key
V2-SOL-01:s1a_keplinger_data- Object ID
V2-SOL-01:s1a_keplinger_data- Status
- unresolved
- V2-SOL-01:s2_drbench — unresolved
Technical identity
- Member
V2-SOL-01:s2_drbench- Object type
- citation occurrence
- Object key
V2-SOL-01:s2_drbench- Object ID
V2-SOL-01:s2_drbench- Status
- unresolved
- V2-SOL-01:s2a_drbench_repo — matched-exact-span
Technical identity
- Member
V2-SOL-01:s2a_drbench_repo- Object type
- citation occurrence
- Object key
V2-SOL-01:s2a_drbench_repo- Object ID
V2-SOL-01:s2a_drbench_repo- Status
- matched-exact-span
- V2-SOL-01:s3_deeptrace — unresolved
Technical identity
- Member
V2-SOL-01:s3_deeptrace- Object type
- citation occurrence
- Object key
V2-SOL-01:s3_deeptrace- Object ID
V2-SOL-01:s3_deeptrace- Status
- unresolved
- V2-SOL-01:s4_cited_not_verified — unresolved
Technical identity
- Member
V2-SOL-01:s4_cited_not_verified- Object type
- citation occurrence
- Object key
V2-SOL-01:s4_cited_not_verified- Object ID
V2-SOL-01:s4_cited_not_verified- Status
- unresolved
- V2-SOL-01:s5_url_health — unresolved
Technical identity
- Member
V2-SOL-01:s5_url_health- Object type
- citation occurrence
- Object key
V2-SOL-01:s5_url_health- Object ID
V2-SOL-01:s5_url_health- Status
- unresolved
- V2-SOL-02:S1 — unresolved
Technical identity
- Member
V2-SOL-02:S1- Object type
- citation occurrence
- Object key
V2-SOL-02:S1- Object ID
V2-SOL-02:S1- Status
- unresolved
- V2-SOL-02:S2 — matched-exact-span
Technical identity
- Member
V2-SOL-02:S2- Object type
- citation occurrence
- Object key
V2-SOL-02:S2- Object ID
V2-SOL-02:S2- Status
- matched-exact-span
- V2-SOL-02:S3 — unresolved
Technical identity
- Member
V2-SOL-02:S3- Object type
- citation occurrence
- Object key
V2-SOL-02:S3- Object ID
V2-SOL-02:S3- Status
- unresolved
- V2-SOL-02:S4 — unresolved
Technical identity
- Member
V2-SOL-02:S4- Object type
- citation occurrence
- Object key
V2-SOL-02:S4- Object ID
V2-SOL-02:S4- Status
- unresolved
- V2-SOL-02:S5 — unresolved
Technical identity
- Member
V2-SOL-02:S5- Object type
- citation occurrence
- Object key
V2-SOL-02:S5- Object ID
V2-SOL-02:S5- Status
- unresolved
- V2-SOL-02:S6 — matched-exact-span
Technical identity
- Member
V2-SOL-02:S6- Object type
- citation occurrence
- Object key
V2-SOL-02:S6- Object ID
V2-SOL-02:S6- Status
- matched-exact-span
- V2-SOL-02:S7 — unresolved
Technical identity
- Member
V2-SOL-02:S7- Object type
- citation occurrence
- Object key
V2-SOL-02:S7- Object ID
V2-SOL-02:S7- Status
- unresolved
- V2-SOL-03:s1 — unresolved
Technical identity
- Member
V2-SOL-03:s1- Object type
- citation occurrence
- Object key
V2-SOL-03:s1- Object ID
V2-SOL-03:s1- Status
- unresolved
- V2-SOL-03:s2 — matched-exact-span
Technical identity
- Member
V2-SOL-03:s2- Object type
- citation occurrence
- Object key
V2-SOL-03:s2- Object ID
V2-SOL-03:s2- Status
- matched-exact-span
- V2-SOL-03:s3 — unresolved
Technical identity
- Member
V2-SOL-03:s3- Object type
- citation occurrence
- Object key
V2-SOL-03:s3- Object ID
V2-SOL-03:s3- Status
- unresolved
- V2-SOL-03:s4 — unresolved
Technical identity
- Member
V2-SOL-03:s4- Object type
- citation occurrence
- Object key
V2-SOL-03:s4- Object ID
V2-SOL-03:s4- Status
- unresolved
- V2-SOL-03:s5 — matched-exact-span
Technical identity
- Member
V2-SOL-03:s5- Object type
- citation occurrence
- Object key
V2-SOL-03:s5- Object ID
V2-SOL-03:s5- Status
- matched-exact-span
- V2-SOL-03:s6 — matched-exact-span
Technical identity
- Member
V2-SOL-03:s6- Object type
- citation occurrence
- Object key
V2-SOL-03:s6- Object ID
V2-SOL-03:s6- Status
- matched-exact-span
- V2-SOL-03:s7 — matched-exact-span
Technical identity
- Member
V2-SOL-03:s7- Object type
- citation occurrence
- Object key
V2-SOL-03:s7- Object ID
V2-SOL-03:s7- Status
- matched-exact-span
- V2-SOL-04:S1 — matched-exact-span
Technical identity
- Member
V2-SOL-04:S1- Object type
- citation occurrence
- Object key
V2-SOL-04:S1- Object ID
V2-SOL-04:S1- Status
- matched-exact-span
- V2-SOL-04:S2 — matched-exact-span
Technical identity
- Member
V2-SOL-04:S2- Object type
- citation occurrence
- Object key
V2-SOL-04:S2- Object ID
V2-SOL-04:S2- Status
- matched-exact-span
- V2-SOL-04:S3 — matched-exact-span
Technical identity
- Member
V2-SOL-04:S3- Object type
- citation occurrence
- Object key
V2-SOL-04:S3- Object ID
V2-SOL-04:S3- Status
- matched-exact-span
- V2-SOL-04:S4 — matched-exact-span
Technical identity
- Member
V2-SOL-04:S4- Object type
- citation occurrence
- Object key
V2-SOL-04:S4- Object ID
V2-SOL-04:S4- Status
- matched-exact-span
- V2-SOL-04:S5 — matched-exact-span
Technical identity
- Member
V2-SOL-04:S5- Object type
- citation occurrence
- Object key
V2-SOL-04:S5- Object ID
V2-SOL-04:S5- Status
- matched-exact-span
- V2-SOL-04:S6 — unresolved
Technical identity
- Member
V2-SOL-04:S6- Object type
- citation occurrence
- Object key
V2-SOL-04:S6- Object ID
V2-SOL-04:S6- Status
- unresolved
- V2-SOL-04:S7 — matched-exact-span
Technical identity
- Member
V2-SOL-04:S7- Object type
- citation occurrence
- Object key
V2-SOL-04:S7- Object ID
V2-SOL-04:S7- Status
- matched-exact-span
- V2-TERRA-01:s1_deepresearchbench — unresolved
Technical identity
- Member
V2-TERRA-01:s1_deepresearchbench- Object type
- citation occurrence
- Object key
V2-TERRA-01:s1_deepresearchbench- Object ID
V2-TERRA-01:s1_deepresearchbench- Status
- unresolved
- V2-TERRA-01:s2_reportbench — unresolved
Technical identity
- Member
V2-TERRA-01:s2_reportbench- Object type
- citation occurrence
- Object key
V2-TERRA-01:s2_reportbench- Object ID
V2-TERRA-01:s2_reportbench- Status
- unresolved
- V2-TERRA-01:s3_researcherbench — unresolved
Technical identity
- Member
V2-TERRA-01:s3_researcherbench- Object type
- citation occurrence
- Object key
V2-TERRA-01:s3_researcherbench- Object ID
V2-TERRA-01:s3_researcherbench- Status
- unresolved
- V2-TERRA-01:s4_cited_not_verified — unresolved
Technical identity
- Member
V2-TERRA-01:s4_cited_not_verified- Object type
- citation occurrence
- Object key
V2-TERRA-01:s4_cited_not_verified- Object ID
V2-TERRA-01:s4_cited_not_verified- Status
- unresolved
- V2-TERRA-01:s5_urlhealth — unresolved
Technical identity
- Member
V2-TERRA-01:s5_urlhealth- Object type
- citation occurrence
- Object key
V2-TERRA-01:s5_urlhealth- Object ID
V2-TERRA-01:s5_urlhealth- Status
- unresolved
- V2-TERRA-02:s1_deepresearchbench — unresolved
Technical identity
- Member
V2-TERRA-02:s1_deepresearchbench- Object type
- citation occurrence
- Object key
V2-TERRA-02:s1_deepresearchbench- Object ID
V2-TERRA-02:s1_deepresearchbench- Status
- unresolved
- V2-TERRA-02:s2_liveresearchbench — unresolved
Technical identity
- Member
V2-TERRA-02:s2_liveresearchbench- Object type
- citation occurrence
- Object key
V2-TERRA-02:s2_liveresearchbench- Object ID
V2-TERRA-02:s2_liveresearchbench- Status
- unresolved
- V2-TERRA-02:s3_deeptrace — unresolved
Technical identity
- Member
V2-TERRA-02:s3_deeptrace- Object type
- citation occurrence
- Object key
V2-TERRA-02:s3_deeptrace- Object ID
V2-TERRA-02:s3_deeptrace- Status
- unresolved
- V2-TERRA-02:s4_researcherbench — unresolved
Technical identity
- Member
V2-TERRA-02:s4_researcherbench- Object type
- citation occurrence
- Object key
V2-TERRA-02:s4_researcherbench- Object ID
V2-TERRA-02:s4_researcherbench- Status
- unresolved
- V2-TERRA-03:S1 — unresolved
Technical identity
- Member
V2-TERRA-03:S1- Object type
- citation occurrence
- Object key
V2-TERRA-03:S1- Object ID
V2-TERRA-03:S1- Status
- unresolved
- V2-TERRA-03:S2 — unresolved
Technical identity
- Member
V2-TERRA-03:S2- Object type
- citation occurrence
- Object key
V2-TERRA-03:S2- Object ID
V2-TERRA-03:S2- Status
- unresolved
- V2-TERRA-03:S3 — unresolved
Technical identity
- Member
V2-TERRA-03:S3- Object type
- citation occurrence
- Object key
V2-TERRA-03:S3- Object ID
V2-TERRA-03:S3- Status
- unresolved
- V2-TERRA-03:S4 — unresolved
Technical identity
- Member
V2-TERRA-03:S4- Object type
- citation occurrence
- Object key
V2-TERRA-03:S4- Object ID
V2-TERRA-03:S4- Status
- unresolved
- V2-TERRA-03:S5 — matched-exact-span
Technical identity
- Member
V2-TERRA-03:S5- Object type
- citation occurrence
- Object key
V2-TERRA-03:S5- Object ID
V2-TERRA-03:S5- Status
- matched-exact-span
- V2-TERRA-03:S6 — unresolved
Technical identity
- Member
V2-TERRA-03:S6- Object type
- citation occurrence
- Object key
V2-TERRA-03:S6- Object ID
V2-TERRA-03:S6- Status
- unresolved
- V2-TERRA-04:S1_deepresearchbench — unresolved
Technical identity
- Member
V2-TERRA-04:S1_deepresearchbench- Object type
- citation occurrence
- Object key
V2-TERRA-04:S1_deepresearchbench- Object ID
V2-TERRA-04:S1_deepresearchbench- Status
- unresolved
- V2-TERRA-04:S2_researcherbench — unresolved
Technical identity
- Member
V2-TERRA-04:S2_researcherbench- Object type
- citation occurrence
- Object key
V2-TERRA-04:S2_researcherbench- Object ID
V2-TERRA-04:S2_researcherbench- Status
- unresolved
- V2-TERRA-04:S3_reportbench — unresolved
Technical identity
- Member
V2-TERRA-04:S3_reportbench- Object type
- citation occurrence
- Object key
V2-TERRA-04:S3_reportbench- Object ID
V2-TERRA-04:S3_reportbench- Status
- unresolved
- V2-TERRA-04:S4_urlhealth — unresolved
Technical identity
- Member
V2-TERRA-04:S4_urlhealth- Object type
- citation occurrence
- Object key
V2-TERRA-04:S4_urlhealth- Object ID
V2-TERRA-04:S4_urlhealth- Status
- unresolved
- V2-TERRA-04:S5_cited_not_verified — unresolved
Technical identity
- Member
V2-TERRA-04:S5_cited_not_verified- Object type
- citation occurrence
- Object key
V2-TERRA-04:S5_cited_not_verified- Object ID
V2-TERRA-04:S5_cited_not_verified- Status
- unresolved
27 · Resolving URL roots
- https://arxiv.org/abs/2604.03173 — retrieved
Technical identity
- Member
https://arxiv.org/abs/2604.03173- Object type
- cited url
- Object key
https://arxiv.org/abs/2604.03173- Object ID
https://arxiv.org/abs/2604.03173- Status
- retrieved
- https://arxiv.org/abs/2605.06635 — retrieved
Technical identity
- Member
https://arxiv.org/abs/2605.06635- Object type
- cited url
- Object key
https://arxiv.org/abs/2605.06635- Object ID
https://arxiv.org/abs/2605.06635- Status
- retrieved
- https://arxiv.org/abs/2607.08700 — retrieved
Technical identity
- Member
https://arxiv.org/abs/2607.08700- Object type
- cited url
- Object key
https://arxiv.org/abs/2607.08700- Object ID
https://arxiv.org/abs/2607.08700- Status
- retrieved
- https://arxiv.org/html/2506.11763 — retrieved
Technical identity
- Member
https://arxiv.org/html/2506.11763- Object type
- cited url
- Object key
https://arxiv.org/html/2506.11763- Object ID
https://arxiv.org/html/2506.11763- Status
- retrieved
- https://arxiv.org/html/2506.11763v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2506.11763v1- Object type
- cited url
- Object key
https://arxiv.org/html/2506.11763v1- Object ID
https://arxiv.org/html/2506.11763v1- Status
- retrieved
- https://arxiv.org/html/2507.16280 — retrieved
Technical identity
- Member
https://arxiv.org/html/2507.16280- Object type
- cited url
- Object key
https://arxiv.org/html/2507.16280- Object ID
https://arxiv.org/html/2507.16280- Status
- retrieved
- https://arxiv.org/html/2508.15804 — retrieved
Technical identity
- Member
https://arxiv.org/html/2508.15804- Object type
- cited url
- Object key
https://arxiv.org/html/2508.15804- Object ID
https://arxiv.org/html/2508.15804- Status
- retrieved
- https://arxiv.org/html/2508.15804v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2508.15804v1- Object type
- cited url
- Object key
https://arxiv.org/html/2508.15804v1- Object ID
https://arxiv.org/html/2508.15804v1- Status
- retrieved
- https://arxiv.org/html/2509.04499 — retrieved
Technical identity
- Member
https://arxiv.org/html/2509.04499- Object type
- cited url
- Object key
https://arxiv.org/html/2509.04499- Object ID
https://arxiv.org/html/2509.04499- Status
- retrieved
- https://arxiv.org/html/2509.04499v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2509.04499v1- Object type
- cited url
- Object key
https://arxiv.org/html/2509.04499v1- Object ID
https://arxiv.org/html/2509.04499v1- Status
- retrieved
- https://arxiv.org/html/2604.03173 — retrieved
Technical identity
- Member
https://arxiv.org/html/2604.03173- Object type
- cited url
- Object key
https://arxiv.org/html/2604.03173- Object ID
https://arxiv.org/html/2604.03173- Status
- retrieved
- https://arxiv.org/html/2604.03173v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2604.03173v1- Object type
- cited url
- Object key
https://arxiv.org/html/2604.03173v1- Object ID
https://arxiv.org/html/2604.03173v1- Status
- retrieved
- https://arxiv.org/html/2605.06635 — retrieved
Technical identity
- Member
https://arxiv.org/html/2605.06635- Object type
- cited url
- Object key
https://arxiv.org/html/2605.06635- Object ID
https://arxiv.org/html/2605.06635- Status
- retrieved
- https://arxiv.org/html/2605.06635v1 — retrieved
Technical identity
- Member
https://arxiv.org/html/2605.06635v1- Object type
- cited url
- Object key
https://arxiv.org/html/2605.06635v1- Object ID
https://arxiv.org/html/2605.06635v1- Status
- retrieved
- https://arxiv.org/pdf/2507.16280 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2507.16280- Object type
- cited url
- Object key
https://arxiv.org/pdf/2507.16280- Object ID
https://arxiv.org/pdf/2507.16280- Status
- retrieved
- https://arxiv.org/pdf/2508.15804 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2508.15804- Object type
- cited url
- Object key
https://arxiv.org/pdf/2508.15804- Object ID
https://arxiv.org/pdf/2508.15804- Status
- retrieved
- https://arxiv.org/pdf/2510.14240v5 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2510.14240v5- Object type
- cited url
- Object key
https://arxiv.org/pdf/2510.14240v5- Object ID
https://arxiv.org/pdf/2510.14240v5- Status
- retrieved
- https://arxiv.org/pdf/2604.03173 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2604.03173- Object type
- cited url
- Object key
https://arxiv.org/pdf/2604.03173- Object ID
https://arxiv.org/pdf/2604.03173- Status
- retrieved
- https://arxiv.org/pdf/2605.06635 — retrieved
Technical identity
- Member
https://arxiv.org/pdf/2605.06635- Object type
- cited url
- Object key
https://arxiv.org/pdf/2605.06635- Object ID
https://arxiv.org/pdf/2605.06635- Status
- retrieved
- https://data.mendeley.com/datasets/3s73z9zf3c/1 — retrieved
Technical identity
- Member
https://data.mendeley.com/datasets/3s73z9zf3c/1- Object type
- cited url
- Object key
https://data.mendeley.com/datasets/3s73z9zf3c/1- Object ID
https://data.mendeley.com/datasets/3s73z9zf3c/1- Status
- retrieved
- https://data.mendeley.com/datasets/3s73z9zf3c/2 — retrieved
Technical identity
- Member
https://data.mendeley.com/datasets/3s73z9zf3c/2- Object type
- cited url
- Object key
https://data.mendeley.com/datasets/3s73z9zf3c/2- Object ID
https://data.mendeley.com/datasets/3s73z9zf3c/2- Status
- retrieved
- https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf — retrieved
Technical identity
- Member
https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf- Object type
- cited url
- Object key
https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf- Object ID
https://deepresearch-bench.github.io/static/papers/deepresearch-bench.pdf- Status
- retrieved
- https://github.com/Ayanami0730/deep_research_bench — retrieved
Technical identity
- Member
https://github.com/Ayanami0730/deep_research_bench- Object type
- cited url
- Object key
https://github.com/Ayanami0730/deep_research_bench- Object ID
https://github.com/Ayanami0730/deep_research_bench- Status
- retrieved
- https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/ — retrieved
Technical identity
- Member
https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/- Object type
- cited url
- Object key
https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/- Object ID
https://pmc.ncbi.nlm.nih.gov/articles/PMC13109748/- Status
- retrieved
- https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf — retrieved
Technical identity
- Member
https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf- Object type
- cited url
- Object key
https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf- Object ID
https://proceedings.iclr.cc/paper_files/paper/2026/file/465f22be10e07b301c6ed58f0472f704-Paper-Conference.pdf- Status
- retrieved
- https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf — retrieved
Technical identity
- Member
https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf- Object type
- cited url
- Object key
https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf- Object ID
https://proceedings.iclr.cc/paper_files/paper/2026/file/ad08767706825033b99122332293033d-Paper-Conference.pdf- Status
- retrieved
- https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html — retrieved
Technical identity
- Member
https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html- Object type
- cited url
- Object key
https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html- Object ID
https://proceedings.iclr.cc/paper_files/paper/2026/hash/ad08767706825033b99122332293033d-Abstract-Conference.html- Status
- retrieved
14 · Examined editions
- Quote-minimal projection of edition:citation-verifier-arxiv-v1 — examined-edition
Technical identity
- Member
edition-citation-verifier-arxiv-v1-acfd4abab7- Object type
- edition
- Object key
edition-citation-verifier-arxiv-v1-acfd4abab7- Object ID
em:dossier-edition:sha256:11f00fc6576322cec62671d5ff7dec3c0c9bed06c139e6f704054259b06241c4
- Quote-minimal projection of edition:cnv-arxiv-v1 — examined-edition
Technical identity
- Member
edition-cnv-arxiv-v1-f24001c50a- Object type
- edition
- Object key
edition-cnv-arxiv-v1-f24001c50a- Object ID
em:dossier-edition:sha256:601f0e4510819607265b94c8261884c072d559e63de9f71dbfc6bca5d33c5e29
- Quote-minimal projection of edition:deeptrace-arxiv-v1 — examined-edition
Technical identity
- Member
edition-deeptrace-arxiv-v1-70a6e720c1- Object type
- edition
- Object key
edition-deeptrace-arxiv-v1-70a6e720c1- Object ID
em:dossier-edition:sha256:c7779c770aa24aa5925b5fe6e66f968c733e8522d30bcdc4290bc9409bbe8b5b
- Quote-minimal projection of edition:deeptrace-iclr-2026 — examined-edition
Technical identity
- Member
edition-deeptrace-iclr-2026-b2b153eaa6- Object type
- edition
- Object key
edition-deeptrace-iclr-2026-b2b153eaa6- Object ID
em:dossier-edition:sha256:1a587168a59e161ea083b7b289339c5f41444a26f2f82a2eb8acb43b27367f70
- Quote-minimal projection of edition:drbench-arxiv-v1 — examined-edition
Technical identity
- Member
edition-drbench-arxiv-v1-7afa5ade36- Object type
- edition
- Object key
edition-drbench-arxiv-v1-7afa5ade36- Object ID
em:dossier-edition:sha256:c0f1d83abed0c9adcc86259b5bfe38e3f18b290f25227b5b9e77c99322fe0b2c
- Quote-minimal projection of edition:drbench-iclr-2026 — examined-edition
Technical identity
- Member
edition-drbench-iclr-2026-d00a3dcdb6- Object type
- edition
- Object key
edition-drbench-iclr-2026-d00a3dcdb6- Object ID
em:dossier-edition:sha256:47d8d33326a498097021dc5754365cbb8f5abfd3e628e90908d2342f0b6c7cf1
- Quote-minimal projection of edition:drbench-repo-main-469cce5 — examined-edition
Technical identity
- Member
edition-drbench-repo-main-469cce5-4f8964f3e3- Object type
- edition
- Object key
edition-drbench-repo-main-469cce5-4f8964f3e3- Object ID
em:dossier-edition:sha256:bf5c65b640b321fb75bf8b7f96854f151f834a7d31a2fc9d2bfb783852e7262b
- Quote-minimal projection of edition:keplinger-supplement-v1 — examined-edition
Technical identity
- Member
edition-keplinger-supplement-v1-f6ddb4c04a- Object type
- edition
- Object key
edition-keplinger-supplement-v1-f6ddb4c04a- Object ID
em:dossier-edition:sha256:8c80a50cd40cbb31bdaedb6730e8e173e3edc0f3440538dbcc4878eb0997ffd9
- Quote-minimal projection of edition:keplinger-supplement-v2 — examined-edition
Technical identity
- Member
edition-keplinger-supplement-v2-01e44c09d8- Object type
- edition
- Object key
edition-keplinger-supplement-v2-01e44c09d8- Object ID
em:dossier-edition:sha256:dca82f9514bbd76d7afb655b2fe3d11d98dc6950b90c3065d81afa335bd86418
- Quote-minimal projection of edition:keplinger-vor-2025 — examined-edition
Technical identity
- Member
edition-keplinger-vor-2025-10ba10f860- Object type
- edition
- Object key
edition-keplinger-vor-2025-10ba10f860- Object ID
em:dossier-edition:sha256:ecbbc5366e2c53ebf6358f0f4c06b7076e158210edd3a081f16af7ab0b029761
- Quote-minimal projection of edition:liveresearchbench-arxiv-v5 — examined-edition
Technical identity
- Member
edition-liveresearchbench-arxiv-v5-f5644763e5- Object type
- edition
- Object key
edition-liveresearchbench-arxiv-v5-f5644763e5- Object ID
em:dossier-edition:sha256:73c767cab5707e7c87ea4cb96cc6a3434512ae75363371f6d0aad2a365c4e11c
- Quote-minimal projection of edition:reportbench-arxiv-v1 — examined-edition
Technical identity
- Member
edition-reportbench-arxiv-v1-25888dc44b- Object type
- edition
- Object key
edition-reportbench-arxiv-v1-25888dc44b- Object ID
em:dossier-edition:sha256:c674e09fbcbadea10ca1f9c3bb17f5573f020fbc209410c85f3c8f56d53255b6
- Quote-minimal projection of edition:researcherbench-arxiv-v1 — examined-edition
Technical identity
- Member
edition-researcherbench-arxiv-v1-39a8b256d7- Object type
- edition
- Object key
edition-researcherbench-arxiv-v1-39a8b256d7- Object ID
em:dossier-edition:sha256:e1cb847e48cc813a003705644839d51e54af0b84d06e0f8419d14a03764b93cd
- Quote-minimal projection of edition:url-health-arxiv-v1 — examined-edition
Technical identity
- Member
edition-url-health-arxiv-v1-85fb934b53- Object type
- edition
- Object key
edition-url-health-arxiv-v1-85fb934b53- Object ID
em:dossier-edition:sha256:89224c483a2c88c51351393bd2ae482b8f2642a27b621c5a7a1401b05fe86b2f
72 · Accepted exact span roots
- Evaluation methodology, lines 144-149 — matched-exact-span
Technical identity
- Member
span-015bb68c904bf225e84c82b1acffb3cc38a4a087d7b0f79d-4c454092b1- Object type
- span
- Object key
span-015bb68c904bf225e84c82b1acffb3cc38a4a087d7b0f79d-4c454092b1- Object ID
em:dossier-span:sha256:ed08815f4aabd455caf37f61a1e37a2dc35725098f2e9be5c6da6c9d5854d612
- Appendix A.1 'Limitations' — matched-exact-span
Technical identity
- Member
span-084f11e57cf779850ea87aaf30ba1277438ff9efcb533fd2-fe72b27cfb- Object type
- span
- Object key
span-084f11e57cf779850ea87aaf30ba1277438ff9efcb533fd2-fe72b27cfb- Object ID
em:dossier-span:sha256:bc41155b5354576b75743d3e75b4e6242ea19e93d211c82faceeb28b3974c083
- Main text, paragraph beginning 'For their high performances in generating reference lists' — matched-exact-span
Technical identity
- Member
span-092745c7db6407d4d52927642741cde229fad05a5347bb18-7b04227f8f- Object type
- span
- Object key
span-092745c7db6407d4d52927642741cde229fad05a5347bb18-7b04227f8f- Object ID
em:dossier-span:sha256:9f91508aa7be57f8e16c902e5399763ce349e7318b10d6085b65f0f53d5bdb56
- repository README, Overview — matched-exact-span
Technical identity
- Member
span-0abbab3d6269d58eb76d8e90eff1e4c27512cf46d9b8e5ff-54e5759a8b- Object type
- span
- Object key
span-0abbab3d6269d58eb76d8e90eff1e4c27512cf46d9b8e5ff-54e5759a8b- Object ID
em:dossier-span:sha256:59d1cfd2232e3f962c838993d6a5456b6a1f66dfb989bcee79f4fc7b5b76a378
- Table 1, lines 177-182 — matched-exact-span
Technical identity
- Member
span-0d4f357f2a5565bdaea01a1e537650958d71216868d1a2b0-9b0af35d76- Object type
- span
- Object key
span-0d4f357f2a5565bdaea01a1e537650958d71216868d1a2b0-9b0af35d76- Object ID
em:dossier-span:sha256:fd8835d2aaa9358bd7dfbcf07848ed19001fa82f11e45ceff3374cdd4e882be3
- Section 3.2, lines 144-146 — matched-exact-span
Technical identity
- Member
span-13cb0ddb087b82988b7445a9cfb02562f9c044ef4f244e8b-87c3b42c68- Object type
- span
- Object key
span-13cb0ddb087b82988b7445a9cfb02562f9c044ef4f244e8b-87c3b42c68- Object ID
em:dossier-span:sha256:4648142e8019a2d54f201844685fbb87a921d93fc24b0f5c08f8124a82ffc374
- Table 1, Perplexity Deep Research citation-accuracy cell — matched-exact-span
Technical identity
- Member
span-196c54d6212fbc0c054dbf8e8467f2388c1f788bb93f4b1a-d460e927f6- Object type
- span
- Object key
span-196c54d6212fbc0c054dbf8e8467f2388c1f788bb93f4b1a-d460e927f6- Object ID
em:dossier-span:sha256:b118f44725ec505886f92a94123fe289be763523b8afb669757c72ccd0d8c352
- Limitations, lines 259-261 — matched-exact-span
Technical identity
- Member
span-1db12b68cfeb4c5f5a96fa9cd2e2bd46e8dfb4f096f73154-cea47f0c65- Object type
- span
- Object key
span-1db12b68cfeb4c5f5a96fa9cd2e2bd46e8dfb4f096f73154-cea47f0c65- Object ID
em:dossier-span:sha256:bf94ce1ab912090b1db248bca0eae62fb77c0f4f12f2fffca9cafaf6524deadd
- page 16, FACT judge validation — matched-exact-span
Technical identity
- Member
span-279db725380c133044944dccb379b75a396242219aa30437-569fc9e2fd- Object type
- span
- Object key
span-279db725380c133044944dccb379b75a396242219aa30437-569fc9e2fd- Object ID
em:dossier-span:sha256:a59ed2a9ea0e6972bc3f71d63feb1c361b76eb8d8fa5bb679c7beab61a32b713
- Table 1, OpenAI Deep Research row; FACT columns — matched-exact-span
Technical identity
- Member
span-2f311bfb451c6208101cb7583af37c338914fcdb10f5c75b-90e7764ce2- Object type
- span
- Object key
span-2f311bfb451c6208101cb7583af37c338914fcdb10f5c75b-90e7764ce2- Object ID
em:dossier-span:sha256:762ebe0afa7a2ddf8eb19d879c91f63d1de7d25192f10d248b65fefb0e113038
- Section 4, line 186 — matched-exact-span
Technical identity
- Member
span-3015a109e7898cb720e426e9a57c526277b648c75f1fb4b1-745d84ff44- Object type
- span
- Object key
span-3015a109e7898cb720e426e9a57c526277b648c75f1fb4b1-745d84ff44- Object ID
em:dossier-span:sha256:e896138fd05fe0904311d35606553601c77784112c448651ce822a85e31ed99c
- page 14, Table 3 — matched-exact-span
Technical identity
- Member
span-35927851edd2e7e5e0f60d98498940f88304ba99bf1f85a0-2fe586436b- Object type
- span
- Object key
span-35927851edd2e7e5e0f60d98498940f88304ba99bf1f85a0-2fe586436b- Object ID
em:dossier-span:sha256:6cf2883b02dd404844a662bae3367ab60d91f6847160a3df9c6ec6b287dc0858
- Table 1, ChatGPT all-correct subtotal — matched-exact-span
Technical identity
- Member
span-39a9931f05ea356fe904ed15768fa08c66440b1fcb20f98e-191c24bbb2- Object type
- span
- Object key
span-39a9931f05ea356fe904ed15768fa08c66440b1fcb20f98e-191c24bbb2- Object ID
em:dossier-span:sha256:72a3edb3976aa397d38e9a7ccbc18b5e4af6f00c91540cd47aadcf9eddce2439
- Section 4.3, line 212 — matched-exact-span
Technical identity
- Member
span-417182b4c15ac550469e435a02aab1e91b395f72f186312d-e9e2c4a70c- Object type
- span
- Object key
span-417182b4c15ac550469e435a02aab1e91b395f72f186312d-e9e2c4a70c- Object ID
em:dossier-span:sha256:f70e443b9842d25a613f4ee0665344914a109815031eda205da5cd0babba10ae
- main text, paragraph beginning 'For their high performances'; Figure 1 — matched-exact-span
Technical identity
- Member
span-46c392bc942cd88d525d74298e6bc6ebd9aeaec533ddfb7b-774f5b996e- Object type
- span
- Object key
span-46c392bc942cd88d525d74298e6bc6ebd9aeaec533ddfb7b-774f5b996e- Object ID
em:dossier-span:sha256:910f7758be3883fc0964cd1e5412b9c75a586e6c4c7c08e64ebda5b9f541a132
- pp. 1-2, lines 64-95 — matched-exact-span
Technical identity
- Member
span-55de6a6ca9414a252592e9f77544a9259533dd713ce1f12f-0826216ffc- Object type
- span
- Object key
span-55de6a6ca9414a252592e9f77544a9259533dd713ce1f12f-0826216ffc- Object ID
em:dossier-span:sha256:179697ec62048a6465fa50dda34ff54530e700430013a878201b9dadde405cc0
- Section 2 definition discussion and Section 3.3 — matched-exact-span
Technical identity
- Member
span-59d0da64f738e1d8745f2bff3663eb89e273f93fe501afe3-ba69fc58eb- Object type
- span
- Object key
span-59d0da64f738e1d8745f2bff3663eb89e273f93fe501afe3-ba69fc58eb- Object ID
em:dossier-span:sha256:c9ea9babc817442f7cd3a5dc96392c22f987c46d4f8684b7db9942aac245abc0
- Limitations, lines 219-224 — matched-exact-span
Technical identity
- Member
span-5cd9ba4ca72da10cf51c0beddc6ea2765c74721bdd526a67-ed8f789629- Object type
- span
- Object key
span-5cd9ba4ca72da10cf51c0beddc6ea2765c74721bdd526a67-ed8f789629- Object ID
em:dossier-span:sha256:c488019e611ca8dbe62a30e922a1fc7f2201fc1f5caedd8da2886de924d82e35
- Section 1 contributions — matched-exact-span
Technical identity
- Member
span-6885cf2524462022475b5829da081b2d35fcfe7463ca6ad0-3b1a122faf- Object type
- span
- Object key
span-6885cf2524462022475b5829da081b2d35fcfe7463ca6ad0-3b1a122faf- Object ID
em:dossier-span:sha256:c2f13c8a50d0c4d694de87dd111bc046e5b64061f3481f1cf4cb41878791b099
- Section 3.3, line 155 — matched-exact-span
Technical identity
- Member
span-6c1d327e58ef001533ea1c11010e974436bbeafbde138efc-f6efd8d376- Object type
- span
- Object key
span-6c1d327e58ef001533ea1c11010e974436bbeafbde138efc-f6efd8d376- Object ID
em:dossier-span:sha256:d87df9d6e418184717863f7c621ddc6c16838dc569a1ab2a558421fbc20eeaa9
- Section 4.3, Tables 2–3 — matched-exact-span
Technical identity
- Member
span-6e961498ed0f81a950f775956587f741e0eb9f11640fd3cb-afa5b59854- Object type
- span
- Object key
span-6e961498ed0f81a950f775956587f741e0eb9f11640fd3cb-afa5b59854- Object ID
em:dossier-span:sha256:48368b4a9e46339c88189de3ff152e4048ed062992fb4789c77e47e645bcc865
- dataset page, Description — matched-exact-span
Technical identity
- Member
span-6f79c3c824ccf889d73e234335661e5fca68d90f8c78ee97-dbf7848a72- Object type
- span
- Object key
span-6f79c3c824ccf889d73e234335661e5fca68d90f8c78ee97-dbf7848a72- Object ID
em:dossier-span:sha256:5a849ff87effb5df1ca3dfa79cb62b7cc3c30c6a5197cef4a5330f49bf062dd2
- Section 3.3.1-3.3.3 — matched-exact-span
Technical identity
- Member
span-732c03e69c6e142a492275cee5d1e2d474c75422c9b84aaa-f7675998cc- Object type
- span
- Object key
span-732c03e69c6e142a492275cee5d1e2d474c75422c9b84aaa-f7675998cc- Object ID
em:dossier-span:sha256:d4e2f35392b064365ad867f33ead8636bb8bbf3af03c0141585e5ae56c868090
- Abstract, lines 47-48 — matched-exact-span
Technical identity
- Member
span-74f6acafbb4c54d556a572460bf1b45bacd1e293f4aa16cc-5ee15c82c4- Object type
- span
- Object key
span-74f6acafbb4c54d556a572460bf1b45bacd1e293f4aa16cc-5ee15c82c4- Object ID
em:dossier-span:sha256:ea33bc17365ed01ed68ab06f33c4fd2020dc8e6947659e4e9629b44af4aef635
- Appendix D, Table 5 — matched-exact-span
Technical identity
- Member
span-76e9bd59b31c7ebd2ed7a2186e59753a79d3c730e0d7b4fb-9c98d99242- Object type
- span
- Object key
span-76e9bd59b31c7ebd2ed7a2186e59753a79d3c730e0d7b4fb-9c98d99242- Object ID
em:dossier-span:sha256:e247bc28c78a353c87489473329585b1051cf199a4b66c81569e31947e10386a
- Abstract, line 16 — matched-exact-span
Technical identity
- Member
span-794bdf7e0595799afbb0d55f3dc522077aed9615c59f1e35-43f2ba944d- Object type
- span
- Object key
span-794bdf7e0595799afbb0d55f3dc522077aed9615c59f1e35-43f2ba944d- Object ID
em:dossier-span:sha256:1628933030cf1849267cc250802d96ad06a1dc463ebc598b3034885f5eefcd3f
- p. 5, lines 315-329 — matched-exact-span
Technical identity
- Member
span-7a6046a756d6ec0315d330cf0817d062ea48498bdc9c90b3-c3a1e80029- Object type
- span
- Object key
span-7a6046a756d6ec0315d330cf0817d062ea48498bdc9c90b3-c3a1e80029- Object ID
em:dossier-span:sha256:3c149d37c88677f94f1715b536ad1808c4e476392f7e02212adbc723e30d8e27
- page 4, Section 3.2, Support Judgment — matched-exact-span
Technical identity
- Member
span-7d7331942f9d0520e18e96206e7718e5187788be4d48cef9-dfdbc1d019- Object type
- span
- Object key
span-7d7331942f9d0520e18e96206e7718e5187788be4d48cef9-dfdbc1d019- Object ID
em:dossier-span:sha256:d915faef70b54c6751577ba10f4057744b2b1b0b4d10613cdd8d74720a5da23b
- Section 4.2.1, Citation Support Verification and Score Computation — matched-exact-span
Technical identity
- Member
span-886b50d94e3facabc487342cd2af5157cf956622ecfc3686-e7bdad0935- Object type
- span
- Object key
span-886b50d94e3facabc487342cd2af5157cf956622ecfc3686-e7bdad0935- Object ID
em:dossier-span:sha256:96fb10c5924d80b1bf350f219f220a730a2da95d14e01a679c3355d7fd8fc706
- Table 1, ChatGPT subtotal — matched-exact-span
Technical identity
- Member
span-8c8d9a6dc003bf0298542b85df3f6f08db631e68e89f606f-92731379f2- Object type
- span
- Object key
span-8c8d9a6dc003bf0298542b85df3f6f08db631e68e89f606f-92731379f2- Object ID
em:dossier-span:sha256:d9dab2e8e8da55f5a5ddbe3e62c658a7f643cd05c36c117aa8a0dfc76a7b6d09
- Abstract, line 46 — matched-exact-span
Technical identity
- Member
span-8cce3d9ee1e1674ba1b93321dd9b99a55d834ca980451f8a-d2fceafe11- Object type
- span
- Object key
span-8cce3d9ee1e1674ba1b93321dd9b99a55d834ca980451f8a-d2fceafe11- Object ID
em:dossier-span:sha256:e748230bbc2f6b31433eaba4536917834c454cb73a7f18e8d9b975e2cac447b5
- Abstract and Table 1 — matched-exact-span
Technical identity
- Member
span-912c931063109f84ea88aea34891dd5e0f9147d2176af258-4d566ca076- Object type
- span
- Object key
span-912c931063109f84ea88aea34891dd5e0f9147d2176af258-4d566ca076- Object ID
em:dossier-span:sha256:49ee66722d6d523dd485f05c796181af55736c3ceab2a235c5c3b40cca95e439
- README FACT, lines 240-248 — matched-exact-span
Technical identity
- Member
span-92eb7cf19745e24190dda84c77d590941134d09f06805c0f-88afe43377- Object type
- span
- Object key
span-92eb7cf19745e24190dda84c77d590941134d09f06805c0f-88afe43377- Object ID
em:dossier-span:sha256:a28651fed7ffef6fdbbe7f322faa2482aa1e0f6b1e2a0a909eddef59a72740f2
- Dataset description — matched-exact-span
Technical identity
- Member
span-94ad583514aa7e04b8d5f7b8f9cdda6fdffe8ca6712f033d-63c1ba24eb- Object type
- span
- Object key
span-94ad583514aa7e04b8d5f7b8f9cdda6fdffe8ca6712f033d-63c1ba24eb- Object ID
em:dossier-span:sha256:38bf64d13c4edef9c0aba131c84d42e0e08637a661d2552cbf2cb49536813488
- Section 2.2 'Cited statements' — matched-exact-span
Technical identity
- Member
span-9c7a4c186cc85f185aa293a7c5a46c08f9dbbc1a9e63c449-feff07a6e2- Object type
- span
- Object key
span-9c7a4c186cc85f185aa293a7c5a46c08f9dbbc1a9e63c449-feff07a6e2- Object ID
em:dossier-span:sha256:5da64a3b244d7aa2f4baebee7a32be87f2f4255de92db8287d1b11a2a396932d
- pp.4-7, Sections 3.1.1 and 3.2 — matched-exact-span
Technical identity
- Member
span-9cb1700c08368feb234207045354cbf559d6ed80f2b0bae8-f898722eb5- Object type
- span
- Object key
span-9cb1700c08368feb234207045354cbf559d6ed80f2b0bae8-f898722eb5- Object ID
em:dossier-span:sha256:b9cbe6b1d35e74f3c8133d2be41a47d9361a26958e9f644dafd97e9e5acb516a
- Section 3.2, lines 163-171 — matched-exact-span
Technical identity
- Member
span-9dd6eb46529e77a62748093528e52685fbd92d46a756aef7-96d75d9e2b- Object type
- span
- Object key
span-9dd6eb46529e77a62748093528e52685fbd92d46a756aef7-96d75d9e2b- Object ID
em:dossier-span:sha256:8c1ac40e63a414c1a41cd0842632677269c8800967f22ef8247b6fb36f6242ea
- Section 3.2, paragraphs 'Statement-URL Pair Extraction and Deduplication' and 'Support Judgment' — matched-exact-span
Technical identity
- Member
span-9fe42cb48702d8d96ebbbc0309692214ece6ec495c447c06-80da541506- Object type
- span
- Object key
span-9fe42cb48702d8d96ebbbc0309692214ece6ec495c447c06-80da541506- Object ID
em:dossier-span:sha256:aba61c5b1685e20da29c0d6a42dd49b66f0b6c2f3ca08483716ae5c518562d4f
- Official ICLR abstract — matched-exact-span
Technical identity
- Member
span-a08468cb62f2feb21d9cbb95175ce00f54592bd83573cc91-03f65cfa45- Object type
- span
- Object key
span-a08468cb62f2feb21d9cbb95175ce00f54592bd83573cc91-03f65cfa45- Object ID
em:dossier-span:sha256:06ea026aae360f700369f4b1f658c4ca85e8acce431923cd7978ff2358b1ec05
- page 4, source scraping — matched-exact-span
Technical identity
- Member
span-a15ab02e9fcb23df02fb03d28967d4220ddf65ad380d2230-ddf85fa359- Object type
- span
- Object key
span-a15ab02e9fcb23df02fb03d28967d4220ddf65ad380d2230-ddf85fa359- Object ID
em:dossier-span:sha256:12ab62355d178256bbaed6cdf5cbf6ae150410d9364f98cced347b54161fa5e8
- page 3, Section 3.3 — matched-exact-span
Technical identity
- Member
span-a18e778fac3d49e81167f05e09fbc361e91af8c0c01b0fec-ca1b18e206- Object type
- span
- Object key
span-a18e778fac3d49e81167f05e09fbc361e91af8c0c01b0fec-ca1b18e206- Object ID
em:dossier-span:sha256:73d72803976f4bb5529880a7185545e8b0ce5581409b9f64ba6ace3ac07c4e2c
- p.14, Table 3 — matched-exact-span
Technical identity
- Member
span-aa1534ce2e177153ab85e512deb8d064d14ec1eae16d8032-2299096a09- Object type
- span
- Object key
span-aa1534ce2e177153ab85e512deb8d064d14ec1eae16d8032-2299096a09- Object ID
em:dossier-span:sha256:2aa386b3653a99db3b670f783272056371480ed287dc1f62a51d3d587d680996
- p. 4, lines 150-159 — matched-exact-span
Technical identity
- Member
span-b0a39c963cdfdc5f9852cfc9f7e33e05d31232bd1d899885-adf9545222- Object type
- span
- Object key
span-b0a39c963cdfdc5f9852cfc9f7e33e05d31232bd1d899885-adf9545222- Object ID
em:dossier-span:sha256:0b565d8281beb5c9b95d300108446049bc4c93de4dc3e80a501f41e85d0a98a5
- Main text, paragraph beginning 'To address the gap' (search-indexed primary full text) — matched-exact-span
Technical identity
- Member
span-b38a2af5982b4c85bc205d2f533a23ed3a8f40a49b651a5f-27395a6291- Object type
- span
- Object key
span-b38a2af5982b4c85bc205d2f533a23ed3a8f40a49b651a5f-27395a6291- Object ID
em:dossier-span:sha256:54d8710861e7e1ee03c50697f1316c12138246e303a08c843fdadecfa99b8c5e
- Section 5.1 Results — matched-exact-span
Technical identity
- Member
span-b68153666e4e12aee8dc887fef0a61fa5f44b5f680a0b7eb-769c2cc17d- Object type
- span
- Object key
span-b68153666e4e12aee8dc887fef0a61fa5f44b5f680a0b7eb-769c2cc17d- Object ID
em:dossier-span:sha256:d90d09f34963ab45eebda00e5606202b7a929a8e000663d691d6536936d7a85d
- Main text, following paragraph (search-indexed primary full text) — matched-exact-span
Technical identity
- Member
span-b6a6ba48a2c4e352c8565b671a15a90400739f2aeefda8a6-e8232daf27- Object type
- span
- Object key
span-b6a6ba48a2c4e352c8565b671a15a90400739f2aeefda8a6-e8232daf27- Object ID
em:dossier-span:sha256:b9e4b58f255c32e2a9e5e6796e8d35f7f28d7481060d6b35f1e02a3c74d2b3d6
- Appendix C, line 365 — matched-exact-span
Technical identity
- Member
span-b83996e3b5fdf878e04d6d41d0e7a1eebee9fdd9bbccf2ae-820a3eab86- Object type
- span
- Object key
span-b83996e3b5fdf878e04d6d41d0e7a1eebee9fdd9bbccf2ae-820a3eab86- Object ID
em:dossier-span:sha256:d753bc9c860da325190141f3f78a0d031f2d6c7cf5e1a51f19f355f44cfb47db
- body, paragraph immediately after Table 1 — matched-exact-span
Technical identity
- Member
span-b903dc2284e1b4d80bb6ef948d79bbdbc7d7447e871281b8-6ef6234316- Object type
- span
- Object key
span-b903dc2284e1b4d80bb6ef948d79bbdbc7d7447e871281b8-6ef6234316- Object ID
em:dossier-span:sha256:f687ae7c3889980d4d3eea1b63b7bea25ae674ebc04caf8c59e7ae4f4fb77464
- Settings and metrics, lines 132-139 — matched-exact-span
Technical identity
- Member
span-ba6b8a8b7d9121ebb05d594176ceed3d1e9dbc637876783a-d85147b6b0- Object type
- span
- Object key
span-ba6b8a8b7d9121ebb05d594176ceed3d1e9dbc637876783a-d85147b6b0- Object ID
em:dossier-span:sha256:f3bc53b3bd401949fea37755e5943e417ceb79e044727a73f7219cfc824ab859
- Abstract and Table 1 — matched-exact-span
Technical identity
- Member
span-bb16d5f06abe8641d9ea6694e549aa15e240dd88946aa47a-5946b6e6b7- Object type
- span
- Object key
span-bb16d5f06abe8641d9ea6694e549aa15e240dd88946aa47a-5946b6e6b7- Object ID
em:dossier-span:sha256:8cf2ff4c32b2dac6d6dfc7684dd2bf7dca9d40fe7b7b36d50dfdcddad067bff3
- Section 3.3 'URL extraction and classification' — matched-exact-span
Technical identity
- Member
span-bb62928b5e0cb4e373b2f6bfeb579d8564d05da5588f8b15-771310f4ef- Object type
- span
- Object key
span-bb62928b5e0cb4e373b2f6bfeb579d8564d05da5588f8b15-771310f4ef- Object ID
em:dossier-span:sha256:57bdc827daee408c0042ec10327966b2b898d525449bee7ecbce1e02330f7f5f
- page 5, Section 4.1 — matched-exact-span
Technical identity
- Member
span-c27aaca02bda06ed764be53351158fc862af9d4a556d3e82-104e7cda52- Object type
- span
- Object key
span-c27aaca02bda06ed764be53351158fc862af9d4a556d3e82-104e7cda52- Object ID
em:dossier-span:sha256:4aa9441f93251fa969f1fe8cc8a4fb6cf728ec3f8879efae3ffff55fabae759d
- page 5, Section 3.3.3 — matched-exact-span
Technical identity
- Member
span-c3dfc98566c27561eb7267972e00e3e1ba6a399a3ff5d002-37f40d3260- Object type
- span
- Object key
span-c3dfc98566c27561eb7267972e00e3e1ba6a399a3ff5d002-37f40d3260- Object ID
em:dossier-span:sha256:5b052dcb433428d39db474fc5c8ae7549944ea380839cf60538b66940163df78
- Section 5 'Limitations' — matched-exact-span
Technical identity
- Member
span-c7dbd1d9e09980703ecbee8161594e4b426c1af63117b286-153d26f046- Object type
- span
- Object key
span-c7dbd1d9e09980703ecbee8161594e4b426c1af63117b286-153d26f046- Object ID
em:dossier-span:sha256:cd2b068589af7da7601362a457b7ac96058de3989dd5187d9e11e3e532e29699
- Abstract, lines 45-49 — matched-exact-span
Technical identity
- Member
span-cd21c450c0d33df20a2b1a539d5725347db1b5bab7d1e986-2e3e0c3ac7- Object type
- span
- Object key
span-cd21c450c0d33df20a2b1a539d5725347db1b5bab7d1e986-2e3e0c3ac7- Object ID
em:dossier-span:sha256:237508b682de825711f61762deb5ce7661d5d197e9fde3aed5f5e80f05fdcdb5
- Section 4.3, Tables 2-3 and following paragraph — matched-exact-span
Technical identity
- Member
span-d638c8b21f0e4a0f840880b6ffe0217ce1623758cc09fdcc-8585f6d39b- Object type
- span
- Object key
span-d638c8b21f0e4a0f840880b6ffe0217ce1623758cc09fdcc-8585f6d39b- Object ID
em:dossier-span:sha256:354ceda8de2c156cc583b4cbb66b6a0f60199ddba0461331a5c1b121e09c2000
- p.33, Appendix E — matched-exact-span
Technical identity
- Member
span-d880991ad784390029d49f84949d083c4789d67d45893d87-c6ef8a5c13- Object type
- span
- Object key
span-d880991ad784390029d49f84949d083c4789d67d45893d87-c6ef8a5c13- Object ID
em:dossier-span:sha256:bebe5aa8ac392afd6d6bf674c11671ebdbfda99e8b197603f13e3d944bed7ea3
- Section 3.1 'Setttings' — matched-exact-span
Technical identity
- Member
span-ddf4320a6d302c13d28b6225eb7e79ac15583349e1b449d4-f89bb46179- Object type
- span
- Object key
span-ddf4320a6d302c13d28b6225eb7e79ac15583349e1b449d4-f89bb46179- Object ID
em:dossier-span:sha256:abc076cdbec4977f668ce36fa6e5edcfebfd81c18c90a4f7913fbb0f8d5fe33a
- Section 4.4, line 217 — matched-exact-span
Technical identity
- Member
span-deada8bacb987a47f2a42e52fbfeb5c1beb3d250c0be79e2-0e91f5cacc- Object type
- span
- Object key
span-deada8bacb987a47f2a42e52fbfeb5c1beb3d250c0be79e2-0e91f5cacc- Object ID
em:dossier-span:sha256:2bd67a5caa606894f4301ca1185c88a4dde02d3c5c4a2cf311463a0f39332443
- Table 1, OpenAI Deep Research row and cited-statements Match Rate column — matched-exact-span
Technical identity
- Member
span-e223640cb0ed12c87ca1d2406f3276f30a3b8d2017dd4dc1-3cfecd76bf- Object type
- span
- Object key
span-e223640cb0ed12c87ca1d2406f3276f30a3b8d2017dd4dc1-3cfecd76bf- Object ID
em:dossier-span:sha256:5ea28918cbd966b0fc14072426f2b7132bfe47f03d327e0b6eaee0629c3740ca
- Paper section 3.1.1, factual-support validation — matched-exact-span
Technical identity
- Member
span-e2c9f6220843a04665f5d1cd142ac15f04211ace5c579fa6-c5e0476df0- Object type
- span
- Object key
span-e2c9f6220843a04665f5d1cd142ac15f04211ace5c579fa6-c5e0476df0- Object ID
em:dossier-span:sha256:a575506a3cca26acda376aa922fdb0e269767f71b01f502a7c50f3d4492e6f03
- pp.17-18, Appendix E, equations 4-6 — matched-exact-span
Technical identity
- Member
span-e4a9f30effc031388ed5c9993dc6f071903bec5e3f1998db-5d95269b76- Object type
- span
- Object key
span-e4a9f30effc031388ed5c9993dc6f071903bec5e3f1998db-5d95269b76- Object ID
em:dossier-span:sha256:c6710bb4b411353c7c600e449cc556e39a3530dc63c002a7b3973ef6bb1793bf
- Abstract, line 16 — matched-exact-span
Technical identity
- Member
span-e54ee1457854a9a5e46f7c7c2e66ac6a5a69b963f8ee3450-8f875cfe94- Object type
- span
- Object key
span-e54ee1457854a9a5e46f7c7c2e66ac6a5a69b963f8ee3450-8f875cfe94- Object ID
em:dossier-span:sha256:df4fc5c1b77f89b40d53711554081c09d64b3257a54bf32e74be00b3f15d9ca4
- README News, 2026-05-11 evaluator migration notice — matched-exact-span
Technical identity
- Member
span-e5bcf0241a1aeae7d9a92755b1bcf0adeeea93a8922f22f8-77a5ff4cc0- Object type
- span
- Object key
span-e5bcf0241a1aeae7d9a92755b1bcf0adeeea93a8922f22f8-77a5ff4cc0- Object ID
em:dossier-span:sha256:abc4ab811e5c574575a0024557dda57a45d8d439ad4ff4ce08bef3753f7a86ef
- p.23, Appendix C, Citation Accuracy — matched-exact-span
Technical identity
- Member
span-e6f447129d9a662fb202d4ac22e16822bacfdbcbcdb7afe3-f7abe2194c- Object type
- span
- Object key
span-e6f447129d9a662fb202d4ac22e16822bacfdbcbcdb7afe3-f7abe2194c- Object ID
em:dossier-span:sha256:2d12624d0f0b1c18bd17cd81ce1742f1daf339a4d5dc188faf576502baa1e6ed
- Section 5.1 and Appendix E, Table 4 — matched-exact-span
Technical identity
- Member
span-ea9cb2e1b0078c0857b789d61d0a0d26801cf66891864705-2f19633d83- Object type
- span
- Object key
span-ea9cb2e1b0078c0857b789d61d0a0d26801cf66891864705-2f19633d83- Object ID
em:dossier-span:sha256:7f4968754938f5e1c4aa96fe8d0c81aed24a12268e7fd6fd09ee3b3b7c9b2579
- p.4, Section 3.2, lines 148-155 — matched-exact-span
Technical identity
- Member
span-eaf37bef7b8dc35f3e00b85d3e58ad872dc0ea604a062c8c-fa09300f85- Object type
- span
- Object key
span-eaf37bef7b8dc35f3e00b85d3e58ad872dc0ea604a062c8c-fa09300f85- Object ID
em:dossier-span:sha256:27d667cb8cff21b646ec759c6c6fe79c5744a28079337d7a7fa9ac98abf8da9d
- README News, lines 176-188 — matched-exact-span
Technical identity
- Member
span-ef637b38f36195bea09205d532e8744daf3e257f93d97144-26007673a3- Object type
- span
- Object key
span-ef637b38f36195bea09205d532e8744daf3e257f93d97144-26007673a3- Object ID
em:dossier-span:sha256:fd761963efd1f957ebe8dae1eb76239c2d17ce1553109a4e0ac420525c73cfcb
- Paragraph after Table 1 — matched-exact-span
Technical identity
- Member
span-f05b3189dc3fafd45b5bde643a91fd0616832928215a37a2-47f72e77e4- Object type
- span
- Object key
span-f05b3189dc3fafd45b5bde643a91fd0616832928215a37a2-47f72e77e4- Object ID
em:dossier-span:sha256:2f331f1e2636907b0cab1000b0947e440fa5f24eec0edaf9498470522e1abe1a
- Appendix C, line 365 — matched-exact-span
Technical identity
- Member
span-f35c9565f2fd047f6e7272dc608bbf6a63813a717bad5354-e6a07f05b6- Object type
- span
- Object key
span-f35c9565f2fd047f6e7272dc608bbf6a63813a717bad5354-e6a07f05b6- Object ID
em:dossier-span:sha256:a18ccb20769a7f5026931d907492839678079992f3ecefcecbfe05557d211246
- Section 4.2.1 'Citation Support Verification' and Section 4.2 'Score Computation', equations (2)-(3) — matched-exact-span
Technical identity
- Member
span-f96ad5daa81153a3689f52f5777fedfd70e8a87d44e7a1c9-3da72b8748- Object type
- span
- Object key
span-f96ad5daa81153a3689f52f5777fedfd70e8a87d44e7a1c9-3da72b8748- Object ID
em:dossier-span:sha256:5aba6568d3cbc2f788868b9ad96059aba175e6976e6989dab2736e0de95355b1
- p.17, Appendix C, lines 704-708 — matched-exact-span
Technical identity
- Member
span-f98f1274859ba98cc538e3be6d11d345a5382cfcb9516aa1-d60b765c48- Object type
- span
- Object key
span-f98f1274859ba98cc538e3be6d11d345a5382cfcb9516aa1-d60b765c48- Object ID
em:dossier-span:sha256:17193f2aab7106eece041bcabda963d9bd172d798792efc058b6a93c9bd4cb0c
0 · Independently confirmed warrant roots
4 · Pending warrant groups
- The captured spans do not semantically close the normalized proposition; the warrant remains pending and receives no credit.
Technical identity
- Member
relation-citation-verifier-calibration-5b40082faa- Object type
- evidence relation
- Object key
relation-citation-verifier-calibration-5b40082faa- Object ID
em:dossier-evidence-relation:sha256:ef8f517c3d030147f56936e279e6260a63f142b3514a5e98475bb83e95940d21
- The captured spans do not semantically close the normalized proposition; the warrant remains pending and receives no credit.
Technical identity
- Member
relation-liveresearchbench-e1-e2-e3-5fb5d671f7- Object type
- evidence relation
- Object key
relation-liveresearchbench-e1-e2-e3-5fb5d671f7- Object ID
em:dossier-evidence-relation:sha256:d8f8705949761213814c9a9c1c47dca7d298d10a0c2f763c5c6ac6c6a372c880
- The captured spans do not semantically close the normalized proposition; the warrant remains pending and receives no credit.
Technical identity
- Member
relation-researcherbench-faithfulness-groundedness-c84dcaee54- Object type
- evidence relation
- Object key
relation-researcherbench-faithfulness-groundedness-c84dcaee54- Object ID
em:dossier-evidence-relation:sha256:c059f728a9e941f48d872e2b9acd4d1c7019a7428045412234b4aa6f44a4a30f
- The captured spans do not semantically close the normalized proposition; the warrant remains pending and receives no credit.
Technical identity
- Member
relation-url-health-correction-loop-eb8a6384c6- Object type
- evidence relation
- Object key
relation-url-health-correction-loop-eb8a6384c6- Object ID
em:dossier-evidence-relation:sha256:22dd32ad9045555bbab3a8c52380e5dd71c6d6769f24ce61436bbcdbc582a736
20 · Unsupported or force-raised claims
- V2-SOL-01:r3_deepresearch_bench_fact — no-credit
Technical identity
- Member
V2-SOL-01:r3_deepresearch_bench_fact- Object type
- claim occurrence
- Object key
V2-SOL-01:r3_deepresearch_bench_fact- Object ID
V2-SOL-01:r3_deepresearch_bench_fact- Status
- no-credit
- V2-SOL-01:r4_deeptrace_support — no-credit
Technical identity
- Member
V2-SOL-01:r4_deeptrace_support- Object type
- claim occurrence
- Object key
V2-SOL-01:r4_deeptrace_support- Object ID
V2-SOL-01:r4_deeptrace_support- Status
- no-credit
- V2-SOL-02:R3_deepresearch_bench_fact — no-credit
Technical identity
- Member
V2-SOL-02:R3_deepresearch_bench_fact- Object type
- claim occurrence
- Object key
V2-SOL-02:R3_deepresearch_bench_fact- Object ID
V2-SOL-02:R3_deepresearch_bench_fact- Status
- no-credit
- V2-SOL-02:R5_deeptrace_audit — no-credit
Technical identity
- Member
V2-SOL-02:R5_deeptrace_audit- Object type
- claim occurrence
- Object key
V2-SOL-02:R5_deeptrace_audit- Object ID
V2-SOL-02:R5_deeptrace_audit- Status
- no-credit
- V2-SOL-03:r3_deepresearch_bench_fact — no-credit
Technical identity
- Member
V2-SOL-03:r3_deepresearch_bench_fact- Object type
- claim occurrence
- Object key
V2-SOL-03:r3_deepresearch_bench_fact- Object ID
V2-SOL-03:r3_deepresearch_bench_fact- Status
- no-credit
- V2-SOL-03:r4_deeptrace_support — no-credit
Technical identity
- Member
V2-SOL-03:r4_deeptrace_support- Object type
- claim occurrence
- Object key
V2-SOL-03:r4_deeptrace_support- Object ID
V2-SOL-03:r4_deeptrace_support- Status
- no-credit
- V2-SOL-03:r8_search_depth_ablation — no-credit
Technical identity
- Member
V2-SOL-03:r8_search_depth_ablation- Object type
- claim occurrence
- Object key
V2-SOL-03:r8_search_depth_ablation- Object ID
V2-SOL-03:r8_search_depth_ablation- Status
- no-credit
- V2-SOL-03:r9_verifier_calibration — no-credit
Technical identity
- Member
V2-SOL-03:r9_verifier_calibration- Object type
- claim occurrence
- Object key
V2-SOL-03:r9_verifier_calibration- Object ID
V2-SOL-03:r9_verifier_calibration- Status
- no-credit
- V2-SOL-04:R1 — no-credit
Technical identity
- Member
V2-SOL-04:R1- Object type
- claim occurrence
- Object key
V2-SOL-04:R1- Object ID
V2-SOL-04:R1- Status
- no-credit
- V2-SOL-04:R2 — no-credit
Technical identity
- Member
V2-SOL-04:R2- Object type
- claim occurrence
- Object key
V2-SOL-04:R2- Object ID
V2-SOL-04:R2- Status
- no-credit
- V2-SOL-04:R3 — no-credit
Technical identity
- Member
V2-SOL-04:R3- Object type
- claim occurrence
- Object key
V2-SOL-04:R3- Object ID
V2-SOL-04:R3- Status
- no-credit
- V2-SOL-04:R4 — no-credit
Technical identity
- Member
V2-SOL-04:R4- Object type
- claim occurrence
- Object key
V2-SOL-04:R4- Object ID
V2-SOL-04:R4- Status
- no-credit
- V2-SOL-04:R5 — no-credit
Technical identity
- Member
V2-SOL-04:R5- Object type
- claim occurrence
- Object key
V2-SOL-04:R5- Object ID
V2-SOL-04:R5- Status
- no-credit
- V2-SOL-04:R8 — no-credit
Technical identity
- Member
V2-SOL-04:R8- Object type
- claim occurrence
- Object key
V2-SOL-04:R8- Object ID
V2-SOL-04:R8- Status
- no-credit
- V2-TERRA-01:r1_deepresearchbench_fact — no-credit
Technical identity
- Member
V2-TERRA-01:r1_deepresearchbench_fact- Object type
- claim occurrence
- Object key
V2-TERRA-01:r1_deepresearchbench_fact- Object ID
V2-TERRA-01:r1_deepresearchbench_fact- Status
- no-credit
- V2-TERRA-01:r4_cited_not_verified_source_attribution — no-credit
Technical identity
- Member
V2-TERRA-01:r4_cited_not_verified_source_attribution- Object type
- claim occurrence
- Object key
V2-TERRA-01:r4_cited_not_verified_source_attribution- Object ID
V2-TERRA-01:r4_cited_not_verified_source_attribution- Status
- no-credit
- V2-TERRA-02:answer — no-credit
Technical identity
- Member
V2-TERRA-02:answer- Object type
- claim occurrence
- Object key
V2-TERRA-02:answer- Object ID
V2-TERRA-02:answer- Status
- no-credit
- V2-TERRA-02:r1_deepresearchbench_fact — no-credit
Technical identity
- Member
V2-TERRA-02:r1_deepresearchbench_fact- Object type
- claim occurrence
- Object key
V2-TERRA-02:r1_deepresearchbench_fact- Object ID
V2-TERRA-02:r1_deepresearchbench_fact- Status
- no-credit
- V2-TERRA-02:r4_deeptrace — no-credit
Technical identity
- Member
V2-TERRA-02:r4_deeptrace- Object type
- claim occurrence
- Object key
V2-TERRA-02:r4_deeptrace- Object ID
V2-TERRA-02:r4_deeptrace- Status
- no-credit
- V2-TERRA-03:R3 — no-credit
Technical identity
- Member
V2-TERRA-03:R3- Object type
- claim occurrence
- Object key
V2-TERRA-03:R3- Object ID
V2-TERRA-03:R3- Status
- no-credit
9 · Independently rejected claims
- V2-SOL-02:R5_deeptrace_audit — independently-rejected
Technical identity
- Member
V2-SOL-02:R5_deeptrace_audit- Object type
- claim occurrence
- Object key
V2-SOL-02:R5_deeptrace_audit- Object ID
V2-SOL-02:R5_deeptrace_audit- Status
- independently-rejected
- V2-SOL-03:r3_deepresearch_bench_fact — independently-rejected
Technical identity
- Member
V2-SOL-03:r3_deepresearch_bench_fact- Object type
- claim occurrence
- Object key
V2-SOL-03:r3_deepresearch_bench_fact- Object ID
V2-SOL-03:r3_deepresearch_bench_fact- Status
- independently-rejected
- V2-SOL-03:r8_search_depth_ablation — independently-rejected
Technical identity
- Member
V2-SOL-03:r8_search_depth_ablation- Object type
- claim occurrence
- Object key
V2-SOL-03:r8_search_depth_ablation- Object ID
V2-SOL-03:r8_search_depth_ablation- Status
- independently-rejected
- V2-SOL-03:r9_verifier_calibration — independently-rejected
Technical identity
- Member
V2-SOL-03:r9_verifier_calibration- Object type
- claim occurrence
- Object key
V2-SOL-03:r9_verifier_calibration- Object ID
V2-SOL-03:r9_verifier_calibration- Status
- independently-rejected
- V2-SOL-04:R1 — independently-rejected
Technical identity
- Member
V2-SOL-04:R1- Object type
- claim occurrence
- Object key
V2-SOL-04:R1- Object ID
V2-SOL-04:R1- Status
- independently-rejected
- V2-SOL-04:R2 — independently-rejected
Technical identity
- Member
V2-SOL-04:R2- Object type
- claim occurrence
- Object key
V2-SOL-04:R2- Object ID
V2-SOL-04:R2- Status
- independently-rejected
- V2-SOL-04:R3 — independently-rejected
Technical identity
- Member
V2-SOL-04:R3- Object type
- claim occurrence
- Object key
V2-SOL-04:R3- Object ID
V2-SOL-04:R3- Status
- independently-rejected
- V2-SOL-04:R4 — independently-rejected
Technical identity
- Member
V2-SOL-04:R4- Object type
- claim occurrence
- Object key
V2-SOL-04:R4- Object ID
V2-SOL-04:R4- Status
- independently-rejected
- V2-SOL-04:R8 — independently-rejected
Technical identity
- Member
V2-SOL-04:R8- Object type
- claim occurrence
- Object key
V2-SOL-04:R8- Object ID
V2-SOL-04:R8- Status
- independently-rejected
3 · Inaccessible carriers
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents — inaccessible
Technical identity
- Member
V2-SOL-02:S4- Object type
- citation occurrence
- Object key
V2-SOL-02:S4- Object ID
V2-SOL-02:S4- Status
- inaccessible
- Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype — inaccessible
Technical identity
- Member
V2-SOL-03:s1- Object type
- citation occurrence
- Object key
V2-SOL-03:s1- Object ID
V2-SOL-03:s1- Status
- inaccessible
- PubMed record and Figure 1 caption for Assessment of Deep Research for dermatology literature reviews: Deep concern over the hype — inaccessible
Technical identity
- Member
V2-TERRA-03:S6- Object type
- citation occurrence
- Object key
V2-TERRA-03:S6- Object ID
V2-TERRA-03:S6- Status
- inaccessible
Five-line lexicon
The units are different on purpose
- Citation occurrence
- One report-level use of a citation, before repeated URLs are collapsed.
- URL root
- One distinct cited URL string; resolution does not prove claim support.
- Source work
- One logical paper, dataset, repository, or audit instrument across editions.
- Candidate warrant root
- One source-method-data proposition that survived bounded semantic review, while residual independence remains unresolved.
- No credit
- The item remains visible but does not support the stronger claim because its carrier, span, semantics, or lineage did not close.