# Span Readbacks V1 - Object ID: `em:research-note:sha256:1aed173e1cf92526561e354439019798b6b51f9371f0dd6fde403f956542f364` - Kind: `research-note` - Repository path: [`research/how-we-know/agent-citation-lineage/span-readbacks-v1.json`](https://github.com/yoheinakajima/epistemedia/blob/f92846570180dfa4511263f8ba98ecd18f7772c9/research/how-we-know/agent-citation-lineage/span-readbacks-v1.json) - Content digest: `48ddabaec9b75acf43bdfc9ab917bee6e6fece418316eba8f1012e646d59dde5` **Also filed under:** [Research Program](https://epistemedia.org/topics/research-program/) ## Source content { "captured_at": "2026-08-23T16:28:41Z", "credit_rule": "Only exact-normalized-match and ordered-fragment-match create exact-span roots; semantic warrant remains a separate review.", "limitations": [ "Text extraction can reorder tables, formulas, and multi-column PDF content.", "An ordered-fragment match confirms each quoted fragment in sequence, not a contiguous sentence.", "A text match does not by itself establish that the source warrants an agent proposition." ], "normalization": "Unicode NFKC, typographic punctuation normalization, and whitespace collapse", "records": [ { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "body, paragraph beginning 'Taking ChatGPT as an example'; Table 1", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "94db53a0356c79519c78f1f5bd01799894b83babb1fc3ced35f740a68a5b3b79", "run_id": "V2-SOL-01", "source_id": "s1_keplinger", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "sp1a", "span_occurrence_id": "V2-SOL-01:s1_keplinger:sp1a", "span_root_id": "span:sha256:c29518951f6335c3c613ebed9c4babc2bc1903426992cd90118a999be69b5cdd" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "body, paragraph immediately after Table 1", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "2e43a0652065a6a1fb69de224082ac79d903cc71cac0664a1cb376cbfa09d0e8", "run_id": "V2-SOL-01", "source_id": "s1_keplinger", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "sp1b", "span_occurrence_id": "V2-SOL-01:s1_keplinger:sp1b", "span_root_id": "span:sha256:b903dc2284e1b4d80bb6ef948d79bbdbc7d7447e871281b8577284883f75ccfa" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "Figure 1 caption", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "05af5f5f154c4bed8267aac71674219aad878b9ec2635ab85e3ae60474cd02c5", "run_id": "V2-SOL-01", "source_id": "s1_keplinger", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "sp1c", "span_occurrence_id": "V2-SOL-01:s1_keplinger:sp1c", "span_root_id": "span:sha256:0bea3f00dfce1763dae86c14901bee21053f2d8ceee7f9dde4ab33ec78d3eb50" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-supplement-v2", "locator": "dataset page, Description", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "c5ab0cef07fb26a5758cd8b25a249016665c446b524e1443a10c4c8929938d21", "run_id": "V2-SOL-01", "source_id": "s1a_keplinger_data", "source_text_sha256": "2e96cc4ae8e28c60fcb94dd40ef64a15252e4416e7bf33185b8b76ea6ff228e4", "span_id": "sp1d", "span_occurrence_id": "V2-SOL-01:s1a_keplinger_data:sp1d", "span_root_id": "span:sha256:6f79c3c824ccf889d73e234335661e5fca68d90f8c78ee97aef488e4fdb32a49" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-iclr-2026", "locator": "page 4, Section 3.2, Support Judgment", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "78f021c07980218ead835a986c84780444479e627dcfa9f2ea126b3604b89ad7", "run_id": "V2-SOL-01", "source_id": "s2_drbench", "source_text_sha256": "ced9e7b0ae4ab2c26add3230a7b40200673ee4fc0c5c763df226bfe784d60016", "span_id": "sp2a", "span_occurrence_id": "V2-SOL-01:s2_drbench:sp2a", "span_root_id": "span:sha256:7d7331942f9d0520e18e96206e7718e5187788be4d48cef995fac79b235db757" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-iclr-2026", "locator": "page 6, Table 1, proprietary deep-research-agent rows", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "fa0ab638c02ed6458f5f0f70cb866f3b5cb4f09dacdd05782d6fa43d58e3a283", "run_id": "V2-SOL-01", "source_id": "s2_drbench", "source_text_sha256": "ced9e7b0ae4ab2c26add3230a7b40200673ee4fc0c5c763df226bfe784d60016", "span_id": "sp2b", "span_occurrence_id": "V2-SOL-01:s2_drbench:sp2b", "span_root_id": "span:sha256:6070d8d9e7ba0d923aca7ae3517013c0e865119cea05c3e9cb0565d273eee0ee" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-iclr-2026", "locator": "page 5, Section 4.1", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "11034cf2238003f213bf87210c9017f57cc743910fa70754f3e61f875abe75e6", "run_id": "V2-SOL-01", "source_id": "s2_drbench", "source_text_sha256": "ced9e7b0ae4ab2c26add3230a7b40200673ee4fc0c5c763df226bfe784d60016", "span_id": "sp2c", "span_occurrence_id": "V2-SOL-01:s2_drbench:sp2c", "span_root_id": "span:sha256:c27aaca02bda06ed764be53351158fc862af9d4a556d3e82074507436f48c3f8" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-iclr-2026", "locator": "page 16, FACT judge validation", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "8be6257e74c3696813fb0079c27e93e8bec16c71d214b6da43811fbd9b406ba4", "run_id": "V2-SOL-01", "source_id": "s2_drbench", "source_text_sha256": "ced9e7b0ae4ab2c26add3230a7b40200673ee4fc0c5c763df226bfe784d60016", "span_id": "sp2d", "span_occurrence_id": "V2-SOL-01:s2_drbench:sp2d", "span_root_id": "span:sha256:279db725380c133044944dccb379b75a396242219aa30437b26ddc40b09a3b5c" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-repo-main-469cce5", "locator": "repository README, Overview", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "2e8262448070ca7bcc1ea305d2d87a722f34721737d455d55f62185010bd2e32", "run_id": "V2-SOL-01", "source_id": "s2a_drbench_repo", "source_text_sha256": "afebe200cb45042b2783d6ad581770bbd8674027d4e7443e2eb6c26720c6cb0c", "span_id": "sp2e", "span_occurrence_id": "V2-SOL-01:s2a_drbench_repo:sp2e", "span_root_id": "span:sha256:0abbab3d6269d58eb76d8e90eff1e4c27512cf46d9b8e5ff0a9f537b18f232fa" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "page 6, Section 3.1.4", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "1320d1a169d78cdf9f0b87b4263fbf3ee04067daefddfa8a93722cf51ac69485", "run_id": "V2-SOL-01", "source_id": "s3_deeptrace", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "sp3a", "span_occurrence_id": "V2-SOL-01:s3_deeptrace:sp3a", "span_root_id": "span:sha256:b45b782077327a7123cff72789773ad2f70f5608c8e0e33b0d211b3d60e0de0a" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "page 8, Table 1", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "b2708c9e7c59cc34ab973c79d61bad55c7cb3a0ad55a47d9e35f17d9e7c98cc3", "run_id": "V2-SOL-01", "source_id": "s3_deeptrace", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "sp3b", "span_occurrence_id": "V2-SOL-01:s3_deeptrace:sp3b", "span_root_id": "span:sha256:4e55438723cddd7dfbd56c115e5fe6e809c0091ec7631928d67490aafc49f118" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "page 4, source scraping", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "a38c9ac275570f2b78dd1e1bf7663579e35f9037131e12d721dfb4c6f005683d", "run_id": "V2-SOL-01", "source_id": "s3_deeptrace", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "sp3c", "span_occurrence_id": "V2-SOL-01:s3_deeptrace:sp3c", "span_root_id": "span:sha256:a15ab02e9fcb23df02fb03d28967d4220ddf65ad380d223049f22b6ab68ed5eb" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "page 14, Table 3", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "bb4f28cd0f4527c633bcfacf51b18ced7387c4a2f266c59d41de7ee899b24b85", "run_id": "V2-SOL-01", "source_id": "s3_deeptrace", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "sp3d", "span_occurrence_id": "V2-SOL-01:s3_deeptrace:sp3d", "span_root_id": "span:sha256:35927851edd2e7e5e0f60d98498940f88304ba99bf1f85a08535663943c2f40d" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "page 6, Table 1", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "8e88d02c36a4e4f27c1f74f8fee3442fce910fa93c790203cec48a745630b0c8", "run_id": "V2-SOL-01", "source_id": "s4_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "sp4a", "span_occurrence_id": "V2-SOL-01:s4_cited_not_verified:sp4a", "span_root_id": "span:sha256:9339db261929e3b56820214b791131dcbe342e20111e4b08916cfa523893810f" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "pages 7-8, Tables 2-3", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "5fb4b4e6e9019214b7a5fef54027c65b1d397c3bd7c38fb58c960f3514697da5", "run_id": "V2-SOL-01", "source_id": "s4_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "sp4b", "span_occurrence_id": "V2-SOL-01:s4_cited_not_verified:sp4b", "span_root_id": "span:sha256:419fcae33b7758515a2334e64b7dca713a139a11d6930bc9cc772559989ae12e" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "page 5, Section 3.3.3", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "e084f6ff65e9a116b127ab06d9745be6354fbcf3e66052c0182bc38177a9ae48", "run_id": "V2-SOL-01", "source_id": "s4_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "sp4c", "span_occurrence_id": "V2-SOL-01:s4_cited_not_verified:sp4c", "span_root_id": "span:sha256:c3dfc98566c27561eb7267972e00e3e1ba6a399a3ff5d002dca2d1233836790c" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "page 3, Section 3.3", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "3a14d6f574bed17e76ef8b560bbca0aa27b3a50918e49461433e34ec7770a4c9", "run_id": "V2-SOL-01", "source_id": "s5_url_health", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "sp5a", "span_occurrence_id": "V2-SOL-01:s5_url_health:sp5a", "span_root_id": "span:sha256:a18e778fac3d49e81167f05e09fbc361e91af8c0c01b0fec52991f0a1e3d0b91" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "page 4, Table 2", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "501db42e628f70556263b3cb1961ea0a67c57fda022002ca72cbe9c7b8a608b3", "run_id": "V2-SOL-01", "source_id": "s5_url_health", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "sp5b", "span_occurrence_id": "V2-SOL-01:s5_url_health:sp5b", "span_root_id": "span:sha256:db9dc28183620369f5ad1fb0f179e8aadbc14c69c0fdb57b8a8b79cd8e95e2a6" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "page 4, Table 2", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "63aba91235638fc3788940cd284864863aee605892d0334c712de8a591789029", "run_id": "V2-SOL-01", "source_id": "s5_url_health", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "sp5c", "span_occurrence_id": "V2-SOL-01:s5_url_health:sp5c", "span_root_id": "span:sha256:541aadd42c71d1bd9c2c458c8e250d5000ffb75f3801eea832a0a0ef58a3914b" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Table 2, openai-deepresearch row", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "5bd6e5242ac0a8839758376181b806b9e9556b6c69e6a5b846c4bae5aaaf60cf", "run_id": "V2-SOL-02", "source_id": "S1", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "S1_SPAN_1", "span_occurrence_id": "V2-SOL-02:S1:S1_SPAN_1", "span_root_id": "span:sha256:a7e8b6b9e8aa380a3d1eaedaae1439792bc858a48735284ecbd2822da1c3c0fe" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Table 2, gemini-2.5-pro-deepresearch row", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "66801673319516701b64b72ab382bc2924cafcd3a33d971598b22c8f90fa37bf", "run_id": "V2-SOL-02", "source_id": "S1", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "S1_SPAN_2", "span_occurrence_id": "V2-SOL-02:S1:S1_SPAN_2", "span_root_id": "span:sha256:388e78d0c793138d79699c82540cb28cbd5722adfe6df119b36ee40a4502d9b5" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "Main text, paragraph beginning 'For their high performances in generating reference lists'", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "39f799b4bf1bcc50a74e5b019c585b970fa01779cf4b07bdeb27d71f35ea455b", "run_id": "V2-SOL-02", "source_id": "S2", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "S2_SPAN_1", "span_occurrence_id": "V2-SOL-02:S2:S2_SPAN_1", "span_root_id": "span:sha256:092745c7db6407d4d52927642741cde229fad05a5347bb1867a5154421060e70" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-supplement-v2", "locator": "Supplementary Text 1, 'ChatGPT Deep Research: Results based on online search for evidence'", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "d95bbfc885a7c2d9a88775f09d0428d6403d88a657b64ce142ae8b9366b400ce", "run_id": "V2-SOL-02", "source_id": "S3", "source_text_sha256": "2e96cc4ae8e28c60fcb94dd40ef64a15252e4416e7bf33185b8b76ea6ff228e4", "span_id": "S3_SPAN_1", "span_occurrence_id": "V2-SOL-02:S3:S3_SPAN_1", "span_root_id": "span:sha256:870d5c8e029e0c3d25b0a4682848e6caafc22ee35db116517a55bf334eea3e2d" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-supplement-v2", "locator": "Supplementary Text 1, uploaded-papers mode summary", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "2cf619f684c7bbccc4e28b04f0b3f93f48e3f8e1289db1bce5b77d379b8bb001", "run_id": "V2-SOL-02", "source_id": "S3", "source_text_sha256": "2e96cc4ae8e28c60fcb94dd40ef64a15252e4416e7bf33185b8b76ea6ff228e4", "span_id": "S3_SPAN_2", "span_occurrence_id": "V2-SOL-02:S3:S3_SPAN_2", "span_root_id": "span:sha256:3bbe9293af4ece39817697cf29b0fe4ab9423d429d9867dec2540b72c82fd5ba" }, { "citation_carrier_accessible": false, "edition_id": "edition:drbench-iclr-2026", "locator": "Figure 1, FACT Citation Accuracy, final ICLR edition", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "dd39f211e8aa60e5851a5102b3ccc07f0549564f4d61b228a2dd89aa58bc6c40", "run_id": "V2-SOL-02", "source_id": "S4", "source_text_sha256": "ced9e7b0ae4ab2c26add3230a7b40200673ee4fc0c5c763df226bfe784d60016", "span_id": "S4_SPAN_1", "span_occurrence_id": "V2-SOL-02:S4:S4_SPAN_1", "span_root_id": "span:sha256:c8683e7dad85f22158370acbb6a6e949b304b41bcba2c06f55cd31e90ce27130" }, { "citation_carrier_accessible": false, "edition_id": "edition:drbench-iclr-2026", "locator": "Appendix E, support judgment definition", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "b940b72ea9971a1b22f3e492c50d3888e3c8090b1363dca86b4722f2234c9364", "run_id": "V2-SOL-02", "source_id": "S4", "source_text_sha256": "ced9e7b0ae4ab2c26add3230a7b40200673ee4fc0c5c763df226bfe784d60016", "span_id": "S4_SPAN_2", "span_occurrence_id": "V2-SOL-02:S4:S4_SPAN_2", "span_root_id": "span:sha256:5899663b10cbe488c635c75743b9cf4ba1aab8c3e3a67604d4fa29248b387324" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Table 1, OpenAI Deep Research row and cited-statements Match Rate column", "match_status": "ordered-fragment-match", "matched_fragments": [ "OpenAI Deep Research", "Match Rate 78.87%" ], "quote_sha256": "9b1bf034e823976ac267434e9c67ee7e4038da04f3d2582a0de7d6d729fc6916", "run_id": "V2-SOL-02", "source_id": "S5", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S5_SPAN_1", "span_occurrence_id": "V2-SOL-02:S5:S5_SPAN_1", "span_root_id": "span:sha256:e223640cb0ed12c87ca1d2406f3276f30a3b8d2017dd4dc1457fe59a94471040" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Table 1, Gemini Deep Research row and cited-statements Match Rate column", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "460889dae2de871cd0538938b63dff194183b356e79fd6f944afb7d78eaebb32", "run_id": "V2-SOL-02", "source_id": "S5", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S5_SPAN_2", "span_occurrence_id": "V2-SOL-02:S5:S5_SPAN_2", "span_root_id": "span:sha256:3b6f33fc8d800c8712c7b9fc2daafa5027f5176b23aa9120eeea323a21790a3a" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "Official ICLR abstract", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "af76864a50c641f8d693216d3b7ebe2a414eebf75467305c1e1a6946b6746590", "run_id": "V2-SOL-02", "source_id": "S6", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "S6_SPAN_1", "span_occurrence_id": "V2-SOL-02:S6:S6_SPAN_1", "span_root_id": "span:sha256:a08468cb62f2feb21d9cbb95175ce00f54592bd83573cc9166e2375947f62fee" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "Paper section 3.1.1, factual-support validation", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "d2f6a4561a938ee913dadde2fc4a80c32c492fbcb3b47f236c9639375843ae8d", "run_id": "V2-SOL-02", "source_id": "S6", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "S6_SPAN_2", "span_occurrence_id": "V2-SOL-02:S6:S6_SPAN_2", "span_root_id": "span:sha256:e2c9f6220843a04665f5d1cd142ac15f04211ace5c579fa67f77e74e84a76dfe" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Abstract and Table 1", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "44d4c6941f2920e907de1e4cd22aeb9a725f24cc19432723754e316bd6f5cc49", "run_id": "V2-SOL-02", "source_id": "S7", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S7_SPAN_1", "span_occurrence_id": "V2-SOL-02:S7:S7_SPAN_1", "span_root_id": "span:sha256:912c931063109f84ea88aea34891dd5e0f9147d2176af258059246431e9abfb1" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Table 2, GPT-5.4 rows for 2 and 150 tool calls", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "6d0377338a7fd91d8a513a277e9b64fd23420a14ef374f7f815ce45b88fc815c", "run_id": "V2-SOL-02", "source_id": "S7", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S7_SPAN_2", "span_occurrence_id": "V2-SOL-02:S7:S7_SPAN_2", "span_root_id": "span:sha256:1f0504defcd0c58184e6958c7cf30ddd2120357feb41c2753301a5912457fef9" }, { "citation_carrier_accessible": false, "edition_id": "edition:keplinger-vor-2025", "locator": "main text, paragraph beginning 'For their high performances'; Figure 1", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "39f799b4bf1bcc50a74e5b019c585b970fa01779cf4b07bdeb27d71f35ea455b", "run_id": "V2-SOL-03", "source_id": "s1", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "s1_span1", "span_occurrence_id": "V2-SOL-03:s1:s1_span1", "span_root_id": "span:sha256:46c392bc942cd88d525d74298e6bc6ebd9aeaec533ddfb7b7b761a9f5b454b05" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Table 1, OpenAI Deep Research row; FACT columns", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "dedd156999fa7d57ae9c22a166c56c263547eee3c37e6f41fe7644d980110986", "run_id": "V2-SOL-03", "source_id": "s2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "s2_span1", "span_occurrence_id": "V2-SOL-03:s2:s2_span1", "span_root_id": "span:sha256:2f311bfb451c6208101cb7583af37c338914fcdb10f5c75b131e23d5bb08e66a" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-arxiv-v1", "locator": "Table 1, Citation Metrics, column order GPT-5(DR), YouChat(DR), GPT-5(S), PPLX(DR), Copilot(TD), Gemini(DR)", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "0a64ed8971e8457f4435d1334992e160d9e519df38aa242c8df0e17b15266532", "run_id": "V2-SOL-03", "source_id": "s3", "source_text_sha256": "d3d5e54884b46ff1815be6080405a9751e2b84b1a704a926e4af4806f68c9272", "span_id": "s3_span1", "span_occurrence_id": "V2-SOL-03:s3:s3_span1", "span_root_id": "span:sha256:91dd7d34a9546d71c8789056ebde06de25247281b1fb03ff41fc3a3ff20e9520" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Table 2, OpenAI Deep Research row", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "5bd6e5242ac0a8839758376181b806b9e9556b6c69e6a5b846c4bae5aaaf60cf", "run_id": "V2-SOL-03", "source_id": "s4", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "s4_span1", "span_occurrence_id": "V2-SOL-03:s4:s4_span1", "span_root_id": "span:sha256:c130950377ad7bcb4218863dbbb72f86c43005d543056438e07501f32d369df7" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Table 2, Gemini Deep Research row", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "66801673319516701b64b72ab382bc2924cafcd3a33d971598b22c8f90fa37bf", "run_id": "V2-SOL-03", "source_id": "s4", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "s4_span2", "span_occurrence_id": "V2-SOL-03:s4:s4_span2", "span_root_id": "span:sha256:814248358095099e8d04475d7f17ce5aff8b4fe64f11239ea48edaf4d9a4b030" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Section 5.1 Results", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "7d1d86a3ca815ee38aafe98b3deb50c72abbf9f21f79336f8ab4843801b2dba5", "run_id": "V2-SOL-03", "source_id": "s4", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "s4_span3", "span_occurrence_id": "V2-SOL-03:s4:s4_span3", "span_root_id": "span:sha256:b68153666e4e12aee8dc887fef0a61fa5f44b5f680a0b7eb95ff3defcf8b5bf1" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Abstract and Table 1", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "e35ca66d12349d7290a6dbe7449bf6da173eb0671765644b581713528b316c74", "run_id": "V2-SOL-03", "source_id": "s5", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "s5_span1", "span_occurrence_id": "V2-SOL-03:s5:s5_span1", "span_root_id": "span:sha256:bb16d5f06abe8641d9ea6694e549aa15e240dd88946aa47a2d4e30ddd3351a24" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Section 4.3, Tables 2\u20133", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "4046b3ea7b246aa51b11f554509b50ebde3ca883cdcb8424e74a663b354bb845", "run_id": "V2-SOL-03", "source_id": "s5", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "s5_span2", "span_occurrence_id": "V2-SOL-03:s5:s5_span2", "span_root_id": "span:sha256:6e961498ed0f81a950f775956587f741e0eb9f11640fd3cb40870585558d869d" }, { "citation_carrier_accessible": true, "edition_id": "edition:citation-verifier-arxiv-v1", "locator": "Section 1 contributions", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "8bebee03d81b15ad0af5b8ef69993f7e3cf525a7daa6e2608007fa9bac9b9a40", "run_id": "V2-SOL-03", "source_id": "s6", "source_text_sha256": "0bd9a0bedc4b8ea9b08689109a9a6d763cb78d7513df2598874f147afa9ff9f7", "span_id": "s6_span1", "span_occurrence_id": "V2-SOL-03:s6:s6_span1", "span_root_id": "span:sha256:6885cf2524462022475b5829da081b2d35fcfe7463ca6ad0979e7c4fb1f0b54d" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-repo-main-469cce5", "locator": "README News, 2026-05-11 evaluator migration notice", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "02cd1c04d6312fcda76549885095d9c9d971cc14709ae8f749cf47fc2c11bcee", "run_id": "V2-SOL-03", "source_id": "s7", "source_text_sha256": "afebe200cb45042b2783d6ad581770bbd8674027d4e7443e2eb6c26720c6cb0c", "span_id": "s7_span1", "span_occurrence_id": "V2-SOL-03:s7:s7_span1", "span_root_id": "span:sha256:e5bcf0241a1aeae7d9a92755b1bcf0adeeea93a8922f22f832693c61780386e7" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Abstract, lines 47-48", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "be05510d58cc0231bf968f29c70b3d669a82d5cd0c74a778a5f8c4e035bf45b4", "run_id": "V2-SOL-04", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-SP1", "span_occurrence_id": "V2-SOL-04:S1:S1-SP1", "span_root_id": "span:sha256:74f6acafbb4c54d556a572460bf1b45bacd1e293f4aa16cc2d499174096b9c20" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Section 4.4, line 217", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "da34a8e2a1d4e190d3b2095d79886b3cbf7edb2c63874189aa381302d2c2924e", "run_id": "V2-SOL-04", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-SP2", "span_occurrence_id": "V2-SOL-04:S1:S1-SP2", "span_root_id": "span:sha256:deada8bacb987a47f2a42e52fbfeb5c1beb3d250c0be79e2f9c5cdd6e16b4bc7" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Section 4.3, line 212", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "e29185e1dd93d69d1cf4328288773206e15b35990c7de068b31765e058bd50fd", "run_id": "V2-SOL-04", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-SP3", "span_occurrence_id": "V2-SOL-04:S1:S1-SP3", "span_root_id": "span:sha256:417182b4c15ac550469e435a02aab1e91b395f72f186312de9d34d57fd1c6c98" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Table 1, Perplexity Deep Research citation-accuracy cell", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "64c911242980826f92ffae6d0571646ecc3aceca73c213791c6d3a8d889b4cc7", "run_id": "V2-SOL-04", "source_id": "S2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S2-SP1", "span_occurrence_id": "V2-SOL-04:S2:S2-SP1", "span_root_id": "span:sha256:196c54d6212fbc0c054dbf8e8467f2388c1f788bb93f4b1a4b6ae085eed17685" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Section 3.2, lines 144-146", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "a49c200ea10833496ac73719992be09d5fd3fd021fdd51ccc587ac2592225f56", "run_id": "V2-SOL-04", "source_id": "S2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S2-SP2", "span_occurrence_id": "V2-SOL-04:S2:S2-SP2", "span_root_id": "span:sha256:13cb0ddb087b82988b7445a9cfb02562f9c044ef4f244e8b176ff475859eaea3" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Appendix C, line 365", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "ae845f85955fa47d52d51f32803e6a26afa8b725c523e53d9ef30b2abca72d9b", "run_id": "V2-SOL-04", "source_id": "S2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S2-SP3", "span_occurrence_id": "V2-SOL-04:S2:S2-SP3", "span_root_id": "span:sha256:b83996e3b5fdf878e04d6d41d0e7a1eebee9fdd9bbccf2ae4eaf33524fcfca44" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Appendix C, line 365", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "e9c779296734583861b22f45da62bff61c9c899018602fda17716d69fc449a63", "run_id": "V2-SOL-04", "source_id": "S2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S2-SP4", "span_occurrence_id": "V2-SOL-04:S2:S2-SP4", "span_root_id": "span:sha256:f35c9565f2fd047f6e7272dc608bbf6a63813a717bad5354c24bdaac65e40bfe" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Section 3.3, line 155", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "4545fdd46cab2ffc151c9ddbfaab08b82862b68eebf5205cda180b5875a3aa81", "run_id": "V2-SOL-04", "source_id": "S3", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3-SP1", "span_occurrence_id": "V2-SOL-04:S3:S3-SP1", "span_root_id": "span:sha256:6c1d327e58ef001533ea1c11010e974436bbeafbde138efcc7b516281f6d25a5" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Section 4, line 186", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "ac4714fdd34ead02999923441a133a798a67254f0449f293905ef5b1d1caffab", "run_id": "V2-SOL-04", "source_id": "S3", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3-SP2", "span_occurrence_id": "V2-SOL-04:S3:S3-SP2", "span_root_id": "span:sha256:3015a109e7898cb720e426e9a57c526277b648c75f1fb4b13631b00524eac943" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-arxiv-v1", "locator": "Abstract, line 46", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "a0eeca5c86f9c7aeda9167f626a8cb0ed56dc87ea1ac5ca8c4a7a0add76e7625", "run_id": "V2-SOL-04", "source_id": "S4", "source_text_sha256": "d3d5e54884b46ff1815be6080405a9751e2b84b1a704a926e4af4806f68c9272", "span_id": "S4-SP1", "span_occurrence_id": "V2-SOL-04:S4:S4-SP1", "span_root_id": "span:sha256:8cce3d9ee1e1674ba1b93321dd9b99a55d834ca980451f8ab61bcaf5bdda8e4d" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-arxiv-v1", "locator": "Section 3.2, lines 163-171", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "5cc83ab699cb1342475b407e34d33fc106d64b5d9270e5bb9445d80586ebabc2", "run_id": "V2-SOL-04", "source_id": "S4", "source_text_sha256": "d3d5e54884b46ff1815be6080405a9751e2b84b1a704a926e4af4806f68c9272", "span_id": "S4-SP2", "span_occurrence_id": "V2-SOL-04:S4:S4-SP2", "span_root_id": "span:sha256:9dd6eb46529e77a62748093528e52685fbd92d46a756aef750d22aa25981db23" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "Table 1, ChatGPT subtotal", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "5428bd1a04d5d2e332015107e915fe3a38f1d5e173e8c7246b743d98ecfd8618", "run_id": "V2-SOL-04", "source_id": "S5", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "S5-SP1", "span_occurrence_id": "V2-SOL-04:S5:S5-SP1", "span_root_id": "span:sha256:8c8d9a6dc003bf0298542b85df3f6f08db631e68e89f606f4e53e36e86dde167" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "Table 1, ChatGPT all-correct subtotal", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "b6c3ff6f2ff60f37ae1c6b773ba6aa5a6c01015b61e3cc6f2a06bfcef69b53ad", "run_id": "V2-SOL-04", "source_id": "S5", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "S5-SP2", "span_occurrence_id": "V2-SOL-04:S5:S5-SP2", "span_root_id": "span:sha256:39a9931f05ea356fe904ed15768fa08c66440b1fcb20f98e267a315e6d562af9" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "Paragraph after Table 1", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "1f863c1f35c37af1fd2c3e4927ea0b289d94a9532fa5855e209ce98ea344d498", "run_id": "V2-SOL-04", "source_id": "S5", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "S5-SP3", "span_occurrence_id": "V2-SOL-04:S5:S5-SP3", "span_root_id": "span:sha256:f05b3189dc3fafd45b5bde643a91fd0616832928215a37a2430a5a658e592029" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-supplement-v1", "locator": "Dataset description", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "e3ec5c81f615c657f7c6b124c5b2150d86f18281384ca0bd24ebb43a3317796f", "run_id": "V2-SOL-04", "source_id": "S6", "source_text_sha256": "1ed2ccfeb91e0346787a5c3122e191a6798d522a86f740e10ae9956c5b3f4cd4", "span_id": "S6-SP1", "span_occurrence_id": "V2-SOL-04:S6:S6-SP1", "span_root_id": "span:sha256:94ad583514aa7e04b8d5f7b8f9cdda6fdffe8ca6712f033da3ce4f18fe7c03f1" }, { "citation_carrier_accessible": true, "edition_id": "edition:citation-verifier-arxiv-v1", "locator": "Abstract, line 16", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "0e980e624cddfead247a93771e68f3c678bd30495cd310fd81c0812ecab2bb8b", "run_id": "V2-SOL-04", "source_id": "S7", "source_text_sha256": "0bd9a0bedc4b8ea9b08689109a9a6d763cb78d7513df2598874f147afa9ff9f7", "span_id": "S7-SP1", "span_occurrence_id": "V2-SOL-04:S7:S7-SP1", "span_root_id": "span:sha256:e54ee1457854a9a5e46f7c7c2e66ac6a5a69b963f8ee3450f40052f138d5d0c1" }, { "citation_carrier_accessible": true, "edition_id": "edition:citation-verifier-arxiv-v1", "locator": "Abstract, line 16", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "6a7d5dd08b03dbb3fb7acaa3d8f8943e1ee7d8dcaeb8b2b829ba36a7963e4991", "run_id": "V2-SOL-04", "source_id": "S7", "source_text_sha256": "0bd9a0bedc4b8ea9b08689109a9a6d763cb78d7513df2598874f147afa9ff9f7", "span_id": "S7-SP2", "span_occurrence_id": "V2-SOL-04:S7:S7-SP2", "span_root_id": "span:sha256:794bdf7e0595799afbb0d55f3dc522077aed9615c59f1e3575707148cf444bcf" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "p. 4, lines 150-159", "match_status": "ordered-fragment-match", "matched_fragments": [ "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" ], "quote_sha256": "4edb75ec3f690eb2d15089923ba5e9c4e6174f55094d0919041bf10625901ceb", "run_id": "V2-TERRA-01", "source_id": "s1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "s1_method", "span_occurrence_id": "V2-TERRA-01:s1_deepresearchbench:s1_method", "span_root_id": "span:sha256:b0a39c963cdfdc5f9852cfc9f7e33e05d31232bd1d8998851e879c38e6c34843" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "p. 5, Table 1, lines 179-198", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "b6e43bff5e4d384a69288ea69405d3ff49f44c00c5a8b6ab44e3a5a427b8bee1", "run_id": "V2-TERRA-01", "source_id": "s1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "s1_table", "span_occurrence_id": "V2-TERRA-01:s1_deepresearchbench:s1_table", "span_root_id": "span:sha256:77001af3bf7a976754d0b5d149da1c4e9b464c3515694958fe01a3c4ca8c7a5c" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "p. 17, Table 5, lines 715-729", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "bc8f24337ac0718946ee4dfb90675a92120f890d5ca0d25fdc4279c368a1875e", "run_id": "V2-TERRA-01", "source_id": "s1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "s1_dates", "span_occurrence_id": "V2-TERRA-01:s1_deepresearchbench:s1_dates", "span_root_id": "span:sha256:34a61ece593714d9608073ee5aeea22635a3fb111582fc8e2e8bf0b371955b70" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "p. 5, lines 289-300", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "191b5aedee7e0a6a8d59f0be1c67a99f37326461a0baadabcc66d181f917d6d1", "run_id": "V2-TERRA-01", "source_id": "s2_reportbench", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "s2_method", "span_occurrence_id": "V2-TERRA-01:s2_reportbench:s2_method", "span_root_id": "span:sha256:f4c499ea114f2647a0dc4830b72e4b9120d6c368f846efb1ccd3ae4c0ed4f2c7" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "p. 6, Table 1, lines 333-355", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "427d50b4f83bb70f9b686fc45eb7b484eb0587caab4658d55301a555b371d7e5", "run_id": "V2-TERRA-01", "source_id": "s2_reportbench", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "s2_metric_table", "span_occurrence_id": "V2-TERRA-01:s2_reportbench:s2_metric_table", "span_root_id": "span:sha256:a6bde87f202e383e8bdd8403b2e5241b65380e0616e61b18f36a7c3719b55d76" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "p. 5, lines 315-329", "match_status": "ordered-fragment-match", "matched_fragments": [ "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" ], "quote_sha256": "e45fbf61feb38fc8de32433d439fdb8544133e905103b884c92327930a929b0a", "run_id": "V2-TERRA-01", "source_id": "s2_reportbench", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "s2_collection", "span_occurrence_id": "V2-TERRA-01:s2_reportbench:s2_collection", "span_root_id": "span:sha256:7a6046a756d6ec0315d330cf0817d062ea48498bdc9c90b3489d64b2bd12a3a4" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "p. 6, lines 361-387", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "2e2d475bdbdccacc310754eb68bb8f1b5dac25480684dc29773cbb8cf9141ea0", "run_id": "V2-TERRA-01", "source_id": "s3_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "s3_definition", "span_occurrence_id": "V2-TERRA-01:s3_researcherbench:s3_definition", "span_root_id": "span:sha256:5351ba5f0c5afba376e1a70ffafab3d6a4eefae1d9507b5206a64951f360a095" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "p. 6-7, lines 395-409", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "bf48819f2f28fb5eeb1fde9568c7398687840f03034e87f0f634df8416b91d64", "run_id": "V2-TERRA-01", "source_id": "s3_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "s3_models_time", "span_occurrence_id": "V2-TERRA-01:s3_researcherbench:s3_models_time", "span_root_id": "span:sha256:5fb35a076c774fd7141fd642f5490f3679fc2452e9e886b62d2e3c370b9c029d" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "p. 7, Table 2, lines 415-427", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "bf2cdd33d00d7b1110c4ac5d5af27d53a7acc505bf17ea7796e029bdf31c948f", "run_id": "V2-TERRA-01", "source_id": "s3_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "s3_table", "span_occurrence_id": "V2-TERRA-01:s3_researcherbench:s3_table", "span_root_id": "span:sha256:eadcf02c45f4b152c73c6f871d116e7d1db8e78c796671580a5eb72e7ff16687" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "pp. 5-6, lines 209-217 and Table 1, lines 254-271", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "609cbee79dcf2e423af2abff67454fa2c88b3c30ae286fd7f8c8f88ed2ddd73f", "run_id": "V2-TERRA-01", "source_id": "s4_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "s4_definition_table", "span_occurrence_id": "V2-TERRA-01:s4_cited_not_verified:s4_definition_table", "span_root_id": "span:sha256:48a692e799a44e37783d312cb80a0500cca0aa94abb30dc074c1cb6f0bb0ead1" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "pp. 6-7, lines 286-318", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "b75318c065718db1259a86220f8793c81ef12ee9798d8fc4e0d4354fd83c2e45", "run_id": "V2-TERRA-01", "source_id": "s4_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "s4_depth", "span_occurrence_id": "V2-TERRA-01:s4_cited_not_verified:s4_depth", "span_root_id": "span:sha256:a9625285d829a0463b566e89d328e49b9c21cc07e83dbf845ac422f5a8e4b72e" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "pp. 1-2, lines 64-95", "match_status": "ordered-fragment-match", "matched_fragments": [ "This study focuses on URL-based citation hallucinations", "fabricated snippets", "and invented bibliographic entries", "require separate systematic study" ], "quote_sha256": "ee1de7374c67e208aa5d1331c20a08c8c83418309f1bd768d380620bfdc27901", "run_id": "V2-TERRA-01", "source_id": "s5_urlhealth", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "s5_scope", "span_occurrence_id": "V2-TERRA-01:s5_urlhealth:s5_scope", "span_root_id": "span:sha256:55de6a6ca9414a252592e9f77544a9259533dd713ce1f12f6a216752a2b76e8f" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "p. 3, Table 2, lines 173-200", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "83d55ca96f5207144829514b8d88e689901701eb1f4b992dd6b2e5af8c288924", "run_id": "V2-TERRA-01", "source_id": "s5_urlhealth", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "s5_table", "span_occurrence_id": "V2-TERRA-01:s5_urlhealth:s5_table", "span_root_id": "span:sha256:6af594d0155420f020802bee4a4dae0cd19f46d2c69dc107c69e75e298299169" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "p. 4, lines 210-226", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "923c3a4f90999d5c32b7eacfcabb033566f20427fbe4078c2404eb3725ae7226", "run_id": "V2-TERRA-01", "source_id": "s5_urlhealth", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "s5_comparison", "span_occurrence_id": "V2-TERRA-01:s5_urlhealth:s5_comparison", "span_root_id": "span:sha256:baa7644423c27da0263b753522f1c14915dfdb8f9505577f8ff755a0e668c023" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "p.4, Section 3.2, lines 148-155", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "3cca518ed14d7451346a35623b20e7f9e350e4cb5cbcec3d7f622cc6aac509ce", "run_id": "V2-TERRA-02", "source_id": "s1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "s1_fact_method", "span_occurrence_id": "V2-TERRA-02:s1_deepresearchbench:s1_fact_method", "span_root_id": "span:sha256:eaf37bef7b8dc35f3e00b85d3e58ad872dc0ea604a062c8cdd8929184587d5d9" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "p.5, Table 1, Deep Research Agent rows", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "c5b9745d64c8a1f99fcbbc08a6faebbf6cea6a3aac271effa2dbe31efb82d0eb", "run_id": "V2-TERRA-02", "source_id": "s1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "s1_fact_results", "span_occurrence_id": "V2-TERRA-02:s1_deepresearchbench:s1_fact_results", "span_root_id": "span:sha256:b74af48901531355cd4351211eac41aef691ea4eb29488347782fca1ec2d1eb8" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "pp.17-18, Appendix E, equations 4-6", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "82b9361b6e696a92b41fdfae500f56b05d48575c0d429f15b3a8d6786c83b8d7", "run_id": "V2-TERRA-02", "source_id": "s1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "s1_fact_formula", "span_occurrence_id": "V2-TERRA-02:s1_deepresearchbench:s1_fact_formula", "span_root_id": "span:sha256:e4a9f30effc031388ed5c9993dc6f071903bec5e3f1998db4c08ab00b284b27f" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "p.17, Appendix C, lines 704-708", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "43c892b582d42a335c982009f97347b5bf2ae2799cc3e478c53504f4d01e4388", "run_id": "V2-TERRA-02", "source_id": "s1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "s1_fact_judge_validation", "span_occurrence_id": "V2-TERRA-02:s1_deepresearchbench:s1_fact_judge_validation", "span_root_id": "span:sha256:f98f1274859ba98cc538e3be6d11d345a5382cfcb9516aa1cf3f3278ea646b92" }, { "citation_carrier_accessible": true, "edition_id": "edition:liveresearchbench-arxiv-v5", "locator": "p.33, Appendix E", "match_status": "ordered-fragment-match", "matched_fragments": [ "E1: URL is inaccessible or does not resolve; E2: URL content is irrelevant", "E3: URL content does not support the specific statements" ], "quote_sha256": "064c8e109876030c9fdc887811e31b1e5505c4bb3968369b65b26566813cca3e", "run_id": "V2-TERRA-02", "source_id": "s2_liveresearchbench", "source_text_sha256": "6605fcf67de305d0313f395e2493bf6c3bbd7ae87d7fa08358364ded225d9b77", "span_id": "s2_rubric_tree", "span_occurrence_id": "V2-TERRA-02:s2_liveresearchbench:s2_rubric_tree", "span_root_id": "span:sha256:d880991ad784390029d49f84949d083c4789d67d45893d87cfb6b5a38703453f" }, { "citation_carrier_accessible": true, "edition_id": "edition:liveresearchbench-arxiv-v5", "locator": "p.33, Table 7", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "9947eb1b16a73e4f266a2d2cd0cfcbbe40f403428bab87f653e3634580182437", "run_id": "V2-TERRA-02", "source_id": "s2_liveresearchbench", "source_text_sha256": "6605fcf67de305d0313f395e2493bf6c3bbd7ae87d7fa08358364ded225d9b77", "span_id": "s2_table7", "span_occurrence_id": "V2-TERRA-02:s2_liveresearchbench:s2_table7", "span_root_id": "span:sha256:256817dca0b5aac5741ec51862ec8d0f9b4b93ea78186a4041052c7b2d1c4382" }, { "citation_carrier_accessible": true, "edition_id": "edition:liveresearchbench-arxiv-v5", "locator": "p.23, Appendix C, Citation Accuracy", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "0d570d54a0712207d83f71aae02fc0c8ca424a120d61b36c0d0e243611d8f842", "run_id": "V2-TERRA-02", "source_id": "s2_liveresearchbench", "source_text_sha256": "6605fcf67de305d0313f395e2493bf6c3bbd7ae87d7fa08358364ded225d9b77", "span_id": "s2_validation", "span_occurrence_id": "V2-TERRA-02:s2_liveresearchbench:s2_validation", "span_root_id": "span:sha256:e6f447129d9a662fb202d4ac22e16822bacfdbcbcdb7afe3b589e21802890b8a" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "p.6, Section 3.1.4, equation 7", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "b08cab9336fb2681d652b0f8d512cbf8d45ecf977ed5130269b5e909d96435e7", "run_id": "V2-TERRA-02", "source_id": "s3_deeptrace", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "s3_definition", "span_occurrence_id": "V2-TERRA-02:s3_deeptrace:s3_definition", "span_root_id": "span:sha256:4d92f4721bb3d81403154a23d7fde5b342251d50a2d1034ec6d4542a35e9fc8b" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "p.8, Table 1", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "015ad79fdb7279dd5f90e40459c389178dd660327dfd04ceb74ea002814289eb", "run_id": "V2-TERRA-02", "source_id": "s3_deeptrace", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "s3_table1", "span_occurrence_id": "V2-TERRA-02:s3_deeptrace:s3_table1", "span_root_id": "span:sha256:7572651679e7e8a0a1a6e394504e75749ae2649cfb55f7a80531c8b53acb31dc" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "pp.4-7, Sections 3.1.1 and 3.2", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "2ce91759797b86455a478a9ced58ec59d032e1a32a1c964347f96be4ab9e2054", "run_id": "V2-TERRA-02", "source_id": "s3_deeptrace", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "s3_corpus_and_retrieval", "span_occurrence_id": "V2-TERRA-02:s3_deeptrace:s3_corpus_and_retrieval", "span_root_id": "span:sha256:9cb1700c08368feb234207045354cbf559d6ed80f2b0bae814d2b5b3c858b73c" }, { "citation_carrier_accessible": true, "edition_id": "edition:deeptrace-iclr-2026", "locator": "p.14, Table 3", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "75a9212dc448c15ffc1e4a36bdf190728977470661bd9f45be534010704faa25", "run_id": "V2-TERRA-02", "source_id": "s3_deeptrace", "source_text_sha256": "0eaa415eca25bed5e591b8250640d695b86f6dac6601f5f00167ee3ac7ab9171", "span_id": "s3_judge_validation", "span_occurrence_id": "V2-TERRA-02:s3_deeptrace:s3_judge_validation", "span_root_id": "span:sha256:aa1534ce2e177153ab85e512deb8d064d14ec1eae16d8032bdb5043252738d4c" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "Section 4.2.1, Citation Support Verification and Score Computation", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "12525ade29e741070aec9df092b69ee828e7f4333a4c41c331784cfab48bef56", "run_id": "V2-TERRA-02", "source_id": "s4_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "s4_method", "span_occurrence_id": "V2-TERRA-02:s4_researcherbench:s4_method", "span_root_id": "span:sha256:886b50d94e3facabc487342cd2af5157cf956622ecfc368684596c5f6b61c350" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "Section 5.2, Table 2", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "5c9ca63ca1d8757a3e9e598d441fbca1675657a026bb4f97424112eded86594d", "run_id": "V2-TERRA-02", "source_id": "s4_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "s4_results", "span_occurrence_id": "V2-TERRA-02:s4_researcherbench:s4_results", "span_root_id": "span:sha256:f85edb1051cbc19ee38bc796ed3392abf5e44fc869d59d7e82bfe2cb81696e9b" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Abstract, lines 45-49", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "d34096a9d9b1fbb43ef50ba503c3894607c008b563e1e1a5d1643cbc23c5d447", "run_id": "V2-TERRA-03", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-A", "span_occurrence_id": "V2-TERRA-03:S1:S1-A", "span_root_id": "span:sha256:cd21c450c0d33df20a2b1a539d5725347db1b5bab7d1e9866c24790d845e5873" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Table 1, lines 163-180", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "2dbc4a7649c02b8633c0a85f4073b013f1a5a9888905cb95135d7c2600082c38", "run_id": "V2-TERRA-03", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-B", "span_occurrence_id": "V2-TERRA-03:S1:S1-B", "span_root_id": "span:sha256:35357cd8e4ff1531a84b4a5c8923db97c7b44fecd19d7666f326bbf7a1d5ec45" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Methods 3.4, lines 153-156", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "75a8b058bb89da032df063c5b46c02062ba048b4fd46b396fe29d5020d5c60a8", "run_id": "V2-TERRA-03", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-C", "span_occurrence_id": "V2-TERRA-03:S1:S1-C", "span_root_id": "span:sha256:d004f718815ff769195d087f1159e50cf5d00261b8ef85229625a65740d55b3d" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Tables 2-3, lines 191-210", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "65918d19bdc3830f58ba9cb05e9cb9ae592d9409ffcaf50af9a5fefe7d843dc8", "run_id": "V2-TERRA-03", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-D", "span_occurrence_id": "V2-TERRA-03:S1:S1-D", "span_root_id": "span:sha256:ec8d8cf5ad9b690ecd983e4d5c673d9624200351579e72868291abc15d0f2949" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Evaluation 4.3, lines 211-215", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "d13421745ce8497cd47633527b808016a37fd65c43c761d448e325fc14e1ad73", "run_id": "V2-TERRA-03", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-E", "span_occurrence_id": "V2-TERRA-03:S1:S1-E", "span_root_id": "span:sha256:fe6b18fa48b171b5bd7c74fda45f38ed1b087ee5035f6d35dcf8c701b3033ea8" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Limitations, lines 219-224", "match_status": "ordered-fragment-match", "matched_fragments": [ "the LLM-as-a-judge approach", "may retain biases inherent to the judge model" ], "quote_sha256": "af0b066b292e6d887067c6cfa9802eb8b1984929b622d91cdca61d0e8a3bc31f", "run_id": "V2-TERRA-03", "source_id": "S1", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S1-F", "span_occurrence_id": "V2-TERRA-03:S1:S1-F", "span_root_id": "span:sha256:5cd9ba4ca72da10cf51c0beddc6ea2765c74721bdd526a67156f44754219f440" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Evaluation methodology, lines 144-149", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "1bde849b0f5df91e847e907dd763f27be01ffdc7eb0c7e61898c8a9731472c35", "run_id": "V2-TERRA-03", "source_id": "S2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S2-A", "span_occurrence_id": "V2-TERRA-03:S2:S2-A", "span_root_id": "span:sha256:015bb68c904bf225e84c82b1acffb3cc38a4a087d7b0f79d3b0102b685b2265e" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Table 1, lines 177-182", "match_status": "ordered-fragment-match", "matched_fragments": [ "Perplexity Deep Research |", "| 90.24 | 31.26", "Gemini-2.5-Pro Deep Research |", "| 81.44 | 111.21", "OpenAI Deep Research |", "| 77.96 | 40.79" ], "quote_sha256": "53d38f9cf0d0aedf28a77d7de32935372202fff78a0c02d98f8c269ef223906a", "run_id": "V2-TERRA-03", "source_id": "S2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S2-B", "span_occurrence_id": "V2-TERRA-03:S2:S2-B", "span_root_id": "span:sha256:0d4f357f2a5565bdaea01a1e537650958d71216868d1a2b0bc14c47a45b6d0ef" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Appendix E, lines 404-423", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "74bf93e5475ed37377e1f4e679a9ef8d76ac73beba297cd3cfde4a3527052c76", "run_id": "V2-TERRA-03", "source_id": "S2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S2-C", "span_occurrence_id": "V2-TERRA-03:S2:S2-C", "span_root_id": "span:sha256:3ec266d89a7c774ebcee3d2b8b758ac56176c382481cd0d2f0bd893aaa142281" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Appendix A, lines 339-348", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "2449d1c875bd9467747b4953e29dee8a011c23e0bc1535356161584206727f68", "run_id": "V2-TERRA-03", "source_id": "S2", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S2-D", "span_occurrence_id": "V2-TERRA-03:S2:S2-D", "span_root_id": "span:sha256:de53fab3c5b2e262ba56cdd5a27eb002c2b4641755ccc38c734a5bd506a670ef" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Cited-statements pipeline, lines 121-124", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "5932bddfa8d2098b21caf7e4432af9726c4d258f8d52f8c0f9a77c077f76889d", "run_id": "V2-TERRA-03", "source_id": "S3", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3-A", "span_occurrence_id": "V2-TERRA-03:S3:S3-A", "span_root_id": "span:sha256:42a4184b2e116330dc263a3d8e9b77f4b88c9da1c325fc67c4375df0f818a514" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Settings and metrics, lines 132-139", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "397d217cf5022ad78aa1072c2e82bcf3197e5a87cf4ef96ea81a78e1ad39b384", "run_id": "V2-TERRA-03", "source_id": "S3", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3-B", "span_occurrence_id": "V2-TERRA-03:S3:S3-B", "span_root_id": "span:sha256:ba6b8a8b7d9121ebb05d594176ceed3d1e9dbc637876783abfd0141ebbd0a822" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Table 1, lines 140-150", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "f62ae7f5e2d3de4804554378ea5745b0c2d100a1374ef638ec508efcb5bdb0b4", "run_id": "V2-TERRA-03", "source_id": "S3", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3-C", "span_occurrence_id": "V2-TERRA-03:S3:S3-C", "span_root_id": "span:sha256:7eefee71f11e6f5ec8c2e70272fd9189464650e68b904d9fa9c6d059bedc4195" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Limitations, lines 259-261", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "4947edaf643bd0a234e0ca914d920a1a5b068d18b017dcfe6d6103c466d422ca", "run_id": "V2-TERRA-03", "source_id": "S3", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3-D", "span_occurrence_id": "V2-TERRA-03:S3:S3-D", "span_root_id": "span:sha256:1db12b68cfeb4c5f5a96fa9cd2e2bd46e8dfb4f096f73154481d29e22a4d5414" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "Main text, paragraph beginning 'To address the gap' (search-indexed primary full text)", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "1c94be957cfe750f445dc9143722905b5784b02f754a9b4071a3381e2bd493e9", "run_id": "V2-TERRA-03", "source_id": "S4", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "S4-A", "span_occurrence_id": "V2-TERRA-03:S4:S4-A", "span_root_id": "span:sha256:b38a2af5982b4c85bc205d2f533a23ed3a8f40a49b651a5f00ec6932dcc67f7d" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "Main text, following paragraph (search-indexed primary full text)", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "28141fd1b0222658eb93a338783358926de770223eea24f8c5cbcf632d67f955", "run_id": "V2-TERRA-03", "source_id": "S4", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "S4-B", "span_occurrence_id": "V2-TERRA-03:S4:S4-B", "span_root_id": "span:sha256:b6a6ba48a2c4e352c8565b671a15a90400739f2aeefda8a65a31ad8a1ff9a4e4" }, { "citation_carrier_accessible": true, "edition_id": "edition:keplinger-vor-2025", "locator": "Same paragraph (search-indexed primary full text)", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "389559d433dae83a26d09f0ed85e1ca6761cee2d09850e974e215398d187d721", "run_id": "V2-TERRA-03", "source_id": "S4", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "S4-C", "span_occurrence_id": "V2-TERRA-03:S4:S4-C", "span_root_id": "span:sha256:f8ff0887370fedb6d6676d1eaf59f86461fe5083d20dfa5b28f8ba94175ed031" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-repo-main-469cce5", "locator": "README News, lines 176-188", "match_status": "ordered-fragment-match", "matched_fragments": [ "Official Evaluator Switched to GPT-5.5", "Legacy code: the previous Gemini-2.5-Pro / Gemini-2.5-Flash evaluation code is preserved" ], "quote_sha256": "9c713be4fc872b46e66d812e033708b51b4e385c81aa45f7b1798459a677343d", "run_id": "V2-TERRA-03", "source_id": "S5", "source_text_sha256": "afebe200cb45042b2783d6ad581770bbd8674027d4e7443e2eb6c26720c6cb0c", "span_id": "S5-A", "span_occurrence_id": "V2-TERRA-03:S5:S5-A", "span_root_id": "span:sha256:ef637b38f36195bea09205d532e8744daf3e257f93d97144f061024092bf67fe" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-repo-main-469cce5", "locator": "README FACT, lines 240-248", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "549018c6df261f27bd10133ad4e4f565e004f07710095259a7889cc79d149794", "run_id": "V2-TERRA-03", "source_id": "S5", "source_text_sha256": "afebe200cb45042b2783d6ad581770bbd8674027d4e7443e2eb6c26720c6cb0c", "span_id": "S5-B", "span_occurrence_id": "V2-TERRA-03:S5:S5-B", "span_root_id": "span:sha256:92eb7cf19745e24190dda84c77d590941134d09f06805c0fb605207fd942ae11" }, { "citation_carrier_accessible": false, "edition_id": "edition:keplinger-vor-2025", "locator": "Figure 1 caption", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "1f9dd50794adad5378f0c97308d45a724c2f421f5cbfafd2d251d06bfb3b510e", "run_id": "V2-TERRA-03", "source_id": "S6", "source_text_sha256": "8fd80ac582690bc0733dec0ebd65e9894a05915d117384f3e8bb6d8b0840a7c1", "span_id": "S6-A", "span_occurrence_id": "V2-TERRA-03:S6:S6-A", "span_root_id": "span:sha256:fdc35d731d751e7e0691158d8fed4a2934851897f9fef016b33376cde973827a" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Section 3.2, paragraphs 'Statement-URL Pair Extraction and Deduplication' and 'Support Judgment'", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "3cca518ed14d7451346a35623b20e7f9e350e4cb5cbcec3d7f622cc6aac509ce", "run_id": "V2-TERRA-04", "source_id": "S1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S1_method", "span_occurrence_id": "V2-TERRA-04:S1_deepresearchbench:S1_method", "span_root_id": "span:sha256:9fe42cb48702d8d96ebbbc0309692214ece6ec495c447c06e2be62f32ff00894" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Table 1, Deep Research Agent rows", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "3997cfbb7dbefe6e98d2f77dd72ea2bda917c6838d9241e75139e7df312b149a", "run_id": "V2-TERRA-04", "source_id": "S1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S1_table1", "span_occurrence_id": "V2-TERRA-04:S1_deepresearchbench:S1_table1", "span_root_id": "span:sha256:539d8123b83aa1250f16cb7a8a4a66ece5d42099c0ae7c7d1fd877f1fbafb3bd" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Appendix E.1, equations (4)-(5)", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "d7619da3b090b3608e35b23fb944490f090732ac0f42a4bdfc73a90f43094bdb", "run_id": "V2-TERRA-04", "source_id": "S1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S1_metric", "span_occurrence_id": "V2-TERRA-04:S1_deepresearchbench:S1_metric", "span_root_id": "span:sha256:a13bd114b7a394950897d477dccb999910794b70914bbc3a45fa6c4667181992" }, { "citation_carrier_accessible": true, "edition_id": "edition:drbench-arxiv-v1", "locator": "Appendix D, Table 5", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "86d5d20702fbe736e87099be370fadf16b4acea42bea16ba28ebb473ba2ae670", "run_id": "V2-TERRA-04", "source_id": "S1_deepresearchbench", "source_text_sha256": "c8391dc3b757d97aa6d781636819180d34cb7343d290896d54db43f6f467da89", "span_id": "S1_time", "span_occurrence_id": "V2-TERRA-04:S1_deepresearchbench:S1_time", "span_root_id": "span:sha256:76e9bd59b31c7ebd2ed7a2186e59753a79d3c730e0d7b4fbf0146fb39f4e9c5f" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "Section 4.2.1 'Citation Support Verification' and Section 4.2 'Score Computation', equations (2)-(3)", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "12525ade29e741070aec9df092b69ee828e7f4333a4c41c331784cfab48bef56", "run_id": "V2-TERRA-04", "source_id": "S2_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "S2_method", "span_occurrence_id": "V2-TERRA-04:S2_researcherbench:S2_method", "span_root_id": "span:sha256:f96ad5daa81153a3689f52f5777fedfd70e8a87d44e7a1c9e2c22b5789a3707d" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "Table 2, Deep Research System rows", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "5c9ca63ca1d8757a3e9e598d441fbca1675657a026bb4f97424112eded86594d", "run_id": "V2-TERRA-04", "source_id": "S2_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "S2_table2", "span_occurrence_id": "V2-TERRA-04:S2_researcherbench:S2_table2", "span_root_id": "span:sha256:5dbd4e3e48480f5b3c54ce606082c35bfd55bf40cd0be847cc03a8fd4d9993f6" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "Abstract and Section 5.1 'Evaluation Configuration'", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "02c896e17544a2a9ab762d11facbfda91495f997bcf02560161c971a40ae78fa", "run_id": "V2-TERRA-04", "source_id": "S2_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "S2_scope", "span_occurrence_id": "V2-TERRA-04:S2_researcherbench:S2_scope", "span_root_id": "span:sha256:0d70187dbf9e3044ae9efd387faf34b29b9ab556aae6b0ea4c06e05964bfa2c7" }, { "citation_carrier_accessible": true, "edition_id": "edition:researcherbench-arxiv-v1", "locator": "Section 5.1 and Appendix E, Table 4", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "1eb2dcb713304fb76409f4ea450d6b06ba05e95e02110aed33dad456ab3d8ce8", "run_id": "V2-TERRA-04", "source_id": "S2_researcherbench", "source_text_sha256": "1aa77342c2571bb564fe1b3e9a2ba2333b4ef0d637c4a3ef622540741927b0ec", "span_id": "S2_time", "span_occurrence_id": "V2-TERRA-04:S2_researcherbench:S2_time", "span_root_id": "span:sha256:ea9cb2e1b0078c0857b789d61d0a0d26801cf6689186470588a87b98b4639796" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Section 2.2 'Cited statements'", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "153b2f37a8662ac0dbbd7fe51bcbb291afd5d227c4da3f4c6463274c63a11fb2", "run_id": "V2-TERRA-04", "source_id": "S3_reportbench", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3_method", "span_occurrence_id": "V2-TERRA-04:S3_reportbench:S3_method", "span_root_id": "span:sha256:9c7a4c186cc85f185aa293a7c5a46c08f9dbbc1a9e63c449dc737447e42f8ee4" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Section 3.2, Table 1", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "2670aff9a658c1e206579253b86b7ce0d543c6bd1bede985279faa0a3df18b27", "run_id": "V2-TERRA-04", "source_id": "S3_reportbench", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3_table1", "span_occurrence_id": "V2-TERRA-04:S3_reportbench:S3_table1", "span_root_id": "span:sha256:9a2cf22761f2ebb97eb31dfa02a32775248c3a7396b1e410565c313d30585cf3" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Section 3.1 'Setttings'", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "b55cc3d05dbba5d160b75515ce407128fe2e2cf8c2d679517e79309d6ed6ab40", "run_id": "V2-TERRA-04", "source_id": "S3_reportbench", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3_time", "span_occurrence_id": "V2-TERRA-04:S3_reportbench:S3_time", "span_root_id": "span:sha256:ddf4320a6d302c13d28b6225eb7e79ac15583349e1b449d4bb967eb89a257a3d" }, { "citation_carrier_accessible": true, "edition_id": "edition:reportbench-arxiv-v1", "locator": "Appendix A.1 'Limitations'", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "ee6c65565e833960bd4ef6552fe3153a1108a743989a21b261b571cf6f066aa4", "run_id": "V2-TERRA-04", "source_id": "S3_reportbench", "source_text_sha256": "014f247563e015dfe7cd6ea4dee6c410f57c74788a6fb5bd589f65df078e8c95", "span_id": "S3_limitations", "span_occurrence_id": "V2-TERRA-04:S3_reportbench:S3_limitations", "span_root_id": "span:sha256:084f11e57cf779850ea87aaf30ba1277438ff9efcb533fd2ebb09dba3665be8d" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Section 4.1, Figure 1/Table 2", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "fa5bbff787d875e995bd714b8b2f60a9a3cc9ece9e99d6af5f47861aa54e3a97", "run_id": "V2-TERRA-04", "source_id": "S4_urlhealth", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "S4_table2", "span_occurrence_id": "V2-TERRA-04:S4_urlhealth:S4_table2", "span_root_id": "span:sha256:131799471acf2f83cc3a17322a1c5cda6b5b46020bd894be54a1708db62eb14b" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Section 4.2, paragraph beginning 'Deep research agents cite far more URLs per query'", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "f667344d15b6ab97def48b5c4b60af01b003048a652166d1c27045c53bcc1c74", "run_id": "V2-TERRA-04", "source_id": "S4_urlhealth", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "S4_comparison", "span_occurrence_id": "V2-TERRA-04:S4_urlhealth:S4_comparison", "span_root_id": "span:sha256:dc108a5e00fb6ce5306fcde8fd0c36c85352dac361662fab3ad1eea89d66c048" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Section 3.3 'URL extraction and classification'", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "b240bd208cb4c322f3c9c242d01e13da53b3fd2a64e41b8b0f26653032e0ee54", "run_id": "V2-TERRA-04", "source_id": "S4_urlhealth", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "S4_method", "span_occurrence_id": "V2-TERRA-04:S4_urlhealth:S4_method", "span_root_id": "span:sha256:bb62928b5e0cb4e373b2f6bfeb579d8564d05da5588f8b150a89ea4b9b2ed0db" }, { "citation_carrier_accessible": true, "edition_id": "edition:url-health-arxiv-v1", "locator": "Section 2 definition discussion and Section 3.3", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "19f5203d42cda0ad9b817dc8b5e7abf1b449fc7fa9792a8cdcbf6ea8782349b1", "run_id": "V2-TERRA-04", "source_id": "S4_urlhealth", "source_text_sha256": "d00cf613da17939694913654e404c5d61e78c62779fdd9d154655f5986fe643f", "span_id": "S4_limitations", "span_occurrence_id": "V2-TERRA-04:S4_urlhealth:S4_limitations", "span_root_id": "span:sha256:59d0da64f738e1d8745f2bff3663eb89e273f93fe501afe37e2494a8e0ff31a1" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Section 3.3.1-3.3.3", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "a4386d56325583893d806fdd15ccd475d5096f0b445b1b9f52aeba253c910987", "run_id": "V2-TERRA-04", "source_id": "S5_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S5_method", "span_occurrence_id": "V2-TERRA-04:S5_cited_not_verified:S5_method", "span_root_id": "span:sha256:732c03e69c6e142a492275cee5d1e2d474c75422c9b84aaaf273100e937338ed" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Section 3.4 'Experimental setup'", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "d8bd0561648c1f5ac4ca416fa90891f186ae248737edc9d973703ea20b1231d4", "run_id": "V2-TERRA-04", "source_id": "S5_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S5_scope", "span_occurrence_id": "V2-TERRA-04:S5_cited_not_verified:S5_scope", "span_root_id": "span:sha256:cebc739ec2bf421e0853467bfeccb3f42bda1cf05472076a1c1bc6d9fb1edfb9" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Section 4.1, Table 1", "match_status": "unresolved", "matched_fragments": [], "quote_sha256": "42b7ccd7579ae20fa667410ef47609278f518af058f6feb1b15409b7fb253d01", "run_id": "V2-TERRA-04", "source_id": "S5_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S5_table1", "span_occurrence_id": "V2-TERRA-04:S5_cited_not_verified:S5_table1", "span_root_id": "span:sha256:caaa3e2fbb4cef64558f2c8cc30388281e1505c9353fb775f960a5f18c816111" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Section 4.3, Tables 2-3 and following paragraph", "match_status": "exact-normalized-match", "matched_fragments": [], "quote_sha256": "4ff735800b0f2aca92c4c6865a7bcf5746c1b7711a6105d5403bdffb68adce63", "run_id": "V2-TERRA-04", "source_id": "S5_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S5_depth", "span_occurrence_id": "V2-TERRA-04:S5_cited_not_verified:S5_depth", "span_root_id": "span:sha256:d638c8b21f0e4a0f840880b6ffe0217ce1623758cc09fdccc32cacf2db3dd958" }, { "citation_carrier_accessible": true, "edition_id": "edition:cnv-arxiv-v1", "locator": "Section 5 'Limitations'", "match_status": "ordered-fragment-match", "matched_fragments": [ "LLM-as-a-judge", "may retain biases inherent to the judge model" ], "quote_sha256": "a14ffeb203983bb9ab414d79300766c78a29ade822b77d94bdd51c6788cfe450", "run_id": "V2-TERRA-04", "source_id": "S5_cited_not_verified", "source_text_sha256": "1dd04031e118646bdebec5e35d289cc625e758ff165a63ba3cbf0680ad12bb10", "span_id": "S5_limitations", "span_occurrence_id": "V2-TERRA-04:S5_cited_not_verified:S5_limitations", "span_root_id": "span:sha256:c7dbd1d9e09980703ecbee8161594e4b426c1af63117b28662a7e98686107621" } ], "schema": "https://epistemedia.org/research/span-readbacks-v1.json", "task_id": "EM-0026" }