{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IBHVJMMF5J3XVUXIV7HL3TQEIT","short_pith_number":"pith:IBHVJMMF","schema_version":"1.0","canonical_sha256":"404f54b185ea777ad2e8afcebdce0444f9b48024f49de5851a18b18c7bd3ef50","source":{"kind":"arxiv","id":"2511.16134","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Table Extraction from Heterogeneous Scientific PDF Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"C\\'ecile Gracianne, Ioana Manolescu, Marijan Soric, Pierre Senellart","submitted_at":"2025-11-20T08:09:48Z","abstract_excerpt":"Table Extraction (TE) consists in extracting tables from PDF documents, in a structured format enabling automatic processing. While numerous TE tools exist, the variety of methods and techniques makes it difficult for users to choose the most appropriate one. We propose a novel benchmark for assessing end-to-end TE methods (from PDF to the final table) over 86k pages. We contribute an analysis of TE evaluation metrics, and a novel, rigorous evaluation process, which allows scoring each TE sub-task as well as end-to-end TE, and captures model uncertainty. Along with prior datasets, our benchmar"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2511.16134","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-11-20T08:09:48Z","cross_cats_sorted":[],"title_canon_sha256":"ff961aa400c4c248f783f5a89736f564bf1a53f7f7a7b47c12d415ac1e672c51","abstract_canon_sha256":"a570336f9f6b43194176de7ac61103b15b33470f37844efba273c3e5d5c27b45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:12:15.115970Z","signature_b64":"sLwxCYOZDjZMvEeSCzIvfkdQkY2TI0QOUtSK4RRo8JwgW6+cACWUnJkShk3xo7Nr7lYst/V6jgI0KUAo/EE1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"404f54b185ea777ad2e8afcebdce0444f9b48024f49de5851a18b18c7bd3ef50","last_reissued_at":"2026-08-03T01:12:15.114006Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:12:15.114006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Table Extraction from Heterogeneous Scientific PDF Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"C\\'ecile Gracianne, Ioana Manolescu, Marijan Soric, Pierre Senellart","submitted_at":"2025-11-20T08:09:48Z","abstract_excerpt":"Table Extraction (TE) consists in extracting tables from PDF documents, in a structured format enabling automatic processing. While numerous TE tools exist, the variety of methods and techniques makes it difficult for users to choose the most appropriate one. We propose a novel benchmark for assessing end-to-end TE methods (from PDF to the final table) over 86k pages. We contribute an analysis of TE evaluation metrics, and a novel, rigorous evaluation process, which allows scoring each TE sub-task as well as end-to-end TE, and captures model uncertainty. Along with prior datasets, our benchmar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.16134","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2511.16134/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2511.16134","created_at":"2026-08-03T01:12:15.115073+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.16134v2","created_at":"2026-08-03T01:12:15.115073+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16134","created_at":"2026-08-03T01:12:15.115073+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBHVJMMF5J3X","created_at":"2026-08-03T01:12:15.115073+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBHVJMMF5J3XVUXI","created_at":"2026-08-03T01:12:15.115073+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBHVJMMF","created_at":"2026-08-03T01:12:15.115073+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT","json":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT.json","graph_json":"https://pith.science/api/pith-number/IBHVJMMF5J3XVUXIV7HL3TQEIT/graph.json","events_json":"https://pith.science/api/pith-number/IBHVJMMF5J3XVUXIV7HL3TQEIT/events.json","paper":"https://pith.science/paper/IBHVJMMF"},"agent_actions":{"view_html":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT","download_json":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT.json","view_paper":"https://pith.science/paper/IBHVJMMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.16134&json=true","fetch_graph":"https://pith.science/api/pith-number/IBHVJMMF5J3XVUXIV7HL3TQEIT/graph.json","fetch_events":"https://pith.science/api/pith-number/IBHVJMMF5J3XVUXIV7HL3TQEIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/action/storage_attestation","attest_author":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/action/author_attestation","sign_citation":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/action/citation_signature","submit_replication":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/action/replication_record"}},"created_at":"2026-08-03T01:12:15.115073+00:00","updated_at":"2026-08-03T01:12:15.115073+00:00"}