{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IBHVJMMF5J3XVUXIV7HL3TQEIT","short_pith_number":"pith:IBHVJMMF","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"},"canonical_sha256":"404f54b185ea777ad2e8afcebdce0444f9b48024f49de5851a18b18c7bd3ef50","source":{"kind":"arxiv","id":"2511.16134","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.16134","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"arxiv_version","alias_value":"2511.16134v2","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16134","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"pith_short_12","alias_value":"IBHVJMMF5J3X","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"pith_short_16","alias_value":"IBHVJMMF5J3XVUXI","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"pith_short_8","alias_value":"IBHVJMMF","created_at":"2026-08-03T01:12:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IBHVJMMF5J3XVUXIV7HL3TQEIT","target":"record","payload":{"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"},"canonical_sha256":"404f54b185ea777ad2e8afcebdce0444f9b48024f49de5851a18b18c7bd3ef50","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"},"source_kind":"arxiv","source_id":"2511.16134","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-03T01:12:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FKpA+SJifRvP1G1FemLuJZ/7+fxZUFXHP9xv8QMQtuVeWmG/bzdHOBfF0xNfYIpNEgGmEAeIH/SW0CS/0bWNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:28:12.381546Z"},"content_sha256":"4136929eee55fda60e60312327d3ad4a16e9db7cc3584890ebd06d79ed72046c","schema_version":"1.0","event_id":"sha256:4136929eee55fda60e60312327d3ad4a16e9db7cc3584890ebd06d79ed72046c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IBHVJMMF5J3XVUXIV7HL3TQEIT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-03T01:12:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z0IaqsSNw/VHNy4+a6WJjEN3goQbO3mmDKoy6UczDgat7CCaEw5f2Oa5CwRaLpMbX27L9WSrBx3+cHP9pejmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:28:12.382049Z"},"content_sha256":"02784945c17d44a494e1aedc23e840c45c2d1b8dcc1fed39844c0a339a1cefbf","schema_version":"1.0","event_id":"sha256:02784945c17d44a494e1aedc23e840c45c2d1b8dcc1fed39844c0a339a1cefbf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/bundle.json","state_url":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T18:28:12Z","links":{"resolver":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT","bundle":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/bundle.json","state":"https://pith.science/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBHVJMMF5J3XVUXIV7HL3TQEIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IBHVJMMF5J3XVUXIV7HL3TQEIT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a570336f9f6b43194176de7ac61103b15b33470f37844efba273c3e5d5c27b45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-11-20T08:09:48Z","title_canon_sha256":"ff961aa400c4c248f783f5a89736f564bf1a53f7f7a7b47c12d415ac1e672c51"},"schema_version":"1.0","source":{"id":"2511.16134","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.16134","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"arxiv_version","alias_value":"2511.16134v2","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.16134","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"pith_short_12","alias_value":"IBHVJMMF5J3X","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"pith_short_16","alias_value":"IBHVJMMF5J3XVUXI","created_at":"2026-08-03T01:12:15Z"},{"alias_kind":"pith_short_8","alias_value":"IBHVJMMF","created_at":"2026-08-03T01:12:15Z"}],"graph_snapshots":[{"event_id":"sha256:02784945c17d44a494e1aedc23e840c45c2d1b8dcc1fed39844c0a339a1cefbf","target":"graph","created_at":"2026-08-03T01:12:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.16134/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"C\\'ecile Gracianne, Ioana Manolescu, Marijan Soric, Pierre Senellart","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-11-20T08:09:48Z","title":"Benchmarking Table Extraction from Heterogeneous Scientific PDF Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.16134","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4136929eee55fda60e60312327d3ad4a16e9db7cc3584890ebd06d79ed72046c","target":"record","created_at":"2026-08-03T01:12:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a570336f9f6b43194176de7ac61103b15b33470f37844efba273c3e5d5c27b45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-11-20T08:09:48Z","title_canon_sha256":"ff961aa400c4c248f783f5a89736f564bf1a53f7f7a7b47c12d415ac1e672c51"},"schema_version":"1.0","source":{"id":"2511.16134","kind":"arxiv","version":2}},"canonical_sha256":"404f54b185ea777ad2e8afcebdce0444f9b48024f49de5851a18b18c7bd3ef50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"404f54b185ea777ad2e8afcebdce0444f9b48024f49de5851a18b18c7bd3ef50","first_computed_at":"2026-08-03T01:12:15.114006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:12:15.114006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sLwxCYOZDjZMvEeSCzIvfkdQkY2TI0QOUtSK4RRo8JwgW6+cACWUnJkShk3xo7Nr7lYst/V6jgI0KUAo/EE1Bw==","signature_status":"signed_v1","signed_at":"2026-08-03T01:12:15.115970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.16134","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4136929eee55fda60e60312327d3ad4a16e9db7cc3584890ebd06d79ed72046c","sha256:02784945c17d44a494e1aedc23e840c45c2d1b8dcc1fed39844c0a339a1cefbf"],"state_sha256":"caa5163ae23b5c77c38eea6df225fc1ba1c9a50fa16ed4a08c728cc3345251f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WLWTxxMaIBcsctrukr8WnXZ67Asr6nT767l9d36odolbd9ADcqjRM03Qc/3VbbCn0dS6TKOP+jlTZu/N+/aTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T18:28:12.385373Z","bundle_sha256":"e6a5523baca98e1703b424d0bfc55b6b711f98e8d7761c046f38ac490e9381d0"}}