{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MGU35G7F4E2V7LSHLSZWXUHU5I","short_pith_number":"pith:MGU35G7F","schema_version":"1.0","canonical_sha256":"61a9be9be5e1355fae475cb36bd0f4ea2932d3c43cf1eacadf54058edb3ad4ab","source":{"kind":"arxiv","id":"2512.10888","version":3},"attestation_state":"computed","paper":{"title":"PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amrit Ramesh, Brandon Smock, Libin Liang, Maury Courtland, Max Sokolov, Tayyibah Khanam, Valerie Faucon-Morin","submitted_at":"2025-12-11T18:19:00Z","abstract_excerpt":"Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Recently, interest has surged in developing methods, such as vision-language models (VLMs), to extract tables directly in their full page or document context. However, a lack of annotated data has made progress difficult to demonstrate. To address this, we create a new large-scale dataset, PubTables-v2. PubTables-v2 unifies TE across various levels of surrounding context and, notably, is the first benchmark for multi-page TE. Our evaluations reveal tha"},"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":"2512.10888","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T18:19:00Z","cross_cats_sorted":[],"title_canon_sha256":"26160e1426495cf8a2456bdae1d759dd67ede59d6c0d4eabb8a66cb86d44ad43","abstract_canon_sha256":"8b1cb7514b21bec716403ca96a050950123f5d36f2924d87d885d7e2f92c8106"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:05:44.076151Z","signature_b64":"kX897BZUE6VFRxK5AHtED8vFjPhk8ALa9qgZv35euq7YryejyQc6QytRTyUYhmin7YvBU8GFqpAxLzr7p0hSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61a9be9be5e1355fae475cb36bd0f4ea2932d3c43cf1eacadf54058edb3ad4ab","last_reissued_at":"2026-06-03T02:05:44.075645Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:05:44.075645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amrit Ramesh, Brandon Smock, Libin Liang, Maury Courtland, Max Sokolov, Tayyibah Khanam, Valerie Faucon-Morin","submitted_at":"2025-12-11T18:19:00Z","abstract_excerpt":"Table extraction (TE) is a key challenge in document understanding. Traditional approaches detect tables first, then recognize their structure. Recently, interest has surged in developing methods, such as vision-language models (VLMs), to extract tables directly in their full page or document context. However, a lack of annotated data has made progress difficult to demonstrate. To address this, we create a new large-scale dataset, PubTables-v2. PubTables-v2 unifies TE across various levels of surrounding context and, notably, is the first benchmark for multi-page TE. Our evaluations reveal tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10888","kind":"arxiv","version":3},"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/2512.10888/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":"2512.10888","created_at":"2026-06-03T02:05:44.075701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.10888v3","created_at":"2026-06-03T02:05:44.075701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10888","created_at":"2026-06-03T02:05:44.075701+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGU35G7F4E2V","created_at":"2026-06-03T02:05:44.075701+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGU35G7F4E2V7LSH","created_at":"2026-06-03T02:05:44.075701+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGU35G7F","created_at":"2026-06-03T02:05:44.075701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.09788","citing_title":"POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I","json":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I.json","graph_json":"https://pith.science/api/pith-number/MGU35G7F4E2V7LSHLSZWXUHU5I/graph.json","events_json":"https://pith.science/api/pith-number/MGU35G7F4E2V7LSHLSZWXUHU5I/events.json","paper":"https://pith.science/paper/MGU35G7F"},"agent_actions":{"view_html":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I","download_json":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I.json","view_paper":"https://pith.science/paper/MGU35G7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.10888&json=true","fetch_graph":"https://pith.science/api/pith-number/MGU35G7F4E2V7LSHLSZWXUHU5I/graph.json","fetch_events":"https://pith.science/api/pith-number/MGU35G7F4E2V7LSHLSZWXUHU5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I/action/storage_attestation","attest_author":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I/action/author_attestation","sign_citation":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I/action/citation_signature","submit_replication":"https://pith.science/pith/MGU35G7F4E2V7LSHLSZWXUHU5I/action/replication_record"}},"created_at":"2026-06-03T02:05:44.075701+00:00","updated_at":"2026-06-03T02:05:44.075701+00:00"}