{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MGU35G7F4E2V7LSHLSZWXUHU5I","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":"8b1cb7514b21bec716403ca96a050950123f5d36f2924d87d885d7e2f92c8106","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T18:19:00Z","title_canon_sha256":"26160e1426495cf8a2456bdae1d759dd67ede59d6c0d4eabb8a66cb86d44ad43"},"schema_version":"1.0","source":{"id":"2512.10888","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.10888","created_at":"2026-06-03T02:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2512.10888v3","created_at":"2026-06-03T02:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10888","created_at":"2026-06-03T02:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"MGU35G7F4E2V","created_at":"2026-06-03T02:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"MGU35G7F4E2V7LSH","created_at":"2026-06-03T02:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"MGU35G7F","created_at":"2026-06-03T02:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:a4306ae0051971f172b7d91d386eeb7208145edb8d094a92ee644350bfbedd1e","target":"graph","created_at":"2026-06-03T02:05:44Z","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/2512.10888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Amrit Ramesh, Brandon Smock, Libin Liang, Maury Courtland, Max Sokolov, Tayyibah Khanam, Valerie Faucon-Morin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T18:19:00Z","title":"PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10888","kind":"arxiv","version":3},"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:b7c33516226e822771f62f5aef1dc324dde864bb7a22c39b2492ea8c1bd7e794","target":"record","created_at":"2026-06-03T02:05:44Z","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":"8b1cb7514b21bec716403ca96a050950123f5d36f2924d87d885d7e2f92c8106","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T18:19:00Z","title_canon_sha256":"26160e1426495cf8a2456bdae1d759dd67ede59d6c0d4eabb8a66cb86d44ad43"},"schema_version":"1.0","source":{"id":"2512.10888","kind":"arxiv","version":3}},"canonical_sha256":"61a9be9be5e1355fae475cb36bd0f4ea2932d3c43cf1eacadf54058edb3ad4ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61a9be9be5e1355fae475cb36bd0f4ea2932d3c43cf1eacadf54058edb3ad4ab","first_computed_at":"2026-06-03T02:05:44.075645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:05:44.075645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kX897BZUE6VFRxK5AHtED8vFjPhk8ALa9qgZv35euq7YryejyQc6QytRTyUYhmin7YvBU8GFqpAxLzr7p0hSDg==","signature_status":"signed_v1","signed_at":"2026-06-03T02:05:44.076151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.10888","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7c33516226e822771f62f5aef1dc324dde864bb7a22c39b2492ea8c1bd7e794","sha256:a4306ae0051971f172b7d91d386eeb7208145edb8d094a92ee644350bfbedd1e"],"state_sha256":"dfb82333f0699e23587c0030bb72d8da49c41d03f6e684a8869e2c9d06e7cbd1"}