{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3A5LSQSBBX2LM34C5AH2VRFLFG","short_pith_number":"pith:3A5LSQSB","schema_version":"1.0","canonical_sha256":"d83ab942410df4b66f82e80faac4ab299b27119f6720f6d03a131ab1b60ef3f7","source":{"kind":"arxiv","id":"2606.09788","version":1},"attestation_state":"computed","paper":{"title":"POTATR: A Lightweight Image-to-Graph Model for Page-Level 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":"2026-06-08T17:43:44Z","abstract_excerpt":"Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundreds of autoregressive steps, or costly API inference. Motivated by this, we introduce the Page-Object Table Transformer (POTATR), a lightweight 29M parameter image-to-graph model that extends the Table Transformer (TATR) for contextualized page-level TE. POTATR outperforms all models tested on the PubTables-v2 Single Pages benchmark -- including frontier MLLMs -- achieving $\\textrm{GriTS}_\\textrm{Con}$ of 0.964 while "},"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":"2606.09788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T17:43:44Z","cross_cats_sorted":[],"title_canon_sha256":"404110a11467de72a35e0e08568416bad2c9afe54ad0cb52ea8ba62a82930b2d","abstract_canon_sha256":"5894cd7f85e8ff1916669444b69b81f26067e52f5a12b5ceadb881ff5b74ad2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:09.914926Z","signature_b64":"jw6YldHqa4eKaciyPmAL8wyqJLYFKqmMgokOxUrC2i7MaO49NDSgprN6tgGwH61s6qgUVljPAA+8Qo++jrGiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d83ab942410df4b66f82e80faac4ab299b27119f6720f6d03a131ab1b60ef3f7","last_reissued_at":"2026-06-09T02:09:09.914086Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:09.914086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POTATR: A Lightweight Image-to-Graph Model for Page-Level 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":"2026-06-08T17:43:44Z","abstract_excerpt":"Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundreds of autoregressive steps, or costly API inference. Motivated by this, we introduce the Page-Object Table Transformer (POTATR), a lightweight 29M parameter image-to-graph model that extends the Table Transformer (TATR) for contextualized page-level TE. POTATR outperforms all models tested on the PubTables-v2 Single Pages benchmark -- including frontier MLLMs -- achieving $\\textrm{GriTS}_\\textrm{Con}$ of 0.964 while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09788","kind":"arxiv","version":1},"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/2606.09788/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":"2606.09788","created_at":"2026-06-09T02:09:09.914216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09788v1","created_at":"2026-06-09T02:09:09.914216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09788","created_at":"2026-06-09T02:09:09.914216+00:00"},{"alias_kind":"pith_short_12","alias_value":"3A5LSQSBBX2L","created_at":"2026-06-09T02:09:09.914216+00:00"},{"alias_kind":"pith_short_16","alias_value":"3A5LSQSBBX2LM34C","created_at":"2026-06-09T02:09:09.914216+00:00"},{"alias_kind":"pith_short_8","alias_value":"3A5LSQSB","created_at":"2026-06-09T02:09:09.914216+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/3A5LSQSBBX2LM34C5AH2VRFLFG","json":"https://pith.science/pith/3A5LSQSBBX2LM34C5AH2VRFLFG.json","graph_json":"https://pith.science/api/pith-number/3A5LSQSBBX2LM34C5AH2VRFLFG/graph.json","events_json":"https://pith.science/api/pith-number/3A5LSQSBBX2LM34C5AH2VRFLFG/events.json","paper":"https://pith.science/paper/3A5LSQSB"},"agent_actions":{"view_html":"https://pith.science/pith/3A5LSQSBBX2LM34C5AH2VRFLFG","download_json":"https://pith.science/pith/3A5LSQSBBX2LM34C5AH2VRFLFG.json","view_paper":"https://pith.science/paper/3A5LSQSB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09788&json=true","fetch_graph":"https://pith.science/api/pith-number/3A5LSQSBBX2LM34C5AH2VRFLFG/graph.json","fetch_events":"https://pith.science/api/pith-number/3A5LSQSBBX2LM34C5AH2VRFLFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3A5LSQSBBX2LM34C5AH2VRFLFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3A5LSQSBBX2LM34C5AH2VRFLFG/action/storage_attestation","attest_author":"https://pith.science/pith/3A5LSQSBBX2LM34C5AH2VRFLFG/action/author_attestation","sign_citation":"https://pith.science/pith/3A5LSQSBBX2LM34C5AH2VRFLFG/action/citation_signature","submit_replication":"https://pith.science/pith/3A5LSQSBBX2LM34C5AH2VRFLFG/action/replication_record"}},"created_at":"2026-06-09T02:09:09.914216+00:00","updated_at":"2026-06-09T02:09:09.914216+00:00"}