{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2VC2HONQ65LKSW7MLJ2PP5FQM4","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":"310f18930051851c710a55f9bb3f53c3a8fa4d5f1060b26587f858f44e67ee9c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T18:20:24Z","title_canon_sha256":"1024ea139a8a7cda1bbd18254ea79055f16f39ce58d5d9c7bd6581a4aef2c596"},"schema_version":"1.0","source":{"id":"2303.00716","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00716","created_at":"2026-07-05T06:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00716v2","created_at":"2026-07-05T06:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00716","created_at":"2026-07-05T06:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"2VC2HONQ65LK","created_at":"2026-07-05T06:13:19Z"},{"alias_kind":"pith_short_16","alias_value":"2VC2HONQ65LKSW7M","created_at":"2026-07-05T06:13:19Z"},{"alias_kind":"pith_short_8","alias_value":"2VC2HONQ","created_at":"2026-07-05T06:13:19Z"}],"graph_snapshots":[{"event_id":"sha256:47f966b23628e344a61784ad397f72985f809de9482778e2a0897a26bfce39e3","target":"graph","created_at":"2026-07-05T06:13:19Z","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/2303.00716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark datasets for table structure recognition (TSR) must be carefully processed to ensure they are annotated consistently. However, even if a dataset's annotations are self-consistent, there may be significant inconsistency across datasets, which can harm the performance of models trained and evaluated on them. In this work, we show that aligning these benchmarks$\\unicode{x2014}$removing both errors and inconsistency between them$\\unicode{x2014}$improves model performance significantly. We demonstrate this through a data-centric approach where we adopt one model architecture, the Table Tr","authors_text":"Brandon Smock, Robin Abraham, Rohith Pesala","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T18:20:24Z","title":"Aligning benchmark datasets for table structure recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00716","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":"sha256:68a9302c327c22007f46ecbc39423c7a715c64507a05f0cded439cabb9b46aa3","target":"record","created_at":"2026-07-05T06:13:19Z","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":"310f18930051851c710a55f9bb3f53c3a8fa4d5f1060b26587f858f44e67ee9c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T18:20:24Z","title_canon_sha256":"1024ea139a8a7cda1bbd18254ea79055f16f39ce58d5d9c7bd6581a4aef2c596"},"schema_version":"1.0","source":{"id":"2303.00716","kind":"arxiv","version":2}},"canonical_sha256":"d545a3b9b0f756a95bec5a74f7f4b06732848a17dbcc81036c99dca788a84f57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d545a3b9b0f756a95bec5a74f7f4b06732848a17dbcc81036c99dca788a84f57","first_computed_at":"2026-07-05T06:13:19.722031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:19.722031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i4TUyNp06vXqZXCtGbiPXyyH9P9uaStziQNRUP8qmhIc8lfYr4CovLAGJ5BJvgU/Dsfzm+uVM4o/uxrEpcbqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:19.722455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00716","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68a9302c327c22007f46ecbc39423c7a715c64507a05f0cded439cabb9b46aa3","sha256:47f966b23628e344a61784ad397f72985f809de9482778e2a0897a26bfce39e3"],"state_sha256":"4f03c63f4468cdb1b8f6bbb2adf3b4658536f57464503c6c075b665a0af8ee2c"}