{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FL7PQ3OY3HQ5WVG2QWD6FYWXHK","short_pith_number":"pith:FL7PQ3OY","schema_version":"1.0","canonical_sha256":"2afef86dd8d9e1db54da8587e2e2d73ab67d92f421e2899fed57dab7a03ca565","source":{"kind":"arxiv","id":"2507.02009","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware Complex Scientific Table Data Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jian Wu, Kehinde Ajayi, Yi He","submitted_at":"2025-07-02T03:36:15Z","abstract_excerpt":"Table structure recognition (TSR) and optical character recognition (OCR) play crucial roles in extracting structured data from tables in scientific documents. However, existing extraction frameworks built on top of TSR and OCR methods often fail to quantify the uncertainties of extracted results. To obtain highly accurate data for scientific domains, all extracted data must be manually verified, which can be time-consuming and labor-intensive. We propose a framework that performs uncertainty-aware data extraction for complex scientific tables, built on conformal prediction, a model-agnostic m"},"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":"2507.02009","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-02T03:36:15Z","cross_cats_sorted":[],"title_canon_sha256":"086c613056acfbf0d4b6f8c883d2be990a49f6fced69143356eeae2448b98c08","abstract_canon_sha256":"9a5932cdab20119b0a214bf41165d45ab2a9c608f8f0d1122fd8027bf93ed2f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:11.040172Z","signature_b64":"QHLaeBjZrhvtdafPngRrb+Jb35aqCyPplYCPWFi2VRTDfkB9stq4U+KeKDjJSl2aFAMRjDj7oJ2Pmr+N2AnoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2afef86dd8d9e1db54da8587e2e2d73ab67d92f421e2899fed57dab7a03ca565","last_reissued_at":"2026-07-05T11:34:11.039682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:11.039682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Complex Scientific Table Data Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Jian Wu, Kehinde Ajayi, Yi He","submitted_at":"2025-07-02T03:36:15Z","abstract_excerpt":"Table structure recognition (TSR) and optical character recognition (OCR) play crucial roles in extracting structured data from tables in scientific documents. However, existing extraction frameworks built on top of TSR and OCR methods often fail to quantify the uncertainties of extracted results. To obtain highly accurate data for scientific domains, all extracted data must be manually verified, which can be time-consuming and labor-intensive. We propose a framework that performs uncertainty-aware data extraction for complex scientific tables, built on conformal prediction, a model-agnostic m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02009","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/2507.02009/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":"2507.02009","created_at":"2026-07-05T11:34:11.039740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02009v2","created_at":"2026-07-05T11:34:11.039740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02009","created_at":"2026-07-05T11:34:11.039740+00:00"},{"alias_kind":"pith_short_12","alias_value":"FL7PQ3OY3HQ5","created_at":"2026-07-05T11:34:11.039740+00:00"},{"alias_kind":"pith_short_16","alias_value":"FL7PQ3OY3HQ5WVG2","created_at":"2026-07-05T11:34:11.039740+00:00"},{"alias_kind":"pith_short_8","alias_value":"FL7PQ3OY","created_at":"2026-07-05T11:34:11.039740+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/FL7PQ3OY3HQ5WVG2QWD6FYWXHK","json":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK.json","graph_json":"https://pith.science/api/pith-number/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/graph.json","events_json":"https://pith.science/api/pith-number/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/events.json","paper":"https://pith.science/paper/FL7PQ3OY"},"agent_actions":{"view_html":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK","download_json":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK.json","view_paper":"https://pith.science/paper/FL7PQ3OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02009&json=true","fetch_graph":"https://pith.science/api/pith-number/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/graph.json","fetch_events":"https://pith.science/api/pith-number/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/action/storage_attestation","attest_author":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/action/author_attestation","sign_citation":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/action/citation_signature","submit_replication":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/action/replication_record"}},"created_at":"2026-07-05T11:34:11.039740+00:00","updated_at":"2026-07-05T11:34:11.039740+00:00"}