{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FL7PQ3OY3HQ5WVG2QWD6FYWXHK","short_pith_number":"pith:FL7PQ3OY","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"},"canonical_sha256":"2afef86dd8d9e1db54da8587e2e2d73ab67d92f421e2899fed57dab7a03ca565","source":{"kind":"arxiv","id":"2507.02009","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02009","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02009v2","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02009","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"FL7PQ3OY3HQ5","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"FL7PQ3OY3HQ5WVG2","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"FL7PQ3OY","created_at":"2026-07-05T11:34:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FL7PQ3OY3HQ5WVG2QWD6FYWXHK","target":"record","payload":{"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"},"canonical_sha256":"2afef86dd8d9e1db54da8587e2e2d73ab67d92f421e2899fed57dab7a03ca565","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"},"source_kind":"arxiv","source_id":"2507.02009","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JTwEGLqb7DOPuxy+VEwr33gWhxcSoPRh6u5v9z9efBervalGzj1M/O/Q4Qy2EhhDJjbi5ODIy0UKXHRNUuTuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:42:26.892837Z"},"content_sha256":"98223243f8d4c125bb29caf137eac428819f802f7075f4be5ec0aff10bb7d461","schema_version":"1.0","event_id":"sha256:98223243f8d4c125bb29caf137eac428819f802f7075f4be5ec0aff10bb7d461"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FL7PQ3OY3HQ5WVG2QWD6FYWXHK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KODyIAhbdDGowAy7em9HvQYHSC62iOAVqmwuFXUykmnVA8skfXgUUY2O9bcHt3MuOuSKsWT+MaASpXGGfBZuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:42:26.894701Z"},"content_sha256":"1a231f0e9b13058974d7425e34b476e8890de81658772d4c3a4e5615b6141a86","schema_version":"1.0","event_id":"sha256:1a231f0e9b13058974d7425e34b476e8890de81658772d4c3a4e5615b6141a86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/bundle.json","state_url":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T15:42:26Z","links":{"resolver":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK","bundle":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/bundle.json","state":"https://pith.science/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FL7PQ3OY3HQ5WVG2QWD6FYWXHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FL7PQ3OY3HQ5WVG2QWD6FYWXHK","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":"9a5932cdab20119b0a214bf41165d45ab2a9c608f8f0d1122fd8027bf93ed2f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-02T03:36:15Z","title_canon_sha256":"086c613056acfbf0d4b6f8c883d2be990a49f6fced69143356eeae2448b98c08"},"schema_version":"1.0","source":{"id":"2507.02009","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02009","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02009v2","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02009","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_12","alias_value":"FL7PQ3OY3HQ5","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_16","alias_value":"FL7PQ3OY3HQ5WVG2","created_at":"2026-07-05T11:34:11Z"},{"alias_kind":"pith_short_8","alias_value":"FL7PQ3OY","created_at":"2026-07-05T11:34:11Z"}],"graph_snapshots":[{"event_id":"sha256:1a231f0e9b13058974d7425e34b476e8890de81658772d4c3a4e5615b6141a86","target":"graph","created_at":"2026-07-05T11:34:11Z","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/2507.02009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jian Wu, Kehinde Ajayi, Yi He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-02T03:36:15Z","title":"Uncertainty-Aware Complex Scientific Table Data Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02009","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":"sha256:98223243f8d4c125bb29caf137eac428819f802f7075f4be5ec0aff10bb7d461","target":"record","created_at":"2026-07-05T11:34:11Z","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":"9a5932cdab20119b0a214bf41165d45ab2a9c608f8f0d1122fd8027bf93ed2f1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-02T03:36:15Z","title_canon_sha256":"086c613056acfbf0d4b6f8c883d2be990a49f6fced69143356eeae2448b98c08"},"schema_version":"1.0","source":{"id":"2507.02009","kind":"arxiv","version":2}},"canonical_sha256":"2afef86dd8d9e1db54da8587e2e2d73ab67d92f421e2899fed57dab7a03ca565","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2afef86dd8d9e1db54da8587e2e2d73ab67d92f421e2899fed57dab7a03ca565","first_computed_at":"2026-07-05T11:34:11.039682Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:11.039682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QHLaeBjZrhvtdafPngRrb+Jb35aqCyPplYCPWFi2VRTDfkB9stq4U+KeKDjJSl2aFAMRjDj7oJ2Pmr+N2AnoBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:11.040172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02009","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98223243f8d4c125bb29caf137eac428819f802f7075f4be5ec0aff10bb7d461","sha256:1a231f0e9b13058974d7425e34b476e8890de81658772d4c3a4e5615b6141a86"],"state_sha256":"bd13275de56bbc728245ac8d0f2fed4a0b1a2f920cd2aaa1d65c70af390dee61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m8Vv9QTlk8IxTgX2JgMXW2e4K6c6EO60CqkqMqH5hPRfefGCNIyqQoG19s1gxS32IQpHnSAbrpDo6gcAWHLiCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:42:26.899282Z","bundle_sha256":"435e2a6ab42599615a2bb072523fc7df63ab647a7d4124a312f19d802e39737a"}}