{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NF6X2QJZVAC7YBHRFKXRTGWEDI","short_pith_number":"pith:NF6X2QJZ","schema_version":"1.0","canonical_sha256":"697d7d4139a805fc04f12aaf199ac41a00385caefe3ab195a1754642770f0f4c","source":{"kind":"arxiv","id":"2606.07401","version":1},"attestation_state":"computed","paper":{"title":"RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameya Joshi, Cindy Hao, Eli Badgio, Gus Eggert, Jing Reyhan, Joon Kim, Joseph Bajor, Kushal Byatnal","submitted_at":"2026-06-05T15:41:34Z","abstract_excerpt":"Document parsing systems are increasingly deployed in high-stakes, regulated workflows such as mortgage underwriting, financial reporting, supply-chain logistics, and clinical records. Yet most public benchmarks evaluate parsers on clean academic layouts or synthetic prose, and report a single OCR or markdown-level similarity score. Such documents and metrics correlate poorly with what downstream agents actually need: the correct value for a specific field on a messy real-world page. We introduce RealDocBench, a two-track benchmark built from real regulated documents. The QA track contains 1,3"},"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":"2606.07401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T15:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"7c50b425d4ffd15e1eff85d4d8256d9ed97502226edbe81a2deb05f2d94a39c1","abstract_canon_sha256":"6bc9d667a696e42df6cf953179c58a7d36cdc8db61420cfbf3e9743ace135f6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:24.979752Z","signature_b64":"ljFlErCXOFcexzy+kOVhQ3gb5aDHkENhF70jll0W4tkeWlsCtF40zplPTbpm5dTtQR9bA+uD+JMDPWH+6r7aAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"697d7d4139a805fc04f12aaf199ac41a00385caefe3ab195a1754642770f0f4c","last_reissued_at":"2026-06-08T01:05:24.978874Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:24.978874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameya Joshi, Cindy Hao, Eli Badgio, Gus Eggert, Jing Reyhan, Joon Kim, Joseph Bajor, Kushal Byatnal","submitted_at":"2026-06-05T15:41:34Z","abstract_excerpt":"Document parsing systems are increasingly deployed in high-stakes, regulated workflows such as mortgage underwriting, financial reporting, supply-chain logistics, and clinical records. Yet most public benchmarks evaluate parsers on clean academic layouts or synthetic prose, and report a single OCR or markdown-level similarity score. Such documents and metrics correlate poorly with what downstream agents actually need: the correct value for a specific field on a messy real-world page. We introduce RealDocBench, a two-track benchmark built from real regulated documents. The QA track contains 1,3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07401","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/2606.07401/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":"2606.07401","created_at":"2026-06-08T01:05:24.979011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07401v1","created_at":"2026-06-08T01:05:24.979011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07401","created_at":"2026-06-08T01:05:24.979011+00:00"},{"alias_kind":"pith_short_12","alias_value":"NF6X2QJZVAC7","created_at":"2026-06-08T01:05:24.979011+00:00"},{"alias_kind":"pith_short_16","alias_value":"NF6X2QJZVAC7YBHR","created_at":"2026-06-08T01:05:24.979011+00:00"},{"alias_kind":"pith_short_8","alias_value":"NF6X2QJZ","created_at":"2026-06-08T01:05:24.979011+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/NF6X2QJZVAC7YBHRFKXRTGWEDI","json":"https://pith.science/pith/NF6X2QJZVAC7YBHRFKXRTGWEDI.json","graph_json":"https://pith.science/api/pith-number/NF6X2QJZVAC7YBHRFKXRTGWEDI/graph.json","events_json":"https://pith.science/api/pith-number/NF6X2QJZVAC7YBHRFKXRTGWEDI/events.json","paper":"https://pith.science/paper/NF6X2QJZ"},"agent_actions":{"view_html":"https://pith.science/pith/NF6X2QJZVAC7YBHRFKXRTGWEDI","download_json":"https://pith.science/pith/NF6X2QJZVAC7YBHRFKXRTGWEDI.json","view_paper":"https://pith.science/paper/NF6X2QJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07401&json=true","fetch_graph":"https://pith.science/api/pith-number/NF6X2QJZVAC7YBHRFKXRTGWEDI/graph.json","fetch_events":"https://pith.science/api/pith-number/NF6X2QJZVAC7YBHRFKXRTGWEDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NF6X2QJZVAC7YBHRFKXRTGWEDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NF6X2QJZVAC7YBHRFKXRTGWEDI/action/storage_attestation","attest_author":"https://pith.science/pith/NF6X2QJZVAC7YBHRFKXRTGWEDI/action/author_attestation","sign_citation":"https://pith.science/pith/NF6X2QJZVAC7YBHRFKXRTGWEDI/action/citation_signature","submit_replication":"https://pith.science/pith/NF6X2QJZVAC7YBHRFKXRTGWEDI/action/replication_record"}},"created_at":"2026-06-08T01:05:24.979011+00:00","updated_at":"2026-06-08T01:05:24.979011+00:00"}