{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:N3ZDMBT3W3PCSF2PO2OWSSD2MD","short_pith_number":"pith:N3ZDMBT3","schema_version":"1.0","canonical_sha256":"6ef236067bb6de29174f769d69487a60c8316204584500f6727e10f21d9b12dc","source":{"kind":"arxiv","id":"2010.05322","version":1},"attestation_state":"computed","paper":{"title":"Revising FUNSD dataset for key-value detection in document images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diep Thi-Ngoc Nguyen, Hieu M. Vu","submitted_at":"2020-10-11T19:06:56Z","abstract_excerpt":"FUNSD is one of the limited publicly available datasets for information extraction from document im-ages. The information in the FUNSD dataset is defined by text areas of four categories (\"key\", \"value\", \"header\", \"other\", and \"background\") and connectivity between areas as key-value relations. In-specting FUNSD, we found several inconsistency in labeling, which impeded its applicability to thekey-value extraction problem. In this report, we described some labeling issues in FUNSD and therevision we made to the dataset. We also reported our implementation of for key-value detection onFUNSD usi"},"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":"2010.05322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-11T19:06:56Z","cross_cats_sorted":[],"title_canon_sha256":"8170b505c611ae7df474c793a584b2364658fe2da0640bfb0b281ac63b10dc5a","abstract_canon_sha256":"f22dc4a0f388dcc65b426894f61ec4b4d191f14209b09249b1e3f7450ef894b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:05.154785Z","signature_b64":"bOjRWYXzjw8VTVO2nNXl47b5YkCg4ZLYF0REHGUcW3ZWabL6sa+blibPIa/Cqvn1IdzDg3yYfwCoesKbS1PbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef236067bb6de29174f769d69487a60c8316204584500f6727e10f21d9b12dc","last_reissued_at":"2026-07-05T01:42:05.154366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:05.154366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revising FUNSD dataset for key-value detection in document images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diep Thi-Ngoc Nguyen, Hieu M. Vu","submitted_at":"2020-10-11T19:06:56Z","abstract_excerpt":"FUNSD is one of the limited publicly available datasets for information extraction from document im-ages. The information in the FUNSD dataset is defined by text areas of four categories (\"key\", \"value\", \"header\", \"other\", and \"background\") and connectivity between areas as key-value relations. In-specting FUNSD, we found several inconsistency in labeling, which impeded its applicability to thekey-value extraction problem. In this report, we described some labeling issues in FUNSD and therevision we made to the dataset. We also reported our implementation of for key-value detection onFUNSD usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05322","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/2010.05322/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":"2010.05322","created_at":"2026-07-05T01:42:05.154423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.05322v1","created_at":"2026-07-05T01:42:05.154423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05322","created_at":"2026-07-05T01:42:05.154423+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3ZDMBT3W3PC","created_at":"2026-07-05T01:42:05.154423+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3ZDMBT3W3PCSF2P","created_at":"2026-07-05T01:42:05.154423+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3ZDMBT3","created_at":"2026-07-05T01:42:05.154423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31446","citing_title":"Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD","json":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD.json","graph_json":"https://pith.science/api/pith-number/N3ZDMBT3W3PCSF2PO2OWSSD2MD/graph.json","events_json":"https://pith.science/api/pith-number/N3ZDMBT3W3PCSF2PO2OWSSD2MD/events.json","paper":"https://pith.science/paper/N3ZDMBT3"},"agent_actions":{"view_html":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD","download_json":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD.json","view_paper":"https://pith.science/paper/N3ZDMBT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.05322&json=true","fetch_graph":"https://pith.science/api/pith-number/N3ZDMBT3W3PCSF2PO2OWSSD2MD/graph.json","fetch_events":"https://pith.science/api/pith-number/N3ZDMBT3W3PCSF2PO2OWSSD2MD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD/action/storage_attestation","attest_author":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD/action/author_attestation","sign_citation":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD/action/citation_signature","submit_replication":"https://pith.science/pith/N3ZDMBT3W3PCSF2PO2OWSSD2MD/action/replication_record"}},"created_at":"2026-07-05T01:42:05.154423+00:00","updated_at":"2026-07-05T01:42:05.154423+00:00"}