{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V2ILM5M3OVV4Z2CUUA7M2OVTJN","short_pith_number":"pith:V2ILM5M3","schema_version":"1.0","canonical_sha256":"ae90b6759b756bcce854a03ecd3ab34b4bf2c13b267cb2f0e62190ddeaa8a9ee","source":{"kind":"arxiv","id":"1905.13538","version":2},"attestation_state":"computed","paper":{"title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Guillaume Jaume, Hazim Kemal Ekenel, Jean-Philippe Thiran","submitted_at":"2019-05-27T10:40:40Z","abstract_excerpt":"We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely in appearance, making form understanding (FoUn) a challenging task. The proposed dataset can be used for various tasks, including text detection, optical character recognition, spatial layout analysis, and entity labeling/linking. To the best of our knowledge, this is the first publicly available dataset with comprehensive annotations to add"},"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":"1905.13538","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-05-27T10:40:40Z","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"title_canon_sha256":"65f2824518f2f94934b106d5b5131d03e22b74ba65c8522c96cf68b893abf0ea","abstract_canon_sha256":"3ce3e85394629bcd1c9f48b5e7ec2cfc3dea1a8b2d6970c84f7fb1310e5fa07c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:37.565289Z","signature_b64":"pH/sQaxB6PEPVG8yZ9NME5SkTGOgU/4p+mAWfbD7gSEoThdP62waD3GtXsRcR8BV4G6ypoJPk5wxBVEiMwCwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae90b6759b756bcce854a03ecd3ab34b4bf2c13b267cb2f0e62190ddeaa8a9ee","last_reissued_at":"2026-07-05T00:15:37.564736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:37.564736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Guillaume Jaume, Hazim Kemal Ekenel, Jean-Philippe Thiran","submitted_at":"2019-05-27T10:40:40Z","abstract_excerpt":"We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy and vary widely in appearance, making form understanding (FoUn) a challenging task. The proposed dataset can be used for various tasks, including text detection, optical character recognition, spatial layout analysis, and entity labeling/linking. To the best of our knowledge, this is the first publicly available dataset with comprehensive annotations to add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13538","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/1905.13538/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":"1905.13538","created_at":"2026-07-05T00:15:37.564819+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13538v2","created_at":"2026-07-05T00:15:37.564819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13538","created_at":"2026-07-05T00:15:37.564819+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2ILM5M3OVV4","created_at":"2026-07-05T00:15:37.564819+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2ILM5M3OVV4Z2CU","created_at":"2026-07-05T00:15:37.564819+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2ILM5M3","created_at":"2026-07-05T00:15:37.564819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02162","citing_title":"Multimodal Approaches for Visually-Rich Document Type Classification: A Comparative Analysis","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25185","citing_title":"The category of Whittaker modules over the Cartan Type Lie algebra $\\bar{S}_2$","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00161","citing_title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25186","citing_title":"FCMBench-Video: Benchmarking Document Video Intelligence","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08115","citing_title":"Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN","json":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN.json","graph_json":"https://pith.science/api/pith-number/V2ILM5M3OVV4Z2CUUA7M2OVTJN/graph.json","events_json":"https://pith.science/api/pith-number/V2ILM5M3OVV4Z2CUUA7M2OVTJN/events.json","paper":"https://pith.science/paper/V2ILM5M3"},"agent_actions":{"view_html":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN","download_json":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN.json","view_paper":"https://pith.science/paper/V2ILM5M3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13538&json=true","fetch_graph":"https://pith.science/api/pith-number/V2ILM5M3OVV4Z2CUUA7M2OVTJN/graph.json","fetch_events":"https://pith.science/api/pith-number/V2ILM5M3OVV4Z2CUUA7M2OVTJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/action/storage_attestation","attest_author":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/action/author_attestation","sign_citation":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/action/citation_signature","submit_replication":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/action/replication_record"}},"created_at":"2026-07-05T00:15:37.564819+00:00","updated_at":"2026-07-05T00:15:37.564819+00:00"}