{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:V2ILM5M3OVV4Z2CUUA7M2OVTJN","short_pith_number":"pith:V2ILM5M3","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"},"canonical_sha256":"ae90b6759b756bcce854a03ecd3ab34b4bf2c13b267cb2f0e62190ddeaa8a9ee","source":{"kind":"arxiv","id":"1905.13538","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13538","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13538v2","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13538","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"V2ILM5M3OVV4","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"pith_short_16","alias_value":"V2ILM5M3OVV4Z2CU","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"pith_short_8","alias_value":"V2ILM5M3","created_at":"2026-07-05T00:15:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:V2ILM5M3OVV4Z2CUUA7M2OVTJN","target":"record","payload":{"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"},"canonical_sha256":"ae90b6759b756bcce854a03ecd3ab34b4bf2c13b267cb2f0e62190ddeaa8a9ee","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"},"source_kind":"arxiv","source_id":"1905.13538","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":"2026-07-05T00:15:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yaYuRNxkHmTsygw2cJlrYH2RLxlEFvAaP7F2rA7MCBMi8n9LdylsF7gQEKByhS91Ba4MXrp51aYzEbBhTzQJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:09:53.399697Z"},"content_sha256":"681c57192172a2060d672d49b268dfa4bb8ab710ecb91d676ba158aeea394fca","schema_version":"1.0","event_id":"sha256:681c57192172a2060d672d49b268dfa4bb8ab710ecb91d676ba158aeea394fca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:V2ILM5M3OVV4Z2CUUA7M2OVTJN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:15:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WFqnb79t5uWLHVbjjXoHyrFsf8Ld1Kr9sBuCJH8HOWtEcHZC6DmG9ZyzoTeARSZbio69vHL4i6jjJpsuuhJNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:09:53.400279Z"},"content_sha256":"a87a3b4e15f68d51c6975aa0f0408db8bfa78726a25c34de19fe0daa44dd387c","schema_version":"1.0","event_id":"sha256:a87a3b4e15f68d51c6975aa0f0408db8bfa78726a25c34de19fe0daa44dd387c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/bundle.json","state_url":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/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":"2026-08-08T03:09:53Z","links":{"resolver":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN","bundle":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/bundle.json","state":"https://pith.science/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V2ILM5M3OVV4Z2CUUA7M2OVTJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:V2ILM5M3OVV4Z2CUUA7M2OVTJN","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":"3ce3e85394629bcd1c9f48b5e7ec2cfc3dea1a8b2d6970c84f7fb1310e5fa07c","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-05-27T10:40:40Z","title_canon_sha256":"65f2824518f2f94934b106d5b5131d03e22b74ba65c8522c96cf68b893abf0ea"},"schema_version":"1.0","source":{"id":"1905.13538","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13538","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13538v2","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13538","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"pith_short_12","alias_value":"V2ILM5M3OVV4","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"pith_short_16","alias_value":"V2ILM5M3OVV4Z2CU","created_at":"2026-07-05T00:15:37Z"},{"alias_kind":"pith_short_8","alias_value":"V2ILM5M3","created_at":"2026-07-05T00:15:37Z"}],"graph_snapshots":[{"event_id":"sha256:a87a3b4e15f68d51c6975aa0f0408db8bfa78726a25c34de19fe0daa44dd387c","target":"graph","created_at":"2026-07-05T00:15:37Z","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/1905.13538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guillaume Jaume, Hazim Kemal Ekenel, Jean-Philippe Thiran","cross_cats":["cs.CV","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-05-27T10:40:40Z","title":"FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13538","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":"sha256:681c57192172a2060d672d49b268dfa4bb8ab710ecb91d676ba158aeea394fca","target":"record","created_at":"2026-07-05T00:15:37Z","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":"3ce3e85394629bcd1c9f48b5e7ec2cfc3dea1a8b2d6970c84f7fb1310e5fa07c","cross_cats_sorted":["cs.CV","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-05-27T10:40:40Z","title_canon_sha256":"65f2824518f2f94934b106d5b5131d03e22b74ba65c8522c96cf68b893abf0ea"},"schema_version":"1.0","source":{"id":"1905.13538","kind":"arxiv","version":2}},"canonical_sha256":"ae90b6759b756bcce854a03ecd3ab34b4bf2c13b267cb2f0e62190ddeaa8a9ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae90b6759b756bcce854a03ecd3ab34b4bf2c13b267cb2f0e62190ddeaa8a9ee","first_computed_at":"2026-07-05T00:15:37.564736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:15:37.564736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pH/sQaxB6PEPVG8yZ9NME5SkTGOgU/4p+mAWfbD7gSEoThdP62waD3GtXsRcR8BV4G6ypoJPk5wxBVEiMwCwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:15:37.565289Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13538","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:681c57192172a2060d672d49b268dfa4bb8ab710ecb91d676ba158aeea394fca","sha256:a87a3b4e15f68d51c6975aa0f0408db8bfa78726a25c34de19fe0daa44dd387c"],"state_sha256":"65b3a0f9ce1fefa50f8878e34a336a081250fe3e1fe830622ba907e4478ef29c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qwf9KKlubDBxwjHMv88okyCs5gi3TLlvfh83R3lOkpKor3QbLJp2lXzPbJxmOX2oHsZGuN8+XVlpS/Vj1c9bDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:09:53.405006Z","bundle_sha256":"64f71a764caafc0d5975fe64cd58a9faca03139578ae32daf32d87319aa7b3f2"}}