{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G5WSCWTNU6WOVS67BPK7NCJ4SQ","short_pith_number":"pith:G5WSCWTN","canonical_record":{"source":{"id":"2010.11685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-15T08:54:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78729e77f598024534cf7903bf48d8615132d83f6069ab50d8ea9387ee71fc05","abstract_canon_sha256":"54b9cd8cb2dce68dd546ae848b4c94552577e604c261f95dd7aab91f58389344"},"schema_version":"1.0"},"canonical_sha256":"376d215a6da7aceacbdf0bd5f6893c940944f474a80f0c8e2f8626cb48bdbe65","source":{"kind":"arxiv","id":"2010.11685","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11685","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11685v1","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11685","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"G5WSCWTNU6WO","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"G5WSCWTNU6WOVS67","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"G5WSCWTN","created_at":"2026-07-05T01:45:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G5WSCWTNU6WOVS67BPK7NCJ4SQ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.11685","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-15T08:54:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78729e77f598024534cf7903bf48d8615132d83f6069ab50d8ea9387ee71fc05","abstract_canon_sha256":"54b9cd8cb2dce68dd546ae848b4c94552577e604c261f95dd7aab91f58389344"},"schema_version":"1.0"},"canonical_sha256":"376d215a6da7aceacbdf0bd5f6893c940944f474a80f0c8e2f8626cb48bdbe65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:12.577695Z","signature_b64":"vrpSLVW+idBtwIiqeYQkek9o5GSwTXtDNymUax4A/NbECJcbgw29qSW0G8UgfEdkHPeKZ4RjnihB1TjQJJ7WAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"376d215a6da7aceacbdf0bd5f6893c940944f474a80f0c8e2f8626cb48bdbe65","last_reissued_at":"2026-07-05T01:45:12.577224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:12.577224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.11685","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bVx00LNFMOAQTR+Tj9Y5uWatxtorp2jvx0dMPEsBw6l2EZOmckXrfQflFVw0/ja6ul1Pym6TfgJ5hBmFfTxSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:23:03.561078Z"},"content_sha256":"adac3ada8d2d84a42b8c1793a426d56aacd57c1628c8d70937d7eb77ebc525dc","schema_version":"1.0","event_id":"sha256:adac3ada8d2d84a42b8c1793a426d56aacd57c1628c8d70937d7eb77ebc525dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G5WSCWTNU6WOVS67BPK7NCJ4SQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ding Liang, Mingjie Zhan, Xuebo Liu, Zilong Wang","submitted_at":"2020-10-15T08:54:17Z","abstract_excerpt":"Form understanding depends on both textual contents and organizational structure. Although modern OCR performs well, it is still challenging to realize general form understanding because forms are commonly used and of various formats. The table detection and handcrafted features in previous works cannot apply to all forms because of their requirements on formats. Therefore, we concentrate on the most elementary components, the key-value pairs, and adopt multimodal methods to extract features. We consider the form structure as a tree-like or graph-like hierarchy of text fragments. The parent-ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11685","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/2010.11685/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":"2026-07-05T01:45:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hmJfzoKHQARzDMH2tWFnumwOLnlh6AmYH0YBki643ohpsVQ2LqcIqC0O/KLidZ5HbQB/EnrnQaz5UpGhkKBvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:23:03.561973Z"},"content_sha256":"faf489a4534bb48609ba61338e4216bed0c19045f963a78a0ccaa239c4702861","schema_version":"1.0","event_id":"sha256:faf489a4534bb48609ba61338e4216bed0c19045f963a78a0ccaa239c4702861"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G5WSCWTNU6WOVS67BPK7NCJ4SQ/bundle.json","state_url":"https://pith.science/pith/G5WSCWTNU6WOVS67BPK7NCJ4SQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G5WSCWTNU6WOVS67BPK7NCJ4SQ/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":"2026-08-09T02:23:03Z","links":{"resolver":"https://pith.science/pith/G5WSCWTNU6WOVS67BPK7NCJ4SQ","bundle":"https://pith.science/pith/G5WSCWTNU6WOVS67BPK7NCJ4SQ/bundle.json","state":"https://pith.science/pith/G5WSCWTNU6WOVS67BPK7NCJ4SQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G5WSCWTNU6WOVS67BPK7NCJ4SQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G5WSCWTNU6WOVS67BPK7NCJ4SQ","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":"54b9cd8cb2dce68dd546ae848b4c94552577e604c261f95dd7aab91f58389344","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-15T08:54:17Z","title_canon_sha256":"78729e77f598024534cf7903bf48d8615132d83f6069ab50d8ea9387ee71fc05"},"schema_version":"1.0","source":{"id":"2010.11685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11685","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11685v1","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11685","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_12","alias_value":"G5WSCWTNU6WO","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_16","alias_value":"G5WSCWTNU6WOVS67","created_at":"2026-07-05T01:45:12Z"},{"alias_kind":"pith_short_8","alias_value":"G5WSCWTN","created_at":"2026-07-05T01:45:12Z"}],"graph_snapshots":[{"event_id":"sha256:faf489a4534bb48609ba61338e4216bed0c19045f963a78a0ccaa239c4702861","target":"graph","created_at":"2026-07-05T01:45:12Z","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/2010.11685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Form understanding depends on both textual contents and organizational structure. Although modern OCR performs well, it is still challenging to realize general form understanding because forms are commonly used and of various formats. The table detection and handcrafted features in previous works cannot apply to all forms because of their requirements on formats. Therefore, we concentrate on the most elementary components, the key-value pairs, and adopt multimodal methods to extract features. We consider the form structure as a tree-like or graph-like hierarchy of text fragments. The parent-ch","authors_text":"Ding Liang, Mingjie Zhan, Xuebo Liu, Zilong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-15T08:54:17Z","title":"DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11685","kind":"arxiv","version":1},"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:adac3ada8d2d84a42b8c1793a426d56aacd57c1628c8d70937d7eb77ebc525dc","target":"record","created_at":"2026-07-05T01:45:12Z","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":"54b9cd8cb2dce68dd546ae848b4c94552577e604c261f95dd7aab91f58389344","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-15T08:54:17Z","title_canon_sha256":"78729e77f598024534cf7903bf48d8615132d83f6069ab50d8ea9387ee71fc05"},"schema_version":"1.0","source":{"id":"2010.11685","kind":"arxiv","version":1}},"canonical_sha256":"376d215a6da7aceacbdf0bd5f6893c940944f474a80f0c8e2f8626cb48bdbe65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"376d215a6da7aceacbdf0bd5f6893c940944f474a80f0c8e2f8626cb48bdbe65","first_computed_at":"2026-07-05T01:45:12.577224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:12.577224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vrpSLVW+idBtwIiqeYQkek9o5GSwTXtDNymUax4A/NbECJcbgw29qSW0G8UgfEdkHPeKZ4RjnihB1TjQJJ7WAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:12.577695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adac3ada8d2d84a42b8c1793a426d56aacd57c1628c8d70937d7eb77ebc525dc","sha256:faf489a4534bb48609ba61338e4216bed0c19045f963a78a0ccaa239c4702861"],"state_sha256":"ae24df01dea89012add5488080c1a8895b854a8a6b442e94a3dee302b16cd70b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pWtq3mxWByL0WjVIEwPiRYExxsZL/YGAjHXvgIPpsgrWtun3pgizt1MSt9HBCh5pFHodIXPzOTInoJNgf12pDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:23:03.568187Z","bundle_sha256":"fdf152753a9731b4cac5a84e93fa8c936bd52bb27a2deb19a2a5bcef960ac982"}}