{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OOUGEQFEAMLV2G2UXJIWHHBEUJ","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":"f40c5bb7a32e1528389bf8bfeb9f6effe1bcc5468eecf88f67341a9abf3f5c56","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T06:08:55Z","title_canon_sha256":"d87ab3e90a04c8f4f253e0b6a2d95898e07a60af7b370a1262343e1854093e68"},"schema_version":"1.0","source":{"id":"2310.11016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11016","created_at":"2026-07-05T07:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11016v1","created_at":"2026-07-05T07:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11016","created_at":"2026-07-05T07:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"OOUGEQFEAMLV","created_at":"2026-07-05T07:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"OOUGEQFEAMLV2G2U","created_at":"2026-07-05T07:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"OOUGEQFE","created_at":"2026-07-05T07:01:49Z"}],"graph_snapshots":[{"event_id":"sha256:447ab2fb14f502f206492777b93b790605294740c198221cd44f6c8fdd345d15","target":"graph","created_at":"2026-07-05T07:01:49Z","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/2310.11016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs), in which named entity recognition (NER) is treated as a sequence-labeling task of predicting the BIO entity tags for tokens, following the typical setting of NLP. However, BIO-tagging scheme relies on the correct order of model inputs, which is not guaranteed in real-world NER on scanned VrDs where text are recognized and arranged by OCR systems. Such reading order issue hinders the accurate marking of entities by BIO-tagging scheme, making it impossible for ","authors_text":"Chong Zhang, Huan Chen, Huijia Zhu, Jinyang Tang, Qi Zhang, Tao Gui, Ya Guo, Yi Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T06:08:55Z","title":"Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11016","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:bd102343f3e990cd92f1d6ac5dbf6f161c75dab38940b1759766aebd3ee3da62","target":"record","created_at":"2026-07-05T07:01:49Z","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":"f40c5bb7a32e1528389bf8bfeb9f6effe1bcc5468eecf88f67341a9abf3f5c56","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T06:08:55Z","title_canon_sha256":"d87ab3e90a04c8f4f253e0b6a2d95898e07a60af7b370a1262343e1854093e68"},"schema_version":"1.0","source":{"id":"2310.11016","kind":"arxiv","version":1}},"canonical_sha256":"73a86240a403175d1b54ba51639c24a243c6c45fbd8cbdb3b0ff8486004e5c5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73a86240a403175d1b54ba51639c24a243c6c45fbd8cbdb3b0ff8486004e5c5d","first_computed_at":"2026-07-05T07:01:49.367791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:49.367791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wU34waFBqn75G9tkNbt4Cctl6gU9WpIscyacJJzoRrgMrQdqyofDdpf8CasmVu3I+cghBMqcAfD6BExuB/oGBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:49.368339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd102343f3e990cd92f1d6ac5dbf6f161c75dab38940b1759766aebd3ee3da62","sha256:447ab2fb14f502f206492777b93b790605294740c198221cd44f6c8fdd345d15"],"state_sha256":"9e147d8a5d898ec60c4dadc1c736847bd4e303eaabf547c9ac52db883859c1fa"}