{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MQFNXNJEON2347AAG5FQD3EVGV","short_pith_number":"pith:MQFNXNJE","canonical_record":{"source":{"id":"2408.01287","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T14:19:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ebc39702645ed4e4a117f42b29719cb3b1d82b06daf66345ecf83c0b1bdad73b","abstract_canon_sha256":"27a8e9d97f50d9cf7ad75c09961a9d10cbfc156fa631a57474644922b3489598"},"schema_version":"1.0"},"canonical_sha256":"640adbb5247375be7c00374b01ec9535688ce1a0692997f498bba9f0e7e55be5","source":{"kind":"arxiv","id":"2408.01287","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01287","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01287v2","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01287","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"MQFNXNJEON23","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"MQFNXNJEON2347AA","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"MQFNXNJE","created_at":"2026-07-05T11:24:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MQFNXNJEON2347AAG5FQD3EVGV","target":"record","payload":{"canonical_record":{"source":{"id":"2408.01287","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T14:19:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ebc39702645ed4e4a117f42b29719cb3b1d82b06daf66345ecf83c0b1bdad73b","abstract_canon_sha256":"27a8e9d97f50d9cf7ad75c09961a9d10cbfc156fa631a57474644922b3489598"},"schema_version":"1.0"},"canonical_sha256":"640adbb5247375be7c00374b01ec9535688ce1a0692997f498bba9f0e7e55be5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:05.671140Z","signature_b64":"X994a9WQIhLzOSVx2Vn+WiU4Rwk83hEoFwvvvYDDa+ag2fmFfzLV3xAhrrmNetZsYWq0PigIlYIMjgkZ2rKyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"640adbb5247375be7c00374b01ec9535688ce1a0692997f498bba9f0e7e55be5","last_reissued_at":"2026-07-05T11:24:05.670569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:05.670569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.01287","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":"2026-07-05T11:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p49BuzmQtJWL2MFEqulPsLDvGZaCZwK80XuAhRf/Ob83aZU74cbJTavKaySPpZy9B3xOsASNamvCnshXV6nSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:58:58.279885Z"},"content_sha256":"b00d8145767e7b496d85526fa62ba007588f9693350a5d61a1d77c8d8bf9d86f","schema_version":"1.0","event_id":"sha256:b00d8145767e7b496d85526fa62ba007588f9693350a5d61a1d77c8d8bf9d86f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MQFNXNJEON2347AAG5FQD3EVGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Eduard Hovy, Jean Lee, Soyeon Caren Han, Yihao Ding","submitted_at":"2024-08-02T14:19:34Z","abstract_excerpt":"Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting information from VRDs rely heavily on expert knowledge and manual annotation, making them labor-intensive and inefficient. Recent advances in deep learning have transformed this landscape by enabling multimodal models that integrate vision, language, and layout features through pretraining, significantly improving information extraction performance. This surve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01287","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/2408.01287/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":"2026-07-05T11:24:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fJkGiv4e1+RDLO1FcyZvzo5XQ+2X3E419kIuytjNSlYRvUyJWMSp8yqEs1BG1rFrRNg4QWcfN2Ga36cpI+JAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:58:58.280354Z"},"content_sha256":"20f9bd5b03009389980a02a6c5e0aac9479efc1734eebbddb97ae3f19770b84a","schema_version":"1.0","event_id":"sha256:20f9bd5b03009389980a02a6c5e0aac9479efc1734eebbddb97ae3f19770b84a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQFNXNJEON2347AAG5FQD3EVGV/bundle.json","state_url":"https://pith.science/pith/MQFNXNJEON2347AAG5FQD3EVGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQFNXNJEON2347AAG5FQD3EVGV/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":"2026-08-06T03:58:58Z","links":{"resolver":"https://pith.science/pith/MQFNXNJEON2347AAG5FQD3EVGV","bundle":"https://pith.science/pith/MQFNXNJEON2347AAG5FQD3EVGV/bundle.json","state":"https://pith.science/pith/MQFNXNJEON2347AAG5FQD3EVGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQFNXNJEON2347AAG5FQD3EVGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MQFNXNJEON2347AAG5FQD3EVGV","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":"27a8e9d97f50d9cf7ad75c09961a9d10cbfc156fa631a57474644922b3489598","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T14:19:34Z","title_canon_sha256":"ebc39702645ed4e4a117f42b29719cb3b1d82b06daf66345ecf83c0b1bdad73b"},"schema_version":"1.0","source":{"id":"2408.01287","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01287","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01287v2","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01287","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"pith_short_12","alias_value":"MQFNXNJEON23","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"pith_short_16","alias_value":"MQFNXNJEON2347AA","created_at":"2026-07-05T11:24:05Z"},{"alias_kind":"pith_short_8","alias_value":"MQFNXNJE","created_at":"2026-07-05T11:24:05Z"}],"graph_snapshots":[{"event_id":"sha256:20f9bd5b03009389980a02a6c5e0aac9479efc1734eebbddb97ae3f19770b84a","target":"graph","created_at":"2026-07-05T11:24:05Z","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/2408.01287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visually Rich Documents (VRDs) play a vital role in domains such as academia, finance, healthcare, and marketing, as they convey information through a combination of text, layout, and visual elements. Traditional approaches to extracting information from VRDs rely heavily on expert knowledge and manual annotation, making them labor-intensive and inefficient. Recent advances in deep learning have transformed this landscape by enabling multimodal models that integrate vision, language, and layout features through pretraining, significantly improving information extraction performance. This surve","authors_text":"Eduard Hovy, Jean Lee, Soyeon Caren Han, Yihao Ding","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T14:19:34Z","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01287","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:b00d8145767e7b496d85526fa62ba007588f9693350a5d61a1d77c8d8bf9d86f","target":"record","created_at":"2026-07-05T11:24:05Z","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":"27a8e9d97f50d9cf7ad75c09961a9d10cbfc156fa631a57474644922b3489598","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T14:19:34Z","title_canon_sha256":"ebc39702645ed4e4a117f42b29719cb3b1d82b06daf66345ecf83c0b1bdad73b"},"schema_version":"1.0","source":{"id":"2408.01287","kind":"arxiv","version":2}},"canonical_sha256":"640adbb5247375be7c00374b01ec9535688ce1a0692997f498bba9f0e7e55be5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"640adbb5247375be7c00374b01ec9535688ce1a0692997f498bba9f0e7e55be5","first_computed_at":"2026-07-05T11:24:05.670569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:05.670569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X994a9WQIhLzOSVx2Vn+WiU4Rwk83hEoFwvvvYDDa+ag2fmFfzLV3xAhrrmNetZsYWq0PigIlYIMjgkZ2rKyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:05.671140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01287","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b00d8145767e7b496d85526fa62ba007588f9693350a5d61a1d77c8d8bf9d86f","sha256:20f9bd5b03009389980a02a6c5e0aac9479efc1734eebbddb97ae3f19770b84a"],"state_sha256":"b311a4783fea306667a906719de7f01fad1e3178dc94c463b4189ca9fcee929f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LWMuWh8ds5ugP7kw+XFqUgzN2XdUPV9k8fqTKzY0hsz0xauGYXwaTU64cpdg2R/MCcxPYn3BjxssV1FWUzhFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:58:58.283396Z","bundle_sha256":"8b0fe2e9c0212a5a57818ed52427a4adb9f01528b86f9151c65eab964131aff8"}}