{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IWSA7LLZ7BSY37RHKJB2HFXUP7","short_pith_number":"pith:IWSA7LLZ","canonical_record":{"source":{"id":"2403.04080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T22:22:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5d8fe22e9b354576972138f5feb344ee57aaa604b926104db4ff8eabaaeeb29f","abstract_canon_sha256":"0a4c96e9829f365107adab695297c11e700742cf389a4d119cd6f36475288b75"},"schema_version":"1.0"},"canonical_sha256":"45a40fad79f8658dfe275243a396f47fe84bf7d166cf6d7827d11c8fa23d63d2","source":{"kind":"arxiv","id":"2403.04080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04080","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04080v1","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04080","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"pith_short_12","alias_value":"IWSA7LLZ7BSY","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"pith_short_16","alias_value":"IWSA7LLZ7BSY37RH","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"pith_short_8","alias_value":"IWSA7LLZ","created_at":"2026-07-05T07:53:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IWSA7LLZ7BSY37RHKJB2HFXUP7","target":"record","payload":{"canonical_record":{"source":{"id":"2403.04080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T22:22:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5d8fe22e9b354576972138f5feb344ee57aaa604b926104db4ff8eabaaeeb29f","abstract_canon_sha256":"0a4c96e9829f365107adab695297c11e700742cf389a4d119cd6f36475288b75"},"schema_version":"1.0"},"canonical_sha256":"45a40fad79f8658dfe275243a396f47fe84bf7d166cf6d7827d11c8fa23d63d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:18.100835Z","signature_b64":"tlsPRErFxJdsEA16WuQoKSWb4So0HsSRoWdO/hWZZb3JEx68HT1wuph9hR5Z3ztqutQBDBErzLMTUifkXGu/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45a40fad79f8658dfe275243a396f47fe84bf7d166cf6d7827d11c8fa23d63d2","last_reissued_at":"2026-07-05T07:53:18.100300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:18.100300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.04080","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":"2026-07-05T07:53:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KIqJsQysSBG6SF/vFkK6YU9rWCgLrnaOXGAGebDO4u9zbDbvDFbxYCFsNnUq5vj8MZ7B0CgeR0uZI7Pa+6MCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:03:42.412501Z"},"content_sha256":"7b4ff7fb1879aefa70fa45294cc858ccd49b0cde973536facffce01fcdb7faf0","schema_version":"1.0","event_id":"sha256:7b4ff7fb1879aefa70fa45294cc858ccd49b0cde973536facffce01fcdb7faf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IWSA7LLZ7BSY37RHKJB2HFXUP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Abdallah, Adam Jatowt, Daniel Eberharter, Zoe Pfister","submitted_at":"2024-03-06T22:22:02Z","abstract_excerpt":"This paper presents a comprehensive survey of research works on the topic of form understanding in the context of scanned documents. We delve into recent advancements and breakthroughs in the field, highlighting the significance of language models and transformers in solving this challenging task. Our research methodology involves an in-depth analysis of popular documents and forms of understanding of trends over the last decade, enabling us to offer valuable insights into the evolution of this domain. Focusing on cutting-edge models, we showcase how transformers have propelled the field forwa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04080","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/2403.04080/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":"2026-07-05T07:53:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UL4lgcISX+ueAx0QB5e2uVphXZtEfQ5IEwFv0CbDVccWAwzn+9N5+T+WwBoQNMs3XZZpxWStsBVNuXxtkl+FDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:03:42.412864Z"},"content_sha256":"742832afcdd637cbc6e42b025821c1b7fbf50bdc1af330ae8cc62dd50133403d","schema_version":"1.0","event_id":"sha256:742832afcdd637cbc6e42b025821c1b7fbf50bdc1af330ae8cc62dd50133403d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWSA7LLZ7BSY37RHKJB2HFXUP7/bundle.json","state_url":"https://pith.science/pith/IWSA7LLZ7BSY37RHKJB2HFXUP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWSA7LLZ7BSY37RHKJB2HFXUP7/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":"2026-07-07T09:03:42Z","links":{"resolver":"https://pith.science/pith/IWSA7LLZ7BSY37RHKJB2HFXUP7","bundle":"https://pith.science/pith/IWSA7LLZ7BSY37RHKJB2HFXUP7/bundle.json","state":"https://pith.science/pith/IWSA7LLZ7BSY37RHKJB2HFXUP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWSA7LLZ7BSY37RHKJB2HFXUP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IWSA7LLZ7BSY37RHKJB2HFXUP7","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":"0a4c96e9829f365107adab695297c11e700742cf389a4d119cd6f36475288b75","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T22:22:02Z","title_canon_sha256":"5d8fe22e9b354576972138f5feb344ee57aaa604b926104db4ff8eabaaeeb29f"},"schema_version":"1.0","source":{"id":"2403.04080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04080","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04080v1","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04080","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"pith_short_12","alias_value":"IWSA7LLZ7BSY","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"pith_short_16","alias_value":"IWSA7LLZ7BSY37RH","created_at":"2026-07-05T07:53:18Z"},{"alias_kind":"pith_short_8","alias_value":"IWSA7LLZ","created_at":"2026-07-05T07:53:18Z"}],"graph_snapshots":[{"event_id":"sha256:742832afcdd637cbc6e42b025821c1b7fbf50bdc1af330ae8cc62dd50133403d","target":"graph","created_at":"2026-07-05T07:53:18Z","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/2403.04080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a comprehensive survey of research works on the topic of form understanding in the context of scanned documents. We delve into recent advancements and breakthroughs in the field, highlighting the significance of language models and transformers in solving this challenging task. Our research methodology involves an in-depth analysis of popular documents and forms of understanding of trends over the last decade, enabling us to offer valuable insights into the evolution of this domain. Focusing on cutting-edge models, we showcase how transformers have propelled the field forwa","authors_text":"Abdelrahman Abdallah, Adam Jatowt, Daniel Eberharter, Zoe Pfister","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T22:22:02Z","title":"Transformers and Language Models in Form Understanding: A Comprehensive Review of Scanned Document Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04080","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":"sha256:7b4ff7fb1879aefa70fa45294cc858ccd49b0cde973536facffce01fcdb7faf0","target":"record","created_at":"2026-07-05T07:53:18Z","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":"0a4c96e9829f365107adab695297c11e700742cf389a4d119cd6f36475288b75","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T22:22:02Z","title_canon_sha256":"5d8fe22e9b354576972138f5feb344ee57aaa604b926104db4ff8eabaaeeb29f"},"schema_version":"1.0","source":{"id":"2403.04080","kind":"arxiv","version":1}},"canonical_sha256":"45a40fad79f8658dfe275243a396f47fe84bf7d166cf6d7827d11c8fa23d63d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45a40fad79f8658dfe275243a396f47fe84bf7d166cf6d7827d11c8fa23d63d2","first_computed_at":"2026-07-05T07:53:18.100300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:18.100300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tlsPRErFxJdsEA16WuQoKSWb4So0HsSRoWdO/hWZZb3JEx68HT1wuph9hR5Z3ztqutQBDBErzLMTUifkXGu/Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:18.100835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b4ff7fb1879aefa70fa45294cc858ccd49b0cde973536facffce01fcdb7faf0","sha256:742832afcdd637cbc6e42b025821c1b7fbf50bdc1af330ae8cc62dd50133403d"],"state_sha256":"4f0fd0d78c5d6e8c051fa73f07749111251af51c9aafb96e2eef987f9c741a6e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wRZxihgzRbjJM68a125atLgyxwGYFsfJ90oNaixGjBHMcNFjTWDubzPMJWa5TwUcoExLJY1SEhuMwr0jiJ0FAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:03:42.415126Z","bundle_sha256":"82e073ba7d95b90e0573aba4b6670f5d7d4c17124fb0d03327447cc9764e345e"}}