{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OVGDPCFN3SNN5BXPKRIFD2DZXE","short_pith_number":"pith:OVGDPCFN","canonical_record":{"source":{"id":"2203.08411","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T06:02:02Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"dd1de97e745c43f0269488caadde623638b982dd914ba017fcf8a7232ce30549","abstract_canon_sha256":"36f69b87ec3826a82ce62789770dea2107f9776ce1cc59b7f9b002612fd7540a"},"schema_version":"1.0"},"canonical_sha256":"754c3788addc9ade86ef545051e879b91df2a25b4564d16220a1d8403e7e1903","source":{"kind":"arxiv","id":"2203.08411","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08411","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08411v2","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08411","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"pith_short_12","alias_value":"OVGDPCFN3SNN","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"pith_short_16","alias_value":"OVGDPCFN3SNN5BXP","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"pith_short_8","alias_value":"OVGDPCFN","created_at":"2026-07-05T04:08:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OVGDPCFN3SNN5BXPKRIFD2DZXE","target":"record","payload":{"canonical_record":{"source":{"id":"2203.08411","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T06:02:02Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"dd1de97e745c43f0269488caadde623638b982dd914ba017fcf8a7232ce30549","abstract_canon_sha256":"36f69b87ec3826a82ce62789770dea2107f9776ce1cc59b7f9b002612fd7540a"},"schema_version":"1.0"},"canonical_sha256":"754c3788addc9ade86ef545051e879b91df2a25b4564d16220a1d8403e7e1903","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:05.128497Z","signature_b64":"eKvHy28RPqUn/ZUoQdpmpkEwgyrA0f+/oGOiLJWcR6AX7TdBWYa3J8Q3dd8Owkq/XmbaTt0n4NheXNseNyfGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"754c3788addc9ade86ef545051e879b91df2a25b4564d16220a1d8403e7e1903","last_reissued_at":"2026-07-05T04:08:05.128031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:05.128031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.08411","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":"2026-07-05T04:08:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZTufhCjzAN8ETKcQFoGtHQGpb5s41VO4TQfSd8VI4CkwSXljPa+qSzIgbBM3x97w9vCDKmmow8rz0rzAFkHLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:06:59.671097Z"},"content_sha256":"e3ef3439db70e02b032d2182f946450f1a0308d88f72327eedd6ebb243de69aa","schema_version":"1.0","event_id":"sha256:e3ef3439db70e02b032d2182f946450f1a0308d88f72327eedd6ebb243de69aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OVGDPCFN3SNN5BXPKRIFD2DZXE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen-Yu Lee, Chun-Liang Li, Guolong Su, Joshua Ainslie, Nan Hua, Renshen Wang, Timothy Dozat, Tomas Pfister, Vincent Perot, Yasuhisa Fujii","submitted_at":"2022-03-16T06:02:02Z","abstract_excerpt":"Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks. However, it is challenging to correctly serialize tokens in form-like documents in practice due to their variety of layout patterns. We propose FormNet, a structure-aware sequence model to mitigate the suboptimal serialization of forms. First, we design Rich Attention that leverages the spatial relationship between tokens in a form for more precise attention score calculation. Second, we construct Super-Tokens for each word by embedding representations from their neighboring to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08411","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/2203.08411/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":"2026-07-05T04:08:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qyVZH4yMOqMlzn8A6Wwj1gfXUqCaDVKRjpsRWqdqhLvNGOjh4WUzY+fzfWOeKjEgKPVLatKrVEhwCKgqYcdVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T15:06:59.671603Z"},"content_sha256":"a2a5f72bae2f72869a89ec56d15e398ddf53b07ed762044b721092d07f4eb129","schema_version":"1.0","event_id":"sha256:a2a5f72bae2f72869a89ec56d15e398ddf53b07ed762044b721092d07f4eb129"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVGDPCFN3SNN5BXPKRIFD2DZXE/bundle.json","state_url":"https://pith.science/pith/OVGDPCFN3SNN5BXPKRIFD2DZXE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVGDPCFN3SNN5BXPKRIFD2DZXE/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":"2026-08-12T15:06:59Z","links":{"resolver":"https://pith.science/pith/OVGDPCFN3SNN5BXPKRIFD2DZXE","bundle":"https://pith.science/pith/OVGDPCFN3SNN5BXPKRIFD2DZXE/bundle.json","state":"https://pith.science/pith/OVGDPCFN3SNN5BXPKRIFD2DZXE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVGDPCFN3SNN5BXPKRIFD2DZXE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OVGDPCFN3SNN5BXPKRIFD2DZXE","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":"36f69b87ec3826a82ce62789770dea2107f9776ce1cc59b7f9b002612fd7540a","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T06:02:02Z","title_canon_sha256":"dd1de97e745c43f0269488caadde623638b982dd914ba017fcf8a7232ce30549"},"schema_version":"1.0","source":{"id":"2203.08411","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08411","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08411v2","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08411","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"pith_short_12","alias_value":"OVGDPCFN3SNN","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"pith_short_16","alias_value":"OVGDPCFN3SNN5BXP","created_at":"2026-07-05T04:08:05Z"},{"alias_kind":"pith_short_8","alias_value":"OVGDPCFN","created_at":"2026-07-05T04:08:05Z"}],"graph_snapshots":[{"event_id":"sha256:a2a5f72bae2f72869a89ec56d15e398ddf53b07ed762044b721092d07f4eb129","target":"graph","created_at":"2026-07-05T04:08:05Z","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/2203.08411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks. However, it is challenging to correctly serialize tokens in form-like documents in practice due to their variety of layout patterns. We propose FormNet, a structure-aware sequence model to mitigate the suboptimal serialization of forms. First, we design Rich Attention that leverages the spatial relationship between tokens in a form for more precise attention score calculation. Second, we construct Super-Tokens for each word by embedding representations from their neighboring to","authors_text":"Chen-Yu Lee, Chun-Liang Li, Guolong Su, Joshua Ainslie, Nan Hua, Renshen Wang, Timothy Dozat, Tomas Pfister, Vincent Perot, Yasuhisa Fujii","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T06:02:02Z","title":"FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08411","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:e3ef3439db70e02b032d2182f946450f1a0308d88f72327eedd6ebb243de69aa","target":"record","created_at":"2026-07-05T04:08:05Z","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":"36f69b87ec3826a82ce62789770dea2107f9776ce1cc59b7f9b002612fd7540a","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T06:02:02Z","title_canon_sha256":"dd1de97e745c43f0269488caadde623638b982dd914ba017fcf8a7232ce30549"},"schema_version":"1.0","source":{"id":"2203.08411","kind":"arxiv","version":2}},"canonical_sha256":"754c3788addc9ade86ef545051e879b91df2a25b4564d16220a1d8403e7e1903","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"754c3788addc9ade86ef545051e879b91df2a25b4564d16220a1d8403e7e1903","first_computed_at":"2026-07-05T04:08:05.128031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:05.128031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eKvHy28RPqUn/ZUoQdpmpkEwgyrA0f+/oGOiLJWcR6AX7TdBWYa3J8Q3dd8Owkq/XmbaTt0n4NheXNseNyfGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:05.128497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08411","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3ef3439db70e02b032d2182f946450f1a0308d88f72327eedd6ebb243de69aa","sha256:a2a5f72bae2f72869a89ec56d15e398ddf53b07ed762044b721092d07f4eb129"],"state_sha256":"5cc88b44b7d948cbc55d2e288ad73a2236164c47faf9ae17e7e23fe4bae2c402"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mg6EL0RBGd3BCG1LmGHJa7C2AYENGYW9XBzSzs9WUVoWhG0zBYyt9EUIVAIzNAi2qwGXh2j3me9sqVCes2e8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T15:06:59.676951Z","bundle_sha256":"a1f416809f6475bd1d2f8065a21a601505c472311394ab5db61d9c6de4569fa0"}}