{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2FIF2XGEHK7MNC45JOXGFMQJBI","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":"5bc5ae501dc860148ba55eadac6718edfb904a5528a0d5367d0bb2959f6cd120","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T11:33:20Z","title_canon_sha256":"b32b433c08a60bee868bdd5e8537b12b3a6a030477b588c06a12fec90ed4811e"},"schema_version":"1.0","source":{"id":"2105.11210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11210","created_at":"2026-07-05T02:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11210v1","created_at":"2026-07-05T02:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11210","created_at":"2026-07-05T02:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"2FIF2XGEHK7M","created_at":"2026-07-05T02:42:36Z"},{"alias_kind":"pith_short_16","alias_value":"2FIF2XGEHK7MNC45","created_at":"2026-07-05T02:42:36Z"},{"alias_kind":"pith_short_8","alias_value":"2FIF2XGE","created_at":"2026-07-05T02:42:36Z"}],"graph_snapshots":[{"event_id":"sha256:c50e857dcb5cb47690ff7dcd202a1569df55613ff0cc23c6ee26e1527aed001a","target":"graph","created_at":"2026-07-05T02:42:36Z","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/2105.11210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, while neglecting cell-level layout information that is important for form image understanding. In this paper, we propose a new pre-training approach, StructuralLM, to jointly leverage cell and layout information from scanned documents. Specifically, we pre-train StructuralLM with two new designs to make the most of the interactions of cell and layout information: 1) each cell as a semantic unit; 2) classification of cell","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Luo Si, Ming Yan, Songfang Huang, Wei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T11:33:20Z","title":"StructuralLM: Structural Pre-training for Form Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11210","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":"sha256:2857f1cbf99a63f28210ac5057e2c6bb323f04eceb8d9e98528bd488f2827434","target":"record","created_at":"2026-07-05T02:42:36Z","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":"5bc5ae501dc860148ba55eadac6718edfb904a5528a0d5367d0bb2959f6cd120","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T11:33:20Z","title_canon_sha256":"b32b433c08a60bee868bdd5e8537b12b3a6a030477b588c06a12fec90ed4811e"},"schema_version":"1.0","source":{"id":"2105.11210","kind":"arxiv","version":1}},"canonical_sha256":"d1505d5cc43abec68b9d4bae62b2090a351b139ecb3c2bbf5d359b7722f82dce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1505d5cc43abec68b9d4bae62b2090a351b139ecb3c2bbf5d359b7722f82dce","first_computed_at":"2026-07-05T02:42:36.454350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:36.454350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gSH0Lm2FNPdJ0fc9fvhlIOXZh1uxlhh/HezMcvPOkJzzP7BmB2NzrgluCMZMh9iiizAG/+CKXsSxsmee3G+tAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:36.454758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2857f1cbf99a63f28210ac5057e2c6bb323f04eceb8d9e98528bd488f2827434","sha256:c50e857dcb5cb47690ff7dcd202a1569df55613ff0cc23c6ee26e1527aed001a"],"state_sha256":"5f9719858fc6352d1107bb0894155645657b18278f4b0738f4ef45cee0738ded"}