{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2FIF2XGEHK7MNC45JOXGFMQJBI","short_pith_number":"pith:2FIF2XGE","canonical_record":{"source":{"id":"2105.11210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T11:33:20Z","cross_cats_sorted":[],"title_canon_sha256":"b32b433c08a60bee868bdd5e8537b12b3a6a030477b588c06a12fec90ed4811e","abstract_canon_sha256":"5bc5ae501dc860148ba55eadac6718edfb904a5528a0d5367d0bb2959f6cd120"},"schema_version":"1.0"},"canonical_sha256":"d1505d5cc43abec68b9d4bae62b2090a351b139ecb3c2bbf5d359b7722f82dce","source":{"kind":"arxiv","id":"2105.11210","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2FIF2XGEHK7MNC45JOXGFMQJBI","target":"record","payload":{"canonical_record":{"source":{"id":"2105.11210","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-24T11:33:20Z","cross_cats_sorted":[],"title_canon_sha256":"b32b433c08a60bee868bdd5e8537b12b3a6a030477b588c06a12fec90ed4811e","abstract_canon_sha256":"5bc5ae501dc860148ba55eadac6718edfb904a5528a0d5367d0bb2959f6cd120"},"schema_version":"1.0"},"canonical_sha256":"d1505d5cc43abec68b9d4bae62b2090a351b139ecb3c2bbf5d359b7722f82dce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:36.454758Z","signature_b64":"gSH0Lm2FNPdJ0fc9fvhlIOXZh1uxlhh/HezMcvPOkJzzP7BmB2NzrgluCMZMh9iiizAG/+CKXsSxsmee3G+tAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1505d5cc43abec68b9d4bae62b2090a351b139ecb3c2bbf5d359b7722f82dce","last_reissued_at":"2026-07-05T02:42:36.454350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:36.454350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.11210","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":"2026-07-05T02:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gmkHMTuvi5NZMaE0tyOa7vvhDvben4qyEBskfFnm+bsnxvZceop2M5qi3suL6ByAuoNsED+/FMgE/va/L22+DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T21:28:03.507108Z"},"content_sha256":"2857f1cbf99a63f28210ac5057e2c6bb323f04eceb8d9e98528bd488f2827434","schema_version":"1.0","event_id":"sha256:2857f1cbf99a63f28210ac5057e2c6bb323f04eceb8d9e98528bd488f2827434"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2FIF2XGEHK7MNC45JOXGFMQJBI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StructuralLM: Structural Pre-training for Form Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Bi, Chenliang Li, Fei Huang, Luo Si, Ming Yan, Songfang Huang, Wei Wang","submitted_at":"2021-05-24T11:33:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11210","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/2105.11210/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":"2026-07-05T02:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LmwalJ8l1RnpAInRJCTaZSqun734klztWyJ5Q7iB5sr0dTyLqbQyEC7DMFV1HNytGGWy0du1lSwmiOxu+dF4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T21:28:03.507619Z"},"content_sha256":"c50e857dcb5cb47690ff7dcd202a1569df55613ff0cc23c6ee26e1527aed001a","schema_version":"1.0","event_id":"sha256:c50e857dcb5cb47690ff7dcd202a1569df55613ff0cc23c6ee26e1527aed001a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2FIF2XGEHK7MNC45JOXGFMQJBI/bundle.json","state_url":"https://pith.science/pith/2FIF2XGEHK7MNC45JOXGFMQJBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2FIF2XGEHK7MNC45JOXGFMQJBI/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":"2026-07-31T21:28:03Z","links":{"resolver":"https://pith.science/pith/2FIF2XGEHK7MNC45JOXGFMQJBI","bundle":"https://pith.science/pith/2FIF2XGEHK7MNC45JOXGFMQJBI/bundle.json","state":"https://pith.science/pith/2FIF2XGEHK7MNC45JOXGFMQJBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2FIF2XGEHK7MNC45JOXGFMQJBI/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K7Tty5m2W4Xob76nB23wJOrh4cAAHUzIJW6hjfjnFW2k5sT4bdERhJq4RqH5TYjm3zpTGTc/UYNRzd60t0SBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T21:28:03.550839Z","bundle_sha256":"a4f22c74c585141042df2ff244d47a8baa22d35e5f6fc6ddb469d9fa0863b165"}}