{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PXMZO7T74DNW5TQVUGHIRNL47M","short_pith_number":"pith:PXMZO7T7","canonical_record":{"source":{"id":"2002.01861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-05T16:45:44Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"9a05404eb911270944e7a49b68bb02f260c814c725266a4831a35af60cf1da72","abstract_canon_sha256":"829fe31a3356f6599cdfbb9bac4c97bcc4d2d9f5e489b9d00b07c91af4dce697"},"schema_version":"1.0"},"canonical_sha256":"7dd9977e7fe0db6ece15a18e88b57cfb2299d9069eb3ffe4d4a8c3eb741f4053","source":{"kind":"arxiv","id":"2002.01861","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.01861","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"arxiv_version","alias_value":"2002.01861v1","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.01861","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"pith_short_12","alias_value":"PXMZO7T74DNW","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"pith_short_16","alias_value":"PXMZO7T74DNW5TQV","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"pith_short_8","alias_value":"PXMZO7T7","created_at":"2026-07-05T00:38:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PXMZO7T74DNW5TQVUGHIRNL47M","target":"record","payload":{"canonical_record":{"source":{"id":"2002.01861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-05T16:45:44Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"9a05404eb911270944e7a49b68bb02f260c814c725266a4831a35af60cf1da72","abstract_canon_sha256":"829fe31a3356f6599cdfbb9bac4c97bcc4d2d9f5e489b9d00b07c91af4dce697"},"schema_version":"1.0"},"canonical_sha256":"7dd9977e7fe0db6ece15a18e88b57cfb2299d9069eb3ffe4d4a8c3eb741f4053","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:41.185751Z","signature_b64":"vCo+xy0zcXIYG1brbrGP7+mW/d/q0NG8Unvzt6ZEsv6BAIu4kLaIKTl7gRIt9KFC4w2AhNzv7oPmk6wxDJUJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dd9977e7fe0db6ece15a18e88b57cfb2299d9069eb3ffe4d4a8c3eb741f4053","last_reissued_at":"2026-07-05T00:38:41.185270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:41.185270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.01861","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":"2026-07-05T00:38:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jNWUTg03CW4RwHsgIkwbO4BieS7/uPFCpUBUjMR1F++i4HtZeGg4Q/fyvfFCMeOKBXqWJWZu4GUFSQ+/vy7eAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:27:56.342281Z"},"content_sha256":"43d63243ef0675cbbdac99b8258933218d85c2b597541d1129a2f46f6b7874af","schema_version":"1.0","event_id":"sha256:43d63243ef0675cbbdac99b8258933218d85c2b597541d1129a2f46f6b7874af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PXMZO7T74DNW5TQVUGHIRNL47M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jimmy Lin, Kun Xiong, Luchen Tan, Luyun Lin, Ruixue Zhang, Wei Yang, Yuhao Xie, Yuqing Xie, Zhengkai Tu, Zihang Fu","submitted_at":"2020-02-05T16:45:44Z","abstract_excerpt":"Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient. This problem can be formulated as a sequence labeling task, and we demonstrate the adaption of BERT to two types of business documents: regulatory filings and property lease agreements. There are aspects of this problem that make it easier than \"standard\" information extraction tasks and other aspects that make it more difficult, but on balance we find that modest amounts of annotated data (less than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.01861","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/2002.01861/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":"2026-07-05T00:38:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Rxb4TOZA1o7Yepgj7qbUlK9rgtAQ2ldEtHRVCj7TLSVG2pNz5RCJ5JrZ7tFWqqwwH/Wl5AJFwbccWFvKNnrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:27:56.342956Z"},"content_sha256":"066ae2c1fb35389df45dd4ade7885f823d24265e808960efc2a53d13ed15d5cf","schema_version":"1.0","event_id":"sha256:066ae2c1fb35389df45dd4ade7885f823d24265e808960efc2a53d13ed15d5cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXMZO7T74DNW5TQVUGHIRNL47M/bundle.json","state_url":"https://pith.science/pith/PXMZO7T74DNW5TQVUGHIRNL47M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXMZO7T74DNW5TQVUGHIRNL47M/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":"2026-07-31T13:27:56Z","links":{"resolver":"https://pith.science/pith/PXMZO7T74DNW5TQVUGHIRNL47M","bundle":"https://pith.science/pith/PXMZO7T74DNW5TQVUGHIRNL47M/bundle.json","state":"https://pith.science/pith/PXMZO7T74DNW5TQVUGHIRNL47M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXMZO7T74DNW5TQVUGHIRNL47M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PXMZO7T74DNW5TQVUGHIRNL47M","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":"829fe31a3356f6599cdfbb9bac4c97bcc4d2d9f5e489b9d00b07c91af4dce697","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-05T16:45:44Z","title_canon_sha256":"9a05404eb911270944e7a49b68bb02f260c814c725266a4831a35af60cf1da72"},"schema_version":"1.0","source":{"id":"2002.01861","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.01861","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"arxiv_version","alias_value":"2002.01861v1","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.01861","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"pith_short_12","alias_value":"PXMZO7T74DNW","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"pith_short_16","alias_value":"PXMZO7T74DNW5TQV","created_at":"2026-07-05T00:38:41Z"},{"alias_kind":"pith_short_8","alias_value":"PXMZO7T7","created_at":"2026-07-05T00:38:41Z"}],"graph_snapshots":[{"event_id":"sha256:066ae2c1fb35389df45dd4ade7885f823d24265e808960efc2a53d13ed15d5cf","target":"graph","created_at":"2026-07-05T00:38:41Z","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/2002.01861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Techniques for automatically extracting important content elements from business documents such as contracts, statements, and filings have the potential to make business operations more efficient. This problem can be formulated as a sequence labeling task, and we demonstrate the adaption of BERT to two types of business documents: regulatory filings and property lease agreements. There are aspects of this problem that make it easier than \"standard\" information extraction tasks and other aspects that make it more difficult, but on balance we find that modest amounts of annotated data (less than","authors_text":"Jimmy Lin, Kun Xiong, Luchen Tan, Luyun Lin, Ruixue Zhang, Wei Yang, Yuhao Xie, Yuqing Xie, Zhengkai Tu, Zihang Fu","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-05T16:45:44Z","title":"Rapid Adaptation of BERT for Information Extraction on Domain-Specific Business Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.01861","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":"sha256:43d63243ef0675cbbdac99b8258933218d85c2b597541d1129a2f46f6b7874af","target":"record","created_at":"2026-07-05T00:38:41Z","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":"829fe31a3356f6599cdfbb9bac4c97bcc4d2d9f5e489b9d00b07c91af4dce697","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-05T16:45:44Z","title_canon_sha256":"9a05404eb911270944e7a49b68bb02f260c814c725266a4831a35af60cf1da72"},"schema_version":"1.0","source":{"id":"2002.01861","kind":"arxiv","version":1}},"canonical_sha256":"7dd9977e7fe0db6ece15a18e88b57cfb2299d9069eb3ffe4d4a8c3eb741f4053","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dd9977e7fe0db6ece15a18e88b57cfb2299d9069eb3ffe4d4a8c3eb741f4053","first_computed_at":"2026-07-05T00:38:41.185270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:38:41.185270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vCo+xy0zcXIYG1brbrGP7+mW/d/q0NG8Unvzt6ZEsv6BAIu4kLaIKTl7gRIt9KFC4w2AhNzv7oPmk6wxDJUJAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:38:41.185751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.01861","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43d63243ef0675cbbdac99b8258933218d85c2b597541d1129a2f46f6b7874af","sha256:066ae2c1fb35389df45dd4ade7885f823d24265e808960efc2a53d13ed15d5cf"],"state_sha256":"8a42023b6b8bdaa5c78e75fa50de61c602452a4f3aaac194da749824d36e8215"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RhftsSKqAcqg0rlrhzuLbuqXKfcl3gUTe25URvu+5X3UtFUOZM2aKVoVGrZx9QgpM33zekS61tmwYAptxbr7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T13:27:56.347991Z","bundle_sha256":"21d1cd2ec06e977fd541b004db3613913326b4e760d51b6bf52064a32689a28d"}}