{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OSZEDD7E2VCYEPBFHPAXCRGXS4","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":"fab048948bc3b7400c159a61ac8cf49b8d323c194e6a184c1c60ee4cfed8c274","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-17T21:10:34Z","title_canon_sha256":"935448bb192477bc31f56b59817edeca7d45b8cd7364ea8e9bdf49a80dfda1a2"},"schema_version":"1.0","source":{"id":"2012.09936","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.09936","created_at":"2026-07-05T02:00:23Z"},{"alias_kind":"arxiv_version","alias_value":"2012.09936v1","created_at":"2026-07-05T02:00:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.09936","created_at":"2026-07-05T02:00:23Z"},{"alias_kind":"pith_short_12","alias_value":"OSZEDD7E2VCY","created_at":"2026-07-05T02:00:23Z"},{"alias_kind":"pith_short_16","alias_value":"OSZEDD7E2VCYEPBF","created_at":"2026-07-05T02:00:23Z"},{"alias_kind":"pith_short_8","alias_value":"OSZEDD7E","created_at":"2026-07-05T02:00:23Z"}],"graph_snapshots":[{"event_id":"sha256:9f14a08c20256a50a1679707bcac013a0272f92371c436a75daf5e52b9ede0c7","target":"graph","created_at":"2026-07-05T02:00:23Z","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/2012.09936/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Named Entity Recognition (NER) is the task of identifying and classifying named entities in unstructured text. In the legal domain, named entities of interest may include the case parties, judges, names of courts, case numbers, references to laws etc. We study the problem of legal NER with noisy text extracted from PDF files of filed court cases from US courts. The \"gold standard\" training data for NER systems provide annotation for each token of the text with the corresponding entity or non-entity label. We work with only partially complete training data, which differ from the gold standard N","authors_text":"Ali Oskooei, Nadja Herger, Omar Bari, Stavroula Skylaki, Zac Kriegman (Thomson Reuters Labs)","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-17T21:10:34Z","title":"Named Entity Recognition in the Legal Domain using a Pointer Generator Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.09936","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:a79a854f05c1f454feca1a102cc8766c56791564e8cfb40ef183fbc3028b7d64","target":"record","created_at":"2026-07-05T02:00:23Z","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":"fab048948bc3b7400c159a61ac8cf49b8d323c194e6a184c1c60ee4cfed8c274","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-17T21:10:34Z","title_canon_sha256":"935448bb192477bc31f56b59817edeca7d45b8cd7364ea8e9bdf49a80dfda1a2"},"schema_version":"1.0","source":{"id":"2012.09936","kind":"arxiv","version":1}},"canonical_sha256":"74b2418fe4d545823c253bc17144d7971064f49d6925dbbc2b8d50a8bfde3ff7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74b2418fe4d545823c253bc17144d7971064f49d6925dbbc2b8d50a8bfde3ff7","first_computed_at":"2026-07-05T02:00:23.219908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:23.219908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ArrOLq4bY2pgCGSjEe1qj4NFQhLG6wL8D6fy14Kwt6cPZTKKZNHl/k12E/tCVUP3XXlwry+mWAzPdP+mJj28Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:23.220337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.09936","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a79a854f05c1f454feca1a102cc8766c56791564e8cfb40ef183fbc3028b7d64","sha256:9f14a08c20256a50a1679707bcac013a0272f92371c436a75daf5e52b9ede0c7"],"state_sha256":"18d49c09d5f12de4b895376b57e1052cc8c3bb4c3d2ee1a04e6e0418b98889c4"}