{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R33YEXWOBYKRCIX73CPPTBBESC","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":"e6b55f70ead4a51c591eac321a3c7b5ff83605db4d0e669e8ba77d0e80911926","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:16:34Z","title_canon_sha256":"7637189dad5f0c87f0339803a35b5c153d53c5141743353d7b60f8fa5c3469e7"},"schema_version":"1.0","source":{"id":"2405.11865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11865","created_at":"2026-07-05T08:20:57Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11865v1","created_at":"2026-07-05T08:20:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11865","created_at":"2026-07-05T08:20:57Z"},{"alias_kind":"pith_short_12","alias_value":"R33YEXWOBYKR","created_at":"2026-07-05T08:20:57Z"},{"alias_kind":"pith_short_16","alias_value":"R33YEXWOBYKRCIX7","created_at":"2026-07-05T08:20:57Z"},{"alias_kind":"pith_short_8","alias_value":"R33YEXWO","created_at":"2026-07-05T08:20:57Z"}],"graph_snapshots":[{"event_id":"sha256:2e0a606eaa1dc171f06ca3052898ba9f461b728f1b39c5f9455477b9c8d3cb60","target":"graph","created_at":"2026-07-05T08:20:57Z","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/2405.11865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern named entity recognition systems have steadily improved performance in the age of larger and more powerful neural models. However, over the past several years, the state-of-the-art has seemingly hit another plateau on the benchmark CoNLL-03 English dataset. In this paper, we perform a deep dive into the test outputs of the highest-performing NER models, conducting a fine-grained evaluation of their performance by introducing new document-level annotations on the test set. We go beyond F1 scores by categorizing errors in order to interpret the true state of the art for NER and guide futu","authors_text":"Andrew Rueda, Constantine Lignos, Elena \\'Alvarez Mellado","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:16:34Z","title":"CoNLL#: Fine-grained Error Analysis and a Corrected Test Set for CoNLL-03 English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11865","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":"sha256:61be5f82da2cdbc0cf629f143779e517bf292f90cdbfe8e7f2c4d2fc592877dc","target":"record","created_at":"2026-07-05T08:20:57Z","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":"e6b55f70ead4a51c591eac321a3c7b5ff83605db4d0e669e8ba77d0e80911926","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:16:34Z","title_canon_sha256":"7637189dad5f0c87f0339803a35b5c153d53c5141743353d7b60f8fa5c3469e7"},"schema_version":"1.0","source":{"id":"2405.11865","kind":"arxiv","version":1}},"canonical_sha256":"8ef7825ece0e151122ffd89ef9842490be48c37e913aa2e51aacf3275713ef62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ef7825ece0e151122ffd89ef9842490be48c37e913aa2e51aacf3275713ef62","first_computed_at":"2026-07-05T08:20:57.103349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:57.103349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8IU539PCAmgdcrR7hsFTMZWYHjBXp2n1Qjod3XItyWVVz9+q1PMQRXcmURgJHQ3Ooirl+Oqey98AnAGVQFy5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:57.103753Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61be5f82da2cdbc0cf629f143779e517bf292f90cdbfe8e7f2c4d2fc592877dc","sha256:2e0a606eaa1dc171f06ca3052898ba9f461b728f1b39c5f9455477b9c8d3cb60"],"state_sha256":"92ecec5babefcb28f7663569c3934b62e022ca155d25c0e0836a8ea697b9bfec"}