{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R33YEXWOBYKRCIX73CPPTBBESC","short_pith_number":"pith:R33YEXWO","schema_version":"1.0","canonical_sha256":"8ef7825ece0e151122ffd89ef9842490be48c37e913aa2e51aacf3275713ef62","source":{"kind":"arxiv","id":"2405.11865","version":1},"attestation_state":"computed","paper":{"title":"CoNLL#: Fine-grained Error Analysis and a Corrected Test Set for CoNLL-03 English","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Rueda, Constantine Lignos, Elena \\'Alvarez Mellado","submitted_at":"2024-05-20T08:16:34Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.11865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-20T08:16:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7637189dad5f0c87f0339803a35b5c153d53c5141743353d7b60f8fa5c3469e7","abstract_canon_sha256":"e6b55f70ead4a51c591eac321a3c7b5ff83605db4d0e669e8ba77d0e80911926"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:57.103753Z","signature_b64":"8IU539PCAmgdcrR7hsFTMZWYHjBXp2n1Qjod3XItyWVVz9+q1PMQRXcmURgJHQ3Ooirl+Oqey98AnAGVQFy5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ef7825ece0e151122ffd89ef9842490be48c37e913aa2e51aacf3275713ef62","last_reissued_at":"2026-07-05T08:20:57.103349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:57.103349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoNLL#: Fine-grained Error Analysis and a Corrected Test Set for CoNLL-03 English","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Rueda, Constantine Lignos, Elena \\'Alvarez Mellado","submitted_at":"2024-05-20T08:16:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11865","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/2405.11865/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.11865","created_at":"2026-07-05T08:20:57.103406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11865v1","created_at":"2026-07-05T08:20:57.103406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11865","created_at":"2026-07-05T08:20:57.103406+00:00"},{"alias_kind":"pith_short_12","alias_value":"R33YEXWOBYKR","created_at":"2026-07-05T08:20:57.103406+00:00"},{"alias_kind":"pith_short_16","alias_value":"R33YEXWOBYKRCIX7","created_at":"2026-07-05T08:20:57.103406+00:00"},{"alias_kind":"pith_short_8","alias_value":"R33YEXWO","created_at":"2026-07-05T08:20:57.103406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC","json":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC.json","graph_json":"https://pith.science/api/pith-number/R33YEXWOBYKRCIX73CPPTBBESC/graph.json","events_json":"https://pith.science/api/pith-number/R33YEXWOBYKRCIX73CPPTBBESC/events.json","paper":"https://pith.science/paper/R33YEXWO"},"agent_actions":{"view_html":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC","download_json":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC.json","view_paper":"https://pith.science/paper/R33YEXWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11865&json=true","fetch_graph":"https://pith.science/api/pith-number/R33YEXWOBYKRCIX73CPPTBBESC/graph.json","fetch_events":"https://pith.science/api/pith-number/R33YEXWOBYKRCIX73CPPTBBESC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC/action/storage_attestation","attest_author":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC/action/author_attestation","sign_citation":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC/action/citation_signature","submit_replication":"https://pith.science/pith/R33YEXWOBYKRCIX73CPPTBBESC/action/replication_record"}},"created_at":"2026-07-05T08:20:57.103406+00:00","updated_at":"2026-07-05T08:20:57.103406+00:00"}