{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ANLEJD3UEUISWMH3HQIS5L5DY5","short_pith_number":"pith:ANLEJD3U","schema_version":"1.0","canonical_sha256":"0356448f7425112b30fb3c112eafa3c77a48fd4cba7116042e58f90f2733ec1d","source":{"kind":"arxiv","id":"2210.03920","version":1},"attestation_state":"computed","paper":{"title":"Detecting Label Errors in Token Classification Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jonas Mueller, Wei-Chen Wang","submitted_at":"2022-10-08T05:14:22Z","abstract_excerpt":"Mislabeled examples are a common issue in real-world data, particularly for tasks like token classification where many labels must be chosen on a fine-grained basis. Here we consider the task of finding sentences that contain label errors in token classification datasets. We study 11 different straightforward methods that score tokens/sentences based on the predicted class probabilities output by a (any) token classification model (trained via any procedure). In precision-recall evaluations based on real-world label errors in entity recognition data from CoNLL-2003, we identify a simple and ef"},"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":"2210.03920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T05:14:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5c09ea07ca4baeabbde460b1f86b0576a15ec5de7f2486fddbed72e65404708","abstract_canon_sha256":"20455eb64b9ecdc73ce2640d6f05f5d8c3d855454bde34a2c65537e7dce5d64a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:52.992332Z","signature_b64":"PjklZ3tR6IRTvbHFmClJB2AIdI8xLtVotP445+BVhjCHd3bAfcgImJceE0cenDAwRklUMfao/nypq4ILIn/bCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0356448f7425112b30fb3c112eafa3c77a48fd4cba7116042e58f90f2733ec1d","last_reissued_at":"2026-07-05T05:08:52.991871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:52.991871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Label Errors in Token Classification Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jonas Mueller, Wei-Chen Wang","submitted_at":"2022-10-08T05:14:22Z","abstract_excerpt":"Mislabeled examples are a common issue in real-world data, particularly for tasks like token classification where many labels must be chosen on a fine-grained basis. Here we consider the task of finding sentences that contain label errors in token classification datasets. We study 11 different straightforward methods that score tokens/sentences based on the predicted class probabilities output by a (any) token classification model (trained via any procedure). In precision-recall evaluations based on real-world label errors in entity recognition data from CoNLL-2003, we identify a simple and ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03920","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/2210.03920/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":"2210.03920","created_at":"2026-07-05T05:08:52.991935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03920v1","created_at":"2026-07-05T05:08:52.991935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03920","created_at":"2026-07-05T05:08:52.991935+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANLEJD3UEUIS","created_at":"2026-07-05T05:08:52.991935+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANLEJD3UEUISWMH3","created_at":"2026-07-05T05:08:52.991935+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANLEJD3U","created_at":"2026-07-05T05:08:52.991935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31446","citing_title":"Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5","json":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5.json","graph_json":"https://pith.science/api/pith-number/ANLEJD3UEUISWMH3HQIS5L5DY5/graph.json","events_json":"https://pith.science/api/pith-number/ANLEJD3UEUISWMH3HQIS5L5DY5/events.json","paper":"https://pith.science/paper/ANLEJD3U"},"agent_actions":{"view_html":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5","download_json":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5.json","view_paper":"https://pith.science/paper/ANLEJD3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03920&json=true","fetch_graph":"https://pith.science/api/pith-number/ANLEJD3UEUISWMH3HQIS5L5DY5/graph.json","fetch_events":"https://pith.science/api/pith-number/ANLEJD3UEUISWMH3HQIS5L5DY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5/action/storage_attestation","attest_author":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5/action/author_attestation","sign_citation":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5/action/citation_signature","submit_replication":"https://pith.science/pith/ANLEJD3UEUISWMH3HQIS5L5DY5/action/replication_record"}},"created_at":"2026-07-05T05:08:52.991935+00:00","updated_at":"2026-07-05T05:08:52.991935+00:00"}