{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FMFONFHBLBWNCAVXWZOHOWMHOV","short_pith_number":"pith:FMFONFHB","schema_version":"1.0","canonical_sha256":"2b0ae694e1586cd102b7b65c775987757afd15eb4a6fb9ef6f5fce5a3a781d2e","source":{"kind":"arxiv","id":"2206.02280","version":2},"attestation_state":"computed","paper":{"title":"Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bonnie Webber, Iryna Gurevych, Jan-Christoph Klie","submitted_at":"2022-06-05T22:31:45Z","abstract_excerpt":"Annotated data is an essential ingredient in natural language processing for training and evaluating machine learning models. It is therefore very desirable for the annotations to be of high quality. Recent work, however, has shown that several popular datasets contain a surprising amount of annotation errors or inconsistencies. To alleviate this issue, many methods for annotation error detection have been devised over the years. While researchers show that their approaches work well on their newly introduced datasets, they rarely compare their methods to previous work or on the same datasets."},"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":"2206.02280","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-05T22:31:45Z","cross_cats_sorted":[],"title_canon_sha256":"55fd4dac18accbbba99c10b0558b6cccb848eaca221150619a4246c42c71abee","abstract_canon_sha256":"5aea06ce8da4fceabd72ea53c98d2d484c2f169ca4aaa37845fd6174b6cab8c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:42.803483Z","signature_b64":"6Y7BHXtnVO42rVsAp5mrmcRXHJGm8WhgTxEZZzJRLnzAMT96CNglFuKp/kUsK/qnBPwg8oBNT9qtIDZfMoABBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b0ae694e1586cd102b7b65c775987757afd15eb4a6fb9ef6f5fce5a3a781d2e","last_reissued_at":"2026-07-05T05:00:42.803122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:42.803122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bonnie Webber, Iryna Gurevych, Jan-Christoph Klie","submitted_at":"2022-06-05T22:31:45Z","abstract_excerpt":"Annotated data is an essential ingredient in natural language processing for training and evaluating machine learning models. It is therefore very desirable for the annotations to be of high quality. Recent work, however, has shown that several popular datasets contain a surprising amount of annotation errors or inconsistencies. To alleviate this issue, many methods for annotation error detection have been devised over the years. While researchers show that their approaches work well on their newly introduced datasets, they rarely compare their methods to previous work or on the same datasets."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02280","kind":"arxiv","version":2},"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/2206.02280/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":"2206.02280","created_at":"2026-07-05T05:00:42.803190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02280v2","created_at":"2026-07-05T05:00:42.803190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02280","created_at":"2026-07-05T05:00:42.803190+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMFONFHBLBWN","created_at":"2026-07-05T05:00:42.803190+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMFONFHBLBWNCAVX","created_at":"2026-07-05T05:00:42.803190+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMFONFHB","created_at":"2026-07-05T05:00:42.803190+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/FMFONFHBLBWNCAVXWZOHOWMHOV","json":"https://pith.science/pith/FMFONFHBLBWNCAVXWZOHOWMHOV.json","graph_json":"https://pith.science/api/pith-number/FMFONFHBLBWNCAVXWZOHOWMHOV/graph.json","events_json":"https://pith.science/api/pith-number/FMFONFHBLBWNCAVXWZOHOWMHOV/events.json","paper":"https://pith.science/paper/FMFONFHB"},"agent_actions":{"view_html":"https://pith.science/pith/FMFONFHBLBWNCAVXWZOHOWMHOV","download_json":"https://pith.science/pith/FMFONFHBLBWNCAVXWZOHOWMHOV.json","view_paper":"https://pith.science/paper/FMFONFHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02280&json=true","fetch_graph":"https://pith.science/api/pith-number/FMFONFHBLBWNCAVXWZOHOWMHOV/graph.json","fetch_events":"https://pith.science/api/pith-number/FMFONFHBLBWNCAVXWZOHOWMHOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMFONFHBLBWNCAVXWZOHOWMHOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMFONFHBLBWNCAVXWZOHOWMHOV/action/storage_attestation","attest_author":"https://pith.science/pith/FMFONFHBLBWNCAVXWZOHOWMHOV/action/author_attestation","sign_citation":"https://pith.science/pith/FMFONFHBLBWNCAVXWZOHOWMHOV/action/citation_signature","submit_replication":"https://pith.science/pith/FMFONFHBLBWNCAVXWZOHOWMHOV/action/replication_record"}},"created_at":"2026-07-05T05:00:42.803190+00:00","updated_at":"2026-07-05T05:00:42.803190+00:00"}