{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R2DZXVQZTD3REDF2FW4IZOBA5N","short_pith_number":"pith:R2DZXVQZ","schema_version":"1.0","canonical_sha256":"8e879bd61998f7120cba2db88cb820eb59df3864a7bb8a449eef63ccd22ca705","source":{"kind":"arxiv","id":"2211.04476","version":2},"attestation_state":"computed","paper":{"title":"Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Haitao Mi, Lifeng Jin, Linfeng Song, Wenyue Hua, Yongfeng Zhang","submitted_at":"2022-11-08T19:00:00Z","abstract_excerpt":"Pretrained natural language processing (NLP) models have achieved high overall performance, but they still make systematic errors. Instead of manual error analysis, research on slice detection models (SDM), which automatically identify underperforming groups of datapoints, has caught escalated attention in Computer Vision for both understanding model behaviors and providing insights for future model training and designing. However, little research on SDM and quantitative evaluation of their effectiveness have been conducted on NLP tasks. Our paper fills the gap by proposing a benchmark named \""},"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":"2211.04476","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-08T19:00:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d1c7c354ffa3097df534902aef6c7fa3d090f3c2668809fad7f2a34b5fb9702f","abstract_canon_sha256":"3dc716ba0620bb07b55d36cb334271331b42d6025fef398cc3077030d79100a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:17.341968Z","signature_b64":"AJr8JNIw+0ORKCJ1dpVTdZjOAt01gat4Yj+HSz2EhMH/DsLkpiLitid5oeKx5udAUqZo/sSdqrSc4yWWdulrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e879bd61998f7120cba2db88cb820eb59df3864a7bb8a449eef63ccd22ca705","last_reissued_at":"2026-07-05T06:49:17.341407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:17.341407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dong Yu, Haitao Mi, Lifeng Jin, Linfeng Song, Wenyue Hua, Yongfeng Zhang","submitted_at":"2022-11-08T19:00:00Z","abstract_excerpt":"Pretrained natural language processing (NLP) models have achieved high overall performance, but they still make systematic errors. Instead of manual error analysis, research on slice detection models (SDM), which automatically identify underperforming groups of datapoints, has caught escalated attention in Computer Vision for both understanding model behaviors and providing insights for future model training and designing. However, little research on SDM and quantitative evaluation of their effectiveness have been conducted on NLP tasks. Our paper fills the gap by proposing a benchmark named \""},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04476","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/2211.04476/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":"2211.04476","created_at":"2026-07-05T06:49:17.341482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.04476v2","created_at":"2026-07-05T06:49:17.341482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04476","created_at":"2026-07-05T06:49:17.341482+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2DZXVQZTD3R","created_at":"2026-07-05T06:49:17.341482+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2DZXVQZTD3REDF2","created_at":"2026-07-05T06:49:17.341482+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2DZXVQZ","created_at":"2026-07-05T06:49:17.341482+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/R2DZXVQZTD3REDF2FW4IZOBA5N","json":"https://pith.science/pith/R2DZXVQZTD3REDF2FW4IZOBA5N.json","graph_json":"https://pith.science/api/pith-number/R2DZXVQZTD3REDF2FW4IZOBA5N/graph.json","events_json":"https://pith.science/api/pith-number/R2DZXVQZTD3REDF2FW4IZOBA5N/events.json","paper":"https://pith.science/paper/R2DZXVQZ"},"agent_actions":{"view_html":"https://pith.science/pith/R2DZXVQZTD3REDF2FW4IZOBA5N","download_json":"https://pith.science/pith/R2DZXVQZTD3REDF2FW4IZOBA5N.json","view_paper":"https://pith.science/paper/R2DZXVQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.04476&json=true","fetch_graph":"https://pith.science/api/pith-number/R2DZXVQZTD3REDF2FW4IZOBA5N/graph.json","fetch_events":"https://pith.science/api/pith-number/R2DZXVQZTD3REDF2FW4IZOBA5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2DZXVQZTD3REDF2FW4IZOBA5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2DZXVQZTD3REDF2FW4IZOBA5N/action/storage_attestation","attest_author":"https://pith.science/pith/R2DZXVQZTD3REDF2FW4IZOBA5N/action/author_attestation","sign_citation":"https://pith.science/pith/R2DZXVQZTD3REDF2FW4IZOBA5N/action/citation_signature","submit_replication":"https://pith.science/pith/R2DZXVQZTD3REDF2FW4IZOBA5N/action/replication_record"}},"created_at":"2026-07-05T06:49:17.341482+00:00","updated_at":"2026-07-05T06:49:17.341482+00:00"}