{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YOCCY3EI26OIALEOKNFUOQCSZP","short_pith_number":"pith:YOCCY3EI","schema_version":"1.0","canonical_sha256":"c3842c6c88d79c802c8e534b474052cbc2966abe997b45e267c1658b85b1c1b7","source":{"kind":"arxiv","id":"2005.00816","version":1},"attestation_state":"computed","paper":{"title":"DQI: Measuring Data Quality in NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anjana Arunkumar, Bhavdeep Sachdeva, Chitta Baral, Chris Bryan, Swaroop Mishra","submitted_at":"2020-05-02T12:34:17Z","abstract_excerpt":"Neural language models have achieved human level performance across several NLP datasets. However, recent studies have shown that these models are not truly learning the desired task; rather, their high performance is attributed to overfitting using spurious biases, which suggests that the capabilities of AI systems have been over-estimated. We introduce a generic formula for Data Quality Index (DQI) to help dataset creators create datasets free of such unwanted biases. We evaluate this formula using a recently proposed approach for adversarial filtering, AFLite. We propose a new data creation"},"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":"2005.00816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T12:34:17Z","cross_cats_sorted":[],"title_canon_sha256":"a646905398bf64378c4d0358348b23924b160524cab6bd78361cc502bb124b0a","abstract_canon_sha256":"4e911f60aafa1c13dc78a4d89bf61a42fef1734e74c8fbad5753ba5d385465e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:01.061222Z","signature_b64":"RK8MajuGLPUOrvtrarrRbPnTXClCSLWUqwQOq83wz525JvyYvlDoPghxMbtIgIKtxjhPR+E9RStehtIkD3xwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3842c6c88d79c802c8e534b474052cbc2966abe997b45e267c1658b85b1c1b7","last_reissued_at":"2026-07-05T01:00:01.060803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:01.060803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DQI: Measuring Data Quality in NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anjana Arunkumar, Bhavdeep Sachdeva, Chitta Baral, Chris Bryan, Swaroop Mishra","submitted_at":"2020-05-02T12:34:17Z","abstract_excerpt":"Neural language models have achieved human level performance across several NLP datasets. However, recent studies have shown that these models are not truly learning the desired task; rather, their high performance is attributed to overfitting using spurious biases, which suggests that the capabilities of AI systems have been over-estimated. We introduce a generic formula for Data Quality Index (DQI) to help dataset creators create datasets free of such unwanted biases. We evaluate this formula using a recently proposed approach for adversarial filtering, AFLite. We propose a new data creation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00816","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/2005.00816/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":"2005.00816","created_at":"2026-07-05T01:00:01.060856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00816v1","created_at":"2026-07-05T01:00:01.060856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00816","created_at":"2026-07-05T01:00:01.060856+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOCCY3EI26OI","created_at":"2026-07-05T01:00:01.060856+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOCCY3EI26OIALEO","created_at":"2026-07-05T01:00:01.060856+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOCCY3EI","created_at":"2026-07-05T01:00:01.060856+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/YOCCY3EI26OIALEOKNFUOQCSZP","json":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP.json","graph_json":"https://pith.science/api/pith-number/YOCCY3EI26OIALEOKNFUOQCSZP/graph.json","events_json":"https://pith.science/api/pith-number/YOCCY3EI26OIALEOKNFUOQCSZP/events.json","paper":"https://pith.science/paper/YOCCY3EI"},"agent_actions":{"view_html":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP","download_json":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP.json","view_paper":"https://pith.science/paper/YOCCY3EI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00816&json=true","fetch_graph":"https://pith.science/api/pith-number/YOCCY3EI26OIALEOKNFUOQCSZP/graph.json","fetch_events":"https://pith.science/api/pith-number/YOCCY3EI26OIALEOKNFUOQCSZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/action/storage_attestation","attest_author":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/action/author_attestation","sign_citation":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/action/citation_signature","submit_replication":"https://pith.science/pith/YOCCY3EI26OIALEOKNFUOQCSZP/action/replication_record"}},"created_at":"2026-07-05T01:00:01.060856+00:00","updated_at":"2026-07-05T01:00:01.060856+00:00"}