{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RVPDQ7OK5V4CDYO4DJZBIWC4NY","short_pith_number":"pith:RVPDQ7OK","schema_version":"1.0","canonical_sha256":"8d5e387dcaed7821e1dc1a7214585c6e3115440938aa346812c5598010479b86","source":{"kind":"arxiv","id":"2212.09272","version":1},"attestation_state":"computed","paper":{"title":"Statistical Dataset Evaluation: Reliability, Difficulty, and Validity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengwen Wang, Haitao Wang, Qingxiu Dong, Xiaochen Wang, Zhifang Sui","submitted_at":"2022-12-19T06:55:42Z","abstract_excerpt":"Datasets serve as crucial training resources and model performance trackers. However, existing datasets have exposed a plethora of problems, inducing biased models and unreliable evaluation results. In this paper, we propose a model-agnostic dataset evaluation framework for automatic dataset quality evaluation. We seek the statistical properties of the datasets and address three fundamental dimensions: reliability, difficulty, and validity, following a classical testing theory. Taking the Named Entity Recognition (NER) datasets as a case study, we introduce $9$ statistical metrics for a statis"},"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":"2212.09272","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T06:55:42Z","cross_cats_sorted":[],"title_canon_sha256":"56cb9da0d556d5721919882f2b6d5b3af9f937c04d78d5862126eaf8a9353fbd","abstract_canon_sha256":"e2afa30793bfc60c69bf0fd9ee4576440e0e3d2a1d2d1cfb9f90aab850a90e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:20.246250Z","signature_b64":"ilzZbRUc0Cs5FcRHFw/GdV3JjoijT+QaDTyHEwsUlXvGlxWxVyNhxpHN3wtTuHghRMufRMhHTeC5ZApqu+nUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d5e387dcaed7821e1dc1a7214585c6e3115440938aa346812c5598010479b86","last_reissued_at":"2026-07-05T05:26:20.245732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:20.245732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Dataset Evaluation: Reliability, Difficulty, and Validity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengwen Wang, Haitao Wang, Qingxiu Dong, Xiaochen Wang, Zhifang Sui","submitted_at":"2022-12-19T06:55:42Z","abstract_excerpt":"Datasets serve as crucial training resources and model performance trackers. However, existing datasets have exposed a plethora of problems, inducing biased models and unreliable evaluation results. In this paper, we propose a model-agnostic dataset evaluation framework for automatic dataset quality evaluation. We seek the statistical properties of the datasets and address three fundamental dimensions: reliability, difficulty, and validity, following a classical testing theory. Taking the Named Entity Recognition (NER) datasets as a case study, we introduce $9$ statistical metrics for a statis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09272","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/2212.09272/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":"2212.09272","created_at":"2026-07-05T05:26:20.245800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09272v1","created_at":"2026-07-05T05:26:20.245800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09272","created_at":"2026-07-05T05:26:20.245800+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVPDQ7OK5V4C","created_at":"2026-07-05T05:26:20.245800+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVPDQ7OK5V4CDYO4","created_at":"2026-07-05T05:26:20.245800+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVPDQ7OK","created_at":"2026-07-05T05:26:20.245800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.01411","citing_title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY","json":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY.json","graph_json":"https://pith.science/api/pith-number/RVPDQ7OK5V4CDYO4DJZBIWC4NY/graph.json","events_json":"https://pith.science/api/pith-number/RVPDQ7OK5V4CDYO4DJZBIWC4NY/events.json","paper":"https://pith.science/paper/RVPDQ7OK"},"agent_actions":{"view_html":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY","download_json":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY.json","view_paper":"https://pith.science/paper/RVPDQ7OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09272&json=true","fetch_graph":"https://pith.science/api/pith-number/RVPDQ7OK5V4CDYO4DJZBIWC4NY/graph.json","fetch_events":"https://pith.science/api/pith-number/RVPDQ7OK5V4CDYO4DJZBIWC4NY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY/action/storage_attestation","attest_author":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY/action/author_attestation","sign_citation":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY/action/citation_signature","submit_replication":"https://pith.science/pith/RVPDQ7OK5V4CDYO4DJZBIWC4NY/action/replication_record"}},"created_at":"2026-07-05T05:26:20.245800+00:00","updated_at":"2026-07-05T05:26:20.245800+00:00"}