{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RVPDQ7OK5V4CDYO4DJZBIWC4NY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e2afa30793bfc60c69bf0fd9ee4576440e0e3d2a1d2d1cfb9f90aab850a90e3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T06:55:42Z","title_canon_sha256":"56cb9da0d556d5721919882f2b6d5b3af9f937c04d78d5862126eaf8a9353fbd"},"schema_version":"1.0","source":{"id":"2212.09272","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.09272","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2212.09272v1","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09272","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"RVPDQ7OK5V4C","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"RVPDQ7OK5V4CDYO4","created_at":"2026-07-05T05:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"RVPDQ7OK","created_at":"2026-07-05T05:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:df082d328b05e92552066b5918e44e4e5891cea3d7ea183de75b38924c9fd9b7","target":"graph","created_at":"2026-07-05T05:26:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2212.09272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chengwen Wang, Haitao Wang, Qingxiu Dong, Xiaochen Wang, Zhifang Sui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T06:55:42Z","title":"Statistical Dataset Evaluation: Reliability, Difficulty, and Validity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09272","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0b452f7aae4b104d97afd43624a827cf25a434c38b46f988a6ed0552b7ab03e9","target":"record","created_at":"2026-07-05T05:26:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e2afa30793bfc60c69bf0fd9ee4576440e0e3d2a1d2d1cfb9f90aab850a90e3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T06:55:42Z","title_canon_sha256":"56cb9da0d556d5721919882f2b6d5b3af9f937c04d78d5862126eaf8a9353fbd"},"schema_version":"1.0","source":{"id":"2212.09272","kind":"arxiv","version":1}},"canonical_sha256":"8d5e387dcaed7821e1dc1a7214585c6e3115440938aa346812c5598010479b86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d5e387dcaed7821e1dc1a7214585c6e3115440938aa346812c5598010479b86","first_computed_at":"2026-07-05T05:26:20.245732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:20.245732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ilzZbRUc0Cs5FcRHFw/GdV3JjoijT+QaDTyHEwsUlXvGlxWxVyNhxpHN3wtTuHghRMufRMhHTeC5ZApqu+nUBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:20.246250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.09272","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b452f7aae4b104d97afd43624a827cf25a434c38b46f988a6ed0552b7ab03e9","sha256:df082d328b05e92552066b5918e44e4e5891cea3d7ea183de75b38924c9fd9b7"],"state_sha256":"4155642c4f826d09858709d2b0bea21b9d8b88eba50630632dc3a54c2418d8d3"}