{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EQMPVVFRPZD5LKT4TCGKZR2SDS","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":"91c54324a03bb834e3638996a6595359b7fbff2dd1070c45b242d02d11283113","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T00:27:49Z","title_canon_sha256":"869e771b3289be2fb13a65554d32dd92745fb93b24a2a24fe468afff3c68cf68"},"schema_version":"1.0","source":{"id":"2502.08669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08669","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08669v1","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08669","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_12","alias_value":"EQMPVVFRPZD5","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_16","alias_value":"EQMPVVFRPZD5LKT4","created_at":"2026-07-05T10:13:28Z"},{"alias_kind":"pith_short_8","alias_value":"EQMPVVFR","created_at":"2026-07-05T10:13:28Z"}],"graph_snapshots":[{"event_id":"sha256:4ce90e7b0feb478aee8abc57bc7c4dee6c62b7f9f417f14eb740490b090211cc","target":"graph","created_at":"2026-07-05T10:13:28Z","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/2502.08669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Background: Data collected in controlled settings typically results in high-quality datasets. However, in real-world applications, the quality of data collection is often compromised. It is well established that the quality of a dataset significantly impacts the performance of machine learning models.\n  Methods: A rudimentary error rate metric was developed to evaluate textual dataset quality at the token level. Mixtral Large Language Model (LLM) was used to quantify and correct errors in low quality datasets. The study analyzed two healthcare datasets: the high-quality MIMIC-III public hospit","authors_text":"Antonio Jose Jimeno Yepes, Lawrence Cavedon, Tabinda Sarwar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T00:27:49Z","title":"Assessing the Impact of the Quality of Textual Data on Feature Representation and Machine Learning Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08669","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":"sha256:7acd8f9510bceee895a5789e13101605a510cc70b8b7540a38c9036872daf2cf","target":"record","created_at":"2026-07-05T10:13:28Z","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":"91c54324a03bb834e3638996a6595359b7fbff2dd1070c45b242d02d11283113","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-12T00:27:49Z","title_canon_sha256":"869e771b3289be2fb13a65554d32dd92745fb93b24a2a24fe468afff3c68cf68"},"schema_version":"1.0","source":{"id":"2502.08669","kind":"arxiv","version":1}},"canonical_sha256":"2418fad4b17e47d5aa7c988cacc7521cbf2ee4f81e44b80ac020a83fc23f45cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2418fad4b17e47d5aa7c988cacc7521cbf2ee4f81e44b80ac020a83fc23f45cf","first_computed_at":"2026-07-05T10:13:28.189461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:28.189461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JRy45YSbC8AFBAF0xqIlQjnGfbUw2eK6VT40fbEfth9fjYO1YczPoep4WWgjl1Rk9pZu+cesWBjSUMWkTK66Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:28.189935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7acd8f9510bceee895a5789e13101605a510cc70b8b7540a38c9036872daf2cf","sha256:4ce90e7b0feb478aee8abc57bc7c4dee6c62b7f9f417f14eb740490b090211cc"],"state_sha256":"ee55df90dcb468585764e5e1bde81aac21578515ef6c9036be858e1f66708f05"}