{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MFH4Q72CTA7HAGFB2HFQRB4IGA","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":"01fe588454d54e3a01c8a347691496491c8a0bca899adc388530177b3f6e35bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T08:47:05Z","title_canon_sha256":"d4212f0499429399e873f5ef9d0930550cd83b5171dd719cea7847cf38f44f30"},"schema_version":"1.0","source":{"id":"2412.06303","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06303","created_at":"2026-07-05T10:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06303v2","created_at":"2026-07-05T10:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06303","created_at":"2026-07-05T10:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"MFH4Q72CTA7H","created_at":"2026-07-05T10:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"MFH4Q72CTA7HAGFB","created_at":"2026-07-05T10:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"MFH4Q72C","created_at":"2026-07-05T10:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:8fa6e49a8b2135d81423fbd3f4b207b16e37547a908d39de720f14b71e081fe1","target":"graph","created_at":"2026-07-05T10:15:47Z","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/2412.06303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) often struggle to objectively identify latent characteristics in large datasets due to their reliance on pre-trained knowledge rather than actual data patterns. To address this data grounding issue, we propose Data Scientist AI (DSAI), a framework that enables unbiased and interpretable feature extraction through a multi-stage pipeline with quantifiable prominence metrics for evaluating extracted features. On synthetic datasets with known ground-truth features, DSAI demonstrates high recall in identifying expert-defined features while faithfully reflecting the unde","authors_text":"Bokyung Son, Daechul Park, Hyowon Cho, Jaewook Kang, Minjoon Seo, Soonwon Ka","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T08:47:05Z","title":"DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06303","kind":"arxiv","version":2},"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:cfe160d2bc864747f694164d04f99ec741d12dad09be3b98a0e5b432655e9f9d","target":"record","created_at":"2026-07-05T10:15:47Z","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":"01fe588454d54e3a01c8a347691496491c8a0bca899adc388530177b3f6e35bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T08:47:05Z","title_canon_sha256":"d4212f0499429399e873f5ef9d0930550cd83b5171dd719cea7847cf38f44f30"},"schema_version":"1.0","source":{"id":"2412.06303","kind":"arxiv","version":2}},"canonical_sha256":"614fc87f42983e7018a1d1cb08878830281020980f558d8ff367a0e3c4acb9d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"614fc87f42983e7018a1d1cb08878830281020980f558d8ff367a0e3c4acb9d4","first_computed_at":"2026-07-05T10:15:47.903535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:47.903535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5o+cg6oC8GzXgVT0cZmO/2pBZIKhQ2/HkogEEERBtTdG5II/0GT30n0tQyMrwUipYjquvq1slDSBAKCaZCjpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:47.904036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06303","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfe160d2bc864747f694164d04f99ec741d12dad09be3b98a0e5b432655e9f9d","sha256:8fa6e49a8b2135d81423fbd3f4b207b16e37547a908d39de720f14b71e081fe1"],"state_sha256":"a55b72f99307c41237e9f110a50fb966ed21e3d3a601781d30067f8867e021d4"}