{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MFH4Q72CTA7HAGFB2HFQRB4IGA","short_pith_number":"pith:MFH4Q72C","schema_version":"1.0","canonical_sha256":"614fc87f42983e7018a1d1cb08878830281020980f558d8ff367a0e3c4acb9d4","source":{"kind":"arxiv","id":"2412.06303","version":2},"attestation_state":"computed","paper":{"title":"DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bokyung Son, Daechul Park, Hyowon Cho, Jaewook Kang, Minjoon Seo, Soonwon Ka","submitted_at":"2024-12-09T08:47:05Z","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"},"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":"2412.06303","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T08:47:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4212f0499429399e873f5ef9d0930550cd83b5171dd719cea7847cf38f44f30","abstract_canon_sha256":"01fe588454d54e3a01c8a347691496491c8a0bca899adc388530177b3f6e35bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:47.904036Z","signature_b64":"5o+cg6oC8GzXgVT0cZmO/2pBZIKhQ2/HkogEEERBtTdG5II/0GT30n0tQyMrwUipYjquvq1slDSBAKCaZCjpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"614fc87f42983e7018a1d1cb08878830281020980f558d8ff367a0e3c4acb9d4","last_reissued_at":"2026-07-05T10:15:47.903535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:47.903535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSAI: Unbiased and Interpretable Latent Feature Extraction for Data-Centric AI","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bokyung Son, Daechul Park, Hyowon Cho, Jaewook Kang, Minjoon Seo, Soonwon Ka","submitted_at":"2024-12-09T08:47:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06303","kind":"arxiv","version":2},"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/2412.06303/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":"2412.06303","created_at":"2026-07-05T10:15:47.903594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06303v2","created_at":"2026-07-05T10:15:47.903594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06303","created_at":"2026-07-05T10:15:47.903594+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFH4Q72CTA7H","created_at":"2026-07-05T10:15:47.903594+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFH4Q72CTA7HAGFB","created_at":"2026-07-05T10:15:47.903594+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFH4Q72C","created_at":"2026-07-05T10:15:47.903594+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/MFH4Q72CTA7HAGFB2HFQRB4IGA","json":"https://pith.science/pith/MFH4Q72CTA7HAGFB2HFQRB4IGA.json","graph_json":"https://pith.science/api/pith-number/MFH4Q72CTA7HAGFB2HFQRB4IGA/graph.json","events_json":"https://pith.science/api/pith-number/MFH4Q72CTA7HAGFB2HFQRB4IGA/events.json","paper":"https://pith.science/paper/MFH4Q72C"},"agent_actions":{"view_html":"https://pith.science/pith/MFH4Q72CTA7HAGFB2HFQRB4IGA","download_json":"https://pith.science/pith/MFH4Q72CTA7HAGFB2HFQRB4IGA.json","view_paper":"https://pith.science/paper/MFH4Q72C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06303&json=true","fetch_graph":"https://pith.science/api/pith-number/MFH4Q72CTA7HAGFB2HFQRB4IGA/graph.json","fetch_events":"https://pith.science/api/pith-number/MFH4Q72CTA7HAGFB2HFQRB4IGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFH4Q72CTA7HAGFB2HFQRB4IGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFH4Q72CTA7HAGFB2HFQRB4IGA/action/storage_attestation","attest_author":"https://pith.science/pith/MFH4Q72CTA7HAGFB2HFQRB4IGA/action/author_attestation","sign_citation":"https://pith.science/pith/MFH4Q72CTA7HAGFB2HFQRB4IGA/action/citation_signature","submit_replication":"https://pith.science/pith/MFH4Q72CTA7HAGFB2HFQRB4IGA/action/replication_record"}},"created_at":"2026-07-05T10:15:47.903594+00:00","updated_at":"2026-07-05T10:15:47.903594+00:00"}