{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZSI5YNJZXHCRQTRDCKVYKM2EXP","short_pith_number":"pith:ZSI5YNJZ","schema_version":"1.0","canonical_sha256":"cc91dc3539b9c5184e2312ab853344bbee7f4be1f87a69059b6e9451d95657b3","source":{"kind":"arxiv","id":"2203.04386","version":1},"attestation_state":"computed","paper":{"title":"Model-free feature selection to facilitate automatic discovery of divergent subgroups in tabular data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","eess.SP","math.IT"],"primary_cat":"cs.LG","authors_text":"Celia Cintas, Girmaw Abebe Tadesse, Skyler Speakman, William Ogallo","submitted_at":"2022-03-08T20:42:56Z","abstract_excerpt":"Data-centric AI encourages the need of cleaning and understanding of data in order to achieve trustworthy AI. Existing technologies, such as AutoML, make it easier to design and train models automatically, but there is a lack of a similar level of capabilities to extract data-centric insights. Manual stratification of tabular data per a feature (e.g., gender) is limited to scale up for higher feature dimension, which could be addressed using automatic discovery of divergent subgroups. Nonetheless, these automatic discovery techniques often search across potentially exponential combinations of "},"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":"2203.04386","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-08T20:42:56Z","cross_cats_sorted":["cs.AI","cs.IT","eess.SP","math.IT"],"title_canon_sha256":"f9c51284256eb0184b133f60f5d067fad4c4740cefa30b3d4624bb3c63521a2c","abstract_canon_sha256":"d562b0053a99acb84383c51401422566e0391d7b82eb48127a6c50bd22645787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:17.669031Z","signature_b64":"l98GvsBl8RhP3RCWs4kEHkJ0n92u2QHbVy/4QcwcatOWJzoTJfdUklgB+aLZgMzX5JfQPhYD6mBk542DMRioCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc91dc3539b9c5184e2312ab853344bbee7f4be1f87a69059b6e9451d95657b3","last_reissued_at":"2026-07-05T04:03:17.668587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:17.668587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-free feature selection to facilitate automatic discovery of divergent subgroups in tabular data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","eess.SP","math.IT"],"primary_cat":"cs.LG","authors_text":"Celia Cintas, Girmaw Abebe Tadesse, Skyler Speakman, William Ogallo","submitted_at":"2022-03-08T20:42:56Z","abstract_excerpt":"Data-centric AI encourages the need of cleaning and understanding of data in order to achieve trustworthy AI. Existing technologies, such as AutoML, make it easier to design and train models automatically, but there is a lack of a similar level of capabilities to extract data-centric insights. Manual stratification of tabular data per a feature (e.g., gender) is limited to scale up for higher feature dimension, which could be addressed using automatic discovery of divergent subgroups. Nonetheless, these automatic discovery techniques often search across potentially exponential combinations of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04386","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/2203.04386/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":"2203.04386","created_at":"2026-07-05T04:03:17.668643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.04386v1","created_at":"2026-07-05T04:03:17.668643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04386","created_at":"2026-07-05T04:03:17.668643+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSI5YNJZXHCR","created_at":"2026-07-05T04:03:17.668643+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSI5YNJZXHCRQTRD","created_at":"2026-07-05T04:03:17.668643+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSI5YNJZ","created_at":"2026-07-05T04:03:17.668643+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/ZSI5YNJZXHCRQTRDCKVYKM2EXP","json":"https://pith.science/pith/ZSI5YNJZXHCRQTRDCKVYKM2EXP.json","graph_json":"https://pith.science/api/pith-number/ZSI5YNJZXHCRQTRDCKVYKM2EXP/graph.json","events_json":"https://pith.science/api/pith-number/ZSI5YNJZXHCRQTRDCKVYKM2EXP/events.json","paper":"https://pith.science/paper/ZSI5YNJZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZSI5YNJZXHCRQTRDCKVYKM2EXP","download_json":"https://pith.science/pith/ZSI5YNJZXHCRQTRDCKVYKM2EXP.json","view_paper":"https://pith.science/paper/ZSI5YNJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.04386&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSI5YNJZXHCRQTRDCKVYKM2EXP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSI5YNJZXHCRQTRDCKVYKM2EXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSI5YNJZXHCRQTRDCKVYKM2EXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSI5YNJZXHCRQTRDCKVYKM2EXP/action/storage_attestation","attest_author":"https://pith.science/pith/ZSI5YNJZXHCRQTRDCKVYKM2EXP/action/author_attestation","sign_citation":"https://pith.science/pith/ZSI5YNJZXHCRQTRDCKVYKM2EXP/action/citation_signature","submit_replication":"https://pith.science/pith/ZSI5YNJZXHCRQTRDCKVYKM2EXP/action/replication_record"}},"created_at":"2026-07-05T04:03:17.668643+00:00","updated_at":"2026-07-05T04:03:17.668643+00:00"}