{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZUQGASG3POCRIMIXM7OFL22ARD","short_pith_number":"pith:ZUQGASG3","schema_version":"1.0","canonical_sha256":"cd206048db7b8514311767dc55eb4088d57e9bc2369ee43db115041aa16f10dc","source":{"kind":"arxiv","id":"2410.06815","version":1},"attestation_state":"computed","paper":{"title":"Shap-Select: Lightweight Feature Selection Using SHAP Values and Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baran Koseoglu, Egor Kraev, Luca Traverso, Mohammed Topiwalla","submitted_at":"2024-10-09T12:14:06Z","abstract_excerpt":"Feature selection is an essential process in machine learning, especially when dealing with high-dimensional datasets. It helps reduce the complexity of machine learning models, improve performance, mitigate overfitting, and decrease computation time. This paper presents a novel feature selection framework, shap-select. The framework conducts a linear or logistic regression of the target on the Shapley values of the features, on the validation set, and uses the signs and significance levels of the regression coefficients to implement an efficient heuristic for feature selection in tabular regr"},"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":"2410.06815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T12:14:06Z","cross_cats_sorted":[],"title_canon_sha256":"d113a9c2c552eda43c65749fead8a5260485144225fd186bf2cabfd96f0edf6a","abstract_canon_sha256":"ab4cade44032fd36f0afd08c536abdc63c2ed13b952c830ca1de52fb77f06de9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:07.262274Z","signature_b64":"Oh67bTlBwtX4ICcVsotwhlqD5S7KZYGdrYv7fkDvKvx/CcVQsLZsfr0iB4197IpWBoK072GLeyuWoggskKQtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd206048db7b8514311767dc55eb4088d57e9bc2369ee43db115041aa16f10dc","last_reissued_at":"2026-07-05T09:18:07.261843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:07.261843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shap-Select: Lightweight Feature Selection Using SHAP Values and Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baran Koseoglu, Egor Kraev, Luca Traverso, Mohammed Topiwalla","submitted_at":"2024-10-09T12:14:06Z","abstract_excerpt":"Feature selection is an essential process in machine learning, especially when dealing with high-dimensional datasets. It helps reduce the complexity of machine learning models, improve performance, mitigate overfitting, and decrease computation time. This paper presents a novel feature selection framework, shap-select. The framework conducts a linear or logistic regression of the target on the Shapley values of the features, on the validation set, and uses the signs and significance levels of the regression coefficients to implement an efficient heuristic for feature selection in tabular regr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06815","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/2410.06815/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":"2410.06815","created_at":"2026-07-05T09:18:07.261916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06815v1","created_at":"2026-07-05T09:18:07.261916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06815","created_at":"2026-07-05T09:18:07.261916+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUQGASG3POCR","created_at":"2026-07-05T09:18:07.261916+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUQGASG3POCRIMIX","created_at":"2026-07-05T09:18:07.261916+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUQGASG3","created_at":"2026-07-05T09:18:07.261916+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/ZUQGASG3POCRIMIXM7OFL22ARD","json":"https://pith.science/pith/ZUQGASG3POCRIMIXM7OFL22ARD.json","graph_json":"https://pith.science/api/pith-number/ZUQGASG3POCRIMIXM7OFL22ARD/graph.json","events_json":"https://pith.science/api/pith-number/ZUQGASG3POCRIMIXM7OFL22ARD/events.json","paper":"https://pith.science/paper/ZUQGASG3"},"agent_actions":{"view_html":"https://pith.science/pith/ZUQGASG3POCRIMIXM7OFL22ARD","download_json":"https://pith.science/pith/ZUQGASG3POCRIMIXM7OFL22ARD.json","view_paper":"https://pith.science/paper/ZUQGASG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06815&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUQGASG3POCRIMIXM7OFL22ARD/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUQGASG3POCRIMIXM7OFL22ARD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUQGASG3POCRIMIXM7OFL22ARD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUQGASG3POCRIMIXM7OFL22ARD/action/storage_attestation","attest_author":"https://pith.science/pith/ZUQGASG3POCRIMIXM7OFL22ARD/action/author_attestation","sign_citation":"https://pith.science/pith/ZUQGASG3POCRIMIXM7OFL22ARD/action/citation_signature","submit_replication":"https://pith.science/pith/ZUQGASG3POCRIMIXM7OFL22ARD/action/replication_record"}},"created_at":"2026-07-05T09:18:07.261916+00:00","updated_at":"2026-07-05T09:18:07.261916+00:00"}