{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3GIKAT6CZHUGRHOBUBFECAPAHT","short_pith_number":"pith:3GIKAT6C","schema_version":"1.0","canonical_sha256":"d990a04fc2c9e8689dc1a04a4101e03cec73270d9533957f8789c6649a40306d","source":{"kind":"arxiv","id":"2409.16787","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Feature Selection and Interpretability in AI Regression Tasks Through Feature Attribution","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Hinterleitner, Christoph Leitenmeier, Richard Schulz, Sebastian Spengler, Thomas Bartz-Beielstein, Thomas Winter","submitted_at":"2024-09-25T09:50:51Z","abstract_excerpt":"Research in Explainable Artificial Intelligence (XAI) is increasing, aiming to make deep learning models more transparent. Most XAI methods focus on justifying the decisions made by Artificial Intelligence (AI) systems in security-relevant applications. However, relatively little attention has been given to using these methods to improve the performance and robustness of deep learning algorithms. Additionally, much of the existing XAI work primarily addresses classification problems. In this study, we investigate the potential of feature attribution methods to filter out uninformative features"},"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":"2409.16787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-25T09:50:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e53381fa969ef52679282200816a80cc79357d5d2a829839994f9dc7a4da0bce","abstract_canon_sha256":"d17f8ae4d47f74d3012fbeee338ed3d7e39381477fa7eb9021550a4cd03ad36b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:39.321145Z","signature_b64":"cXxCQT3CTukw4FsMtyJjPqvGMGP9nnWKPlWBdfoljto+DgxCf9F7vujeVwp53uVGDojIppkixJnZdF8pu9DdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d990a04fc2c9e8689dc1a04a4101e03cec73270d9533957f8789c6649a40306d","last_reissued_at":"2026-07-05T09:11:39.320583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:39.320583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Feature Selection and Interpretability in AI Regression Tasks Through Feature Attribution","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Hinterleitner, Christoph Leitenmeier, Richard Schulz, Sebastian Spengler, Thomas Bartz-Beielstein, Thomas Winter","submitted_at":"2024-09-25T09:50:51Z","abstract_excerpt":"Research in Explainable Artificial Intelligence (XAI) is increasing, aiming to make deep learning models more transparent. Most XAI methods focus on justifying the decisions made by Artificial Intelligence (AI) systems in security-relevant applications. However, relatively little attention has been given to using these methods to improve the performance and robustness of deep learning algorithms. Additionally, much of the existing XAI work primarily addresses classification problems. In this study, we investigate the potential of feature attribution methods to filter out uninformative features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16787","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/2409.16787/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":"2409.16787","created_at":"2026-07-05T09:11:39.320655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16787v1","created_at":"2026-07-05T09:11:39.320655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16787","created_at":"2026-07-05T09:11:39.320655+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GIKAT6CZHUG","created_at":"2026-07-05T09:11:39.320655+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GIKAT6CZHUGRHOB","created_at":"2026-07-05T09:11:39.320655+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GIKAT6C","created_at":"2026-07-05T09:11:39.320655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.08667","citing_title":"Minimal Data, Maximum Clarity: A Heuristic for Explaining Optimization","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT","json":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT.json","graph_json":"https://pith.science/api/pith-number/3GIKAT6CZHUGRHOBUBFECAPAHT/graph.json","events_json":"https://pith.science/api/pith-number/3GIKAT6CZHUGRHOBUBFECAPAHT/events.json","paper":"https://pith.science/paper/3GIKAT6C"},"agent_actions":{"view_html":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT","download_json":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT.json","view_paper":"https://pith.science/paper/3GIKAT6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16787&json=true","fetch_graph":"https://pith.science/api/pith-number/3GIKAT6CZHUGRHOBUBFECAPAHT/graph.json","fetch_events":"https://pith.science/api/pith-number/3GIKAT6CZHUGRHOBUBFECAPAHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT/action/storage_attestation","attest_author":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT/action/author_attestation","sign_citation":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT/action/citation_signature","submit_replication":"https://pith.science/pith/3GIKAT6CZHUGRHOBUBFECAPAHT/action/replication_record"}},"created_at":"2026-07-05T09:11:39.320655+00:00","updated_at":"2026-07-05T09:11:39.320655+00:00"}