{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XHT3Z3SL4P2JHZ3AENL3ICRKXF","short_pith_number":"pith:XHT3Z3SL","schema_version":"1.0","canonical_sha256":"b9e7bcee4be3f493e7602357b40a2ab96c4a992719cfc0970a8baef8afeb3590","source":{"kind":"arxiv","id":"2405.11766","version":1},"attestation_state":"computed","paper":{"title":"From SHAP Scores to Feature Importance Scores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Joao Marques-Silva, Nicholas Asher, Olivier Letoffe, Xuanxiang Huang","submitted_at":"2024-05-20T03:52:41Z","abstract_excerpt":"A central goal of eXplainable Artificial Intelligence (XAI) is to assign relative importance to the features of a Machine Learning (ML) model given some prediction. The importance of this task of explainability by feature attribution is illustrated by the ubiquitous recent use of tools such as SHAP and LIME. Unfortunately, the exact computation of feature attributions, using the game-theoretical foundation underlying SHAP and LIME, can yield manifestly unsatisfactory results, that tantamount to reporting misleading relative feature importance. Recent work targeted rigorous feature attribution,"},"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":"2405.11766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-20T03:52:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9821361b5e8f108d1e3f3cb14100ce697f07340aadf201462e03714af44e7723","abstract_canon_sha256":"a6f05ccf9b8700312bffecb45ece78dc8dfe4b9d6c2d96a93081f932d2f7bc87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:55.421288Z","signature_b64":"DLsl6iHSe1GlxFtKit8jT3YeJnVM0HY4vCGlT5vEvbvA9m0eLMJldudrcfkBh0Ce+sXlW7n6QzCVclnmpYu+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9e7bcee4be3f493e7602357b40a2ab96c4a992719cfc0970a8baef8afeb3590","last_reissued_at":"2026-07-05T08:20:55.420593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:55.420593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From SHAP Scores to Feature Importance Scores","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Joao Marques-Silva, Nicholas Asher, Olivier Letoffe, Xuanxiang Huang","submitted_at":"2024-05-20T03:52:41Z","abstract_excerpt":"A central goal of eXplainable Artificial Intelligence (XAI) is to assign relative importance to the features of a Machine Learning (ML) model given some prediction. The importance of this task of explainability by feature attribution is illustrated by the ubiquitous recent use of tools such as SHAP and LIME. Unfortunately, the exact computation of feature attributions, using the game-theoretical foundation underlying SHAP and LIME, can yield manifestly unsatisfactory results, that tantamount to reporting misleading relative feature importance. Recent work targeted rigorous feature attribution,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11766","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/2405.11766/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":"2405.11766","created_at":"2026-07-05T08:20:55.420656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11766v1","created_at":"2026-07-05T08:20:55.420656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11766","created_at":"2026-07-05T08:20:55.420656+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHT3Z3SL4P2J","created_at":"2026-07-05T08:20:55.420656+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHT3Z3SL4P2JHZ3A","created_at":"2026-07-05T08:20:55.420656+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHT3Z3SL","created_at":"2026-07-05T08:20:55.420656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23147","citing_title":"Foundation Models for Clean Energy Forecasting: A Comprehensive Review","ref_index":200,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF","json":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF.json","graph_json":"https://pith.science/api/pith-number/XHT3Z3SL4P2JHZ3AENL3ICRKXF/graph.json","events_json":"https://pith.science/api/pith-number/XHT3Z3SL4P2JHZ3AENL3ICRKXF/events.json","paper":"https://pith.science/paper/XHT3Z3SL"},"agent_actions":{"view_html":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF","download_json":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF.json","view_paper":"https://pith.science/paper/XHT3Z3SL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11766&json=true","fetch_graph":"https://pith.science/api/pith-number/XHT3Z3SL4P2JHZ3AENL3ICRKXF/graph.json","fetch_events":"https://pith.science/api/pith-number/XHT3Z3SL4P2JHZ3AENL3ICRKXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF/action/storage_attestation","attest_author":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF/action/author_attestation","sign_citation":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF/action/citation_signature","submit_replication":"https://pith.science/pith/XHT3Z3SL4P2JHZ3AENL3ICRKXF/action/replication_record"}},"created_at":"2026-07-05T08:20:55.420656+00:00","updated_at":"2026-07-05T08:20:55.420656+00:00"}