{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OPPL3SKXGYPPCEC5NVES2NDOFJ","short_pith_number":"pith:OPPL3SKX","schema_version":"1.0","canonical_sha256":"73debdc957361ef1105d6d492d346e2a68dc2f02263a45ba3d43400acc3b4247","source":{"kind":"arxiv","id":"2509.00846","version":1},"attestation_state":"computed","paper":{"title":"Causal SHAP: Feature Attribution with Dependency Awareness through Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Li Rong Wang, Siyuan Liu, Woon Yee Ng, Xiuyi Fan","submitted_at":"2025-08-31T13:31:34Z","abstract_excerpt":"Explaining machine learning (ML) predictions has become crucial as ML models are increasingly deployed in high-stakes domains such as healthcare. While SHapley Additive exPlanations (SHAP) is widely used for model interpretability, it fails to differentiate between causality and correlation, often misattributing feature importance when features are highly correlated. We propose Causal SHAP, a novel framework that integrates causal relationships into feature attribution while preserving many desirable properties of SHAP. By combining the Peter-Clark (PC) algorithm for causal discovery and the I"},"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":"2509.00846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-31T13:31:34Z","cross_cats_sorted":["cs.AI","stat.ME"],"title_canon_sha256":"fa31ca0f2635a5d72b6520efb83a00e32c6c9c8a12844acf315e75a341a2ba98","abstract_canon_sha256":"b1114adac79105e4c45a5f5091689cb9cd293133db56103b34fe39587e362cc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:23.596321Z","signature_b64":"3nzkf90tIooiykrzt+NJtQf6iUTIccwDUp/9T5sBn4aTY4SfrSDr6AkPy+r8J/2ok2kpTyf5vzh6LuM1zF9QAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73debdc957361ef1105d6d492d346e2a68dc2f02263a45ba3d43400acc3b4247","last_reissued_at":"2026-07-05T12:02:23.595895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:23.595895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causal SHAP: Feature Attribution with Dependency Awareness through Causal Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Li Rong Wang, Siyuan Liu, Woon Yee Ng, Xiuyi Fan","submitted_at":"2025-08-31T13:31:34Z","abstract_excerpt":"Explaining machine learning (ML) predictions has become crucial as ML models are increasingly deployed in high-stakes domains such as healthcare. While SHapley Additive exPlanations (SHAP) is widely used for model interpretability, it fails to differentiate between causality and correlation, often misattributing feature importance when features are highly correlated. We propose Causal SHAP, a novel framework that integrates causal relationships into feature attribution while preserving many desirable properties of SHAP. By combining the Peter-Clark (PC) algorithm for causal discovery and the I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00846","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/2509.00846/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":"2509.00846","created_at":"2026-07-05T12:02:23.595950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00846v1","created_at":"2026-07-05T12:02:23.595950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00846","created_at":"2026-07-05T12:02:23.595950+00:00"},{"alias_kind":"pith_short_12","alias_value":"OPPL3SKXGYPP","created_at":"2026-07-05T12:02:23.595950+00:00"},{"alias_kind":"pith_short_16","alias_value":"OPPL3SKXGYPPCEC5","created_at":"2026-07-05T12:02:23.595950+00:00"},{"alias_kind":"pith_short_8","alias_value":"OPPL3SKX","created_at":"2026-07-05T12:02:23.595950+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/OPPL3SKXGYPPCEC5NVES2NDOFJ","json":"https://pith.science/pith/OPPL3SKXGYPPCEC5NVES2NDOFJ.json","graph_json":"https://pith.science/api/pith-number/OPPL3SKXGYPPCEC5NVES2NDOFJ/graph.json","events_json":"https://pith.science/api/pith-number/OPPL3SKXGYPPCEC5NVES2NDOFJ/events.json","paper":"https://pith.science/paper/OPPL3SKX"},"agent_actions":{"view_html":"https://pith.science/pith/OPPL3SKXGYPPCEC5NVES2NDOFJ","download_json":"https://pith.science/pith/OPPL3SKXGYPPCEC5NVES2NDOFJ.json","view_paper":"https://pith.science/paper/OPPL3SKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00846&json=true","fetch_graph":"https://pith.science/api/pith-number/OPPL3SKXGYPPCEC5NVES2NDOFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OPPL3SKXGYPPCEC5NVES2NDOFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OPPL3SKXGYPPCEC5NVES2NDOFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OPPL3SKXGYPPCEC5NVES2NDOFJ/action/storage_attestation","attest_author":"https://pith.science/pith/OPPL3SKXGYPPCEC5NVES2NDOFJ/action/author_attestation","sign_citation":"https://pith.science/pith/OPPL3SKXGYPPCEC5NVES2NDOFJ/action/citation_signature","submit_replication":"https://pith.science/pith/OPPL3SKXGYPPCEC5NVES2NDOFJ/action/replication_record"}},"created_at":"2026-07-05T12:02:23.595950+00:00","updated_at":"2026-07-05T12:02:23.595950+00:00"}