{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T3DTCPPX3LQQKZLAAKAP7JHC2R","short_pith_number":"pith:T3DTCPPX","schema_version":"1.0","canonical_sha256":"9ec7313df7dae10565600280ffa4e2d44b8bfea38fdd5f09e455e2e3f5de393b","source":{"kind":"arxiv","id":"2306.14672","version":1},"attestation_state":"computed","paper":{"title":"PWSHAP: A Path-Wise Explanation Model for Targeted Variables","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Holmes, Karla Diaz-Ordaz, Lucile Ter-Minassian, Oscar Clivio, Robin J. Evans","submitted_at":"2023-06-26T13:08:21Z","abstract_excerpt":"Predictive black-box models can exhibit high accuracy but their opaque nature hinders their uptake in safety-critical deployment environments. Explanation methods (XAI) can provide confidence for decision-making through increased transparency. However, existing XAI methods are not tailored towards models in sensitive domains where one predictor is of special interest, such as a treatment effect in a clinical model, or ethnicity in policy models. We introduce Path-Wise Shapley effects (PWSHAP), a framework for assessing the targeted effect of a binary (e.g.~treatment) variable from a complex ou"},"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":"2306.14672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-26T13:08:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"50d64e11b840662985a93b83467c3134769ee68ad3c21a4622548a78a1de827e","abstract_canon_sha256":"318d494256c68d063da3bc224fb3c7e7e8d22724d66fa2404d1fd28eee78ccc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:39.459099Z","signature_b64":"unHT+/Rdz7HQFen69Fy6o0IC2DWfnoN/OgWmdQlgqRg31EQ7+TSUdUOjmTH0auTwXCcBtPPZo+48OyB8wTOXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ec7313df7dae10565600280ffa4e2d44b8bfea38fdd5f09e455e2e3f5de393b","last_reissued_at":"2026-07-05T06:24:39.458655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:39.458655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PWSHAP: A Path-Wise Explanation Model for Targeted Variables","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chris Holmes, Karla Diaz-Ordaz, Lucile Ter-Minassian, Oscar Clivio, Robin J. Evans","submitted_at":"2023-06-26T13:08:21Z","abstract_excerpt":"Predictive black-box models can exhibit high accuracy but their opaque nature hinders their uptake in safety-critical deployment environments. Explanation methods (XAI) can provide confidence for decision-making through increased transparency. However, existing XAI methods are not tailored towards models in sensitive domains where one predictor is of special interest, such as a treatment effect in a clinical model, or ethnicity in policy models. We introduce Path-Wise Shapley effects (PWSHAP), a framework for assessing the targeted effect of a binary (e.g.~treatment) variable from a complex ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14672","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/2306.14672/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":"2306.14672","created_at":"2026-07-05T06:24:39.458714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14672v1","created_at":"2026-07-05T06:24:39.458714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14672","created_at":"2026-07-05T06:24:39.458714+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3DTCPPX3LQQ","created_at":"2026-07-05T06:24:39.458714+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3DTCPPX3LQQKZLA","created_at":"2026-07-05T06:24:39.458714+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3DTCPPX","created_at":"2026-07-05T06:24:39.458714+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/T3DTCPPX3LQQKZLAAKAP7JHC2R","json":"https://pith.science/pith/T3DTCPPX3LQQKZLAAKAP7JHC2R.json","graph_json":"https://pith.science/api/pith-number/T3DTCPPX3LQQKZLAAKAP7JHC2R/graph.json","events_json":"https://pith.science/api/pith-number/T3DTCPPX3LQQKZLAAKAP7JHC2R/events.json","paper":"https://pith.science/paper/T3DTCPPX"},"agent_actions":{"view_html":"https://pith.science/pith/T3DTCPPX3LQQKZLAAKAP7JHC2R","download_json":"https://pith.science/pith/T3DTCPPX3LQQKZLAAKAP7JHC2R.json","view_paper":"https://pith.science/paper/T3DTCPPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14672&json=true","fetch_graph":"https://pith.science/api/pith-number/T3DTCPPX3LQQKZLAAKAP7JHC2R/graph.json","fetch_events":"https://pith.science/api/pith-number/T3DTCPPX3LQQKZLAAKAP7JHC2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3DTCPPX3LQQKZLAAKAP7JHC2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3DTCPPX3LQQKZLAAKAP7JHC2R/action/storage_attestation","attest_author":"https://pith.science/pith/T3DTCPPX3LQQKZLAAKAP7JHC2R/action/author_attestation","sign_citation":"https://pith.science/pith/T3DTCPPX3LQQKZLAAKAP7JHC2R/action/citation_signature","submit_replication":"https://pith.science/pith/T3DTCPPX3LQQKZLAAKAP7JHC2R/action/replication_record"}},"created_at":"2026-07-05T06:24:39.458714+00:00","updated_at":"2026-07-05T06:24:39.458714+00:00"}