{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UOAVXLLLDGQNO6LAJJM2QL7PYR","short_pith_number":"pith:UOAVXLLL","schema_version":"1.0","canonical_sha256":"a3815bad6b19a0d779604a59a82fefc45a7197259913d9510e1f6cc59b16345f","source":{"kind":"arxiv","id":"2307.10654","version":1},"attestation_state":"computed","paper":{"title":"Conditional expectation network for SHAP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mario V. W\\\"uthrich, Ronald Richman","submitted_at":"2023-07-20T07:35:15Z","abstract_excerpt":"A very popular model-agnostic technique for explaining predictive models is the SHapley Additive exPlanation (SHAP). The two most popular versions of SHAP are a conditional expectation version and an unconditional expectation version (the latter is also known as interventional SHAP). Except for tree-based methods, usually the unconditional version is used (for computational reasons). We provide a (surrogate) neural network approach which allows us to efficiently calculate the conditional version for both neural networks and other regression models, and which properly considers the dependence s"},"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":"2307.10654","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T07:35:15Z","cross_cats_sorted":["cs.CE","stat.AP","stat.ML"],"title_canon_sha256":"3a95acccf9fff7ff3283191ccb3e67dcea99cd1fd33ddc994f8f00d1441360fe","abstract_canon_sha256":"9222f8ec8fa4e7738987effa0d308e36b7b37ba0ad7abb4813176b1421eccfb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:08.216307Z","signature_b64":"xHWcXe/gL59m9aQs5+rjTM1ykH8OuQxrvoN+TSqAzj/lXZFbdNsf9Wo8A0bDUvfzIyVteTcwZq2urQeCm/OJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3815bad6b19a0d779604a59a82fefc45a7197259913d9510e1f6cc59b16345f","last_reissued_at":"2026-07-05T06:33:08.215898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:08.215898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional expectation network for SHAP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE","stat.AP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mario V. W\\\"uthrich, Ronald Richman","submitted_at":"2023-07-20T07:35:15Z","abstract_excerpt":"A very popular model-agnostic technique for explaining predictive models is the SHapley Additive exPlanation (SHAP). The two most popular versions of SHAP are a conditional expectation version and an unconditional expectation version (the latter is also known as interventional SHAP). Except for tree-based methods, usually the unconditional version is used (for computational reasons). We provide a (surrogate) neural network approach which allows us to efficiently calculate the conditional version for both neural networks and other regression models, and which properly considers the dependence s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10654","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/2307.10654/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":"2307.10654","created_at":"2026-07-05T06:33:08.215963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10654v1","created_at":"2026-07-05T06:33:08.215963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10654","created_at":"2026-07-05T06:33:08.215963+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOAVXLLLDGQN","created_at":"2026-07-05T06:33:08.215963+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOAVXLLLDGQNO6LA","created_at":"2026-07-05T06:33:08.215963+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOAVXLLL","created_at":"2026-07-05T06:33:08.215963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13158","citing_title":"On Model Extrapolation in Marginal Shapley Values","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR","json":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR.json","graph_json":"https://pith.science/api/pith-number/UOAVXLLLDGQNO6LAJJM2QL7PYR/graph.json","events_json":"https://pith.science/api/pith-number/UOAVXLLLDGQNO6LAJJM2QL7PYR/events.json","paper":"https://pith.science/paper/UOAVXLLL"},"agent_actions":{"view_html":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR","download_json":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR.json","view_paper":"https://pith.science/paper/UOAVXLLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10654&json=true","fetch_graph":"https://pith.science/api/pith-number/UOAVXLLLDGQNO6LAJJM2QL7PYR/graph.json","fetch_events":"https://pith.science/api/pith-number/UOAVXLLLDGQNO6LAJJM2QL7PYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR/action/storage_attestation","attest_author":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR/action/author_attestation","sign_citation":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR/action/citation_signature","submit_replication":"https://pith.science/pith/UOAVXLLLDGQNO6LAJJM2QL7PYR/action/replication_record"}},"created_at":"2026-07-05T06:33:08.215963+00:00","updated_at":"2026-07-05T06:33:08.215963+00:00"}