{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:777735INTX2HQI5Y6ZQQ6I22II","short_pith_number":"pith:777735IN","schema_version":"1.0","canonical_sha256":"fffffdf50d9df47823b8f6610f235a42297cfc33532f68c9bdecf1c61caf7cbc","source":{"kind":"arxiv","id":"2006.16234","version":1},"attestation_state":"computed","paper":{"title":"True to the Model or True to the Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugh Chen, Joseph D. Janizek, Scott Lundberg, Su-In Lee","submitted_at":"2020-06-29T17:54:39Z","abstract_excerpt":"A variety of recent papers discuss the application of Shapley values, a concept for explaining coalitional games, for feature attribution in machine learning. However, the correct way to connect a machine learning model to a coalitional game has been a source of controversy. The two main approaches that have been proposed differ in the way that they condition on known features, using either (1) an interventional or (2) an observational conditional expectation. While previous work has argued that one of the two approaches is preferable in general, we argue that the choice is application depende"},"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":"2006.16234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T17:54:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"18d8256d8420f26fb46ecf32df1245a5551d35cea5450201a0fc57441fff5c0c","abstract_canon_sha256":"dfba0baf0999770dfd88dba1bf0de8366ea06a2be1bbb8e10b4cd862eca63093"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:13.638740Z","signature_b64":"OcUBcrPjBuAfToYfDJC9IcnBGOnj0MWhxwQlCC/rOKKIGyTfssIbHN2MlzPY9l65ILy4Zq2+bF9USD/QA1z9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fffffdf50d9df47823b8f6610f235a42297cfc33532f68c9bdecf1c61caf7cbc","last_reissued_at":"2026-07-05T01:14:13.638291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:13.638291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"True to the Model or True to the Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hugh Chen, Joseph D. Janizek, Scott Lundberg, Su-In Lee","submitted_at":"2020-06-29T17:54:39Z","abstract_excerpt":"A variety of recent papers discuss the application of Shapley values, a concept for explaining coalitional games, for feature attribution in machine learning. However, the correct way to connect a machine learning model to a coalitional game has been a source of controversy. The two main approaches that have been proposed differ in the way that they condition on known features, using either (1) an interventional or (2) an observational conditional expectation. While previous work has argued that one of the two approaches is preferable in general, we argue that the choice is application depende"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16234","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/2006.16234/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":"2006.16234","created_at":"2026-07-05T01:14:13.638360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16234v1","created_at":"2026-07-05T01:14:13.638360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16234","created_at":"2026-07-05T01:14:13.638360+00:00"},{"alias_kind":"pith_short_12","alias_value":"777735INTX2H","created_at":"2026-07-05T01:14:13.638360+00:00"},{"alias_kind":"pith_short_16","alias_value":"777735INTX2HQI5Y","created_at":"2026-07-05T01:14:13.638360+00:00"},{"alias_kind":"pith_short_8","alias_value":"777735IN","created_at":"2026-07-05T01:14:13.638360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19118","citing_title":"Analysing drivers and interdependencies in European electricity markets using XAI","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2511.09376","citing_title":"From Decision Trees to Boolean Logic: A Fast and Unified SHAP Algorithm","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22662","citing_title":"Rethinking XAI Evaluation: A Human-Centered Audit of Shapley Benchmarks in High-Stakes Settings","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05870","citing_title":"QuadraSHAP: Stable and Scalable Shapley Values for Product Games via Gauss-Legendre Quadrature","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II","json":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II.json","graph_json":"https://pith.science/api/pith-number/777735INTX2HQI5Y6ZQQ6I22II/graph.json","events_json":"https://pith.science/api/pith-number/777735INTX2HQI5Y6ZQQ6I22II/events.json","paper":"https://pith.science/paper/777735IN"},"agent_actions":{"view_html":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II","download_json":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II.json","view_paper":"https://pith.science/paper/777735IN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16234&json=true","fetch_graph":"https://pith.science/api/pith-number/777735INTX2HQI5Y6ZQQ6I22II/graph.json","fetch_events":"https://pith.science/api/pith-number/777735INTX2HQI5Y6ZQQ6I22II/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II/action/timestamp_anchor","attest_storage":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II/action/storage_attestation","attest_author":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II/action/author_attestation","sign_citation":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II/action/citation_signature","submit_replication":"https://pith.science/pith/777735INTX2HQI5Y6ZQQ6I22II/action/replication_record"}},"created_at":"2026-07-05T01:14:13.638360+00:00","updated_at":"2026-07-05T01:14:13.638360+00:00"}