{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TRYC5IXEOLPQBRIUVX7T4KAWT4","short_pith_number":"pith:TRYC5IXE","schema_version":"1.0","canonical_sha256":"9c702ea2e472df00c514adff3e28169f1bc2c8060bf23ed748e469c62228e6fc","source":{"kind":"arxiv","id":"2601.18608","version":3},"attestation_state":"computed","paper":{"title":"PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PolySHAP shows that the paired sampling heuristic in KernelSHAP produces exactly the same Shapley approximations as fitting a second-degree polynomial.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christopher Musco, Fabian Fumagalli, R. Teal Witter","submitted_at":"2026-01-26T15:47:45Z","abstract_excerpt":"Shapley values have emerged as a central game-theoretic tool in explainable AI (XAI). However, computing Shapley values exactly requires $2^d$ game evaluations for a model with $d$ features. Lundberg and Lee's KernelSHAP algorithm has emerged as a leading method for avoiding this exponential cost. KernelSHAP approximates Shapley values by approximating the game as a linear function, which is fit using a small number of game evaluations for random feature subsets.\n  In this work, we extend KernelSHAP by approximating the game via higher degree polynomials, which capture non-linear interactions "},"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":true},"canonical_record":{"source":{"id":"2601.18608","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-26T15:47:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5553daa5904076e2c119b996f7450e9a4cea8eb6f9e6f1579ab8f5e165881b0c","abstract_canon_sha256":"9f06d08e3110b00ae045bca22a30fafe44b2b6f2f8e9d0592ae99b2d8fc2805c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:31.854098Z","signature_b64":"GFuYqG/HQzQ+wHy231nUMotdoOW3I2wey+GfEWP96SNdm6MlYF+VpBYFiWkNhOT89r+H3aRy0S8dQNsjEAk7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c702ea2e472df00c514adff3e28169f1bc2c8060bf23ed748e469c62228e6fc","last_reissued_at":"2026-05-18T02:44:31.853597Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:31.853597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PolySHAP shows that the paired sampling heuristic in KernelSHAP produces exactly the same Shapley approximations as fitting a second-degree polynomial.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Christopher Musco, Fabian Fumagalli, R. Teal Witter","submitted_at":"2026-01-26T15:47:45Z","abstract_excerpt":"Shapley values have emerged as a central game-theoretic tool in explainable AI (XAI). However, computing Shapley values exactly requires $2^d$ game evaluations for a model with $d$ features. Lundberg and Lee's KernelSHAP algorithm has emerged as a leading method for avoiding this exponential cost. KernelSHAP approximates Shapley values by approximating the game as a linear function, which is fit using a small number of game evaluations for random feature subsets.\n  In this work, we extend KernelSHAP by approximating the game via higher degree polynomials, which capture non-linear interactions "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We prove that paired sampling outputs exactly the same Shapley value approximations as second-order PolySHAP, without ever fitting a degree 2 polynomial. To the best of our knowledge, this finding provides the first strong theoretical justification for the excellent practical performance of the paired sampling heuristic.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the underlying cooperative game value function admits a useful low-degree polynomial approximation under the sampling distribution used for KernelSHAP-style estimation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PolySHAP approximates Shapley values via polynomial regression and proves paired sampling equals its quadratic version, providing the first theoretical justification for that heuristic.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PolySHAP shows that the paired sampling heuristic in KernelSHAP produces exactly the same Shapley approximations as fitting a second-degree polynomial.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3b87e386a29c35b620689411f500761762e7b57e6d20dea2032b05a1c53eb9a0"},"source":{"id":"2601.18608","kind":"arxiv","version":3},"verdict":{"id":"a598b375-7a5d-4235-aaac-0e4905a637bc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T11:14:21.184479Z","strongest_claim":"We prove that paired sampling outputs exactly the same Shapley value approximations as second-order PolySHAP, without ever fitting a degree 2 polynomial. To the best of our knowledge, this finding provides the first strong theoretical justification for the excellent practical performance of the paired sampling heuristic.","one_line_summary":"PolySHAP approximates Shapley values via polynomial regression and proves paired sampling equals its quadratic version, providing the first theoretical justification for that heuristic.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the underlying cooperative game value function admits a useful low-degree polynomial approximation under the sampling distribution used for KernelSHAP-style estimation.","pith_extraction_headline":"PolySHAP shows that the paired sampling heuristic in KernelSHAP produces exactly the same Shapley approximations as fitting a second-degree polynomial."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8020b9188bd46df9dc350218c84d4e15f64dad05abd3b817cdb8bb828bff3a14"},"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":"2601.18608","created_at":"2026-05-18T02:44:31.853673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18608v3","created_at":"2026-05-18T02:44:31.853673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18608","created_at":"2026-05-18T02:44:31.853673+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRYC5IXEOLPQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRYC5IXEOLPQBRIU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRYC5IXE","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.05870","citing_title":"QuadraSHAP: Stable and Scalable Shapley Values for Product Games via Gauss-Legendre Quadrature","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4","json":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4.json","graph_json":"https://pith.science/api/pith-number/TRYC5IXEOLPQBRIUVX7T4KAWT4/graph.json","events_json":"https://pith.science/api/pith-number/TRYC5IXEOLPQBRIUVX7T4KAWT4/events.json","paper":"https://pith.science/paper/TRYC5IXE"},"agent_actions":{"view_html":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4","download_json":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4.json","view_paper":"https://pith.science/paper/TRYC5IXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18608&json=true","fetch_graph":"https://pith.science/api/pith-number/TRYC5IXEOLPQBRIUVX7T4KAWT4/graph.json","fetch_events":"https://pith.science/api/pith-number/TRYC5IXEOLPQBRIUVX7T4KAWT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4/action/storage_attestation","attest_author":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4/action/author_attestation","sign_citation":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4/action/citation_signature","submit_replication":"https://pith.science/pith/TRYC5IXEOLPQBRIUVX7T4KAWT4/action/replication_record"}},"created_at":"2026-05-18T02:44:31.853673+00:00","updated_at":"2026-05-18T02:44:31.853673+00:00"}