{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XVGVOYWAQSF75VVYZ4S6E7M4ML","short_pith_number":"pith:XVGVOYWA","schema_version":"1.0","canonical_sha256":"bd4d5762c0848bfed6b8cf25e27d9c62c0af1019e940b60ba73322b4945072b4","source":{"kind":"arxiv","id":"2104.12199","version":2},"attestation_state":"computed","paper":{"title":"Sampling Permutations for Shapley Value Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.CO"],"primary_cat":"stat.ML","authors_text":"Eibe Frank, Geoffrey Holmes, Joshua Cooper, Rory Mitchell","submitted_at":"2021-04-25T16:44:18Z","abstract_excerpt":"Game-theoretic attribution techniques based on Shapley values are used to interpret black-box machine learning models, but their exact calculation is generally NP-hard, requiring approximation methods for non-trivial models. As the computation of Shapley values can be expressed as a summation over a set of permutations, a common approach is to sample a subset of these permutations for approximation. Unfortunately, standard Monte Carlo sampling methods can exhibit slow convergence, and more sophisticated quasi-Monte Carlo methods have not yet been applied to the space of permutations. To addres"},"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":"2104.12199","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2021-04-25T16:44:18Z","cross_cats_sorted":["cs.LG","math.CO"],"title_canon_sha256":"91f223d620ca666db0618836992ff2e6fce4a80a447e9e9337611ebf75ab5bb6","abstract_canon_sha256":"383f34657897111bf42d79e6c0c7945e1a0faec82bfaec4e04a40b180830b175"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:47.476087Z","signature_b64":"1uquXLRRWqNQkdgG83/rzgpU3joax6ZvujTRhcie740P3TGYa4kOuFAO8CDb3tvpQTipVkw63zr3rX8HPCAECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4d5762c0848bfed6b8cf25e27d9c62c0af1019e940b60ba73322b4945072b4","last_reissued_at":"2026-07-05T03:53:47.475628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:47.475628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling Permutations for Shapley Value Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.CO"],"primary_cat":"stat.ML","authors_text":"Eibe Frank, Geoffrey Holmes, Joshua Cooper, Rory Mitchell","submitted_at":"2021-04-25T16:44:18Z","abstract_excerpt":"Game-theoretic attribution techniques based on Shapley values are used to interpret black-box machine learning models, but their exact calculation is generally NP-hard, requiring approximation methods for non-trivial models. As the computation of Shapley values can be expressed as a summation over a set of permutations, a common approach is to sample a subset of these permutations for approximation. Unfortunately, standard Monte Carlo sampling methods can exhibit slow convergence, and more sophisticated quasi-Monte Carlo methods have not yet been applied to the space of permutations. To addres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12199","kind":"arxiv","version":2},"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/2104.12199/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":"2104.12199","created_at":"2026-07-05T03:53:47.475690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.12199v2","created_at":"2026-07-05T03:53:47.475690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12199","created_at":"2026-07-05T03:53:47.475690+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVGVOYWAQSF7","created_at":"2026-07-05T03:53:47.475690+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVGVOYWAQSF75VVY","created_at":"2026-07-05T03:53:47.475690+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVGVOYWA","created_at":"2026-07-05T03:53:47.475690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00989","citing_title":"Model-Agnostic FDR Control via Group Gaussian Mirror and Permutation SHAP","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML","json":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML.json","graph_json":"https://pith.science/api/pith-number/XVGVOYWAQSF75VVYZ4S6E7M4ML/graph.json","events_json":"https://pith.science/api/pith-number/XVGVOYWAQSF75VVYZ4S6E7M4ML/events.json","paper":"https://pith.science/paper/XVGVOYWA"},"agent_actions":{"view_html":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML","download_json":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML.json","view_paper":"https://pith.science/paper/XVGVOYWA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.12199&json=true","fetch_graph":"https://pith.science/api/pith-number/XVGVOYWAQSF75VVYZ4S6E7M4ML/graph.json","fetch_events":"https://pith.science/api/pith-number/XVGVOYWAQSF75VVYZ4S6E7M4ML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML/action/storage_attestation","attest_author":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML/action/author_attestation","sign_citation":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML/action/citation_signature","submit_replication":"https://pith.science/pith/XVGVOYWAQSF75VVYZ4S6E7M4ML/action/replication_record"}},"created_at":"2026-07-05T03:53:47.475690+00:00","updated_at":"2026-07-05T03:53:47.475690+00:00"}