{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JAHY5YSZSPVSCBEETENHIDA6MS","short_pith_number":"pith:JAHY5YSZ","schema_version":"1.0","canonical_sha256":"480f8ee25993eb210484991a740c1e64a6f80b24064d112323114185e730c073","source":{"kind":"arxiv","id":"2408.02529","version":2},"attestation_state":"computed","paper":{"title":"Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kevin McAreavey, Qi Zhang, Weiru Liu, Yiwei Shi","submitted_at":"2024-08-05T14:49:12Z","abstract_excerpt":"This paper introduces a novel approach Counterfactual Shapley Values (CSV), which enhances explainability in reinforcement learning (RL) by integrating counterfactual analysis with Shapley Values. The approach aims to quantify and compare the contributions of different state dimensions to various action choices. To more accurately analyze these impacts, we introduce new characteristic value functions, the ``Counterfactual Difference Characteristic Value\" and the ``Average Counterfactual Difference Characteristic Value.\" These functions help calculate the Shapley values to evaluate the differen"},"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":"2408.02529","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-05T14:49:12Z","cross_cats_sorted":[],"title_canon_sha256":"802ab6508a191a9ebea9fefcf52f45d5806094260a92deec3d3fb435af300a7a","abstract_canon_sha256":"5f6a78b042a5608df2fec0600ce58e69e9d14fea58da0be30d322387714c3fa5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:38.399113Z","signature_b64":"xhsGBZodbqX1aRDIPXrmYzEpw2TVuIJIKfwgbjd6E6e2fDAVFrOtdIVcGykae9sIJ40s0751k3LB8tUeVgQXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"480f8ee25993eb210484991a740c1e64a6f80b24064d112323114185e730c073","last_reissued_at":"2026-07-05T08:52:38.398659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:38.398659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining Reinforcement Learning: A Counterfactual Shapley Values Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Kevin McAreavey, Qi Zhang, Weiru Liu, Yiwei Shi","submitted_at":"2024-08-05T14:49:12Z","abstract_excerpt":"This paper introduces a novel approach Counterfactual Shapley Values (CSV), which enhances explainability in reinforcement learning (RL) by integrating counterfactual analysis with Shapley Values. The approach aims to quantify and compare the contributions of different state dimensions to various action choices. To more accurately analyze these impacts, we introduce new characteristic value functions, the ``Counterfactual Difference Characteristic Value\" and the ``Average Counterfactual Difference Characteristic Value.\" These functions help calculate the Shapley values to evaluate the differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02529","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/2408.02529/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":"2408.02529","created_at":"2026-07-05T08:52:38.398721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02529v2","created_at":"2026-07-05T08:52:38.398721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02529","created_at":"2026-07-05T08:52:38.398721+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAHY5YSZSPVS","created_at":"2026-07-05T08:52:38.398721+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAHY5YSZSPVSCBEE","created_at":"2026-07-05T08:52:38.398721+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAHY5YSZ","created_at":"2026-07-05T08:52:38.398721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01460","citing_title":"A Comprehensive Study of Shapley Value in Data Analytics","ref_index":128,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS","json":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS.json","graph_json":"https://pith.science/api/pith-number/JAHY5YSZSPVSCBEETENHIDA6MS/graph.json","events_json":"https://pith.science/api/pith-number/JAHY5YSZSPVSCBEETENHIDA6MS/events.json","paper":"https://pith.science/paper/JAHY5YSZ"},"agent_actions":{"view_html":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS","download_json":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS.json","view_paper":"https://pith.science/paper/JAHY5YSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02529&json=true","fetch_graph":"https://pith.science/api/pith-number/JAHY5YSZSPVSCBEETENHIDA6MS/graph.json","fetch_events":"https://pith.science/api/pith-number/JAHY5YSZSPVSCBEETENHIDA6MS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS/action/storage_attestation","attest_author":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS/action/author_attestation","sign_citation":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS/action/citation_signature","submit_replication":"https://pith.science/pith/JAHY5YSZSPVSCBEETENHIDA6MS/action/replication_record"}},"created_at":"2026-07-05T08:52:38.398721+00:00","updated_at":"2026-07-05T08:52:38.398721+00:00"}