{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QF3TNZ5OLRILVESHQAXWPPEWVL","short_pith_number":"pith:QF3TNZ5O","schema_version":"1.0","canonical_sha256":"817736e7ae5c50ba9247802f67bc96aac5b16f841e4d83f46ef48bef3d94538d","source":{"kind":"arxiv","id":"2505.07797","version":2},"attestation_state":"computed","paper":{"title":"A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Beechey, \\\"Ozg\\\"ur \\c{S}im\\c{s}ek, Thomas M. S. Smith","submitted_at":"2025-05-12T17:48:28Z","abstract_excerpt":"Reinforcement learning agents can achieve super-human performance in complex decision-making tasks, but their behaviour is often difficult to understand and explain. This lack of explanation limits deployment, especially in safety-critical settings where understanding and trust are essential. We identify three core explanatory targets that together provide a comprehensive view of reinforcement learning agents: behaviour, outcomes, and predictions. We develop a unified theoretical framework for explaining these three elements of reinforcement learning agents through the influence of individual "},"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":"2505.07797","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T17:48:28Z","cross_cats_sorted":[],"title_canon_sha256":"b84b6bd683d09cdecb78cd1cb96a53a4956d22bf9246b49e1ba505400e3c8265","abstract_canon_sha256":"bee3e4b5c73bae72eb7452fd51d13ce0df42e170129d812cb9fbc06f5fac7d47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:21.968837Z","signature_b64":"IlPIGTLJV8XeeaL1gScbIY4QuAqvE8tfqxf2Pia+qcP+RXfIqly3QEoosADgpnsPhpCT/mzxBJC93liYWoDhCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"817736e7ae5c50ba9247802f67bc96aac5b16f841e4d83f46ef48bef3d94538d","last_reissued_at":"2026-07-05T11:46:21.968345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:21.968345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Beechey, \\\"Ozg\\\"ur \\c{S}im\\c{s}ek, Thomas M. S. Smith","submitted_at":"2025-05-12T17:48:28Z","abstract_excerpt":"Reinforcement learning agents can achieve super-human performance in complex decision-making tasks, but their behaviour is often difficult to understand and explain. This lack of explanation limits deployment, especially in safety-critical settings where understanding and trust are essential. We identify three core explanatory targets that together provide a comprehensive view of reinforcement learning agents: behaviour, outcomes, and predictions. We develop a unified theoretical framework for explaining these three elements of reinforcement learning agents through the influence of individual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07797","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/2505.07797/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":"2505.07797","created_at":"2026-07-05T11:46:21.968404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07797v2","created_at":"2026-07-05T11:46:21.968404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07797","created_at":"2026-07-05T11:46:21.968404+00:00"},{"alias_kind":"pith_short_12","alias_value":"QF3TNZ5OLRIL","created_at":"2026-07-05T11:46:21.968404+00:00"},{"alias_kind":"pith_short_16","alias_value":"QF3TNZ5OLRILVESH","created_at":"2026-07-05T11:46:21.968404+00:00"},{"alias_kind":"pith_short_8","alias_value":"QF3TNZ5O","created_at":"2026-07-05T11:46:21.968404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL","json":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL.json","graph_json":"https://pith.science/api/pith-number/QF3TNZ5OLRILVESHQAXWPPEWVL/graph.json","events_json":"https://pith.science/api/pith-number/QF3TNZ5OLRILVESHQAXWPPEWVL/events.json","paper":"https://pith.science/paper/QF3TNZ5O"},"agent_actions":{"view_html":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL","download_json":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL.json","view_paper":"https://pith.science/paper/QF3TNZ5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07797&json=true","fetch_graph":"https://pith.science/api/pith-number/QF3TNZ5OLRILVESHQAXWPPEWVL/graph.json","fetch_events":"https://pith.science/api/pith-number/QF3TNZ5OLRILVESHQAXWPPEWVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL/action/storage_attestation","attest_author":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL/action/author_attestation","sign_citation":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL/action/citation_signature","submit_replication":"https://pith.science/pith/QF3TNZ5OLRILVESHQAXWPPEWVL/action/replication_record"}},"created_at":"2026-07-05T11:46:21.968404+00:00","updated_at":"2026-07-05T11:46:21.968404+00:00"}