{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QF3TNZ5OLRILVESHQAXWPPEWVL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bee3e4b5c73bae72eb7452fd51d13ce0df42e170129d812cb9fbc06f5fac7d47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T17:48:28Z","title_canon_sha256":"b84b6bd683d09cdecb78cd1cb96a53a4956d22bf9246b49e1ba505400e3c8265"},"schema_version":"1.0","source":{"id":"2505.07797","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07797","created_at":"2026-07-05T11:46:21Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07797v2","created_at":"2026-07-05T11:46:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07797","created_at":"2026-07-05T11:46:21Z"},{"alias_kind":"pith_short_12","alias_value":"QF3TNZ5OLRIL","created_at":"2026-07-05T11:46:21Z"},{"alias_kind":"pith_short_16","alias_value":"QF3TNZ5OLRILVESH","created_at":"2026-07-05T11:46:21Z"},{"alias_kind":"pith_short_8","alias_value":"QF3TNZ5O","created_at":"2026-07-05T11:46:21Z"}],"graph_snapshots":[{"event_id":"sha256:00e51a7578cce9785eda19f3d29bad0f44ac085517b9bd5e91fb90834384583f","target":"graph","created_at":"2026-07-05T11:46:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.07797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Daniel Beechey, \\\"Ozg\\\"ur \\c{S}im\\c{s}ek, Thomas M. S. Smith","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T17:48:28Z","title":"A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07797","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b240a074c8661f3d62b027fedc7132bd868e86e2168ff933eaf2e6a2419080a","target":"record","created_at":"2026-07-05T11:46:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bee3e4b5c73bae72eb7452fd51d13ce0df42e170129d812cb9fbc06f5fac7d47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T17:48:28Z","title_canon_sha256":"b84b6bd683d09cdecb78cd1cb96a53a4956d22bf9246b49e1ba505400e3c8265"},"schema_version":"1.0","source":{"id":"2505.07797","kind":"arxiv","version":2}},"canonical_sha256":"817736e7ae5c50ba9247802f67bc96aac5b16f841e4d83f46ef48bef3d94538d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"817736e7ae5c50ba9247802f67bc96aac5b16f841e4d83f46ef48bef3d94538d","first_computed_at":"2026-07-05T11:46:21.968345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:21.968345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IlPIGTLJV8XeeaL1gScbIY4QuAqvE8tfqxf2Pia+qcP+RXfIqly3QEoosADgpnsPhpCT/mzxBJC93liYWoDhCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:21.968837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07797","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b240a074c8661f3d62b027fedc7132bd868e86e2168ff933eaf2e6a2419080a","sha256:00e51a7578cce9785eda19f3d29bad0f44ac085517b9bd5e91fb90834384583f"],"state_sha256":"83cf62aa1d427e567940e4e31b99137f60fc54d80e07a4ef0d1d59ad15a63d63"}