{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ATLCQLLDABV6ZBQ5WNXI3KTZ7X","short_pith_number":"pith:ATLCQLLD","canonical_record":{"source":{"id":"2306.05810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T10:52:39Z","cross_cats_sorted":[],"title_canon_sha256":"51b01301313a2952c1c95b33a8366acd55c33a80c78560e6ce7b04f9aa5d7423","abstract_canon_sha256":"036f2c5fde4acb82c0efd5ab5f914b6146d1dd1503b332096d188fc98c528875"},"schema_version":"1.0"},"canonical_sha256":"04d6282d63006bec861db36e8daa79fde11a6356bebdaeca29ada0987471ecfa","source":{"kind":"arxiv","id":"2306.05810","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05810","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05810v1","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05810","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"ATLCQLLDABV6","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"ATLCQLLDABV6ZBQ5","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"ATLCQLLD","created_at":"2026-07-05T06:19:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ATLCQLLDABV6ZBQ5WNXI3KTZ7X","target":"record","payload":{"canonical_record":{"source":{"id":"2306.05810","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T10:52:39Z","cross_cats_sorted":[],"title_canon_sha256":"51b01301313a2952c1c95b33a8366acd55c33a80c78560e6ce7b04f9aa5d7423","abstract_canon_sha256":"036f2c5fde4acb82c0efd5ab5f914b6146d1dd1503b332096d188fc98c528875"},"schema_version":"1.0"},"canonical_sha256":"04d6282d63006bec861db36e8daa79fde11a6356bebdaeca29ada0987471ecfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:10.563084Z","signature_b64":"2pjLoMIYTJDO5IrqbQFuXonsw8xPmCq5Nnx09E1DdZ28tNWU9sR+PwHd7zOuzfD91SFnSiPlYmRpv+y2dkWvBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04d6282d63006bec861db36e8daa79fde11a6356bebdaeca29ada0987471ecfa","last_reissued_at":"2026-07-05T06:19:10.562735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:10.562735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.05810","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25uJx6jOMiyGTVWERB/GIQm8zGz6VSI+JT0AYGFIl7MDrIEyLZjrtYD7/IlZBg4aLsYPXZ/s/wXIxh1+fBjDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:18:19.257746Z"},"content_sha256":"d9da83cab92401c91b82616e6191e33c4bdcb93986c8b33743ecef90f90ecd67","schema_version":"1.0","event_id":"sha256:d9da83cab92401c91b82616e6191e33c4bdcb93986c8b33743ecef90f90ecd67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ATLCQLLDABV6ZBQ5WNXI3KTZ7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"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":"2023-06-09T10:52:39Z","abstract_excerpt":"For reinforcement learning systems to be widely adopted, their users must understand and trust them. We present a theoretical analysis of explaining reinforcement learning using Shapley values, following a principled approach from game theory for identifying the contribution of individual players to the outcome of a cooperative game. We call this general framework Shapley Values for Explaining Reinforcement Learning (SVERL). Our analysis exposes the limitations of earlier uses of Shapley values in reinforcement learning. We then develop an approach that uses Shapley values to explain agent per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05810","kind":"arxiv","version":1},"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/2306.05810/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWLz/4e0WnK76E40CrUntvCg1NV8mSfaTfXmHuS0ypEEtPYP7TxbZQsZ+86QWG8yOSXEGmUekhWisChFkYvADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:18:19.258719Z"},"content_sha256":"b215575d5425f7684edd36d87d43c0945751eed404f788b84d84ae1e17115710","schema_version":"1.0","event_id":"sha256:b215575d5425f7684edd36d87d43c0945751eed404f788b84d84ae1e17115710"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ATLCQLLDABV6ZBQ5WNXI3KTZ7X/bundle.json","state_url":"https://pith.science/pith/ATLCQLLDABV6ZBQ5WNXI3KTZ7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ATLCQLLDABV6ZBQ5WNXI3KTZ7X/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T22:18:19Z","links":{"resolver":"https://pith.science/pith/ATLCQLLDABV6ZBQ5WNXI3KTZ7X","bundle":"https://pith.science/pith/ATLCQLLDABV6ZBQ5WNXI3KTZ7X/bundle.json","state":"https://pith.science/pith/ATLCQLLDABV6ZBQ5WNXI3KTZ7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ATLCQLLDABV6ZBQ5WNXI3KTZ7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ATLCQLLDABV6ZBQ5WNXI3KTZ7X","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":"036f2c5fde4acb82c0efd5ab5f914b6146d1dd1503b332096d188fc98c528875","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T10:52:39Z","title_canon_sha256":"51b01301313a2952c1c95b33a8366acd55c33a80c78560e6ce7b04f9aa5d7423"},"schema_version":"1.0","source":{"id":"2306.05810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05810","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05810v1","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05810","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"ATLCQLLDABV6","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"ATLCQLLDABV6ZBQ5","created_at":"2026-07-05T06:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"ATLCQLLD","created_at":"2026-07-05T06:19:10Z"}],"graph_snapshots":[{"event_id":"sha256:b215575d5425f7684edd36d87d43c0945751eed404f788b84d84ae1e17115710","target":"graph","created_at":"2026-07-05T06:19:10Z","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/2306.05810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For reinforcement learning systems to be widely adopted, their users must understand and trust them. We present a theoretical analysis of explaining reinforcement learning using Shapley values, following a principled approach from game theory for identifying the contribution of individual players to the outcome of a cooperative game. We call this general framework Shapley Values for Explaining Reinforcement Learning (SVERL). Our analysis exposes the limitations of earlier uses of Shapley values in reinforcement learning. We then develop an approach that uses Shapley values to explain agent per","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":"2023-06-09T10:52:39Z","title":"Explaining Reinforcement Learning with Shapley Values"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05810","kind":"arxiv","version":1},"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:d9da83cab92401c91b82616e6191e33c4bdcb93986c8b33743ecef90f90ecd67","target":"record","created_at":"2026-07-05T06:19:10Z","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":"036f2c5fde4acb82c0efd5ab5f914b6146d1dd1503b332096d188fc98c528875","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T10:52:39Z","title_canon_sha256":"51b01301313a2952c1c95b33a8366acd55c33a80c78560e6ce7b04f9aa5d7423"},"schema_version":"1.0","source":{"id":"2306.05810","kind":"arxiv","version":1}},"canonical_sha256":"04d6282d63006bec861db36e8daa79fde11a6356bebdaeca29ada0987471ecfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04d6282d63006bec861db36e8daa79fde11a6356bebdaeca29ada0987471ecfa","first_computed_at":"2026-07-05T06:19:10.562735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:10.562735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2pjLoMIYTJDO5IrqbQFuXonsw8xPmCq5Nnx09E1DdZ28tNWU9sR+PwHd7zOuzfD91SFnSiPlYmRpv+y2dkWvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:10.563084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9da83cab92401c91b82616e6191e33c4bdcb93986c8b33743ecef90f90ecd67","sha256:b215575d5425f7684edd36d87d43c0945751eed404f788b84d84ae1e17115710"],"state_sha256":"17214f5792733d77845b29de8e1f049c2312457830755cde9df3059a6c8341a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vOKjEJ0lWZKkyFmDV0Qjk1tALslwab6DTMfoZAQJ12dpb0hPJ63/8DUd5WZV99MopwjGMOPU7F81zah8Xe+Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:18:19.270159Z","bundle_sha256":"4ee688c01f9dcd71012996e83786881db50848d8713bd125370f797d218736b0"}}