{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F4HWAWSKUI3CGA45S22TYMYNRZ","short_pith_number":"pith:F4HWAWSK","canonical_record":{"source":{"id":"2404.15417","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T18:09:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fd9baedb92e27314fdbc658cb7b07d61a1e113724fd279299cad5af5ff369de6","abstract_canon_sha256":"888ded886a468640c2cc68b17252e59d50b80ba28ab3f1611c26f4cbf81ae735"},"schema_version":"1.0"},"canonical_sha256":"2f0f605a4aa23623039d96b53c330d8e4f1d42e7c0c20ea9f971a812f7153e58","source":{"kind":"arxiv","id":"2404.15417","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15417","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15417v2","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15417","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"F4HWAWSKUI3C","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"F4HWAWSKUI3CGA45","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"F4HWAWSK","created_at":"2026-07-05T08:12:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F4HWAWSKUI3CGA45S22TYMYNRZ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.15417","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T18:09:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fd9baedb92e27314fdbc658cb7b07d61a1e113724fd279299cad5af5ff369de6","abstract_canon_sha256":"888ded886a468640c2cc68b17252e59d50b80ba28ab3f1611c26f4cbf81ae735"},"schema_version":"1.0"},"canonical_sha256":"2f0f605a4aa23623039d96b53c330d8e4f1d42e7c0c20ea9f971a812f7153e58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:32.264383Z","signature_b64":"XLNKZABQG1L9nYww+pJjMbxLDzg6ZCDGVQHcgoqgAxtdMsl7z1a720mK4cIS5unq4liI0SnKxiDDeFkIt5MNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f0f605a4aa23623039d96b53c330d8e4f1d42e7c0c20ea9f971a812f7153e58","last_reissued_at":"2026-07-05T08:12:32.263897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:32.263897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.15417","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5uqDvd9/19ZDCGTp2Gs3nxr7iF+b/UQoJLvxwywtU7rcZ/tyx3/N+0PlwOxKBZ1yAf17T5OW1Ub2VXe7Cj8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:37:51.226507Z"},"content_sha256":"b5ede7f3e2c06af9b61076636a7192f8c348c583a19fc2ca73ebc5e71f87eb53","schema_version":"1.0","event_id":"sha256:b5ede7f3e2c06af9b61076636a7192f8c348c583a19fc2ca73ebc5e71f87eb53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F4HWAWSKUI3CGA45S22TYMYNRZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Power of Resets in Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dylan J. Foster, Zakaria Mhammedi","submitted_at":"2024-04-23T18:09:53Z","abstract_excerpt":"Simulators are a pervasive tool in reinforcement learning, but most existing algorithms cannot efficiently exploit simulator access -- particularly in high-dimensional domains that require general function approximation. We explore the power of simulators through online reinforcement learning with {local simulator access} (or, local planning), an RL protocol where the agent is allowed to reset to previously observed states and follow their dynamics during training. We use local simulator access to unlock new statistical guarantees that were previously out of reach:\n  - We show that MDPs with l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15417","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/2404.15417/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":"2026-07-05T08:12:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNXWk/4maKCTYV2tTYzUU6pUtjP/Q/vKnyKXOtOcl8UvUWw51/cwkxkrPhhQ7PA0vBglfEer8CvD5xyudX/kBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:37:51.226887Z"},"content_sha256":"d7ef16f7635bc1de8796979b97da2f555ee93b7190d6a837e5ddb3d779304c45","schema_version":"1.0","event_id":"sha256:d7ef16f7635bc1de8796979b97da2f555ee93b7190d6a837e5ddb3d779304c45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4HWAWSKUI3CGA45S22TYMYNRZ/bundle.json","state_url":"https://pith.science/pith/F4HWAWSKUI3CGA45S22TYMYNRZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4HWAWSKUI3CGA45S22TYMYNRZ/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":"2026-07-06T20:37:51Z","links":{"resolver":"https://pith.science/pith/F4HWAWSKUI3CGA45S22TYMYNRZ","bundle":"https://pith.science/pith/F4HWAWSKUI3CGA45S22TYMYNRZ/bundle.json","state":"https://pith.science/pith/F4HWAWSKUI3CGA45S22TYMYNRZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4HWAWSKUI3CGA45S22TYMYNRZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F4HWAWSKUI3CGA45S22TYMYNRZ","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":"888ded886a468640c2cc68b17252e59d50b80ba28ab3f1611c26f4cbf81ae735","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T18:09:53Z","title_canon_sha256":"fd9baedb92e27314fdbc658cb7b07d61a1e113724fd279299cad5af5ff369de6"},"schema_version":"1.0","source":{"id":"2404.15417","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15417","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15417v2","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15417","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"F4HWAWSKUI3C","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"F4HWAWSKUI3CGA45","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"F4HWAWSK","created_at":"2026-07-05T08:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:d7ef16f7635bc1de8796979b97da2f555ee93b7190d6a837e5ddb3d779304c45","target":"graph","created_at":"2026-07-05T08:12:32Z","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/2404.15417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Simulators are a pervasive tool in reinforcement learning, but most existing algorithms cannot efficiently exploit simulator access -- particularly in high-dimensional domains that require general function approximation. We explore the power of simulators through online reinforcement learning with {local simulator access} (or, local planning), an RL protocol where the agent is allowed to reset to previously observed states and follow their dynamics during training. We use local simulator access to unlock new statistical guarantees that were previously out of reach:\n  - We show that MDPs with l","authors_text":"Alexander Rakhlin, Dylan J. Foster, Zakaria Mhammedi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T18:09:53Z","title":"The Power of Resets in Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15417","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:b5ede7f3e2c06af9b61076636a7192f8c348c583a19fc2ca73ebc5e71f87eb53","target":"record","created_at":"2026-07-05T08:12:32Z","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":"888ded886a468640c2cc68b17252e59d50b80ba28ab3f1611c26f4cbf81ae735","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-23T18:09:53Z","title_canon_sha256":"fd9baedb92e27314fdbc658cb7b07d61a1e113724fd279299cad5af5ff369de6"},"schema_version":"1.0","source":{"id":"2404.15417","kind":"arxiv","version":2}},"canonical_sha256":"2f0f605a4aa23623039d96b53c330d8e4f1d42e7c0c20ea9f971a812f7153e58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f0f605a4aa23623039d96b53c330d8e4f1d42e7c0c20ea9f971a812f7153e58","first_computed_at":"2026-07-05T08:12:32.263897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:32.263897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XLNKZABQG1L9nYww+pJjMbxLDzg6ZCDGVQHcgoqgAxtdMsl7z1a720mK4cIS5unq4liI0SnKxiDDeFkIt5MNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:32.264383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15417","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5ede7f3e2c06af9b61076636a7192f8c348c583a19fc2ca73ebc5e71f87eb53","sha256:d7ef16f7635bc1de8796979b97da2f555ee93b7190d6a837e5ddb3d779304c45"],"state_sha256":"a44efdc117b81e33b94346bde945eb6507201c74e35d5d0703e83524a762c227"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UyhQDLmEyuqh4r8XsoxoVOqaG984/n2bxgmLV8nN5A4r8OOgMf2HdvyvFi7bnSeXJ5c2st/1atY2mIVWgPhBAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:37:51.230207Z","bundle_sha256":"cb0dd0afdda3af9168d356d1a7d6a6e1c9da65bcb9177265da139b1de7e5aba0"}}