{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2I2CL2CHDDO4GXRR4YK72TB2B3","short_pith_number":"pith:2I2CL2CH","canonical_record":{"source":{"id":"2111.08066","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-15T20:14:18Z","cross_cats_sorted":[],"title_canon_sha256":"9d49c88c7a99b957553744b8c95a8871f9406d75e14f07672be4b86c3de6637b","abstract_canon_sha256":"8a3af9a154496606509f21d0362dee2f91d66ff635ee3224ced976e94807e974"},"schema_version":"1.0"},"canonical_sha256":"d23425e84718ddc35e31e615fd4c3a0ee08e6729ba7e364e0f3c5930556f6b07","source":{"kind":"arxiv","id":"2111.08066","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08066","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08066v5","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08066","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"2I2CL2CHDDO4","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"2I2CL2CHDDO4GXRR","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"2I2CL2CH","created_at":"2026-07-05T06:09:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2I2CL2CHDDO4GXRR4YK72TB2B3","target":"record","payload":{"canonical_record":{"source":{"id":"2111.08066","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-15T20:14:18Z","cross_cats_sorted":[],"title_canon_sha256":"9d49c88c7a99b957553744b8c95a8871f9406d75e14f07672be4b86c3de6637b","abstract_canon_sha256":"8a3af9a154496606509f21d0362dee2f91d66ff635ee3224ced976e94807e974"},"schema_version":"1.0"},"canonical_sha256":"d23425e84718ddc35e31e615fd4c3a0ee08e6729ba7e364e0f3c5930556f6b07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:41.315680Z","signature_b64":"erzAhrlqBdP5gz1skkxyIdmebyjfxpsCkncbdgFNzr1Pypc2ABasNlfcjWVy1xgFAzdq+/S/e1NzfKoaIYClAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d23425e84718ddc35e31e615fd4c3a0ee08e6729ba7e364e0f3c5930556f6b07","last_reissued_at":"2026-07-05T06:09:41.315257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:41.315257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.08066","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVd6YiTwpRO+cQv35aGPGRMZ6RAm7OOfRv6H2w99+eymY8HhywkGYAizPmKw7iESDA+/p5bGypKkpPEvHlztDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:40:16.110681Z"},"content_sha256":"3653e5f68cdb260a6164b3fd9d6f0fba75634a61505b3dcd10bb26b5c5b80bd7","schema_version":"1.0","event_id":"sha256:3653e5f68cdb260a6164b3fd9d6f0fba75634a61505b3dcd10bb26b5c5b80bd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2I2CL2CHDDO4GXRR4YK72TB2B3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"James R. Wright, Martha White, Vincent Liu","submitted_at":"2021-11-15T20:14:18Z","abstract_excerpt":"Offline reinforcement learning -- learning a policy from a batch of data -- is known to be hard for general MDPs. These results motivate the need to look at specific classes of MDPs where offline reinforcement learning might be feasible. In this work, we explore a restricted class of MDPs to obtain guarantees for offline reinforcement learning. The key property, which we call Action Impact Regularity (AIR), is that actions primarily impact a part of the state (an endogenous component) and have limited impact on the remaining part of the state (an exogenous component). AIR is a strong assumptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08066","kind":"arxiv","version":5},"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/2111.08066/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":"2026-07-05T06:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"24A0cx4IcyXbZkt9FD8Gup28vKdvEtnDFOxcEjQ811qmYdW7DShGzVU5lGr+CZnP7mRSqgx+y3ZyVRbyulI5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:40:16.111309Z"},"content_sha256":"0893769468317310b95463cea68bda1f4ce8e4de8be6dc9b2edbc539fa0cc1d1","schema_version":"1.0","event_id":"sha256:0893769468317310b95463cea68bda1f4ce8e4de8be6dc9b2edbc539fa0cc1d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2I2CL2CHDDO4GXRR4YK72TB2B3/bundle.json","state_url":"https://pith.science/pith/2I2CL2CHDDO4GXRR4YK72TB2B3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2I2CL2CHDDO4GXRR4YK72TB2B3/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":"2026-08-05T10:40:16Z","links":{"resolver":"https://pith.science/pith/2I2CL2CHDDO4GXRR4YK72TB2B3","bundle":"https://pith.science/pith/2I2CL2CHDDO4GXRR4YK72TB2B3/bundle.json","state":"https://pith.science/pith/2I2CL2CHDDO4GXRR4YK72TB2B3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2I2CL2CHDDO4GXRR4YK72TB2B3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2I2CL2CHDDO4GXRR4YK72TB2B3","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":"8a3af9a154496606509f21d0362dee2f91d66ff635ee3224ced976e94807e974","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-15T20:14:18Z","title_canon_sha256":"9d49c88c7a99b957553744b8c95a8871f9406d75e14f07672be4b86c3de6637b"},"schema_version":"1.0","source":{"id":"2111.08066","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08066","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08066v5","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08066","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"2I2CL2CHDDO4","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"2I2CL2CHDDO4GXRR","created_at":"2026-07-05T06:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"2I2CL2CH","created_at":"2026-07-05T06:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:0893769468317310b95463cea68bda1f4ce8e4de8be6dc9b2edbc539fa0cc1d1","target":"graph","created_at":"2026-07-05T06:09:41Z","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/2111.08066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning -- learning a policy from a batch of data -- is known to be hard for general MDPs. These results motivate the need to look at specific classes of MDPs where offline reinforcement learning might be feasible. In this work, we explore a restricted class of MDPs to obtain guarantees for offline reinforcement learning. The key property, which we call Action Impact Regularity (AIR), is that actions primarily impact a part of the state (an endogenous component) and have limited impact on the remaining part of the state (an exogenous component). AIR is a strong assumptio","authors_text":"James R. Wright, Martha White, Vincent Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-15T20:14:18Z","title":"Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08066","kind":"arxiv","version":5},"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":"sha256:3653e5f68cdb260a6164b3fd9d6f0fba75634a61505b3dcd10bb26b5c5b80bd7","target":"record","created_at":"2026-07-05T06:09:41Z","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":"8a3af9a154496606509f21d0362dee2f91d66ff635ee3224ced976e94807e974","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-15T20:14:18Z","title_canon_sha256":"9d49c88c7a99b957553744b8c95a8871f9406d75e14f07672be4b86c3de6637b"},"schema_version":"1.0","source":{"id":"2111.08066","kind":"arxiv","version":5}},"canonical_sha256":"d23425e84718ddc35e31e615fd4c3a0ee08e6729ba7e364e0f3c5930556f6b07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d23425e84718ddc35e31e615fd4c3a0ee08e6729ba7e364e0f3c5930556f6b07","first_computed_at":"2026-07-05T06:09:41.315257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:41.315257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"erzAhrlqBdP5gz1skkxyIdmebyjfxpsCkncbdgFNzr1Pypc2ABasNlfcjWVy1xgFAzdq+/S/e1NzfKoaIYClAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:41.315680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.08066","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3653e5f68cdb260a6164b3fd9d6f0fba75634a61505b3dcd10bb26b5c5b80bd7","sha256:0893769468317310b95463cea68bda1f4ce8e4de8be6dc9b2edbc539fa0cc1d1"],"state_sha256":"52a315926d4ee9c8e7b3bcd16f284e421de5c6c18a01ad370e8eb60d448e2a1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FM5IYgd9hYk/R6mCmggZ0hee1fHkaGF80+pE2wBQcz+774pDZppr4ord+KqBKNtbtoWia7LIk6B1tDiKyH3dBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:40:16.116984Z","bundle_sha256":"590c2eba4a96c50cbc152cb7262b212dfeca47bbc5a5c3fa2e6f6d5dfe8830c5"}}