{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:3UFOSJFEE6CGPDXHTSV4BQAZFI","short_pith_number":"pith:3UFOSJFE","canonical_record":{"source":{"id":"2204.12026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T01:48:32Z","cross_cats_sorted":[],"title_canon_sha256":"2f9dcc4a0f5ed5b0756a23812c5660b66680d39147cae15b63b8306d550c5e41","abstract_canon_sha256":"d7656fb520b3233962ac6bb479296d7ac2c95b50f987aefd35942129391c894a"},"schema_version":"1.0"},"canonical_sha256":"dd0ae924a42784678ee79cabc0c0192a0853a890b58871965d24fae1560e91dc","source":{"kind":"arxiv","id":"2204.12026","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12026","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12026v1","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12026","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"pith_short_12","alias_value":"3UFOSJFEE6CG","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"pith_short_16","alias_value":"3UFOSJFEE6CGPDXH","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"pith_short_8","alias_value":"3UFOSJFE","created_at":"2026-07-05T04:17:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:3UFOSJFEE6CGPDXHTSV4BQAZFI","target":"record","payload":{"canonical_record":{"source":{"id":"2204.12026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T01:48:32Z","cross_cats_sorted":[],"title_canon_sha256":"2f9dcc4a0f5ed5b0756a23812c5660b66680d39147cae15b63b8306d550c5e41","abstract_canon_sha256":"d7656fb520b3233962ac6bb479296d7ac2c95b50f987aefd35942129391c894a"},"schema_version":"1.0"},"canonical_sha256":"dd0ae924a42784678ee79cabc0c0192a0853a890b58871965d24fae1560e91dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:43.661713Z","signature_b64":"A4DxfCNA36BrrfKS/ALf8yY2IyjlChH23c0BIMUVziYFOy200RY8KSzN65xDjuUkbXxKKV7ScO1c4/6NoLltBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd0ae924a42784678ee79cabc0c0192a0853a890b58871965d24fae1560e91dc","last_reissued_at":"2026-07-05T04:17:43.661162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:43.661162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.12026","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":"2026-07-05T04:17:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KpFcJ964XxgCiEnd/cBX62UfYmfNtaFy9lNEQcp3caXdY0K41ia2Y/BXvPK4eVy+UyyB+rRf0785d2kvoOQYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:46:46.982910Z"},"content_sha256":"1d473f2c1819675e862a5a113d30699b40352dc5abb195bae4519b06b6ce2539","schema_version":"1.0","event_id":"sha256:1d473f2c1819675e862a5a113d30699b40352dc5abb195bae4519b06b6ce2539"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:3UFOSJFEE6CGPDXHTSV4BQAZFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BATS: Best Action Trajectory Stitching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Villaflor, Ian Char, Jeff Schneider, John M. Dolan, Viraj Mehta","submitted_at":"2022-04-26T01:48:32Z","abstract_excerpt":"The problem of offline reinforcement learning focuses on learning a good policy from a log of environment interactions. Past efforts for developing algorithms in this area have revolved around introducing constraints to online reinforcement learning algorithms to ensure the actions of the learned policy are constrained to the logged data. In this work, we explore an alternative approach by planning on the fixed dataset directly. Specifically, we introduce an algorithm which forms a tabular Markov Decision Process (MDP) over the logged data by adding new transitions to the dataset. We do this b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12026","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/2204.12026/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":"2026-07-05T04:17:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yOFp36rNIc0UyxWwBhPwQRppBsaKEJEzEUHPTmsFz8Y3jj7GxIFaI8yLpHX9kQJEaSitgdj9b6xgdS4fnttrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T08:46:46.983686Z"},"content_sha256":"f837b43aab88b2136f315313e02e274b751f3487c2993310a2770fa0c520df52","schema_version":"1.0","event_id":"sha256:f837b43aab88b2136f315313e02e274b751f3487c2993310a2770fa0c520df52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3UFOSJFEE6CGPDXHTSV4BQAZFI/bundle.json","state_url":"https://pith.science/pith/3UFOSJFEE6CGPDXHTSV4BQAZFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3UFOSJFEE6CGPDXHTSV4BQAZFI/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":"2026-08-17T08:46:46Z","links":{"resolver":"https://pith.science/pith/3UFOSJFEE6CGPDXHTSV4BQAZFI","bundle":"https://pith.science/pith/3UFOSJFEE6CGPDXHTSV4BQAZFI/bundle.json","state":"https://pith.science/pith/3UFOSJFEE6CGPDXHTSV4BQAZFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3UFOSJFEE6CGPDXHTSV4BQAZFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3UFOSJFEE6CGPDXHTSV4BQAZFI","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":"d7656fb520b3233962ac6bb479296d7ac2c95b50f987aefd35942129391c894a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T01:48:32Z","title_canon_sha256":"2f9dcc4a0f5ed5b0756a23812c5660b66680d39147cae15b63b8306d550c5e41"},"schema_version":"1.0","source":{"id":"2204.12026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12026","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12026v1","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12026","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"pith_short_12","alias_value":"3UFOSJFEE6CG","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"pith_short_16","alias_value":"3UFOSJFEE6CGPDXH","created_at":"2026-07-05T04:17:43Z"},{"alias_kind":"pith_short_8","alias_value":"3UFOSJFE","created_at":"2026-07-05T04:17:43Z"}],"graph_snapshots":[{"event_id":"sha256:f837b43aab88b2136f315313e02e274b751f3487c2993310a2770fa0c520df52","target":"graph","created_at":"2026-07-05T04:17:43Z","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/2204.12026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The problem of offline reinforcement learning focuses on learning a good policy from a log of environment interactions. Past efforts for developing algorithms in this area have revolved around introducing constraints to online reinforcement learning algorithms to ensure the actions of the learned policy are constrained to the logged data. In this work, we explore an alternative approach by planning on the fixed dataset directly. Specifically, we introduce an algorithm which forms a tabular Markov Decision Process (MDP) over the logged data by adding new transitions to the dataset. We do this b","authors_text":"Adam Villaflor, Ian Char, Jeff Schneider, John M. Dolan, Viraj Mehta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T01:48:32Z","title":"BATS: Best Action Trajectory Stitching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12026","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":"sha256:1d473f2c1819675e862a5a113d30699b40352dc5abb195bae4519b06b6ce2539","target":"record","created_at":"2026-07-05T04:17:43Z","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":"d7656fb520b3233962ac6bb479296d7ac2c95b50f987aefd35942129391c894a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-04-26T01:48:32Z","title_canon_sha256":"2f9dcc4a0f5ed5b0756a23812c5660b66680d39147cae15b63b8306d550c5e41"},"schema_version":"1.0","source":{"id":"2204.12026","kind":"arxiv","version":1}},"canonical_sha256":"dd0ae924a42784678ee79cabc0c0192a0853a890b58871965d24fae1560e91dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd0ae924a42784678ee79cabc0c0192a0853a890b58871965d24fae1560e91dc","first_computed_at":"2026-07-05T04:17:43.661162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:43.661162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A4DxfCNA36BrrfKS/ALf8yY2IyjlChH23c0BIMUVziYFOy200RY8KSzN65xDjuUkbXxKKV7ScO1c4/6NoLltBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:43.661713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.12026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d473f2c1819675e862a5a113d30699b40352dc5abb195bae4519b06b6ce2539","sha256:f837b43aab88b2136f315313e02e274b751f3487c2993310a2770fa0c520df52"],"state_sha256":"7b37caef9457a15cd80ee39b6a7a8e773cc82f7b030dd213d1145f591bede16d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysEc2GPi6LmTBh89KJBZuFCezaMfdyP7dXo57tuxwYDDOw6VtYrujpyB22wStHSe4Vi85NOOvkpjgTAbLmFlCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T08:46:46.988946Z","bundle_sha256":"717d9e62cf07d50840e004fa7442403cb0aa3176eec667e28fbae3f71e3158c1"}}