{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:R2EKJTNVCPGMHD76HUJZS3AJUW","short_pith_number":"pith:R2EKJTNV","canonical_record":{"source":{"id":"2305.09836","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T22:37:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb3c59c924bc8148ed8fd8a73bc9ef72cb77144fa9c9f5442306996bb91a01a5","abstract_canon_sha256":"f4cc4226877de77ad9b972d345354a03a85310ff1c2f073f796bbe67c6f999d9"},"schema_version":"1.0"},"canonical_sha256":"8e88a4cdb513ccc38ffe3d13996c09a5b5299c3ad845cfa8d3224fb445705f01","source":{"kind":"arxiv","id":"2305.09836","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09836","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09836v2","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09836","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"pith_short_12","alias_value":"R2EKJTNVCPGM","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"pith_short_16","alias_value":"R2EKJTNVCPGMHD76","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"pith_short_8","alias_value":"R2EKJTNV","created_at":"2026-07-05T07:04:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:R2EKJTNVCPGMHD76HUJZS3AJUW","target":"record","payload":{"canonical_record":{"source":{"id":"2305.09836","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T22:37:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb3c59c924bc8148ed8fd8a73bc9ef72cb77144fa9c9f5442306996bb91a01a5","abstract_canon_sha256":"f4cc4226877de77ad9b972d345354a03a85310ff1c2f073f796bbe67c6f999d9"},"schema_version":"1.0"},"canonical_sha256":"8e88a4cdb513ccc38ffe3d13996c09a5b5299c3ad845cfa8d3224fb445705f01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:15.755332Z","signature_b64":"Zt6aViM+EsJsK2fgdTjvWobPEtTsYUjE8UoJ583yOoIweRQqUnn6+PEjPOWcGEe6XsCHMwhUpwuo5UAE7S8jAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e88a4cdb513ccc38ffe3d13996c09a5b5299c3ad845cfa8d3224fb445705f01","last_reissued_at":"2026-07-05T07:04:15.754872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:15.754872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.09836","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":"2026-07-05T07:04:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BE8wtR8nJ/TZyzuvU0V32HO6oQBqgVJyciIBj3XIVjcd8FLj3osxCUauNjAf5RPpcT24zTwCAurYysMAAaOaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:27:57.418590Z"},"content_sha256":"518a02f92a6bbf3866baefafb648d6e7cb09a6f831e347aab4da75364690ecbf","schema_version":"1.0","event_id":"sha256:518a02f92a6bbf3866baefafb648d6e7cb09a6f831e347aab4da75364690ecbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:R2EKJTNVCPGMHD76HUJZS3AJUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov, Vladislav Kurenkov","submitted_at":"2023-05-16T22:37:01Z","abstract_excerpt":"Recent years have witnessed significant advancements in offline reinforcement learning (RL), resulting in the development of numerous algorithms with varying degrees of complexity. While these algorithms have led to noteworthy improvements, many incorporate seemingly minor design choices that impact their effectiveness beyond core algorithmic advances. However, the effect of these design choices on established baselines remains understudied. In this work, we aim to bridge this gap by conducting a retrospective analysis of recent works in offline RL and propose ReBRAC, a minimalistic algorithm "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09836","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/2305.09836/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":"2026-07-05T07:04:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wLWGnDDRqM3lx128c5U5zWil18FuHtPPgRUTddTye3B6dDWBwmNBwc9+Sx/pD2Tx17QQhxL3EIiCmtOxO9A5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:27:57.419278Z"},"content_sha256":"10e6d1c058ec144cf8af0e64ca2985d7f999048a84099b299bd57f7560696fda","schema_version":"1.0","event_id":"sha256:10e6d1c058ec144cf8af0e64ca2985d7f999048a84099b299bd57f7560696fda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R2EKJTNVCPGMHD76HUJZS3AJUW/bundle.json","state_url":"https://pith.science/pith/R2EKJTNVCPGMHD76HUJZS3AJUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R2EKJTNVCPGMHD76HUJZS3AJUW/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":"2026-08-11T08:27:57Z","links":{"resolver":"https://pith.science/pith/R2EKJTNVCPGMHD76HUJZS3AJUW","bundle":"https://pith.science/pith/R2EKJTNVCPGMHD76HUJZS3AJUW/bundle.json","state":"https://pith.science/pith/R2EKJTNVCPGMHD76HUJZS3AJUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R2EKJTNVCPGMHD76HUJZS3AJUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:R2EKJTNVCPGMHD76HUJZS3AJUW","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":"f4cc4226877de77ad9b972d345354a03a85310ff1c2f073f796bbe67c6f999d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T22:37:01Z","title_canon_sha256":"cb3c59c924bc8148ed8fd8a73bc9ef72cb77144fa9c9f5442306996bb91a01a5"},"schema_version":"1.0","source":{"id":"2305.09836","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.09836","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"arxiv_version","alias_value":"2305.09836v2","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.09836","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"pith_short_12","alias_value":"R2EKJTNVCPGM","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"pith_short_16","alias_value":"R2EKJTNVCPGMHD76","created_at":"2026-07-05T07:04:15Z"},{"alias_kind":"pith_short_8","alias_value":"R2EKJTNV","created_at":"2026-07-05T07:04:15Z"}],"graph_snapshots":[{"event_id":"sha256:10e6d1c058ec144cf8af0e64ca2985d7f999048a84099b299bd57f7560696fda","target":"graph","created_at":"2026-07-05T07:04:15Z","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/2305.09836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent years have witnessed significant advancements in offline reinforcement learning (RL), resulting in the development of numerous algorithms with varying degrees of complexity. While these algorithms have led to noteworthy improvements, many incorporate seemingly minor design choices that impact their effectiveness beyond core algorithmic advances. However, the effect of these design choices on established baselines remains understudied. In this work, we aim to bridge this gap by conducting a retrospective analysis of recent works in offline RL and propose ReBRAC, a minimalistic algorithm ","authors_text":"Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov, Vladislav Kurenkov","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T22:37:01Z","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.09836","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":"sha256:518a02f92a6bbf3866baefafb648d6e7cb09a6f831e347aab4da75364690ecbf","target":"record","created_at":"2026-07-05T07:04:15Z","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":"f4cc4226877de77ad9b972d345354a03a85310ff1c2f073f796bbe67c6f999d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-16T22:37:01Z","title_canon_sha256":"cb3c59c924bc8148ed8fd8a73bc9ef72cb77144fa9c9f5442306996bb91a01a5"},"schema_version":"1.0","source":{"id":"2305.09836","kind":"arxiv","version":2}},"canonical_sha256":"8e88a4cdb513ccc38ffe3d13996c09a5b5299c3ad845cfa8d3224fb445705f01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e88a4cdb513ccc38ffe3d13996c09a5b5299c3ad845cfa8d3224fb445705f01","first_computed_at":"2026-07-05T07:04:15.754872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:15.754872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zt6aViM+EsJsK2fgdTjvWobPEtTsYUjE8UoJ583yOoIweRQqUnn6+PEjPOWcGEe6XsCHMwhUpwuo5UAE7S8jAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:15.755332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.09836","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:518a02f92a6bbf3866baefafb648d6e7cb09a6f831e347aab4da75364690ecbf","sha256:10e6d1c058ec144cf8af0e64ca2985d7f999048a84099b299bd57f7560696fda"],"state_sha256":"4cb9a83569bd6d3621f6d18cbdeec278a57246275a0503ce5aedf49e32c54468"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDcnkmOE19tGEJwCG00iardXjSNdKU9S7syjtE31jAuapreesjMqlXhefNOyxVLJu8oPBbss91hHgO/vVBxYDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:27:57.424833Z","bundle_sha256":"d94951604950a670de1036f50a3e1c417c54265f57388bbc7370054ee1a388c4"}}