{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RXA5XNCGW7MVDIYH546T6KPEMX","short_pith_number":"pith:RXA5XNCG","canonical_record":{"source":{"id":"2504.11453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:05Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"09f7fb4ce0916a9ccf8f66883423e51f2cbee206933b7e305ddde18f2bd915d5","abstract_canon_sha256":"47ae410d71ba425b946e9d81f2bd5a249a570496f69e17d02e434f3c07efa0a0"},"schema_version":"1.0"},"canonical_sha256":"8dc1dbb446b7d951a307ef3d3f29e465e30bf079ca060156b5a3714a78a66c33","source":{"kind":"arxiv","id":"2504.11453","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11453","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11453v1","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11453","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_12","alias_value":"RXA5XNCGW7MV","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_16","alias_value":"RXA5XNCGW7MVDIYH","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_8","alias_value":"RXA5XNCG","created_at":"2026-07-05T10:49:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RXA5XNCGW7MVDIYH546T6KPEMX","target":"record","payload":{"canonical_record":{"source":{"id":"2504.11453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:05Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"09f7fb4ce0916a9ccf8f66883423e51f2cbee206933b7e305ddde18f2bd915d5","abstract_canon_sha256":"47ae410d71ba425b946e9d81f2bd5a249a570496f69e17d02e434f3c07efa0a0"},"schema_version":"1.0"},"canonical_sha256":"8dc1dbb446b7d951a307ef3d3f29e465e30bf079ca060156b5a3714a78a66c33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:34.137284Z","signature_b64":"rdFbypvyXVImCPdFdXQDL3QgghNhI7RiuzOuRQFMSBxWYuvNJnigMMK5BDB1BuVfFzgMOUFJmBn6e5Uy3xBrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc1dbb446b7d951a307ef3d3f29e465e30bf079ca060156b5a3714a78a66c33","last_reissued_at":"2026-07-05T10:49:34.136810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:34.136810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.11453","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":"2026-07-05T10:49:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4Gkbq61PGtSdQY2Ft4sX+Bioop7mhffksrQnbIzxU7zmGxBwvOA+J2Zi28D5fDRahfpkCQ60/ghliG7numGAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:34:56.549044Z"},"content_sha256":"3f03a2818e30cdad6eb543c7c703dc0eb02ef706a9f721551a41ceb1b0a47eb4","schema_version":"1.0","event_id":"sha256:3f03a2818e30cdad6eb543c7c703dc0eb02ef706a9f721551a41ceb1b0a47eb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RXA5XNCGW7MVDIYH546T6KPEMX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Clean Slate for Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Jakob Nicolaus Foerster, Jarek Liesen, Matthew Thomas Jackson, Shimon Whiteson, Uljad Berdica","submitted_at":"2025-04-15T17:59:05Z","abstract_excerpt":"Progress in offline reinforcement learning (RL) has been impeded by ambiguous problem definitions and entangled algorithmic designs, resulting in inconsistent implementations, insufficient ablations, and unfair evaluations. Although offline RL explicitly avoids environment interaction, prior methods frequently employ extensive, undocumented online evaluation for hyperparameter tuning, complicating method comparisons. Moreover, existing reference implementations differ significantly in boilerplate code, obscuring their core algorithmic contributions. We address these challenges by first introdu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11453","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/2504.11453/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":"2026-07-05T10:49:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SKVT0W7zNhgO39ZlBdO0SFu9YsFIIBnjoWfqD7S1zDJkePHlzKEmfKiDn3pRM21Kh5FfmW8U0loa4O6VKa5mCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T12:34:56.549541Z"},"content_sha256":"9ba6775c7464eec96a9efd1dfafd8cb021503d9b2ad3413d02cb4587924528a5","schema_version":"1.0","event_id":"sha256:9ba6775c7464eec96a9efd1dfafd8cb021503d9b2ad3413d02cb4587924528a5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXA5XNCGW7MVDIYH546T6KPEMX/bundle.json","state_url":"https://pith.science/pith/RXA5XNCGW7MVDIYH546T6KPEMX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXA5XNCGW7MVDIYH546T6KPEMX/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":"2026-08-21T12:34:56Z","links":{"resolver":"https://pith.science/pith/RXA5XNCGW7MVDIYH546T6KPEMX","bundle":"https://pith.science/pith/RXA5XNCGW7MVDIYH546T6KPEMX/bundle.json","state":"https://pith.science/pith/RXA5XNCGW7MVDIYH546T6KPEMX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXA5XNCGW7MVDIYH546T6KPEMX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RXA5XNCGW7MVDIYH546T6KPEMX","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":"47ae410d71ba425b946e9d81f2bd5a249a570496f69e17d02e434f3c07efa0a0","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:05Z","title_canon_sha256":"09f7fb4ce0916a9ccf8f66883423e51f2cbee206933b7e305ddde18f2bd915d5"},"schema_version":"1.0","source":{"id":"2504.11453","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11453","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11453v1","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11453","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_12","alias_value":"RXA5XNCGW7MV","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_16","alias_value":"RXA5XNCGW7MVDIYH","created_at":"2026-07-05T10:49:34Z"},{"alias_kind":"pith_short_8","alias_value":"RXA5XNCG","created_at":"2026-07-05T10:49:34Z"}],"graph_snapshots":[{"event_id":"sha256:9ba6775c7464eec96a9efd1dfafd8cb021503d9b2ad3413d02cb4587924528a5","target":"graph","created_at":"2026-07-05T10:49:34Z","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/2504.11453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Progress in offline reinforcement learning (RL) has been impeded by ambiguous problem definitions and entangled algorithmic designs, resulting in inconsistent implementations, insufficient ablations, and unfair evaluations. Although offline RL explicitly avoids environment interaction, prior methods frequently employ extensive, undocumented online evaluation for hyperparameter tuning, complicating method comparisons. Moreover, existing reference implementations differ significantly in boilerplate code, obscuring their core algorithmic contributions. We address these challenges by first introdu","authors_text":"Jakob Nicolaus Foerster, Jarek Liesen, Matthew Thomas Jackson, Shimon Whiteson, Uljad Berdica","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:05Z","title":"A Clean Slate for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11453","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":"sha256:3f03a2818e30cdad6eb543c7c703dc0eb02ef706a9f721551a41ceb1b0a47eb4","target":"record","created_at":"2026-07-05T10:49:34Z","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":"47ae410d71ba425b946e9d81f2bd5a249a570496f69e17d02e434f3c07efa0a0","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-15T17:59:05Z","title_canon_sha256":"09f7fb4ce0916a9ccf8f66883423e51f2cbee206933b7e305ddde18f2bd915d5"},"schema_version":"1.0","source":{"id":"2504.11453","kind":"arxiv","version":1}},"canonical_sha256":"8dc1dbb446b7d951a307ef3d3f29e465e30bf079ca060156b5a3714a78a66c33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dc1dbb446b7d951a307ef3d3f29e465e30bf079ca060156b5a3714a78a66c33","first_computed_at":"2026-07-05T10:49:34.136810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:34.136810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rdFbypvyXVImCPdFdXQDL3QgghNhI7RiuzOuRQFMSBxWYuvNJnigMMK5BDB1BuVfFzgMOUFJmBn6e5Uy3xBrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:34.137284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11453","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f03a2818e30cdad6eb543c7c703dc0eb02ef706a9f721551a41ceb1b0a47eb4","sha256:9ba6775c7464eec96a9efd1dfafd8cb021503d9b2ad3413d02cb4587924528a5"],"state_sha256":"3f2e709d94e5b29bbcaf9f0387477e10ed05c48e604b919d9412210171396f26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eSVk4mLvyHkViOnvcbKvxFL0XfD9di2DHDaK66qJ1BgcPkrQ/O13kYl6o2eIXCIM+/bbcesJyyKdESaEFLi0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T12:34:56.554666Z","bundle_sha256":"61387e30445c61762e2bd9b797bd8ef05a3f3047a04db623492f0b368fd14986"}}