{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MWBD3BWKRSLHGGDYV4L5RML66X","short_pith_number":"pith:MWBD3BWK","canonical_record":{"source":{"id":"2201.13425","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T18:39:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef20f303afe90594eb07cab6b738e072c8c830626c4200157d29d4922833c30f","abstract_canon_sha256":"3d1dfbbc2954659d93ee74b8714c905c6371e4b20a161fd3b81a19ab085e6d26"},"schema_version":"1.0"},"canonical_sha256":"65823d86ca8c96731878af17d8b17ef5e49dfdc697f0b5c84940c8afc26f4722","source":{"kind":"arxiv","id":"2201.13425","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.13425","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"arxiv_version","alias_value":"2201.13425v3","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13425","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_12","alias_value":"MWBD3BWKRSLH","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_16","alias_value":"MWBD3BWKRSLHGGDY","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_8","alias_value":"MWBD3BWK","created_at":"2026-07-05T04:12:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MWBD3BWKRSLHGGDYV4L5RML66X","target":"record","payload":{"canonical_record":{"source":{"id":"2201.13425","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T18:39:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef20f303afe90594eb07cab6b738e072c8c830626c4200157d29d4922833c30f","abstract_canon_sha256":"3d1dfbbc2954659d93ee74b8714c905c6371e4b20a161fd3b81a19ab085e6d26"},"schema_version":"1.0"},"canonical_sha256":"65823d86ca8c96731878af17d8b17ef5e49dfdc697f0b5c84940c8afc26f4722","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:05.939953Z","signature_b64":"DnwE//yeS1nYUWuVonJ5wVnvNPlJMaqZeCcxAM9t8Xf/vyBkXwHOLQuLjR8ofEalspu8FrTwBmwVqXEkC0MFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65823d86ca8c96731878af17d8b17ef5e49dfdc697f0b5c84940c8afc26f4722","last_reissued_at":"2026-07-05T04:12:05.939443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:05.939443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.13425","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:12:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fgfQjZfcfK7+rff23uzv6hl5ExzBdXtamvwmDOCHxyRgbOJBAiM2AFB8xbewadFWXAtYT7ApQm25RG2I7025Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:44:02.941664Z"},"content_sha256":"4e938b738885d25cc0cc39513d9a7eb1844201826eca2a5bf8e3bc6945f78d0f","schema_version":"1.0","event_id":"sha256:4e938b738885d25cc0cc39513d9a7eb1844201826eca2a5bf8e3bc6945f78d0f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MWBD3BWKRSLHGGDYV4L5RML66X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, David Brandfonbrener, Denis Yarats, Hao Liu, Lerrel Pinto, Michael Laskin, Pieter Abbeel","submitted_at":"2022-01-31T18:39:27Z","abstract_excerpt":"Recent progress in deep learning has relied on access to large and diverse datasets. Such data-driven progress has been less evident in offline reinforcement learning (RL), because offline RL data is usually collected to optimize specific target tasks limiting the data's diversity. In this work, we propose Exploratory data for Offline RL (ExORL), a data-centric approach to offline RL. ExORL first generates data with unsupervised reward-free exploration, then relabels this data with a downstream reward before training a policy with offline RL. We find that exploratory data allows vanilla off-po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13425","kind":"arxiv","version":3},"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/2201.13425/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":"2026-07-05T04:12:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FClJ4VVrYFKPRTBNgzncpB03qea7zfgZV5TumsD4yzXX5CLuTFdAWwJFMjHl4ed5Yt5k4aTBzWebbm9LfSvqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:44:02.942039Z"},"content_sha256":"c795e0cc28a784c59c122704f5a1a92db2abcd502318a9be28091090cb4b21ba","schema_version":"1.0","event_id":"sha256:c795e0cc28a784c59c122704f5a1a92db2abcd502318a9be28091090cb4b21ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/bundle.json","state_url":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MWBD3BWKRSLHGGDYV4L5RML66X/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":"2026-07-07T11:44:02Z","links":{"resolver":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X","bundle":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/bundle.json","state":"https://pith.science/pith/MWBD3BWKRSLHGGDYV4L5RML66X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MWBD3BWKRSLHGGDYV4L5RML66X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MWBD3BWKRSLHGGDYV4L5RML66X","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":"3d1dfbbc2954659d93ee74b8714c905c6371e4b20a161fd3b81a19ab085e6d26","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T18:39:27Z","title_canon_sha256":"ef20f303afe90594eb07cab6b738e072c8c830626c4200157d29d4922833c30f"},"schema_version":"1.0","source":{"id":"2201.13425","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.13425","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"arxiv_version","alias_value":"2201.13425v3","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13425","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_12","alias_value":"MWBD3BWKRSLH","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_16","alias_value":"MWBD3BWKRSLHGGDY","created_at":"2026-07-05T04:12:05Z"},{"alias_kind":"pith_short_8","alias_value":"MWBD3BWK","created_at":"2026-07-05T04:12:05Z"}],"graph_snapshots":[{"event_id":"sha256:c795e0cc28a784c59c122704f5a1a92db2abcd502318a9be28091090cb4b21ba","target":"graph","created_at":"2026-07-05T04:12:05Z","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/2201.13425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in deep learning has relied on access to large and diverse datasets. Such data-driven progress has been less evident in offline reinforcement learning (RL), because offline RL data is usually collected to optimize specific target tasks limiting the data's diversity. In this work, we propose Exploratory data for Offline RL (ExORL), a data-centric approach to offline RL. ExORL first generates data with unsupervised reward-free exploration, then relabels this data with a downstream reward before training a policy with offline RL. We find that exploratory data allows vanilla off-po","authors_text":"Alessandro Lazaric, David Brandfonbrener, Denis Yarats, Hao Liu, Lerrel Pinto, Michael Laskin, Pieter Abbeel","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T18:39:27Z","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13425","kind":"arxiv","version":3},"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":"sha256:4e938b738885d25cc0cc39513d9a7eb1844201826eca2a5bf8e3bc6945f78d0f","target":"record","created_at":"2026-07-05T04:12:05Z","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":"3d1dfbbc2954659d93ee74b8714c905c6371e4b20a161fd3b81a19ab085e6d26","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-31T18:39:27Z","title_canon_sha256":"ef20f303afe90594eb07cab6b738e072c8c830626c4200157d29d4922833c30f"},"schema_version":"1.0","source":{"id":"2201.13425","kind":"arxiv","version":3}},"canonical_sha256":"65823d86ca8c96731878af17d8b17ef5e49dfdc697f0b5c84940c8afc26f4722","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65823d86ca8c96731878af17d8b17ef5e49dfdc697f0b5c84940c8afc26f4722","first_computed_at":"2026-07-05T04:12:05.939443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:05.939443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DnwE//yeS1nYUWuVonJ5wVnvNPlJMaqZeCcxAM9t8Xf/vyBkXwHOLQuLjR8ofEalspu8FrTwBmwVqXEkC0MFAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:05.939953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.13425","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e938b738885d25cc0cc39513d9a7eb1844201826eca2a5bf8e3bc6945f78d0f","sha256:c795e0cc28a784c59c122704f5a1a92db2abcd502318a9be28091090cb4b21ba"],"state_sha256":"d8ddaadb8711d4e24c8279cfccfea3317bc7a48f7a84609bad1e6ee9bab0e755"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDQUKrCVFoU3XUjefdQ/eq8PC3zwlty2Osx7DEirK5aOcRn6qOci7WJSjytUMoTloD99KD/kiNvJU+QA+jK5Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:44:02.944062Z","bundle_sha256":"a0559d24935c8251bc8c1adb6c2e704397546a0dafdfea091058c9810d7d210e"}}