{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6XQIURETHVM7LHIVZXSPSDF4MS","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":"cd43293d5c28e0a7165ee504526126b6b0dab1c67153e2c6f2f45c611dc9b4e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T18:20:20Z","title_canon_sha256":"f429b66608f220048686f767f0347e0d179bb40cd7b44c2979c1ce2595ef79fe"},"schema_version":"1.0","source":{"id":"2309.15178","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.15178","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"arxiv_version","alias_value":"2309.15178v3","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15178","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"pith_short_12","alias_value":"6XQIURETHVM7","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"pith_short_16","alias_value":"6XQIURETHVM7LHIV","created_at":"2026-07-05T09:28:27Z"},{"alias_kind":"pith_short_8","alias_value":"6XQIURET","created_at":"2026-07-05T09:28:27Z"}],"graph_snapshots":[{"event_id":"sha256:c64d08036c8b30bfc21ce14a4cf1ee89e24789c7d8953d585509635a2406cbba","target":"graph","created_at":"2026-07-05T09:28:27Z","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/2309.15178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot reinforcement learning (RL) promises to provide agents that can perform any task in an environment after an offline, reward-free pre-training phase. Methods leveraging successor measures and successor features have shown strong performance in this setting, but require access to large heterogenous datasets for pre-training which cannot be expected for most real problems. Here, we explore how the performance of zero-shot RL methods degrades when trained on small homogeneous datasets, and propose fixes inspired by conservatism, a well-established feature of performant single-task offlin","authors_text":"Jonathan M. Cullen, Scott Jeen, Tom Bewley","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T18:20:20Z","title":"Zero-Shot Reinforcement Learning from Low Quality Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15178","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":"sha256:9ba6228eda9d4f4d16fa963e789bebe05a866a0fbc6252199bb639b950a5582d","target":"record","created_at":"2026-07-05T09:28:27Z","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":"cd43293d5c28e0a7165ee504526126b6b0dab1c67153e2c6f2f45c611dc9b4e9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T18:20:20Z","title_canon_sha256":"f429b66608f220048686f767f0347e0d179bb40cd7b44c2979c1ce2595ef79fe"},"schema_version":"1.0","source":{"id":"2309.15178","kind":"arxiv","version":3}},"canonical_sha256":"f5e08a44933d59f59d15cde4f90cbc64ad125c4c9f08a6c64019a2a03412378b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5e08a44933d59f59d15cde4f90cbc64ad125c4c9f08a6c64019a2a03412378b","first_computed_at":"2026-07-05T09:28:27.683857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:27.683857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uuGZu5JUKnL8QTnlIMNHo/z6LVBfBR5OkI7zK1G2HWs2SGs9LHkfM1f2lo6YksDNduUuM8o1RP6MHGq+bUhqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:27.684365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.15178","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ba6228eda9d4f4d16fa963e789bebe05a866a0fbc6252199bb639b950a5582d","sha256:c64d08036c8b30bfc21ce14a4cf1ee89e24789c7d8953d585509635a2406cbba"],"state_sha256":"929211b5dad8a9fae8a7d4de1615fc93f882e2c031008b9100bd5392442345f4"}