{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6XQIURETHVM7LHIVZXSPSDF4MS","short_pith_number":"pith:6XQIURET","canonical_record":{"source":{"id":"2309.15178","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T18:20:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f429b66608f220048686f767f0347e0d179bb40cd7b44c2979c1ce2595ef79fe","abstract_canon_sha256":"cd43293d5c28e0a7165ee504526126b6b0dab1c67153e2c6f2f45c611dc9b4e9"},"schema_version":"1.0"},"canonical_sha256":"f5e08a44933d59f59d15cde4f90cbc64ad125c4c9f08a6c64019a2a03412378b","source":{"kind":"arxiv","id":"2309.15178","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6XQIURETHVM7LHIVZXSPSDF4MS","target":"record","payload":{"canonical_record":{"source":{"id":"2309.15178","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-26T18:20:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f429b66608f220048686f767f0347e0d179bb40cd7b44c2979c1ce2595ef79fe","abstract_canon_sha256":"cd43293d5c28e0a7165ee504526126b6b0dab1c67153e2c6f2f45c611dc9b4e9"},"schema_version":"1.0"},"canonical_sha256":"f5e08a44933d59f59d15cde4f90cbc64ad125c4c9f08a6c64019a2a03412378b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:27.684365Z","signature_b64":"uuGZu5JUKnL8QTnlIMNHo/z6LVBfBR5OkI7zK1G2HWs2SGs9LHkfM1f2lo6YksDNduUuM8o1RP6MHGq+bUhqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e08a44933d59f59d15cde4f90cbc64ad125c4c9f08a6c64019a2a03412378b","last_reissued_at":"2026-07-05T09:28:27.683857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:27.683857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.15178","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":"2026-07-05T09:28:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duNsdchD6JmO+RtIB/Z26isT8moBUHsBQeZtjx1yRDPvi3xMJUCHoaqAd1eYb1agojG+1iBxKN/6NtjcnRh/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:31:48.969505Z"},"content_sha256":"9ba6228eda9d4f4d16fa963e789bebe05a866a0fbc6252199bb639b950a5582d","schema_version":"1.0","event_id":"sha256:9ba6228eda9d4f4d16fa963e789bebe05a866a0fbc6252199bb639b950a5582d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6XQIURETHVM7LHIVZXSPSDF4MS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Reinforcement Learning from Low Quality Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jonathan M. Cullen, Scott Jeen, Tom Bewley","submitted_at":"2023-09-26T18:20:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15178","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/2309.15178/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":"2026-07-05T09:28:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fKdHJVtqZYHj6fHIWvJiZ+ie2y+Z8vcMKiCqmIaB0YLYwSd5Aj1gCxUZp7rspv0gZaN49K9aYzY9pYzYgr4uAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:31:48.970252Z"},"content_sha256":"c64d08036c8b30bfc21ce14a4cf1ee89e24789c7d8953d585509635a2406cbba","schema_version":"1.0","event_id":"sha256:c64d08036c8b30bfc21ce14a4cf1ee89e24789c7d8953d585509635a2406cbba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XQIURETHVM7LHIVZXSPSDF4MS/bundle.json","state_url":"https://pith.science/pith/6XQIURETHVM7LHIVZXSPSDF4MS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XQIURETHVM7LHIVZXSPSDF4MS/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":"2026-08-07T17:31:48Z","links":{"resolver":"https://pith.science/pith/6XQIURETHVM7LHIVZXSPSDF4MS","bundle":"https://pith.science/pith/6XQIURETHVM7LHIVZXSPSDF4MS/bundle.json","state":"https://pith.science/pith/6XQIURETHVM7LHIVZXSPSDF4MS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XQIURETHVM7LHIVZXSPSDF4MS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YF8XuZA+VJMs1WiKUdv8QKBTu5eXoIAc5irU0K5jvqa8oQtpCnjoAJ37SG3DB742b+kcRd5/Kx/ijZy/KvIbCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:31:48.975726Z","bundle_sha256":"4c593c648a7465bc418a8f9d0f332b7f86f85b317f5f98f183fd9fba1c1783ef"}}