{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MOFBSZKH2P7V4NAZD6GPUY3X3Z","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":"38a0edec446e4a2941beb598878cfff741d3758cc5ca4f06070875a77c7f6ada","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T20:25:52Z","title_canon_sha256":"259742c68445a797ac3274fc0237f50e9fd7f51d06b6875db24950ad19bebb89"},"schema_version":"1.0","source":{"id":"2506.16590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16590","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16590v1","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16590","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_12","alias_value":"MOFBSZKH2P7V","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_16","alias_value":"MOFBSZKH2P7V4NAZ","created_at":"2026-07-05T11:24:39Z"},{"alias_kind":"pith_short_8","alias_value":"MOFBSZKH","created_at":"2026-07-05T11:24:39Z"}],"graph_snapshots":[{"event_id":"sha256:c71bf7c3e20f709deb496dc20016bed3aa1b54b8a1d9dbea2d54adeb9652c910","target":"graph","created_at":"2026-07-05T11:24:39Z","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/2506.16590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms often suffer from poor sample efficiency, making them challenging to apply in multi-task or continual learning settings. Efficiency can be improved by transferring knowledge from a previously trained teacher policy to guide exploration in new but related tasks. However, if the new task sufficiently differs from the teacher's training task, the transferred guidance may be sub-optimal and bias exploration toward low-reward behaviors. We propose an energy-based transfer learning method that uses out-of-distribution detection to selectively issue guidance, enablin","authors_text":"Fiona Xie, Jasorsi Ghosh, Joseph Campbell, Katia Sycara, Yuzhe Lu, Zeyun Deng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T20:25:52Z","title":"Energy-Based Transfer for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16590","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":"sha256:8e2cb551d6efedc9a796b4d8da147e0f4828846129dbe47b34f96896dcf5b3aa","target":"record","created_at":"2026-07-05T11:24:39Z","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":"38a0edec446e4a2941beb598878cfff741d3758cc5ca4f06070875a77c7f6ada","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-19T20:25:52Z","title_canon_sha256":"259742c68445a797ac3274fc0237f50e9fd7f51d06b6875db24950ad19bebb89"},"schema_version":"1.0","source":{"id":"2506.16590","kind":"arxiv","version":1}},"canonical_sha256":"638a196547d3ff5e34191f8cfa6377de594d5bbee1c16888148b6753178a11a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"638a196547d3ff5e34191f8cfa6377de594d5bbee1c16888148b6753178a11a3","first_computed_at":"2026-07-05T11:24:39.184752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:39.184752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w0oyngoKIVcy4DApg6S+6uADCRxpVNFdxax/89Qz9DKuYJIZjOXCPCa6YpF3iKpQ9zA9toO3IFHiFdMab5+4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:39.185300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e2cb551d6efedc9a796b4d8da147e0f4828846129dbe47b34f96896dcf5b3aa","sha256:c71bf7c3e20f709deb496dc20016bed3aa1b54b8a1d9dbea2d54adeb9652c910"],"state_sha256":"527d215a30d241fabc5fee7d3ea75891139240f855a09793d56947cdcf39150c"}