{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZVET4CO4HJ5WYAFV72WKEXH6J7","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":"3fe3e99c7b4976418135c469e55ce58c2a6319ac1c2de8d6aecdb51c45e2d755","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T17:28:03Z","title_canon_sha256":"8cd84b0f65921cfda78015bf1a2b701e47e3d99372d20c6dfc7429f327782f4f"},"schema_version":"1.0","source":{"id":"2412.06685","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06685","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06685v1","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06685","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"pith_short_12","alias_value":"ZVET4CO4HJ5W","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"pith_short_16","alias_value":"ZVET4CO4HJ5WYAFV","created_at":"2026-07-05T09:46:36Z"},{"alias_kind":"pith_short_8","alias_value":"ZVET4CO4","created_at":"2026-07-05T09:46:36Z"}],"graph_snapshots":[{"event_id":"sha256:6eed5c4db561a6e5b1da0b41a14eb33077e7b432f2f107d1f6563eecb172aed5","target":"graph","created_at":"2026-07-05T09:46:36Z","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/2412.06685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in learning decision-making policies can largely be attributed to training expressive policy models, largely via imitation learning. While imitation learning discards non-expert data, reinforcement learning (RL) can still learn from suboptimal data. However, instantiating RL training of a new policy class often presents a different challenge: most deep RL machinery is co-developed with assumptions on the policy class and backbone, resulting in poor performance when the policy class changes. For instance, SAC utilizes a low-variance reparameterization policy gradient for Gaussia","authors_text":"Archit Sharma, Aviral Kumar, Chelsea Finn, Georgia Gabriela Sampaio, Max Sobol Mark, Mohan Kumar Srirama, Tian Gao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T17:28:03Z","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06685","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:e29a05a6bd4ff8cb7122571576118455d986c7981a8ddf2170c04cfa4b1bf44d","target":"record","created_at":"2026-07-05T09:46:36Z","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":"3fe3e99c7b4976418135c469e55ce58c2a6319ac1c2de8d6aecdb51c45e2d755","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T17:28:03Z","title_canon_sha256":"8cd84b0f65921cfda78015bf1a2b701e47e3d99372d20c6dfc7429f327782f4f"},"schema_version":"1.0","source":{"id":"2412.06685","kind":"arxiv","version":1}},"canonical_sha256":"cd493e09dc3a7b6c00b5feaca25cfe4fda55533c0ad8dbe2edc20a23ef779d1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd493e09dc3a7b6c00b5feaca25cfe4fda55533c0ad8dbe2edc20a23ef779d1c","first_computed_at":"2026-07-05T09:46:36.474916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:36.474916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QvxvwOhJo3/swM7icNHbMMLYrMlLpjP7e0GdRkWuHVT3V4F0CnLaps8JItairYuW2/JzLEh/YO9lyX/QgU7oAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:36.475403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06685","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e29a05a6bd4ff8cb7122571576118455d986c7981a8ddf2170c04cfa4b1bf44d","sha256:6eed5c4db561a6e5b1da0b41a14eb33077e7b432f2f107d1f6563eecb172aed5"],"state_sha256":"a9b4c7374736f06d44312383981a397ab6f00d37737dc6c4c1c273ef058695eb"}