{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PDQ5MAPV2M65YHFM2F4GQWZR42","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":"98009a9b778accb864c8f8bde8b556508400d1daafbaa0f7291f197eb7adf307","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T21:52:44Z","title_canon_sha256":"9d6f883b0982ee20b4a087bfcd19875598d310439647bfac5f30e3720c3ea4fe"},"schema_version":"1.0","source":{"id":"2402.12570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12570","created_at":"2026-07-05T07:47:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12570v1","created_at":"2026-07-05T07:47:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12570","created_at":"2026-07-05T07:47:13Z"},{"alias_kind":"pith_short_12","alias_value":"PDQ5MAPV2M65","created_at":"2026-07-05T07:47:13Z"},{"alias_kind":"pith_short_16","alias_value":"PDQ5MAPV2M65YHFM","created_at":"2026-07-05T07:47:13Z"},{"alias_kind":"pith_short_8","alias_value":"PDQ5MAPV","created_at":"2026-07-05T07:47:13Z"}],"graph_snapshots":[{"event_id":"sha256:91b991b2f2a3e9f5cc57a7171a5342b48afc7b51b330d2ef44dd724aaa6b024f","target":"graph","created_at":"2026-07-05T07:47:13Z","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/2402.12570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori, and aims to learn a shared representation to be used in finding a good policy for a target task. Unlike in online RL where the agent interacts with the environment while learning a policy, in the offline setting there cannot be such interactions in either the source tasks or the target task; thus multi-task offline RL can suffer from incomplete coverage.\n  We propose an algorithm to compute pointwise uncertainty me","authors_text":"Avinandan Bose, Maryam Fazel, Simon Shaolei Du","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T21:52:44Z","title":"Offline Multi-task Transfer RL with Representational Penalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12570","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:f535b7958f0de3337ae7c131fb6facd5c79afd4fdc27bdfc2d4ee9195f28634c","target":"record","created_at":"2026-07-05T07:47:13Z","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":"98009a9b778accb864c8f8bde8b556508400d1daafbaa0f7291f197eb7adf307","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T21:52:44Z","title_canon_sha256":"9d6f883b0982ee20b4a087bfcd19875598d310439647bfac5f30e3720c3ea4fe"},"schema_version":"1.0","source":{"id":"2402.12570","kind":"arxiv","version":1}},"canonical_sha256":"78e1d601f5d33ddc1cacd178685b31e687f9a83495ffe83434747efa0a5974e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78e1d601f5d33ddc1cacd178685b31e687f9a83495ffe83434747efa0a5974e8","first_computed_at":"2026-07-05T07:47:13.092524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:13.092524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bnsF2CkTvTsGoGDJo5yCB/e/QIMrVzW57IIPig7jCMy0bprXtuFRH6mYcb4juWdYUbMXgWmj07fnkgfqvc7nBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:13.093012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f535b7958f0de3337ae7c131fb6facd5c79afd4fdc27bdfc2d4ee9195f28634c","sha256:91b991b2f2a3e9f5cc57a7171a5342b48afc7b51b330d2ef44dd724aaa6b024f"],"state_sha256":"b4473daef666f6a5329d5db37c52cf92add30a124a24a524310ebfc68624e613"}