{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QVPCGZBFVIW4WMBHI2SDEBO4V6","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":"ac87e2255521621bcf69cc46c663dca01619af196791d3196bea718bc3a8a954","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T17:46:12Z","title_canon_sha256":"9e101ba0954487e3094c96997ea78cb77b7208c5b001dcc016486dc0969e13d9"},"schema_version":"1.0","source":{"id":"2310.16029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16029","created_at":"2026-07-05T07:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16029v1","created_at":"2026-07-05T07:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16029","created_at":"2026-07-05T07:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"QVPCGZBFVIW4","created_at":"2026-07-05T07:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"QVPCGZBFVIW4WMBH","created_at":"2026-07-05T07:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"QVPCGZBF","created_at":"2026-07-05T07:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:f0c13fedbbb89c087ff711f1a1488cbeb91cec233c06b2bbe427e1284c167326","target":"graph","created_at":"2026-07-05T07:04:34Z","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/2310.16029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of interaction to learn skills. Recently, offline RL has been proposed as a framework for training RL policies on pre-existing datasets without any online interaction. However, constraining an algorithm to a fixed dataset induces a state-action distribution shift between training and inference, and limits its applicability to new tasks. In this work, we seek to get the","authors_text":"Chandramouli Rajagopalan, Nicklas Hansen, Xiaolong Wang, Yunhai Feng, Ziyan Xiong","cross_cats":["cs.AI","cs.CV","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T17:46:12Z","title":"Finetuning Offline World Models in the Real World"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16029","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:ff40dbb83e2a9e76b9f873908fb4b7adf4cd3cd4a7a77c171e0e1b5d7bb6675c","target":"record","created_at":"2026-07-05T07:04:34Z","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":"ac87e2255521621bcf69cc46c663dca01619af196791d3196bea718bc3a8a954","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T17:46:12Z","title_canon_sha256":"9e101ba0954487e3094c96997ea78cb77b7208c5b001dcc016486dc0969e13d9"},"schema_version":"1.0","source":{"id":"2310.16029","kind":"arxiv","version":1}},"canonical_sha256":"855e236425aa2dcb302746a43205dcafaa9778f17dcb4d891359978043893454","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"855e236425aa2dcb302746a43205dcafaa9778f17dcb4d891359978043893454","first_computed_at":"2026-07-05T07:04:34.040245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:34.040245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9IgBsy5VPwx9BH08YXJCOgg0sYKwM1jIJnYlFEs7XmL0QUqgfmJ9YTghMIvuOX317givik3DQQgNFyI6NHy0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:34.040739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff40dbb83e2a9e76b9f873908fb4b7adf4cd3cd4a7a77c171e0e1b5d7bb6675c","sha256:f0c13fedbbb89c087ff711f1a1488cbeb91cec233c06b2bbe427e1284c167326"],"state_sha256":"da107a7affabb68799f25a8165976283764ec546ce31315319867885586aa165"}