{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZLKNRCPK4MAAJTZ7IFB5LDAWON","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":"90203bb472ccf95dfc93cf221b7643d2228cec1eb7baa587844fc1906dc9e501","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T02:12:34Z","title_canon_sha256":"0963e08d11ae67471061ede16b1314bcee2e79ea78263a6a6b5adf61f51fc087"},"schema_version":"1.0","source":{"id":"2411.05273","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05273","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05273v2","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05273","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZLKNRCPK4MAA","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZLKNRCPK4MAAJTZ7","created_at":"2026-07-05T11:49:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZLKNRCPK","created_at":"2026-07-05T11:49:05Z"}],"graph_snapshots":[{"event_id":"sha256:533bec0a55ac6f3d6c011b814342bf4c27ba2dbdb2bdb90a476d8f1bd5e71e18","target":"graph","created_at":"2026-07-05T11:49:05Z","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/2411.05273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert demonstrations is slow, costly, and risky. However, most existing offline RL works assume the dataset is already labeled with the task rewards, a process that often requires significant human effort, especially when ground-truth states are hard to ascertain (e.g., in the real-world). In this paper, we build on prior work, specifically RL-VLM-F, and propose a","authors_text":"David Held, Navin Sriram Ravie, Sreyas Venkataraman, Yufei Wang, Zackory Erickson, Ziyu Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T02:12:34Z","title":"Real-World Offline Reinforcement Learning from Vision Language Model Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05273","kind":"arxiv","version":2},"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":"sha256:0d96d503992fb9bb46272cfb20b972ae5a1229dca828e859d9e8ef4f1fc4eef2","target":"record","created_at":"2026-07-05T11:49:05Z","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":"90203bb472ccf95dfc93cf221b7643d2228cec1eb7baa587844fc1906dc9e501","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-08T02:12:34Z","title_canon_sha256":"0963e08d11ae67471061ede16b1314bcee2e79ea78263a6a6b5adf61f51fc087"},"schema_version":"1.0","source":{"id":"2411.05273","kind":"arxiv","version":2}},"canonical_sha256":"cad4d889eae30004cf3f4143d58c167378a27d44df7edae3081ee47bd6b4c862","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cad4d889eae30004cf3f4143d58c167378a27d44df7edae3081ee47bd6b4c862","first_computed_at":"2026-07-05T11:49:05.229520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:05.229520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DNTb5s6QXKvHSjP4QkH/PCms9vU7b2NoxaUFoeN/Y72UaQVhFTR85YeBJ+3hQgioahknTlBtjPn4JC0nmtqFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:05.230027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05273","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d96d503992fb9bb46272cfb20b972ae5a1229dca828e859d9e8ef4f1fc4eef2","sha256:533bec0a55ac6f3d6c011b814342bf4c27ba2dbdb2bdb90a476d8f1bd5e71e18"],"state_sha256":"c6f467839f3cee0c624c8a2b75d27001682405f1a31894057bba24c12a92b2e8"}