{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YFVVINSV5OVPG27PV6ROTUG2EL","short_pith_number":"pith:YFVVINSV","canonical_record":{"source":{"id":"2310.20587","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T16:24:17Z","cross_cats_sorted":[],"title_canon_sha256":"6ca2ba61a59f38b715dbb7a4f3f130085dc3a773acb62f408ed8390f2864d0b6","abstract_canon_sha256":"63c3328c5b233a5dedeeb364c0d68cebec02cf81272f78cf3ce90ac237745a25"},"schema_version":"1.0"},"canonical_sha256":"c16b543655ebaaf36befafa2e9d0da22d016c6ec6cfe7e0b0bb05f5cec3ddb75","source":{"kind":"arxiv","id":"2310.20587","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20587","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20587v5","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20587","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"pith_short_12","alias_value":"YFVVINSV5OVP","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"pith_short_16","alias_value":"YFVVINSV5OVPG27P","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"pith_short_8","alias_value":"YFVVINSV","created_at":"2026-07-05T09:50:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YFVVINSV5OVPG27PV6ROTUG2EL","target":"record","payload":{"canonical_record":{"source":{"id":"2310.20587","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T16:24:17Z","cross_cats_sorted":[],"title_canon_sha256":"6ca2ba61a59f38b715dbb7a4f3f130085dc3a773acb62f408ed8390f2864d0b6","abstract_canon_sha256":"63c3328c5b233a5dedeeb364c0d68cebec02cf81272f78cf3ce90ac237745a25"},"schema_version":"1.0"},"canonical_sha256":"c16b543655ebaaf36befafa2e9d0da22d016c6ec6cfe7e0b0bb05f5cec3ddb75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:29.688424Z","signature_b64":"XMsuNTtR/3Hw/gdk81htwixkcDUm76gODmw82d+wc5shRydKmFjzBe12tMcv9GUQUq1KVfauuKjDMvstlGBUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c16b543655ebaaf36befafa2e9d0da22d016c6ec6cfe7e0b0bb05f5cec3ddb75","last_reissued_at":"2026-07-05T09:50:29.687965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:29.687965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.20587","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5yhaFWuXAb6hGRwWOUkr5kPJBbK6w/FRKcjhsJCd+bxqLbpqfnkesuMW1C78JffIa0jVQbNTujcVZQj+A7D0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:34:37.375365Z"},"content_sha256":"748ef7bf30ea7c305b72b7b69d814c10302d1695b0a65ce5376fbc04734b5c72","schema_version":"1.0","event_id":"sha256:748ef7bf30ea7c305b72b7b69d814c10302d1695b0a65ce5376fbc04734b5c72"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YFVVINSV5OVPG27PV6ROTUG2EL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huazhe Xu, Ruizhe Shi, Simon S. Du, Yanjie Ze, Yuyao Liu","submitted_at":"2023-10-31T16:24:17Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the in-domain data is limited. Given recent advances in Large Language Models (LLMs) and their few-shot learning prowess, this paper introduces $\\textbf{La}$nguage Models for $\\textbf{Mo}$tion Control ($\\textbf{LaMo}$), a general framework based on Decision Transformers to effectively use pre-trained Language Models (LMs) for offline RL. Our framework highlights four c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20587","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.20587/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:50:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNVQ06+hQ6wxrQOzAIK+vh5d8erCMGzDd99//0Ai7sP3KZtk1NEMx9o/ic4ZVDIJSzaplbXS9Jw+dFiXqhODBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:34:37.379907Z"},"content_sha256":"cc936596ebbc7e700866c2633ad0bf9d2957c870333e578cd186fa819712230a","schema_version":"1.0","event_id":"sha256:cc936596ebbc7e700866c2633ad0bf9d2957c870333e578cd186fa819712230a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/bundle.json","state_url":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFVVINSV5OVPG27PV6ROTUG2EL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:34:37Z","links":{"resolver":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL","bundle":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/bundle.json","state":"https://pith.science/pith/YFVVINSV5OVPG27PV6ROTUG2EL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFVVINSV5OVPG27PV6ROTUG2EL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YFVVINSV5OVPG27PV6ROTUG2EL","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":"63c3328c5b233a5dedeeb364c0d68cebec02cf81272f78cf3ce90ac237745a25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T16:24:17Z","title_canon_sha256":"6ca2ba61a59f38b715dbb7a4f3f130085dc3a773acb62f408ed8390f2864d0b6"},"schema_version":"1.0","source":{"id":"2310.20587","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.20587","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"arxiv_version","alias_value":"2310.20587v5","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20587","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"pith_short_12","alias_value":"YFVVINSV5OVP","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"pith_short_16","alias_value":"YFVVINSV5OVPG27P","created_at":"2026-07-05T09:50:29Z"},{"alias_kind":"pith_short_8","alias_value":"YFVVINSV","created_at":"2026-07-05T09:50:29Z"}],"graph_snapshots":[{"event_id":"sha256:cc936596ebbc7e700866c2633ad0bf9d2957c870333e578cd186fa819712230a","target":"graph","created_at":"2026-07-05T09:50:29Z","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/2310.20587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the in-domain data is limited. Given recent advances in Large Language Models (LLMs) and their few-shot learning prowess, this paper introduces $\\textbf{La}$nguage Models for $\\textbf{Mo}$tion Control ($\\textbf{LaMo}$), a general framework based on Decision Transformers to effectively use pre-trained Language Models (LMs) for offline RL. Our framework highlights four c","authors_text":"Huazhe Xu, Ruizhe Shi, Simon S. Du, Yanjie Ze, Yuyao Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T16:24:17Z","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20587","kind":"arxiv","version":5},"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":"sha256:748ef7bf30ea7c305b72b7b69d814c10302d1695b0a65ce5376fbc04734b5c72","target":"record","created_at":"2026-07-05T09:50:29Z","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":"63c3328c5b233a5dedeeb364c0d68cebec02cf81272f78cf3ce90ac237745a25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-31T16:24:17Z","title_canon_sha256":"6ca2ba61a59f38b715dbb7a4f3f130085dc3a773acb62f408ed8390f2864d0b6"},"schema_version":"1.0","source":{"id":"2310.20587","kind":"arxiv","version":5}},"canonical_sha256":"c16b543655ebaaf36befafa2e9d0da22d016c6ec6cfe7e0b0bb05f5cec3ddb75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c16b543655ebaaf36befafa2e9d0da22d016c6ec6cfe7e0b0bb05f5cec3ddb75","first_computed_at":"2026-07-05T09:50:29.687965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:29.687965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XMsuNTtR/3Hw/gdk81htwixkcDUm76gODmw82d+wc5shRydKmFjzBe12tMcv9GUQUq1KVfauuKjDMvstlGBUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:29.688424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.20587","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:748ef7bf30ea7c305b72b7b69d814c10302d1695b0a65ce5376fbc04734b5c72","sha256:cc936596ebbc7e700866c2633ad0bf9d2957c870333e578cd186fa819712230a"],"state_sha256":"62908f741836bd12916917e9569e3ae0edd239abf9580d8019198d46d30c6319"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+SUKSElLE934YETNuj7pClBTbnwz/aWppf8FZbIuTQu+YlKJhy501/T/9vI1tFjJZT4ybluQosSwqtWdeR1BBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:34:37.386956Z","bundle_sha256":"11d9b495ac7dddbf0746079775f4c86b6b707134e8592bd213e18ab6d31da88d"}}