{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VSK3SUVVCS5ZBJRGDO5WUEPYLN","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":"8339af71329d6bc46a696ea203da755f37bed92ca4f892a893a691ec2072d7d1","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-11T04:13:26Z","title_canon_sha256":"d38dadf84c26c3889bc6e894a2cf16db7e64e42a79470c407214d44d4643a41a"},"schema_version":"1.0","source":{"id":"2403.06420","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06420","created_at":"2026-07-05T07:57:50Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06420v2","created_at":"2026-07-05T07:57:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06420","created_at":"2026-07-05T07:57:50Z"},{"alias_kind":"pith_short_12","alias_value":"VSK3SUVVCS5Z","created_at":"2026-07-05T07:57:50Z"},{"alias_kind":"pith_short_16","alias_value":"VSK3SUVVCS5ZBJRG","created_at":"2026-07-05T07:57:50Z"},{"alias_kind":"pith_short_8","alias_value":"VSK3SUVV","created_at":"2026-07-05T07:57:50Z"}],"graph_snapshots":[{"event_id":"sha256:3434b6e45ed9e9363ebeadf109acfaef3ddbf177a5e8ced0212b389171c6ac15","target":"graph","created_at":"2026-07-05T07:57:50Z","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/2403.06420/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has demonstrated its capability in solving various tasks but is notorious for its low sample efficiency. In this paper, we propose RLingua, a framework that can leverage the internal knowledge of large language models (LLMs) to reduce the sample complexity of RL in robotic manipulations. To this end, we first present a method for extracting the prior knowledge of LLMs by prompt engineering so that a preliminary rule-based robot controller for a specific task can be generated in a user-friendly manner. Despite being imperfect, the LLM-generated robot controller is ut","authors_text":"Liangjun Zhang, Liangliang Chen, Shiyu Jin, Ying Zhang, Yutian Lei","cross_cats":["cs.AI","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-11T04:13:26Z","title":"RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06420","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":"sha256:01f7bd348c933ef6cbd48b1bc6f07bf994cb9dd8b583293b0db6a98c2ad18828","target":"record","created_at":"2026-07-05T07:57:50Z","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":"8339af71329d6bc46a696ea203da755f37bed92ca4f892a893a691ec2072d7d1","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-11T04:13:26Z","title_canon_sha256":"d38dadf84c26c3889bc6e894a2cf16db7e64e42a79470c407214d44d4643a41a"},"schema_version":"1.0","source":{"id":"2403.06420","kind":"arxiv","version":2}},"canonical_sha256":"ac95b952b514bb90a6261bbb6a11f85b5e80e37d0ed0df057f2047f34a997168","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac95b952b514bb90a6261bbb6a11f85b5e80e37d0ed0df057f2047f34a997168","first_computed_at":"2026-07-05T07:57:50.912622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:50.912622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cKrnDLdxjDDGkOPp1iYzZR7Dkz2HGqhXD3/FpNfi1jBlH4DFo3PjFObughDy2/A2sk88g0+6pP25/vlHfGi9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:50.913128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06420","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01f7bd348c933ef6cbd48b1bc6f07bf994cb9dd8b583293b0db6a98c2ad18828","sha256:3434b6e45ed9e9363ebeadf109acfaef3ddbf177a5e8ced0212b389171c6ac15"],"state_sha256":"dc896da3698723032240cc74e70a900181ebc04a05e91e10c697ee69bd7d1f1d"}