{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BLXIGFOL7NPSRNUKYY7BJ4FQY6","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":"697dfe53647abe03a81d512e24798d28f86171be4dae0f3bdbc1b9fbedfe9bb1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-14T17:18:15Z","title_canon_sha256":"e60cabc7700d014b42b2cdf6bd2e3b79296a006b44b7fa2d0746b505998ecc34"},"schema_version":"1.0","source":{"id":"2403.09583","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09583","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09583v4","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09583","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_12","alias_value":"BLXIGFOL7NPS","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_16","alias_value":"BLXIGFOL7NPSRNUK","created_at":"2026-07-05T10:50:07Z"},{"alias_kind":"pith_short_8","alias_value":"BLXIGFOL","created_at":"2026-07-05T10:50:07Z"}],"graph_snapshots":[{"event_id":"sha256:2830417ca2436d71fdd96165e53c276036d1f8ddf56bdd2af8b9f4d618db43aa","target":"graph","created_at":"2026-07-05T10:50:07Z","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/2403.09583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In robot manipulation, Reinforcement Learning (RL) often suffers from low sample efficiency and uncertain convergence, especially in large observation and action spaces. Foundation Models (FMs) offer an alternative, demonstrating promise in zero-shot and few-shot settings. However, they can be unreliable due to limited physical and spatial understanding. We introduce ExploRLLM, a method that combines the strengths of both paradigms. In our approach, FMs improve RL convergence by generating policy code and efficient representations, while a residual RL agent compensates for the FMs' limited phy","authors_text":"Jelle Luijkx, Jens Kober, Runyu Ma, Zlatan Ajanovic","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-14T17:18:15Z","title":"ExploRLLM: Guiding Exploration in Reinforcement Learning with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09583","kind":"arxiv","version":4},"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":"sha256:73018abd4f4d6b0d1f162c12d204bb72edbe5b80dfe093b1c7b66d809c572e9b","target":"record","created_at":"2026-07-05T10:50:07Z","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":"697dfe53647abe03a81d512e24798d28f86171be4dae0f3bdbc1b9fbedfe9bb1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-03-14T17:18:15Z","title_canon_sha256":"e60cabc7700d014b42b2cdf6bd2e3b79296a006b44b7fa2d0746b505998ecc34"},"schema_version":"1.0","source":{"id":"2403.09583","kind":"arxiv","version":4}},"canonical_sha256":"0aee8315cbfb5f28b68ac63e14f0b0c7b2c7dd1aede3207a212cf047026caf2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aee8315cbfb5f28b68ac63e14f0b0c7b2c7dd1aede3207a212cf047026caf2a","first_computed_at":"2026-07-05T10:50:07.897199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:50:07.897199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HuAsvL3Br8dQ65Jd0oalkLawR/416HyhGe0vpPKQfwQVyj9GrsHIi9YhWweMSkb7tpJSsUEkq89hWDE7Zk+7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:50:07.897637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09583","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73018abd4f4d6b0d1f162c12d204bb72edbe5b80dfe093b1c7b66d809c572e9b","sha256:2830417ca2436d71fdd96165e53c276036d1f8ddf56bdd2af8b9f4d618db43aa"],"state_sha256":"ec8654b2562b22c5ea4caf58932edbd85b79796ca51c8e780b84412120a4ad01"}