{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MWRAIUQULVTOBFHDOIANREXK5N","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":"0d8db954811a892b1ffa50d2be5fd20b767969309c6ecd9a551c002e9be36952","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T13:15:54Z","title_canon_sha256":"eec81e8b453313db35a4595535d0602b5ba8fc7ca1c701ef4be5a693788275c8"},"schema_version":"1.0","source":{"id":"2505.11221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11221","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11221v1","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11221","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"MWRAIUQULVTO","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"MWRAIUQULVTOBFHD","created_at":"2026-07-05T11:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"MWRAIUQU","created_at":"2026-07-05T11:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:e010aec50fc6424594d4212cdb9280216f82e863b08cb2d8ed575b837425dfec","target":"graph","created_at":"2026-07-05T11:04:12Z","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/2505.11221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research highlights the potential of multimodal foundation models in tackling complex decision-making challenges. However, their large parameters make real-world deployment resource-intensive and often impractical for constrained systems. Reinforcement learning (RL) shows promise for task-specific agents but suffers from high sample complexity, limiting practical applications. To address these challenges, we introduce LVLM to Policy (LVLM2P), a novel framework that distills knowledge from large vision-language models (LVLM) into more efficient RL agents. Our approach leverages the LVLM ","authors_text":"Chang D. Yoo, Donghoon Lee, Tung M. Luu, Younghwan Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T13:15:54Z","title":"Sample Efficient Reinforcement Learning via Large Vision Language Model Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11221","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":"sha256:39c480e5256a45bcf6336b8b7b41a5a3c12ff7cb6c5942534f9220409a7c0eee","target":"record","created_at":"2026-07-05T11:04:12Z","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":"0d8db954811a892b1ffa50d2be5fd20b767969309c6ecd9a551c002e9be36952","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T13:15:54Z","title_canon_sha256":"eec81e8b453313db35a4595535d0602b5ba8fc7ca1c701ef4be5a693788275c8"},"schema_version":"1.0","source":{"id":"2505.11221","kind":"arxiv","version":1}},"canonical_sha256":"65a20452145d66e094e37200d892eaeb5da4c5e7c4119a179e552cc3bae6af3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65a20452145d66e094e37200d892eaeb5da4c5e7c4119a179e552cc3bae6af3e","first_computed_at":"2026-07-05T11:04:12.964137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:12.964137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gbHwIPhcQPlXx1mha8L4A7cT6OKrgwEM+qrnqBP1N2K3B5w0gwAk5JI1KU/+K4UDKHUiNWR/CcBik0oQ2EVAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:12.964646Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39c480e5256a45bcf6336b8b7b41a5a3c12ff7cb6c5942534f9220409a7c0eee","sha256:e010aec50fc6424594d4212cdb9280216f82e863b08cb2d8ed575b837425dfec"],"state_sha256":"fbb6d7ec8469eabb85c65a063c06105c985697a5a54e80230865efab7b4f5e0a"}