{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NOG6FTTN7M4XUQG55GQ4EAWERQ","short_pith_number":"pith:NOG6FTTN","canonical_record":{"source":{"id":"2405.16450","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:48Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"3fe7cab0ad40595644c4aa5242ee181b797d2274a86d35e80c42601b479ae24e","abstract_canon_sha256":"03bbf097c008bf1472be2267efd5f4fa99463afb305fd8256f3e38a421b2b54f"},"schema_version":"1.0"},"canonical_sha256":"6b8de2ce6dfb397a40dde9a1c202c48c02055370fc15f5fa0bf7024d53dd5092","source":{"kind":"arxiv","id":"2405.16450","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16450","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16450v3","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16450","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"NOG6FTTN7M4X","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"NOG6FTTN7M4XUQG5","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"NOG6FTTN","created_at":"2026-07-05T10:28:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NOG6FTTN7M4XUQG55GQ4EAWERQ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16450","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:48Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"3fe7cab0ad40595644c4aa5242ee181b797d2274a86d35e80c42601b479ae24e","abstract_canon_sha256":"03bbf097c008bf1472be2267efd5f4fa99463afb305fd8256f3e38a421b2b54f"},"schema_version":"1.0"},"canonical_sha256":"6b8de2ce6dfb397a40dde9a1c202c48c02055370fc15f5fa0bf7024d53dd5092","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:16.818547Z","signature_b64":"w+eeB4M277zfeeq0lUeT+z/Y4qZsMXuSxXt6sankpcveVd0hJfQdBez3THA19rYezgqlkRfm0nkqPhU0pJT/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b8de2ce6dfb397a40dde9a1c202c48c02055370fc15f5fa0bf7024d53dd5092","last_reissued_at":"2026-07-05T10:28:16.817587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:16.817587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16450","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fS6z9UQ5lDYLFdL3Np+KIeRWV9VMu70nNUhXED8ZqX5dUScdyWQ/gWFnKnlep7XprNXHMGQlh1mPcmxOEX1cDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:59:21.633526Z"},"content_sha256":"777b73700ce3c7c857b6d3c6549208f031a445434074a333581ae8a2d3c951ce","schema_version":"1.0","event_id":"sha256:777b73700ce3c7c857b6d3c6549208f031a445434074a333581ae8a2d3c951ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NOG6FTTN7M4XUQG55GQ4EAWERQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.LG","authors_text":"Chan-Hung Yu, Cheng-Wei Hung, Max Liu, Shao-Hua Sun, Wei-Hsu Lee, Yen-Chun Chen","submitted_at":"2024-05-26T06:33:48Z","abstract_excerpt":"Programmatic reinforcement learning (PRL) has been explored for representing policies through programs as a means to achieve interpretability and generalization. Despite promising outcomes, current state-of-the-art PRL methods are hindered by sample inefficiency, necessitating tens of millions of program-environment interactions. To tackle this challenge, we introduce a novel LLM-guided search framework (LLM-GS). Our key insight is to leverage the programming expertise and common sense reasoning of LLMs to enhance the efficiency of assumption-free, random-guessing search methods. We address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16450","kind":"arxiv","version":3},"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/2405.16450/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":"2026-07-05T10:28:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OeVDz+lpP4Vno/hDkCMN4mA0z8F0YBY9dw8UatI2elNLT+iNiGnHpZ2Z4CSeZNQp+o4LbR+zq6J6fGB+GY9TBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:59:21.634897Z"},"content_sha256":"90da2cd618944dd3f382b9ef1f2b1e0d8a5d4dda108bea16d60715de1a47fe4a","schema_version":"1.0","event_id":"sha256:90da2cd618944dd3f382b9ef1f2b1e0d8a5d4dda108bea16d60715de1a47fe4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NOG6FTTN7M4XUQG55GQ4EAWERQ/bundle.json","state_url":"https://pith.science/pith/NOG6FTTN7M4XUQG55GQ4EAWERQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NOG6FTTN7M4XUQG55GQ4EAWERQ/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":"2026-08-18T11:59:21Z","links":{"resolver":"https://pith.science/pith/NOG6FTTN7M4XUQG55GQ4EAWERQ","bundle":"https://pith.science/pith/NOG6FTTN7M4XUQG55GQ4EAWERQ/bundle.json","state":"https://pith.science/pith/NOG6FTTN7M4XUQG55GQ4EAWERQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NOG6FTTN7M4XUQG55GQ4EAWERQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NOG6FTTN7M4XUQG55GQ4EAWERQ","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":"03bbf097c008bf1472be2267efd5f4fa99463afb305fd8256f3e38a421b2b54f","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:48Z","title_canon_sha256":"3fe7cab0ad40595644c4aa5242ee181b797d2274a86d35e80c42601b479ae24e"},"schema_version":"1.0","source":{"id":"2405.16450","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16450","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16450v3","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16450","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"pith_short_12","alias_value":"NOG6FTTN7M4X","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"pith_short_16","alias_value":"NOG6FTTN7M4XUQG5","created_at":"2026-07-05T10:28:16Z"},{"alias_kind":"pith_short_8","alias_value":"NOG6FTTN","created_at":"2026-07-05T10:28:16Z"}],"graph_snapshots":[{"event_id":"sha256:90da2cd618944dd3f382b9ef1f2b1e0d8a5d4dda108bea16d60715de1a47fe4a","target":"graph","created_at":"2026-07-05T10:28:16Z","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/2405.16450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Programmatic reinforcement learning (PRL) has been explored for representing policies through programs as a means to achieve interpretability and generalization. Despite promising outcomes, current state-of-the-art PRL methods are hindered by sample inefficiency, necessitating tens of millions of program-environment interactions. To tackle this challenge, we introduce a novel LLM-guided search framework (LLM-GS). Our key insight is to leverage the programming expertise and common sense reasoning of LLMs to enhance the efficiency of assumption-free, random-guessing search methods. We address th","authors_text":"Chan-Hung Yu, Cheng-Wei Hung, Max Liu, Shao-Hua Sun, Wei-Hsu Lee, Yen-Chun Chen","cross_cats":["cs.AI","cs.PL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:48Z","title":"Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16450","kind":"arxiv","version":3},"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":"sha256:777b73700ce3c7c857b6d3c6549208f031a445434074a333581ae8a2d3c951ce","target":"record","created_at":"2026-07-05T10:28:16Z","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":"03bbf097c008bf1472be2267efd5f4fa99463afb305fd8256f3e38a421b2b54f","cross_cats_sorted":["cs.AI","cs.PL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T06:33:48Z","title_canon_sha256":"3fe7cab0ad40595644c4aa5242ee181b797d2274a86d35e80c42601b479ae24e"},"schema_version":"1.0","source":{"id":"2405.16450","kind":"arxiv","version":3}},"canonical_sha256":"6b8de2ce6dfb397a40dde9a1c202c48c02055370fc15f5fa0bf7024d53dd5092","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b8de2ce6dfb397a40dde9a1c202c48c02055370fc15f5fa0bf7024d53dd5092","first_computed_at":"2026-07-05T10:28:16.817587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:16.817587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w+eeB4M277zfeeq0lUeT+z/Y4qZsMXuSxXt6sankpcveVd0hJfQdBez3THA19rYezgqlkRfm0nkqPhU0pJT/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:16.818547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16450","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:777b73700ce3c7c857b6d3c6549208f031a445434074a333581ae8a2d3c951ce","sha256:90da2cd618944dd3f382b9ef1f2b1e0d8a5d4dda108bea16d60715de1a47fe4a"],"state_sha256":"6af666a110e69a346b29ee1d1880519090bbfab885b8753a5a5cc742f0e6ab50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4SYrwb/np9wa1jAA837/Ac14/U33MTEAKhqw7lrDe2J877SMrHDu2s+XbeUyZtse2A+I/coRZ7XxXDUXpRQlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:59:21.641690Z","bundle_sha256":"78668811a75f1d78afab22c32b144685518e0c532abde7858bfb681feadf67cd"}}