{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CLEBFYI5EFASIMLEU62XSZ57VK","short_pith_number":"pith:CLEBFYI5","canonical_record":{"source":{"id":"2410.07927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T13:54:11Z","cross_cats_sorted":[],"title_canon_sha256":"589af001907bfd437bee4626efb66f0392fa807298acb6f51f79f033053726bc","abstract_canon_sha256":"ccfe0f460b305e145e1ce20ea65e03b38e51fdd3aaf5eb08f791c89ace758efb"},"schema_version":"1.0"},"canonical_sha256":"12c812e11d2141243164a7b57967bfaaaaf82aee0776ff1c0f2f82e512e1b6a6","source":{"kind":"arxiv","id":"2410.07927","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07927","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07927v1","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07927","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"CLEBFYI5EFAS","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"CLEBFYI5EFASIMLE","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"CLEBFYI5","created_at":"2026-07-05T09:18:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CLEBFYI5EFASIMLEU62XSZ57VK","target":"record","payload":{"canonical_record":{"source":{"id":"2410.07927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T13:54:11Z","cross_cats_sorted":[],"title_canon_sha256":"589af001907bfd437bee4626efb66f0392fa807298acb6f51f79f033053726bc","abstract_canon_sha256":"ccfe0f460b305e145e1ce20ea65e03b38e51fdd3aaf5eb08f791c89ace758efb"},"schema_version":"1.0"},"canonical_sha256":"12c812e11d2141243164a7b57967bfaaaaf82aee0776ff1c0f2f82e512e1b6a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:46.301897Z","signature_b64":"Iq0y6h7Jq78OJIFMXPhJYAkf9zyk4gMTAUd2ce7KL+l/B0MX0Xj1yLc4QwAJcFUwDCZKbiUPfrOtgGY1DoMgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12c812e11d2141243164a7b57967bfaaaaf82aee0776ff1c0f2f82e512e1b6a6","last_reissued_at":"2026-07-05T09:18:46.301410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:46.301410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.07927","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jjrdiobhAcg0IqLaj3tbn7VgHIJt2O0EzX2QYzteZhscLtY4bBzA9c2uRzpqDvUqxDoGoZALiUzvSeAijyN+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:54:52.116191Z"},"content_sha256":"18830b5d09a8822ca30a4df8c345137bad6b6f978600c7cf8a8c9892f1e1ceb2","schema_version":"1.0","event_id":"sha256:18830b5d09a8822ca30a4df8c345137bad6b6f978600c7cf8a8c9892f1e1ceb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CLEBFYI5EFASIMLEU62XSZ57VK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Reinforcement Learning with Large Language Model Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haifeng Zhang, Haitham Bou Ammar, Jun Wang, Mengyue Yang, Xidong Feng, Xue Yan, Yan Song","submitted_at":"2024-10-10T13:54:11Z","abstract_excerpt":"In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require extensive exploration and face challenges in generalizing across diverse environments due to their limited grasp of the underlying decision dynamics. In contrast, large language models (LLMs) have recently emerged as powerful general-purpose tools, due to their capacity to maintain vast amounts of domain-specific knowledge. To harness this rich prior knowledge for efficiently solving complex SDM tasks, we propose trea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07927","kind":"arxiv","version":1},"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/2410.07927/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":"2026-07-05T09:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aqoFJYboFFXCYvGi2z029EaFNfgQtPKMFA/LgOxo7Xn6wB0EzGUBYDDQ4lhy306wDk8LWQ2m/k/zcYjlEtqrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:54:52.117016Z"},"content_sha256":"f410f371e09467d5232ea13328c138f5cdf38d3a41ea97f581723abd7b1a0c69","schema_version":"1.0","event_id":"sha256:f410f371e09467d5232ea13328c138f5cdf38d3a41ea97f581723abd7b1a0c69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CLEBFYI5EFASIMLEU62XSZ57VK/bundle.json","state_url":"https://pith.science/pith/CLEBFYI5EFASIMLEU62XSZ57VK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CLEBFYI5EFASIMLEU62XSZ57VK/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":"2026-08-05T04:54:52Z","links":{"resolver":"https://pith.science/pith/CLEBFYI5EFASIMLEU62XSZ57VK","bundle":"https://pith.science/pith/CLEBFYI5EFASIMLEU62XSZ57VK/bundle.json","state":"https://pith.science/pith/CLEBFYI5EFASIMLEU62XSZ57VK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CLEBFYI5EFASIMLEU62XSZ57VK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CLEBFYI5EFASIMLEU62XSZ57VK","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":"ccfe0f460b305e145e1ce20ea65e03b38e51fdd3aaf5eb08f791c89ace758efb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T13:54:11Z","title_canon_sha256":"589af001907bfd437bee4626efb66f0392fa807298acb6f51f79f033053726bc"},"schema_version":"1.0","source":{"id":"2410.07927","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07927","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07927v1","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07927","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"CLEBFYI5EFAS","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"CLEBFYI5EFASIMLE","created_at":"2026-07-05T09:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"CLEBFYI5","created_at":"2026-07-05T09:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:f410f371e09467d5232ea13328c138f5cdf38d3a41ea97f581723abd7b1a0c69","target":"graph","created_at":"2026-07-05T09:18:46Z","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/2410.07927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require extensive exploration and face challenges in generalizing across diverse environments due to their limited grasp of the underlying decision dynamics. In contrast, large language models (LLMs) have recently emerged as powerful general-purpose tools, due to their capacity to maintain vast amounts of domain-specific knowledge. To harness this rich prior knowledge for efficiently solving complex SDM tasks, we propose trea","authors_text":"Haifeng Zhang, Haitham Bou Ammar, Jun Wang, Mengyue Yang, Xidong Feng, Xue Yan, Yan Song","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T13:54:11Z","title":"Efficient Reinforcement Learning with Large Language Model Priors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07927","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":"sha256:18830b5d09a8822ca30a4df8c345137bad6b6f978600c7cf8a8c9892f1e1ceb2","target":"record","created_at":"2026-07-05T09:18:46Z","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":"ccfe0f460b305e145e1ce20ea65e03b38e51fdd3aaf5eb08f791c89ace758efb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T13:54:11Z","title_canon_sha256":"589af001907bfd437bee4626efb66f0392fa807298acb6f51f79f033053726bc"},"schema_version":"1.0","source":{"id":"2410.07927","kind":"arxiv","version":1}},"canonical_sha256":"12c812e11d2141243164a7b57967bfaaaaf82aee0776ff1c0f2f82e512e1b6a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12c812e11d2141243164a7b57967bfaaaaf82aee0776ff1c0f2f82e512e1b6a6","first_computed_at":"2026-07-05T09:18:46.301410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:46.301410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iq0y6h7Jq78OJIFMXPhJYAkf9zyk4gMTAUd2ce7KL+l/B0MX0Xj1yLc4QwAJcFUwDCZKbiUPfrOtgGY1DoMgBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:46.301897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07927","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18830b5d09a8822ca30a4df8c345137bad6b6f978600c7cf8a8c9892f1e1ceb2","sha256:f410f371e09467d5232ea13328c138f5cdf38d3a41ea97f581723abd7b1a0c69"],"state_sha256":"c2326c7f4d4eb99c8fda1aaad156218068a170299a7ef1524d8203c5f2389bf1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xv/zpuHcNN0njXS5jEnEnYe9IRU0KuOUoum5FZOMi4JzLWBeXzOefgX6xvIRzmOyIn1jDDjhzAqwXiQgSvx+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:54:52.122535Z","bundle_sha256":"dd6eaa8264914ceae75e5beec3a17cefe6d3e0c938eb097ebb559072c8ea30b2"}}