{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OVDBONHQKCUO6J7EKDVBA76DHF","short_pith_number":"pith:OVDBONHQ","canonical_record":{"source":{"id":"2311.13373","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T13:15:42Z","cross_cats_sorted":[],"title_canon_sha256":"705d5b8aa94058b8c1a49cde9713f863e38e449723b4c80df1287085b471938a","abstract_canon_sha256":"7afaabd962425d28f85793ba5b4a47f1fa775deef02b5e82c7d5d80882f9313b"},"schema_version":"1.0"},"canonical_sha256":"75461734f050a8ef27e450ea107fc3397d68ffea647662811546237387454cc9","source":{"kind":"arxiv","id":"2311.13373","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13373","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13373v6","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13373","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"pith_short_12","alias_value":"OVDBONHQKCUO","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"pith_short_16","alias_value":"OVDBONHQKCUO6J7E","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"pith_short_8","alias_value":"OVDBONHQ","created_at":"2026-07-05T08:23:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OVDBONHQKCUO6J7EKDVBA76DHF","target":"record","payload":{"canonical_record":{"source":{"id":"2311.13373","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T13:15:42Z","cross_cats_sorted":[],"title_canon_sha256":"705d5b8aa94058b8c1a49cde9713f863e38e449723b4c80df1287085b471938a","abstract_canon_sha256":"7afaabd962425d28f85793ba5b4a47f1fa775deef02b5e82c7d5d80882f9313b"},"schema_version":"1.0"},"canonical_sha256":"75461734f050a8ef27e450ea107fc3397d68ffea647662811546237387454cc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:13.833362Z","signature_b64":"BDhv1BdshAxrBveEJXuWh+mziUEnJhp4vZramRRXAj19MV9Hxn97PXLTUxwzQeLkBrOogKBgcdDtqac3SwV1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75461734f050a8ef27e450ea107fc3397d68ffea647662811546237387454cc9","last_reissued_at":"2026-07-05T08:23:13.832835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:13.832835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.13373","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:23:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JkCZSf7n9Jn8V5F4RP0zNKnusJ/BklIFL283uEihycgIHiMF4BD1BeKp+/uKSGoUSTIVezWA9JHWaYwWziDhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:42.019562Z"},"content_sha256":"9b6d12d2c03e34c17944340753658356eed6c2e75564ae6ab84a19fcf8dcb308","schema_version":"1.0","event_id":"sha256:9b6d12d2c03e34c17944340753658356eed6c2e75564ae6ab84a19fcf8dcb308"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OVDBONHQKCUO6J7EKDVBA76DHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Hu, Bin Liu, Chenyang Zhao, Pu Zhang, Zihao Zhou","submitted_at":"2023-11-22T13:15:42Z","abstract_excerpt":"Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling specific target problems, particularly in real-time dynamic environments. Additionally, deploying an LLM-based agent in practical scenarios can be both costly and time-consuming. On the other hand, reinforcement learning (RL) approaches train agents that specialize in the target task but often suffer from low sampling efficiency and high exploration costs. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13373","kind":"arxiv","version":6},"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/2311.13373/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":"2026-07-05T08:23:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mR7TQtQZ45VL4U7KGUBIdWpEbWiiNr1g2e3+jr0KHgw48n3GV5zFGpOGNVzmAIb0SmCWZe/CgGOnnMu2DZtgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T10:22:42.020203Z"},"content_sha256":"ebbfc807e273e03a518d9ae8d22cc3125ac1c619ef4222e93ffe00f41120dff6","schema_version":"1.0","event_id":"sha256:ebbfc807e273e03a518d9ae8d22cc3125ac1c619ef4222e93ffe00f41120dff6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVDBONHQKCUO6J7EKDVBA76DHF/bundle.json","state_url":"https://pith.science/pith/OVDBONHQKCUO6J7EKDVBA76DHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVDBONHQKCUO6J7EKDVBA76DHF/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":"2026-08-08T10:22:42Z","links":{"resolver":"https://pith.science/pith/OVDBONHQKCUO6J7EKDVBA76DHF","bundle":"https://pith.science/pith/OVDBONHQKCUO6J7EKDVBA76DHF/bundle.json","state":"https://pith.science/pith/OVDBONHQKCUO6J7EKDVBA76DHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVDBONHQKCUO6J7EKDVBA76DHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OVDBONHQKCUO6J7EKDVBA76DHF","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":"7afaabd962425d28f85793ba5b4a47f1fa775deef02b5e82c7d5d80882f9313b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T13:15:42Z","title_canon_sha256":"705d5b8aa94058b8c1a49cde9713f863e38e449723b4c80df1287085b471938a"},"schema_version":"1.0","source":{"id":"2311.13373","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13373","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13373v6","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13373","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"pith_short_12","alias_value":"OVDBONHQKCUO","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"pith_short_16","alias_value":"OVDBONHQKCUO6J7E","created_at":"2026-07-05T08:23:13Z"},{"alias_kind":"pith_short_8","alias_value":"OVDBONHQ","created_at":"2026-07-05T08:23:13Z"}],"graph_snapshots":[{"event_id":"sha256:ebbfc807e273e03a518d9ae8d22cc3125ac1c619ef4222e93ffe00f41120dff6","target":"graph","created_at":"2026-07-05T08:23:13Z","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/2311.13373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling specific target problems, particularly in real-time dynamic environments. Additionally, deploying an LLM-based agent in practical scenarios can be both costly and time-consuming. On the other hand, reinforcement learning (RL) approaches train agents that specialize in the target task but often suffer from low sampling efficiency and high exploration costs. In","authors_text":"Bin Hu, Bin Liu, Chenyang Zhao, Pu Zhang, Zihao Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T13:15:42Z","title":"Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13373","kind":"arxiv","version":6},"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":"sha256:9b6d12d2c03e34c17944340753658356eed6c2e75564ae6ab84a19fcf8dcb308","target":"record","created_at":"2026-07-05T08:23:13Z","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":"7afaabd962425d28f85793ba5b4a47f1fa775deef02b5e82c7d5d80882f9313b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-11-22T13:15:42Z","title_canon_sha256":"705d5b8aa94058b8c1a49cde9713f863e38e449723b4c80df1287085b471938a"},"schema_version":"1.0","source":{"id":"2311.13373","kind":"arxiv","version":6}},"canonical_sha256":"75461734f050a8ef27e450ea107fc3397d68ffea647662811546237387454cc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75461734f050a8ef27e450ea107fc3397d68ffea647662811546237387454cc9","first_computed_at":"2026-07-05T08:23:13.832835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:13.832835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BDhv1BdshAxrBveEJXuWh+mziUEnJhp4vZramRRXAj19MV9Hxn97PXLTUxwzQeLkBrOogKBgcdDtqac3SwV1Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:13.833362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13373","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b6d12d2c03e34c17944340753658356eed6c2e75564ae6ab84a19fcf8dcb308","sha256:ebbfc807e273e03a518d9ae8d22cc3125ac1c619ef4222e93ffe00f41120dff6"],"state_sha256":"473f76ea901c955cbfb8e10a585cd0f330ea2a0d5ff303bfe75cd9607f698b8b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hVDzk4jjEPEx0XL0SzPLx+pUGNA6s+a05aGVIeKUDcvVwufJ9g+ewBdXEnbf4Ma0Rvwq54K0oumF7A2CgXqlDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T10:22:42.024724Z","bundle_sha256":"ed624ba9f866d29df2ef2fa863ebec4b066405d8c74bdfae3d9176bcbd28cf5f"}}