{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QLUR2MTAQI2N64OEVDQANKFXT5","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":"03165f2cc179ae988ade54af9f04582c2fd425043d318e6081c146f7737e1e9b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T03:40:02Z","title_canon_sha256":"c06e14b40e1ba225cd6b9b1bac19230f43611b70544f396e51ea76720e5c7fc7"},"schema_version":"1.0","source":{"id":"2505.20671","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20671","created_at":"2026-07-05T11:10:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20671v1","created_at":"2026-07-05T11:10:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20671","created_at":"2026-07-05T11:10:16Z"},{"alias_kind":"pith_short_12","alias_value":"QLUR2MTAQI2N","created_at":"2026-07-05T11:10:16Z"},{"alias_kind":"pith_short_16","alias_value":"QLUR2MTAQI2N64OE","created_at":"2026-07-05T11:10:16Z"},{"alias_kind":"pith_short_8","alias_value":"QLUR2MTA","created_at":"2026-07-05T11:10:16Z"}],"graph_snapshots":[{"event_id":"sha256:ed0896cd9116401e30c2043f6acfdd841663435d3b96c558f9ba2a6e9ad0b1cf","target":"graph","created_at":"2026-07-05T11:10:16Z","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/2505.20671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing approaches to mitigate training bottlenecks typically fall into two categories: (i) Automated policy refinement, which identifies critical states from past trajectories to guide policy updates, but suffers from costly and uncertain model training; and (ii) Human-in-the-loop refinement, where human feedback is used to correct agent behavior, but this does not sc","authors_text":"Heng Tan, Hua Yan, Yu Yang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T03:40:02Z","title":"LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20671","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:b6211858cdb05005ce2e3f47593c6b7aef95dbab08524f63418e5bd968e0b872","target":"record","created_at":"2026-07-05T11:10:16Z","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":"03165f2cc179ae988ade54af9f04582c2fd425043d318e6081c146f7737e1e9b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T03:40:02Z","title_canon_sha256":"c06e14b40e1ba225cd6b9b1bac19230f43611b70544f396e51ea76720e5c7fc7"},"schema_version":"1.0","source":{"id":"2505.20671","kind":"arxiv","version":1}},"canonical_sha256":"82e91d32608234df71c4a8e006a8b79f7c7de5279b0f323b4a5cfdd6b0f18c5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82e91d32608234df71c4a8e006a8b79f7c7de5279b0f323b4a5cfdd6b0f18c5b","first_computed_at":"2026-07-05T11:10:16.317345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:16.317345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f/qJlKHgHU5cTZDVYD/E3Vt6hPT85D/m543u5bYE5aszQcGX/ueuDuYBdTWfT8H8UGxKRjfuP7rzrSRalakTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:16.317814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20671","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6211858cdb05005ce2e3f47593c6b7aef95dbab08524f63418e5bd968e0b872","sha256:ed0896cd9116401e30c2043f6acfdd841663435d3b96c558f9ba2a6e9ad0b1cf"],"state_sha256":"bf9cba09daff91b0232ec4dd0cfd08a175b09ea4907b9f1fee48d1cd949372b0"}