{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QLUR2MTAQI2N64OEVDQANKFXT5","short_pith_number":"pith:QLUR2MTA","canonical_record":{"source":{"id":"2505.20671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T03:40:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c06e14b40e1ba225cd6b9b1bac19230f43611b70544f396e51ea76720e5c7fc7","abstract_canon_sha256":"03165f2cc179ae988ade54af9f04582c2fd425043d318e6081c146f7737e1e9b"},"schema_version":"1.0"},"canonical_sha256":"82e91d32608234df71c4a8e006a8b79f7c7de5279b0f323b4a5cfdd6b0f18c5b","source":{"kind":"arxiv","id":"2505.20671","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QLUR2MTAQI2N64OEVDQANKFXT5","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T03:40:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c06e14b40e1ba225cd6b9b1bac19230f43611b70544f396e51ea76720e5c7fc7","abstract_canon_sha256":"03165f2cc179ae988ade54af9f04582c2fd425043d318e6081c146f7737e1e9b"},"schema_version":"1.0"},"canonical_sha256":"82e91d32608234df71c4a8e006a8b79f7c7de5279b0f323b4a5cfdd6b0f18c5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:16.317814Z","signature_b64":"f/qJlKHgHU5cTZDVYD/E3Vt6hPT85D/m543u5bYE5aszQcGX/ueuDuYBdTWfT8H8UGxKRjfuP7rzrSRalakTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82e91d32608234df71c4a8e006a8b79f7c7de5279b0f323b4a5cfdd6b0f18c5b","last_reissued_at":"2026-07-05T11:10:16.317345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:16.317345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20671","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":"2026-07-05T11:10:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9BBsRJJ9AjPrJW0J8taX0ISygKCkvNPsIIFJqXWpjPL1Xmt+gMlUyU/bBxqIzFvEYFB3JTTyIsq7FA6b35tPAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:34:14.347726Z"},"content_sha256":"b6211858cdb05005ce2e3f47593c6b7aef95dbab08524f63418e5bd968e0b872","schema_version":"1.0","event_id":"sha256:b6211858cdb05005ce2e3f47593c6b7aef95dbab08524f63418e5bd968e0b872"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QLUR2MTAQI2N64OEVDQANKFXT5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Heng Tan, Hua Yan, Yu Yang","submitted_at":"2025-05-27T03:40:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20671","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/2505.20671/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":"2026-07-05T11:10:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C1Ck3EK83AG4bvezCsIdlHLVDVOsTSgvxSg8U+tVKMedjGaj5tR3FCy6mGILeaTQVdbMVB09j7MaOdYFPj8kCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:34:14.348303Z"},"content_sha256":"ed0896cd9116401e30c2043f6acfdd841663435d3b96c558f9ba2a6e9ad0b1cf","schema_version":"1.0","event_id":"sha256:ed0896cd9116401e30c2043f6acfdd841663435d3b96c558f9ba2a6e9ad0b1cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/bundle.json","state_url":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QLUR2MTAQI2N64OEVDQANKFXT5/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":"2026-08-08T01:34:14Z","links":{"resolver":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5","bundle":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/bundle.json","state":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QLUR2MTAQI2N64OEVDQANKFXT5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IW/ZUHEXVopxWBurkwcV1dsxZNnJkZ/IK5+HgKKWhUUvPp6122U7dKp/sKBnvnROr9JKF8oMqNrrJS/1emGaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:34:14.352030Z","bundle_sha256":"e89891003f7ba285653a6f8b5a7e18c24d0542411d30e95c2f7081fbfc07b789"}}