{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YPOGPC3PRQG46HN6NOKZD4A2GO","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":"3109a032f35b5adf157f6ddb35ea7fd65014351f7b035824d4716d41c1173f90","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T07:05:10Z","title_canon_sha256":"41cb798e836d096a27d3a1934d58dd0ddaaee425b72fdab5a9df71f37ddae51e"},"schema_version":"1.0","source":{"id":"2607.24062","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24062","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24062v1","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24062","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"YPOGPC3PRQG4","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"YPOGPC3PRQG46HN6","created_at":"2026-07-28T01:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"YPOGPC3P","created_at":"2026-07-28T01:23:43Z"}],"graph_snapshots":[{"event_id":"sha256:f6247ee518028b32b7269d62a086ea56ec466d5e7336e40c68494817c56da2bd","target":"graph","created_at":"2026-07-28T01:23:43Z","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/2607.24062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) training for Large Language Models (LLMs) often suffers from instability due to the discrepancy between training and inference. This training-inference discrepancy stems from two primary factors: an architectural separation between training and inference engines, and the use of low-precision quantization in inference versus higher-precision computation in training. To address training instability issues caused by high training-inference discrepancy, we present the principles and methods for its adaptive control. We propose Adaptive Control Reinforcement Learning (AC","authors_text":"Liangsheng Zhu, Qiang Chen, Qihong Lin, Sihao Wang, Wenwu Fan, Zhijie Xia, Zhuo Zheng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T07:05:10Z","title":"ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24062","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":"sha256:934a74653ee0efb6d3f7aef0ef18a4e64a99daab0ce9913f0e9f671da7a390a7","target":"record","created_at":"2026-07-28T01:23:43Z","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":"3109a032f35b5adf157f6ddb35ea7fd65014351f7b035824d4716d41c1173f90","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T07:05:10Z","title_canon_sha256":"41cb798e836d096a27d3a1934d58dd0ddaaee425b72fdab5a9df71f37ddae51e"},"schema_version":"1.0","source":{"id":"2607.24062","kind":"arxiv","version":1}},"canonical_sha256":"c3dc678b6f8c0dcf1dbe6b9591f01a33928f2c5ac01dba4d5e1c6a3ad5535988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3dc678b6f8c0dcf1dbe6b9591f01a33928f2c5ac01dba4d5e1c6a3ad5535988","first_computed_at":"2026-07-28T01:23:43.482258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:43.482258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zzLFP7vXRQHKd0ONb/IB4sAVmHBRoSkfFI7eIBHkPHwCZuD0FA6whB0VT4jjyZV522BU3Hhk3HVSbzvFytVnBQ==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:43.483056Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24062","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:934a74653ee0efb6d3f7aef0ef18a4e64a99daab0ce9913f0e9f671da7a390a7","sha256:f6247ee518028b32b7269d62a086ea56ec466d5e7336e40c68494817c56da2bd"],"state_sha256":"f78b061648fae3522a27d91763550a1c231c5f94baa89304e0d2076e77987044"}