{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4LOUX63FFR2HW5BKYB3B4VC4O4","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":"c0941671937150f8892ea3df075659267190e6be84ff8baeb05a203d08279029","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T05:18:54Z","title_canon_sha256":"cabb7c70e80ad642f109cdbb06eff01d3438353bc7cc5c6ed386d1c6b957778e"},"schema_version":"1.0","source":{"id":"2506.05748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05748","created_at":"2026-07-05T11:17:09Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05748v1","created_at":"2026-07-05T11:17:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05748","created_at":"2026-07-05T11:17:09Z"},{"alias_kind":"pith_short_12","alias_value":"4LOUX63FFR2H","created_at":"2026-07-05T11:17:09Z"},{"alias_kind":"pith_short_16","alias_value":"4LOUX63FFR2HW5BK","created_at":"2026-07-05T11:17:09Z"},{"alias_kind":"pith_short_8","alias_value":"4LOUX63F","created_at":"2026-07-05T11:17:09Z"}],"graph_snapshots":[{"event_id":"sha256:f81b70a7673a56767d17a9aeaf1147f7a80d82098f8643fa805123b500fe3a75","target":"graph","created_at":"2026-07-05T11:17:09Z","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/2506.05748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward-model training is the cost bottleneck in modern Reinforcement Learning Human Feedback (RLHF) pipelines, often requiring tens of billions of parameters and an offline preference-tuning phase. In the proposed method, a frozen, instruction-tuned 7B LLM is augmented with only a one line JSON rubric and a rank-16 LoRA adapter (affecting just 0.8% of the model's parameters), enabling it to serve as a complete substitute for the previously used heavyweight evaluation models. The plug-and-play judge achieves 96.2% accuracy on RewardBench, outperforming specialized reward networks ranging from 2","authors_text":"Ananya Pandey, Rudransh Agnihotri","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T05:18:54Z","title":"Efficient Online RFT with Plug-and-Play LLM Judges: Unlocking State-of-the-Art Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05748","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":"sha256:69ea53cb231845b5121739a30a9f1e2d4e73431866598ce8c370d08949ba7985","target":"record","created_at":"2026-07-05T11:17:09Z","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":"c0941671937150f8892ea3df075659267190e6be84ff8baeb05a203d08279029","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T05:18:54Z","title_canon_sha256":"cabb7c70e80ad642f109cdbb06eff01d3438353bc7cc5c6ed386d1c6b957778e"},"schema_version":"1.0","source":{"id":"2506.05748","kind":"arxiv","version":1}},"canonical_sha256":"e2dd4bfb652c747b742ac0761e545c773f7fd85eab76edbbe39f3ea6f8ca1532","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2dd4bfb652c747b742ac0761e545c773f7fd85eab76edbbe39f3ea6f8ca1532","first_computed_at":"2026-07-05T11:17:09.030228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:09.030228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PfLvGgRuSoNHqRNo83Y1G09P79oOA1r8K+zPmaoLCRtGvJFcxsHXVo2Vm8MZ2VAnQcd640B0/LUDLFFCmnuRAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:09.030835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69ea53cb231845b5121739a30a9f1e2d4e73431866598ce8c370d08949ba7985","sha256:f81b70a7673a56767d17a9aeaf1147f7a80d82098f8643fa805123b500fe3a75"],"state_sha256":"b48858614d65e7886874f1b8f0e7c35789711ec21370194163200f0f31b2283c"}