{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TQDX2IK6EVNT6WC3PZGP7NXDD3","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":"86c9a3669ba07ca56a01ec7516a7e125db12fadbf49e686ebd6ddefe465c5684","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T22:12:22Z","title_canon_sha256":"062990c0aa2bea1bdec3d546d8c8695dfef447967719286368e4a0f589011df4"},"schema_version":"1.0","source":{"id":"2606.27580","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27580","created_at":"2026-06-29T00:14:10Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27580v1","created_at":"2026-06-29T00:14:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27580","created_at":"2026-06-29T00:14:10Z"},{"alias_kind":"pith_short_12","alias_value":"TQDX2IK6EVNT","created_at":"2026-06-29T00:14:10Z"},{"alias_kind":"pith_short_16","alias_value":"TQDX2IK6EVNT6WC3","created_at":"2026-06-29T00:14:10Z"},{"alias_kind":"pith_short_8","alias_value":"TQDX2IK6","created_at":"2026-06-29T00:14:10Z"}],"graph_snapshots":[{"event_id":"sha256:f8e979f8a46a3330617faa7b61361ddfd5fcb0860f8c6d62695d1fd30fe2c962","target":"graph","created_at":"2026-06-29T00:14:10Z","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/2606.27580/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) in production does not always have a synchronous reward signal. Code-execution verifiers, slow judge ensembles, and queued human review can return several gradient steps after the rollout that produced them, breaking the synchronous-reward assumption underlying standard PPO. We address this gap with Retroactive Advantage Correction (RAC): each pending slow completion is queued, aged through a non-negative kernel, and reinjected as a clipped residual into the next optimiser step's advantage. We prove that under an unbiased clipped importance rat","authors_text":"Arnav Raj","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T22:12:22Z","title":"Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27580","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":"sha256:54c5b2d5df27241cace6198521a726e0d7b0e4e0e649ef558d16163aa4a1c400","target":"record","created_at":"2026-06-29T00:14:10Z","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":"86c9a3669ba07ca56a01ec7516a7e125db12fadbf49e686ebd6ddefe465c5684","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T22:12:22Z","title_canon_sha256":"062990c0aa2bea1bdec3d546d8c8695dfef447967719286368e4a0f589011df4"},"schema_version":"1.0","source":{"id":"2606.27580","kind":"arxiv","version":1}},"canonical_sha256":"9c077d215e255b3f585b7e4cffb6e31ef57a178cc8f93baece8eb19c62e13505","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c077d215e255b3f585b7e4cffb6e31ef57a178cc8f93baece8eb19c62e13505","first_computed_at":"2026-06-29T00:14:10.587330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T00:14:10.587330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nmZ5jKaaNtHW/e9ymfjcisH3/XugGKlT851f2B3acaSK+s99chMvZAAnrkYDUJ2phvHliu2i1DZJu4q43mAEAw==","signature_status":"signed_v1","signed_at":"2026-06-29T00:14:10.587701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27580","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54c5b2d5df27241cace6198521a726e0d7b0e4e0e649ef558d16163aa4a1c400","sha256:f8e979f8a46a3330617faa7b61361ddfd5fcb0860f8c6d62695d1fd30fe2c962"],"state_sha256":"d2ba9ee591afd0fcf4771d7ab9e3ec76c9d1d5345df3dca9fcaa807dc1efa154"}