{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TWJHMHFQOPPTCQS4LBWSLUR2IN","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":"d8132ab7b39578169e26544b8c455f697a852bf2fa9cdcf00261205a6152b371","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T19:03:39Z","title_canon_sha256":"f08c712824ab58b55a4fabe81a6a098f821a886512ac36c09663227fabe7f5ee"},"schema_version":"1.0","source":{"id":"2606.04145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04145","created_at":"2026-06-04T00:06:51Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04145v1","created_at":"2026-06-04T00:06:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04145","created_at":"2026-06-04T00:06:51Z"},{"alias_kind":"pith_short_12","alias_value":"TWJHMHFQOPPT","created_at":"2026-06-04T00:06:51Z"},{"alias_kind":"pith_short_16","alias_value":"TWJHMHFQOPPTCQS4","created_at":"2026-06-04T00:06:51Z"},{"alias_kind":"pith_short_8","alias_value":"TWJHMHFQ","created_at":"2026-06-04T00:06:51Z"}],"graph_snapshots":[{"event_id":"sha256:1fc060f0b78073b001c82ad9e58d90754fb3fb6e0eaf1baec560acdede4a709b","target":"graph","created_at":"2026-06-04T00:06:51Z","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/2606.04145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cloud LLM fine-tuning platforms increasingly serve RLHF workloads, where a learned reward model is optimized as a proxy for human quality. As Gao et al. (2023) showed, this proxy diverges from world feedback (downstream eval metrics) under sustained optimization pressure, a phenomenon known as reward overoptimization. Existing platform schedulers ignore this divergence: non-clairvoyant schedulers optimize JCT without any quality signal, SLAQ-style quality-aware schedulers use training loss (a weaker proxy that drops monotonically through hacking), and classical per-job early stopping requires ","authors_text":"Chuanyi Sun, Guilin Zhang, John M. Fossaceca, Shahryar Sarkani","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T19:03:39Z","title":"EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04145","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":"sha256:2e0ab18ae7c556a8c0f5870ca1802273ed83913605114bb5d49a55db7272a4c0","target":"record","created_at":"2026-06-04T00:06:51Z","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":"d8132ab7b39578169e26544b8c455f697a852bf2fa9cdcf00261205a6152b371","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T19:03:39Z","title_canon_sha256":"f08c712824ab58b55a4fabe81a6a098f821a886512ac36c09663227fabe7f5ee"},"schema_version":"1.0","source":{"id":"2606.04145","kind":"arxiv","version":1}},"canonical_sha256":"9d92761cb073df31425c586d25d23a43724d8c14f21835150cb6245ece16b002","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d92761cb073df31425c586d25d23a43724d8c14f21835150cb6245ece16b002","first_computed_at":"2026-06-04T00:06:51.886192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T00:06:51.886192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RENiqfvlHuWS1BF4LHb8bsAKO67K2RpHllYVAVT6ML6xqP8P/pHyocmwjamQX1V0t04CKZ3mdkxqLelxBq/oCw==","signature_status":"signed_v1","signed_at":"2026-06-04T00:06:51.886579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04145","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e0ab18ae7c556a8c0f5870ca1802273ed83913605114bb5d49a55db7272a4c0","sha256:1fc060f0b78073b001c82ad9e58d90754fb3fb6e0eaf1baec560acdede4a709b"],"state_sha256":"ac467f131b547c70572cfba605b32c6cf16b5c0cf93dbe59d4001a5c8017389b"}