{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZJM3G5UM36CZ55Q7FFVWOFRH3Z","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":"37abdcd51ef063a76a50161d0716c337ba2a3070bd73571db53cfcf4a4272740","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T02:27:51Z","title_canon_sha256":"ad3c4659b28181742840fcaad12ef882d75444a261143031005edc1d932d9384"},"schema_version":"1.0","source":{"id":"2606.05606","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05606","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05606v1","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05606","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_12","alias_value":"ZJM3G5UM36CZ","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_16","alias_value":"ZJM3G5UM36CZ55Q7","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_8","alias_value":"ZJM3G5UM","created_at":"2026-06-05T01:14:56Z"}],"graph_snapshots":[{"event_id":"sha256:0500526c32b231314eff282aa91c43384dc9299b2ecd0f7becb782898b2c744c","target":"graph","created_at":"2026-06-05T01:14:56Z","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/2606.05606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM post-training often relies on reinforcement learning methods that sample multiple rollouts per prompt, yet most existing approaches use a fixed rollout budget for every prompt, despite large differences in the training signal different prompts provide. In this paper, we study adaptive rollout allocation under a fixed global budget and formulate the problem as online resource allocation with prompt-level diminishing returns. Our method, CERO, maintains a Beta posterior over each prompt's success probability and uses the posterior expected Bernoulli variance as a Bayesian estimate of the val","authors_text":"Jiashuo Jiang, Yige Wang, Yiming Zong","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T02:27:51Z","title":"Cross-Epoch Adaptive Rollout Optimization for RL Post-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05606","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:a398848b46aa538b50a6f6d1ac4dbfc8462e3342c06e98567fcdd55a9371079d","target":"record","created_at":"2026-06-05T01:14:56Z","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":"37abdcd51ef063a76a50161d0716c337ba2a3070bd73571db53cfcf4a4272740","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T02:27:51Z","title_canon_sha256":"ad3c4659b28181742840fcaad12ef882d75444a261143031005edc1d932d9384"},"schema_version":"1.0","source":{"id":"2606.05606","kind":"arxiv","version":1}},"canonical_sha256":"ca59b3768cdf859ef61f296b671627de5fbc2a617f7d7728ec677c86b9725527","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca59b3768cdf859ef61f296b671627de5fbc2a617f7d7728ec677c86b9725527","first_computed_at":"2026-06-05T01:14:56.217428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:56.217428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QiJYBBRZs49DbjVIo+WHiwDZ/HY9UMLzRBEuFzlCOH0b+QkppwjcDzsK6u4mTlKpuwOuDTjcfwmw6+8CronTAw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:56.217847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05606","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a398848b46aa538b50a6f6d1ac4dbfc8462e3342c06e98567fcdd55a9371079d","sha256:0500526c32b231314eff282aa91c43384dc9299b2ecd0f7becb782898b2c744c"],"state_sha256":"6e33a546e166a1e18c5110bb253729b16184d7784291f3780ef86b7571398f06"}