{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4A3RB6HQ5NE4N55HKRDGFGREMU","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":"bcffa006ed74de75132b650b241ab4e09dfee904348cd2b4982f1d6316a49989","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T12:35:40Z","title_canon_sha256":"abc8c34cb81ebe8e3b702f5fe6642df9bb42495554e2256c8caf1673d05aaab0"},"schema_version":"1.0","source":{"id":"2607.20083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20083","created_at":"2026-07-23T01:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20083v1","created_at":"2026-07-23T01:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20083","created_at":"2026-07-23T01:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"4A3RB6HQ5NE4","created_at":"2026-07-23T01:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"4A3RB6HQ5NE4N55H","created_at":"2026-07-23T01:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"4A3RB6HQ","created_at":"2026-07-23T01:25:00Z"}],"graph_snapshots":[{"event_id":"sha256:e65c05b995fca32253f5b9b8f348583261a7cf819f3dc4e3483b5cb64473f8eb","target":"graph","created_at":"2026-07-23T01:25:00Z","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/2607.20083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improving large language models. As policies improve, these sampled responses become close in quality. These close candidates create a bottleneck for policy optimization: collapsed relative evaluator score gaps yield weak or misleading policy supervision. We theoretically characterize why these gaps matter through a probability allocation view, showing that the directional gain of shifting probability mass from one response to another is exactly the evaluator score gap between them. This identifies ","authors_text":"Beining Wang, Hao Kong, Hongtao Tian, Min Zhang, Qingyao Ai, Qingyi Pan, Tao Yang, Ting Yao, Weihang Su, Yiqun Liu, Yueyue Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T12:35:40Z","title":"Co-Evolving LLM Evaluators and Policies via DynamicRubric"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20083","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:a572e60e40d3df9082f315472b09398777fb5e50bf168a587521be717a5bf415","target":"record","created_at":"2026-07-23T01:25:00Z","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":"bcffa006ed74de75132b650b241ab4e09dfee904348cd2b4982f1d6316a49989","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-22T12:35:40Z","title_canon_sha256":"abc8c34cb81ebe8e3b702f5fe6642df9bb42495554e2256c8caf1673d05aaab0"},"schema_version":"1.0","source":{"id":"2607.20083","kind":"arxiv","version":1}},"canonical_sha256":"e03710f8f0eb49c6f7a75446629a246508f5ee832a684c421d411879b0eaa566","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e03710f8f0eb49c6f7a75446629a246508f5ee832a684c421d411879b0eaa566","first_computed_at":"2026-07-23T01:25:00.535583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:25:00.535583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TDjFqFuWPr8SjQqlgTd/Qw6wROTma25Ga6b52WGZFJLziQzSwATayGWLbs7P7GFv6bOXaHKpGc2hqtr9ZovfAw==","signature_status":"signed_v1","signed_at":"2026-07-23T01:25:00.536465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a572e60e40d3df9082f315472b09398777fb5e50bf168a587521be717a5bf415","sha256:e65c05b995fca32253f5b9b8f348583261a7cf819f3dc4e3483b5cb64473f8eb"],"state_sha256":"5c0ed687705fb6d47f984feb60b3449c3b8a8ec5e993352e6ddf9b628e49452f"}