{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:75NYY2KQ5I6LXYHTMCJCYJTTVP","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":"953cb4710834ab4e317b577b2222834af4924bbd363a18e0b23c686e0282e65a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-27T03:25:53Z","title_canon_sha256":"aa6cac7b5d49e80df38dc99b21399f9d1e5058872a1605a6f037f9353d71b247"},"schema_version":"1.0","source":{"id":"2606.28707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28707","created_at":"2026-06-30T01:16:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28707v1","created_at":"2026-06-30T01:16:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28707","created_at":"2026-06-30T01:16:48Z"},{"alias_kind":"pith_short_12","alias_value":"75NYY2KQ5I6L","created_at":"2026-06-30T01:16:48Z"},{"alias_kind":"pith_short_16","alias_value":"75NYY2KQ5I6LXYHT","created_at":"2026-06-30T01:16:48Z"},{"alias_kind":"pith_short_8","alias_value":"75NYY2KQ","created_at":"2026-06-30T01:16:48Z"}],"graph_snapshots":[{"event_id":"sha256:00580367a43f68712299b17fcb0a0cbb3a36686a5e122ffdd0d481b7c551417d","target":"graph","created_at":"2026-06-30T01:16:48Z","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/2606.28707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value function (critic) and reduces memory and compute overhead relative to critic-based PPO pipelines for aligning large language models. However, GRPO-style advantage estimation depends on prompt-local (within-prompt-group) reward statistics and can be unstable. In particular, when all rollouts in a prompt group receive identical rewards, the within-group reward variance becomes zero, and group normalization yields zero advantages for that group, impe","authors_text":"Yi Chang, Yuan Wu, Yupeng Chang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-27T03:25:53Z","title":"BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28707","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:a6e89c8860f6459b9998056ab0d40f47e8df6143f6604e5a8ef44ce33fd5afaa","target":"record","created_at":"2026-06-30T01:16:48Z","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":"953cb4710834ab4e317b577b2222834af4924bbd363a18e0b23c686e0282e65a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-27T03:25:53Z","title_canon_sha256":"aa6cac7b5d49e80df38dc99b21399f9d1e5058872a1605a6f037f9353d71b247"},"schema_version":"1.0","source":{"id":"2606.28707","kind":"arxiv","version":1}},"canonical_sha256":"ff5b8c6950ea3cbbe0f360922c2673abece7c42cb03a6b0779bcb40223fc712f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff5b8c6950ea3cbbe0f360922c2673abece7c42cb03a6b0779bcb40223fc712f","first_computed_at":"2026-06-30T01:16:48.742046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:16:48.742046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4DT+ydwxqjopnPY1sH3uFAtcyU9++UXYuqwnzdr4p90HdnyYnnD5ignXAfHA2Kl+o4UBsklNL2qWP3f5BKCzDQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:16:48.742559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6e89c8860f6459b9998056ab0d40f47e8df6143f6604e5a8ef44ce33fd5afaa","sha256:00580367a43f68712299b17fcb0a0cbb3a36686a5e122ffdd0d481b7c551417d"],"state_sha256":"7df802707cd2dac82cab761f6b055d4bfeb23274db438e8dc70151c1ba929a31"}