{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BYDZGUXSSGS4LVGKSOBRIHEJTM","merge_version":"pith-open-graph-merge-v1","event_count":12,"valid_event_count":12,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"db9398582f900a7e60a5f52e0f9bfbe92701857617ee8c2c862345a65d531115","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T17:50:18Z","title_canon_sha256":"534d6d248c66b1f670e8640344421204f47243eee5d3e4b4b72ff4e6d685024e"},"schema_version":"1.0","source":{"id":"2605.20164","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20164","created_at":"2026-05-20T02:06:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20164v1","created_at":"2026-05-20T02:06:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20164","created_at":"2026-05-20T02:06:05Z"},{"alias_kind":"pith_short_12","alias_value":"BYDZGUXSSGS4","created_at":"2026-05-20T02:06:05Z"},{"alias_kind":"pith_short_16","alias_value":"BYDZGUXSSGS4LVGK","created_at":"2026-05-20T02:06:05Z"},{"alias_kind":"pith_short_8","alias_value":"BYDZGUXS","created_at":"2026-05-20T02:06:05Z"}],"graph_snapshots":[{"event_id":"sha256:05803dfa89b7723fdfafbba53ecea0fb0c7960f757fa7ca162ffabc9c085066e","target":"graph","created_at":"2026-05-20T02:06:05Z","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/2605.20164/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many important model behaviors require satisfying several qualitative criteria at once. Rubric-based rewards address this setting by grading prompt-specific criteria and aggregating them into a scalar reward. Yet standard static aggregations conflate a criterion's human-assigned importance with its current usefulness as an optimization signal. We show that this assumption breaks down in rubric RL: many important criteria are already saturated or current","authors_text":"Anas Mahmoud, Bing Liu, Daniel George, Jackson Lee, MohammadHossein Rezaei, Utkarsh Tyagi, Xingang Guo, Yunzhong He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T17:50:18Z","title":"Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20164","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":"sha256:0a4fb5927e1029ca5e5a7f79a9c893fc8f00fbc6e07ebead00c254f737a4d9ff","target":"record","created_at":"2026-05-20T02:06:05Z","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":"db9398582f900a7e60a5f52e0f9bfbe92701857617ee8c2c862345a65d531115","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T17:50:18Z","title_canon_sha256":"534d6d248c66b1f670e8640344421204f47243eee5d3e4b4b72ff4e6d685024e"},"schema_version":"1.0","source":{"id":"2605.20164","kind":"arxiv","version":1}},"canonical_sha256":"0e079352f291a5c5d4ca9383141c899b016c4a08c2a5adac37c0c52518dd28a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e079352f291a5c5d4ca9383141c899b016c4a08c2a5adac37c0c52518dd28a5","first_computed_at":"2026-05-20T02:06:05.729992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:06:05.729992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xaPk3Rd3SvHbRLaDZaPAQs+hllL/BRvtjCfBGP4/03o+FYwpR6hnXjqHE+FkcMCoT4DLVyfetmpx1Sz1Y7sfCw==","signature_status":"signed_v1","signed_at":"2026-05-20T02:06:05.730707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20164","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:223166524715ae5f64c85f47a402dd5445f7a3982804be93a3301e052b5268ce","sha256:33a8821b0bdbc7dd46e2440773220a779d4425e8d66b8ca8f13bf4f8a28941e3","sha256:4691083cad985f83ffaa66c47be551d3d34efa400e41085335f6506b9930cda4","sha256:57505825fef762f7725d551173b62c46300cc4108c9d4922d03255ff5786ad8a","sha256:643382a3f75d6b205d9f3aadf45541c52e1428484c3dd80373cc8fbc97e6d44f","sha256:7e64c8765681062845e0d725e4563620b2bb5f6e867b1d0cc5b1d4726d321020","sha256:a2a1f82ce55c11cf7297c161761a3959d1f273bd812d49ac75a81333bfd33eb6","sha256:a5f76acdb213319151258bf107afbe51b31328f3a2383c7b9dea4911b88a4d6b","sha256:ccb9ca7b721ddac32db0a82737cda2ddd4a756e4db2bb14a339e40cbf1aa63bf","sha256:f7f2ee6449603467d71f8197388d7178acacc96dda690405081dde6132d52bb3"]}],"invalid_events":[],"applied_event_ids":["sha256:0a4fb5927e1029ca5e5a7f79a9c893fc8f00fbc6e07ebead00c254f737a4d9ff","sha256:05803dfa89b7723fdfafbba53ecea0fb0c7960f757fa7ca162ffabc9c085066e"],"state_sha256":"e156b615f01e3db9bc9c232de949ed4e9cf8bca0fdeca43fd0989ccf5b2fed3e"}