{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MGJIUH3266HCOSHPRXRMVDFJU4","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":"60bfcd88e0d575b5e00fb248d980fd2276c6b07cef65422ee8dacebb5cc7797f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T17:53:04Z","title_canon_sha256":"9ec4260338b691504fb1971555eed82f58d05cde79771dc48dba3753b7a0ae95"},"schema_version":"1.0","source":{"id":"2606.03968","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03968","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03968v1","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03968","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"MGJIUH3266HC","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"MGJIUH3266HCOSHP","created_at":"2026-06-03T02:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"MGJIUH32","created_at":"2026-06-03T02:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:0625ec9636646179acbe64b1fa90d0cde221b10a702a9ca32b35d0d96baf6715","target":"graph","created_at":"2026-06-03T02:06:08Z","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/2606.03968/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rubric-based RL is a promising route for extending reinforcement learning beyond verifiable rewards, yet existing methods optimize rubrics while treating the query distribution as fixed. We identify a structural bottleneck: rubric quality is constrained by query structure. Open-ended queries yield vague rubrics; naively narrowing them introduces fabricated references that no model can verify, so all responses fail and training receives no reward signal. We present QUBRIC, a framework that co-designs queries and rubrics. Teacher-derived key points ground the rewriting of open-ended queries into","authors_text":"Bing Yin, Chao Zhang, Jingfeng Yang, Priyanka Nigam, Qingyu Yin, Rongzhi Zhang, Rui Feng, Tuo Zhao, Xin Liu, Zhihan Zhang, Zixuan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T17:53:04Z","title":"QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03968","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":"sha256:531810fdeb023d3c23940edc3015b8ca09ecfb3488b507774c66cb62409aee3d","target":"record","created_at":"2026-06-03T02:06:08Z","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":"60bfcd88e0d575b5e00fb248d980fd2276c6b07cef65422ee8dacebb5cc7797f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T17:53:04Z","title_canon_sha256":"9ec4260338b691504fb1971555eed82f58d05cde79771dc48dba3753b7a0ae95"},"schema_version":"1.0","source":{"id":"2606.03968","kind":"arxiv","version":1}},"canonical_sha256":"61928a1f7af78e2748ef8de2ca8ca9a70aa34e2f6d39fef8a788d8b28a34447d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61928a1f7af78e2748ef8de2ca8ca9a70aa34e2f6d39fef8a788d8b28a34447d","first_computed_at":"2026-06-03T02:06:08.228338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:08.228338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZJkea6//asav+joKdK+8NSm2RvKQtllAVkbmibUjjSMLMiRAP6VLjO7JIjY3r9QEzMIb7ill0MPqa4+s7exKCw==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:08.228751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03968","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:531810fdeb023d3c23940edc3015b8ca09ecfb3488b507774c66cb62409aee3d","sha256:0625ec9636646179acbe64b1fa90d0cde221b10a702a9ca32b35d0d96baf6715"],"state_sha256":"9ce73853a188c15322ba4d4eeb05bd79cf1e1f8b16ec57ce5d8b93db70a86986"}