{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GSHUNBCTYLR5LNOLAUU7TXXYX7","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":"f25dfa655ce7e6b5100509d399ac3555cdf64316280b0ca18e0cdfcf0ec313b5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:11:03Z","title_canon_sha256":"fd9512a2cd5e9625b5163aaec84222773f142d1fbe7efc7d75d7f446342fda89"},"schema_version":"1.0","source":{"id":"2605.30244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30244","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30244v1","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30244","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"GSHUNBCTYLR5","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"GSHUNBCTYLR5LNOL","created_at":"2026-05-29T02:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"GSHUNBCT","created_at":"2026-05-29T02:06:13Z"}],"graph_snapshots":[{"event_id":"sha256:5b05ccf10ff438140fdaccf1ccb8cf3d92c28da9536e162a97fdd161b06a8370","target":"graph","created_at":"2026-05-29T02:06:13Z","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/2605.30244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning steps, and constraints). Rubrics provide a natural interface for this fine-grained supervision, but their effectiveness depends on the execution accuracy during online RL. We propose Reinforcement Learning with Robust Rubric Rewards ($\\text{RLR}^3$), extending RLVR from task-level verification to criterion-level verification. $\\text{RLR}^3$ routes instance-sp","authors_text":"Dandan Tu, Dezhi Peng, Fangyu Hong, Gaojie Wu, Haonan Li, Hao Wang, Haoyu Ren, Huixin Wang, Jihao Wu, Minghui Liao, Nuo Xu, Qiaoyu Luo, Wuheng Xu, Xiangyang Qu, Ya-Qi Yu, Yongxin Liao, Zihao Chen, Ziming Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:11:03Z","title":"Reinforcement Learning with Robust Rubric Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30244","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":"sha256:89de4b61ebe4824a0ea40d03bde47bcc9e74693ccb9187820ab70670aa47a3a9","target":"record","created_at":"2026-05-29T02:06:13Z","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":"f25dfa655ce7e6b5100509d399ac3555cdf64316280b0ca18e0cdfcf0ec313b5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T17:11:03Z","title_canon_sha256":"fd9512a2cd5e9625b5163aaec84222773f142d1fbe7efc7d75d7f446342fda89"},"schema_version":"1.0","source":{"id":"2605.30244","kind":"arxiv","version":1}},"canonical_sha256":"348f468453c2e3d5b5cb0529f9def8bfe053b533af69002d6f980ad93fe010eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"348f468453c2e3d5b5cb0529f9def8bfe053b533af69002d6f980ad93fe010eb","first_computed_at":"2026-05-29T02:06:13.831411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:13.831411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sCY6eqIiczFPfY5GCYC12rhZI0QSer/mJCFbi8pAFMj0Uizeu1+arxfgJsOaBZKNm7SoE+Y0c9eVxeKNXGV/CQ==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:13.831837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89de4b61ebe4824a0ea40d03bde47bcc9e74693ccb9187820ab70670aa47a3a9","sha256:5b05ccf10ff438140fdaccf1ccb8cf3d92c28da9536e162a97fdd161b06a8370"],"state_sha256":"69057e1d50264eecdcf39c0d5db8b41f5c0281d41f4df01a96e070a2d3374f04"}