{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PFOLCF5S5IVG7VRFX5GZJEQZ3O","short_pith_number":"pith:PFOLCF5S","schema_version":"1.0","canonical_sha256":"795cb117b2ea2a6fd625bf4d949219db897d179d1947c5e26df805a58d2fca7a","source":{"kind":"arxiv","id":"2605.29847","version":1},"attestation_state":"computed","paper":{"title":"EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Liu, Bo Zhang, Jiuxin Cao, Pengjun Xie, Shen Huang, Xiaomeng Hu, Xin Guan, Zhenyi Wang, Zijian Li","submitted_at":"2026-05-28T12:28:49Z","abstract_excerpt":"Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challenging due to the lack of definitive rewards. Current rubric-based RL methods mitigate this by employing explicit criteria; however, they rely heavily on static, human-annotated rubrics that inevitably cause policy lag, or expensive external proprietary models for dynamic updates. In this paper, we propose EvoRubric, a novel single-policy co-evolutionary RL framework that eliminates the reliance on static criteria and o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.29847","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T12:28:49Z","cross_cats_sorted":[],"title_canon_sha256":"6744967b1d2c00cf0e5418ad718d0f566b249d46f046083e97a9d289f61887e2","abstract_canon_sha256":"24433aad7fbd89e1c6ce0df733cb2fa0d50987722e0d8c09455171ef6d7a5273"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:55.867780Z","signature_b64":"NNAXJm5E2MYr29rKAsiaEOSZ2MAP9OQTTqyabOPU2vwSvioDoHwA51P4K9xQYLDku9RetqfNSglQdCPwlkx+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"795cb117b2ea2a6fd625bf4d949219db897d179d1947c5e26df805a58d2fca7a","last_reissued_at":"2026-05-29T02:05:55.866989Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:55.866989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Liu, Bo Zhang, Jiuxin Cao, Pengjun Xie, Shen Huang, Xiaomeng Hu, Xin Guan, Zhenyi Wang, Zijian Li","submitted_at":"2026-05-28T12:28:49Z","abstract_excerpt":"Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challenging due to the lack of definitive rewards. Current rubric-based RL methods mitigate this by employing explicit criteria; however, they rely heavily on static, human-annotated rubrics that inevitably cause policy lag, or expensive external proprietary models for dynamic updates. In this paper, we propose EvoRubric, a novel single-policy co-evolutionary RL framework that eliminates the reliance on static criteria and o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29847","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.29847/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.29847","created_at":"2026-05-29T02:05:55.867088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29847v1","created_at":"2026-05-29T02:05:55.867088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29847","created_at":"2026-05-29T02:05:55.867088+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFOLCF5S5IVG","created_at":"2026-05-29T02:05:55.867088+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFOLCF5S5IVG7VRF","created_at":"2026-05-29T02:05:55.867088+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFOLCF5S","created_at":"2026-05-29T02:05:55.867088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O","json":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O.json","graph_json":"https://pith.science/api/pith-number/PFOLCF5S5IVG7VRFX5GZJEQZ3O/graph.json","events_json":"https://pith.science/api/pith-number/PFOLCF5S5IVG7VRFX5GZJEQZ3O/events.json","paper":"https://pith.science/paper/PFOLCF5S"},"agent_actions":{"view_html":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O","download_json":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O.json","view_paper":"https://pith.science/paper/PFOLCF5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29847&json=true","fetch_graph":"https://pith.science/api/pith-number/PFOLCF5S5IVG7VRFX5GZJEQZ3O/graph.json","fetch_events":"https://pith.science/api/pith-number/PFOLCF5S5IVG7VRFX5GZJEQZ3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O/action/storage_attestation","attest_author":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O/action/author_attestation","sign_citation":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O/action/citation_signature","submit_replication":"https://pith.science/pith/PFOLCF5S5IVG7VRFX5GZJEQZ3O/action/replication_record"}},"created_at":"2026-05-29T02:05:55.867088+00:00","updated_at":"2026-05-29T02:05:55.867088+00:00"}