{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZROJB42XLLBOSY362OJ7Y45HQX","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":"a113f3fc328ca9593509a31cfa0f8219b65156f5b1cfc5855d1fc32b465e6d08","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-19T09:38:02Z","title_canon_sha256":"24cd19b5fd802287e79e519b3e08ee62f2024a5592812236c6a398f80250fec5"},"schema_version":"1.0","source":{"id":"2606.21262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21262","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21262v1","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21262","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_12","alias_value":"ZROJB42XLLBO","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_16","alias_value":"ZROJB42XLLBOSY36","created_at":"2026-06-23T01:12:35Z"},{"alias_kind":"pith_short_8","alias_value":"ZROJB42X","created_at":"2026-06-23T01:12:35Z"}],"graph_snapshots":[{"event_id":"sha256:c7acb0e48f236d7ba686ed16ce3a0e6ab7d70284f6c83ac45e82761407ff14e0","target":"graph","created_at":"2026-06-23T01:12:35Z","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/2606.21262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning for multi-step LLM agents often relies on scalar rewards that indicate success but cannot explain why a trajectory is good or bad. Rubric-based rewards improve interpretability through natural-language criteria, but existing methods score at the trajectory level and freeze the scorer behind a closed-source judge, leaving step-level credit assignment unresolved and the judge itself static. We propose ARCO (Adaptive Rubric CO-evolution), a rubric framework in which a same-scale model $\\mu$ shares a backbone with two heads: a generation head that produces per-step criteria,","authors_text":"Jingsen Zhang, Rui Li, Xiaohe Bo, Xu Chen, Yuanzi Li, Zihang Tian","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-19T09:38:02Z","title":"ARCO: Adaptive Rubric with Co-Evolution for Multi-Step LLM-Based Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21262","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":"sha256:2ccac9e61f1efb60f9ade02e091961c4794fc256eeb44bf7cf47460414a378f4","target":"record","created_at":"2026-06-23T01:12:35Z","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":"a113f3fc328ca9593509a31cfa0f8219b65156f5b1cfc5855d1fc32b465e6d08","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-19T09:38:02Z","title_canon_sha256":"24cd19b5fd802287e79e519b3e08ee62f2024a5592812236c6a398f80250fec5"},"schema_version":"1.0","source":{"id":"2606.21262","kind":"arxiv","version":1}},"canonical_sha256":"cc5c90f3575ac2e9637ed393fc73a785c0e8f6dced216f28307c71c9d7986436","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc5c90f3575ac2e9637ed393fc73a785c0e8f6dced216f28307c71c9d7986436","first_computed_at":"2026-06-23T01:12:35.150902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:35.150902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HlNhxrH6jI1zPAsoAUpK/JAOQouhCkLdi0dvR+Z0NTPAXfwiS2q9uO07apiK80I/WsHej6UbWjRHPU5xK+rpDw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:35.151392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ccac9e61f1efb60f9ade02e091961c4794fc256eeb44bf7cf47460414a378f4","sha256:c7acb0e48f236d7ba686ed16ce3a0e6ab7d70284f6c83ac45e82761407ff14e0"],"state_sha256":"f24e958f7a52e34ee3c7a695b5693dd1e0a5b1b50402a918becfe01736ad68b1"}