{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZROJB42XLLBOSY362OJ7Y45HQX","short_pith_number":"pith:ZROJB42X","canonical_record":{"source":{"id":"2606.21262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-19T09:38:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"24cd19b5fd802287e79e519b3e08ee62f2024a5592812236c6a398f80250fec5","abstract_canon_sha256":"a113f3fc328ca9593509a31cfa0f8219b65156f5b1cfc5855d1fc32b465e6d08"},"schema_version":"1.0"},"canonical_sha256":"cc5c90f3575ac2e9637ed393fc73a785c0e8f6dced216f28307c71c9d7986436","source":{"kind":"arxiv","id":"2606.21262","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZROJB42XLLBOSY362OJ7Y45HQX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.21262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-19T09:38:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"24cd19b5fd802287e79e519b3e08ee62f2024a5592812236c6a398f80250fec5","abstract_canon_sha256":"a113f3fc328ca9593509a31cfa0f8219b65156f5b1cfc5855d1fc32b465e6d08"},"schema_version":"1.0"},"canonical_sha256":"cc5c90f3575ac2e9637ed393fc73a785c0e8f6dced216f28307c71c9d7986436","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:35.151392Z","signature_b64":"HlNhxrH6jI1zPAsoAUpK/JAOQouhCkLdi0dvR+Z0NTPAXfwiS2q9uO07apiK80I/WsHej6UbWjRHPU5xK+rpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc5c90f3575ac2e9637ed393fc73a785c0e8f6dced216f28307c71c9d7986436","last_reissued_at":"2026-06-23T01:12:35.150902Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:35.150902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.21262","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obBtC5/8Fb8zgXhOFT45Q5M3gSluiTEYeJbDlYxq78MjKdv6iQUAP3yfsApcUxAALqM0Qm2mRtOj9K+eUwcbBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:14:25.412944Z"},"content_sha256":"2ccac9e61f1efb60f9ade02e091961c4794fc256eeb44bf7cf47460414a378f4","schema_version":"1.0","event_id":"sha256:2ccac9e61f1efb60f9ade02e091961c4794fc256eeb44bf7cf47460414a378f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZROJB42XLLBOSY362OJ7Y45HQX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ARCO: Adaptive Rubric with Co-Evolution for Multi-Step LLM-Based Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jingsen Zhang, Rui Li, Xiaohe Bo, Xu Chen, Yuanzi Li, Zihang Tian","submitted_at":"2026-06-19T09:38:02Z","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,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21262","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/2606.21262/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S1Y5aM67Qn0MrDDw6Crf65zQfMTM7+F14PSkjKvqPNF4eeQ4v+9qOvAlnfTfF1TCRKtPvj+kl6Y2nzKZdyY3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T18:14:25.413326Z"},"content_sha256":"c7acb0e48f236d7ba686ed16ce3a0e6ab7d70284f6c83ac45e82761407ff14e0","schema_version":"1.0","event_id":"sha256:c7acb0e48f236d7ba686ed16ce3a0e6ab7d70284f6c83ac45e82761407ff14e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZROJB42XLLBOSY362OJ7Y45HQX/bundle.json","state_url":"https://pith.science/pith/ZROJB42XLLBOSY362OJ7Y45HQX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZROJB42XLLBOSY362OJ7Y45HQX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T18:14:25Z","links":{"resolver":"https://pith.science/pith/ZROJB42XLLBOSY362OJ7Y45HQX","bundle":"https://pith.science/pith/ZROJB42XLLBOSY362OJ7Y45HQX/bundle.json","state":"https://pith.science/pith/ZROJB42XLLBOSY362OJ7Y45HQX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZROJB42XLLBOSY362OJ7Y45HQX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GBUQlGtqO4ZLdVRNNncYKKhIcgOMnXbKMi1EWqztzwQjCHlalJEaOr5L8A5QQTWz1PjXKGAtRJV8xnz0EQtzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T18:14:25.415281Z","bundle_sha256":"e4668e4741d5fc30001c419454d495edf25108c830e2393e92e782cdac4fc9c3"}}