{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TCMR2K5VGHH5XHOFKAPNZII4FE","short_pith_number":"pith:TCMR2K5V","schema_version":"1.0","canonical_sha256":"98991d2bb531cfdb9dc5501edca11c2935f020794c21b4a58c02791137d8edb5","source":{"kind":"arxiv","id":"2605.23590","version":1},"attestation_state":"computed","paper":{"title":"Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Zhang, Da Zhu, Guanjun Jiang, Jiangwang Chen, Jiazheng Kang, Xiao Yang, Zixin Song","submitted_at":"2026-05-22T12:59:16Z","abstract_excerpt":"ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to take next, and when to stop, often producing shallow, redundant, or poorly targeted trajectories. Prior work has explored rubrics as external quality signals, but existing uses are mostly evaluative rather than action-guiding: rubrics typically serve as training-time rewards or post-hoc evaluators of completed outputs, and in deep-research settings they are often coarse-grained and report-level rather than step-level."},"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":"2605.23590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-22T12:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"00a240c34aadddc69a00614f42e6f726b76eb9234372169d457269adc45d764d","abstract_canon_sha256":"54ec9a66962416c5dbd2d27c57c1082f192f88456a9b66bbcbed69a483c9b797"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:21.194036Z","signature_b64":"Xy06PLSlANziTrgfxvRkc6MSC8HX8jc6lk3hCbpiSLmT7S9IhN2wULssyFhnPIWTKEuYhLOs+c0MWQRN5zXXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98991d2bb531cfdb9dc5501edca11c2935f020794c21b4a58c02791137d8edb5","last_reissued_at":"2026-05-25T02:02:21.193452Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:21.193452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bowen Zhang, Da Zhu, Guanjun Jiang, Jiangwang Chen, Jiazheng Kang, Xiao Yang, Zixin Song","submitted_at":"2026-05-22T12:59:16Z","abstract_excerpt":"ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which reasoning or action step to take next, and when to stop, often producing shallow, redundant, or poorly targeted trajectories. Prior work has explored rubrics as external quality signals, but existing uses are mostly evaluative rather than action-guiding: rubrics typically serve as training-time rewards or post-hoc evaluators of completed outputs, and in deep-research settings they are often coarse-grained and report-level rather than step-level."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23590","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/2605.23590/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":"2605.23590","created_at":"2026-05-25T02:02:21.193556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23590v1","created_at":"2026-05-25T02:02:21.193556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23590","created_at":"2026-05-25T02:02:21.193556+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCMR2K5VGHH5","created_at":"2026-05-25T02:02:21.193556+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCMR2K5VGHH5XHOF","created_at":"2026-05-25T02:02:21.193556+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCMR2K5V","created_at":"2026-05-25T02:02:21.193556+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/TCMR2K5VGHH5XHOFKAPNZII4FE","json":"https://pith.science/pith/TCMR2K5VGHH5XHOFKAPNZII4FE.json","graph_json":"https://pith.science/api/pith-number/TCMR2K5VGHH5XHOFKAPNZII4FE/graph.json","events_json":"https://pith.science/api/pith-number/TCMR2K5VGHH5XHOFKAPNZII4FE/events.json","paper":"https://pith.science/paper/TCMR2K5V"},"agent_actions":{"view_html":"https://pith.science/pith/TCMR2K5VGHH5XHOFKAPNZII4FE","download_json":"https://pith.science/pith/TCMR2K5VGHH5XHOFKAPNZII4FE.json","view_paper":"https://pith.science/paper/TCMR2K5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23590&json=true","fetch_graph":"https://pith.science/api/pith-number/TCMR2K5VGHH5XHOFKAPNZII4FE/graph.json","fetch_events":"https://pith.science/api/pith-number/TCMR2K5VGHH5XHOFKAPNZII4FE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCMR2K5VGHH5XHOFKAPNZII4FE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCMR2K5VGHH5XHOFKAPNZII4FE/action/storage_attestation","attest_author":"https://pith.science/pith/TCMR2K5VGHH5XHOFKAPNZII4FE/action/author_attestation","sign_citation":"https://pith.science/pith/TCMR2K5VGHH5XHOFKAPNZII4FE/action/citation_signature","submit_replication":"https://pith.science/pith/TCMR2K5VGHH5XHOFKAPNZII4FE/action/replication_record"}},"created_at":"2026-05-25T02:02:21.193556+00:00","updated_at":"2026-05-25T02:02:21.193556+00:00"}