{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FET5AKRYSR2ONV7H5LGM5WHFW4","short_pith_number":"pith:FET5AKRY","schema_version":"1.0","canonical_sha256":"2927d02a389474e6d7e7eaccced8e5b734dcdd60a9b9c847d9232c3689fd6e2a","source":{"kind":"arxiv","id":"2602.08586","version":3},"attestation_state":"computed","paper":{"title":"DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fanxiang Zeng, Hao Fu, Yiming Yang, Yue Liu, Zhuoyuan Li","submitted_at":"2026-02-09T12:24:56Z","abstract_excerpt":"Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or diagnose why one fails. We argue this gap persists largely because the field lacks a diagnostic framework with measurable primitives and testable predictions. We introduce \\textbf{DIANOIA}, a three-channel decomposition of multi-agent reasoning gain into coverage, fidelity, and synthesis, each of which is empirically measurable. From this decomposition, we derive a diagnostic protocol that identifies the bottleneck channels for any given task. We i"},"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":"2602.08586","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-09T12:24:56Z","cross_cats_sorted":[],"title_canon_sha256":"e365b57386c0427cc8eebcdd6e3767c873aac2f92124285617b8de44a3d443a1","abstract_canon_sha256":"e0cd173e3b5451181d8479d604b6ca9c2967ce74cea083919576a787df9258fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:44.271532Z","signature_b64":"p0aJTYU8AUo7MjiQWO0r9+NimveK+21IqPggb2pd20nzNT6eCRaDPbHChdXeKcjrNLADKkOLW0BzcpgitXehAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2927d02a389474e6d7e7eaccced8e5b734dcdd60a9b9c847d9232c3689fd6e2a","last_reissued_at":"2026-05-27T01:05:44.270825Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:44.270825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fanxiang Zeng, Hao Fu, Yiming Yang, Yue Liu, Zhuoyuan Li","submitted_at":"2026-02-09T12:24:56Z","abstract_excerpt":"Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or diagnose why one fails. We argue this gap persists largely because the field lacks a diagnostic framework with measurable primitives and testable predictions. We introduce \\textbf{DIANOIA}, a three-channel decomposition of multi-agent reasoning gain into coverage, fidelity, and synthesis, each of which is empirically measurable. From this decomposition, we derive a diagnostic protocol that identifies the bottleneck channels for any given task. We i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08586","kind":"arxiv","version":3},"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/2602.08586/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":"2602.08586","created_at":"2026-05-27T01:05:44.270942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.08586v3","created_at":"2026-05-27T01:05:44.270942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08586","created_at":"2026-05-27T01:05:44.270942+00:00"},{"alias_kind":"pith_short_12","alias_value":"FET5AKRYSR2O","created_at":"2026-05-27T01:05:44.270942+00:00"},{"alias_kind":"pith_short_16","alias_value":"FET5AKRYSR2ONV7H","created_at":"2026-05-27T01:05:44.270942+00:00"},{"alias_kind":"pith_short_8","alias_value":"FET5AKRY","created_at":"2026-05-27T01:05:44.270942+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/FET5AKRYSR2ONV7H5LGM5WHFW4","json":"https://pith.science/pith/FET5AKRYSR2ONV7H5LGM5WHFW4.json","graph_json":"https://pith.science/api/pith-number/FET5AKRYSR2ONV7H5LGM5WHFW4/graph.json","events_json":"https://pith.science/api/pith-number/FET5AKRYSR2ONV7H5LGM5WHFW4/events.json","paper":"https://pith.science/paper/FET5AKRY"},"agent_actions":{"view_html":"https://pith.science/pith/FET5AKRYSR2ONV7H5LGM5WHFW4","download_json":"https://pith.science/pith/FET5AKRYSR2ONV7H5LGM5WHFW4.json","view_paper":"https://pith.science/paper/FET5AKRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.08586&json=true","fetch_graph":"https://pith.science/api/pith-number/FET5AKRYSR2ONV7H5LGM5WHFW4/graph.json","fetch_events":"https://pith.science/api/pith-number/FET5AKRYSR2ONV7H5LGM5WHFW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FET5AKRYSR2ONV7H5LGM5WHFW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FET5AKRYSR2ONV7H5LGM5WHFW4/action/storage_attestation","attest_author":"https://pith.science/pith/FET5AKRYSR2ONV7H5LGM5WHFW4/action/author_attestation","sign_citation":"https://pith.science/pith/FET5AKRYSR2ONV7H5LGM5WHFW4/action/citation_signature","submit_replication":"https://pith.science/pith/FET5AKRYSR2ONV7H5LGM5WHFW4/action/replication_record"}},"created_at":"2026-05-27T01:05:44.270942+00:00","updated_at":"2026-05-27T01:05:44.270942+00:00"}