{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UTWVZ5QQR564VEWFUIFFXW6GI3","short_pith_number":"pith:UTWVZ5QQ","schema_version":"1.0","canonical_sha256":"a4ed5cf6108f7dca92c5a20a5bdbc646d05a94161472c073290e7e5fba859596","source":{"kind":"arxiv","id":"2605.17467","version":1},"attestation_state":"computed","paper":{"title":"VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Ee-Peng Lim, Guansong Pang, Hanghang Tong, Hezhe Qiao","submitted_at":"2026-05-17T14:09:35Z","abstract_excerpt":"Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing approaches, such as direct prediction of agent-error pairs and agent-first failure attribution, rely on local logs of agents and miss global failures that only manifest over full interaction trajectories, such as cross-step inconsistencies and inter-agent coordination errors. Moreover, directly predicting failures induces a large combinatorial search space, hindering fine-gr"},"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":"2605.17467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T14:09:35Z","cross_cats_sorted":[],"title_canon_sha256":"e8b6e1a9a0b29a1fac327e1ad28eb48f4d96082d9c1f48f6f3bfc2e8b3fb1b47","abstract_canon_sha256":"5be1941fdb162682a8f31a17c602aa402f36fd7d88bc7d08f40119506bd96f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:40.457303Z","signature_b64":"H7640gKKKsJb7WkYbJWn5wnYqZXaIMcWo2vnjMGgvtQO2Ho5GYFyx51uW+GIDQp2SEvAzp7Jug/bdM2Dwag7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4ed5cf6108f7dca92c5a20a5bdbc646d05a94161472c073290e7e5fba859596","last_reissued_at":"2026-05-20T00:04:40.456661Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:40.456661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Ee-Peng Lim, Guansong Pang, Hanghang Tong, Hezhe Qiao","submitted_at":"2026-05-17T14:09:35Z","abstract_excerpt":"Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attribution is therefore critical, but existing approaches, such as direct prediction of agent-error pairs and agent-first failure attribution, rely on local logs of agents and miss global failures that only manifest over full interaction trajectories, such as cross-step inconsistencies and inter-agent coordination errors. Moreover, directly predicting failures induces a large combinatorial search space, hindering fine-gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17467","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/2605.17467/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.700461Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.656458Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d38adf6b7f3379030a7f64dc08aaf19f54a227baf96974c0ee9943fc22641dee"},"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":"2605.17467","created_at":"2026-05-20T00:04:40.456754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17467v1","created_at":"2026-05-20T00:04:40.456754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17467","created_at":"2026-05-20T00:04:40.456754+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTWVZ5QQR564","created_at":"2026-05-20T00:04:40.456754+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTWVZ5QQR564VEWF","created_at":"2026-05-20T00:04:40.456754+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTWVZ5QQ","created_at":"2026-05-20T00:04:40.456754+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/UTWVZ5QQR564VEWFUIFFXW6GI3","json":"https://pith.science/pith/UTWVZ5QQR564VEWFUIFFXW6GI3.json","graph_json":"https://pith.science/api/pith-number/UTWVZ5QQR564VEWFUIFFXW6GI3/graph.json","events_json":"https://pith.science/api/pith-number/UTWVZ5QQR564VEWFUIFFXW6GI3/events.json","paper":"https://pith.science/paper/UTWVZ5QQ"},"agent_actions":{"view_html":"https://pith.science/pith/UTWVZ5QQR564VEWFUIFFXW6GI3","download_json":"https://pith.science/pith/UTWVZ5QQR564VEWFUIFFXW6GI3.json","view_paper":"https://pith.science/paper/UTWVZ5QQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17467&json=true","fetch_graph":"https://pith.science/api/pith-number/UTWVZ5QQR564VEWFUIFFXW6GI3/graph.json","fetch_events":"https://pith.science/api/pith-number/UTWVZ5QQR564VEWFUIFFXW6GI3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTWVZ5QQR564VEWFUIFFXW6GI3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTWVZ5QQR564VEWFUIFFXW6GI3/action/storage_attestation","attest_author":"https://pith.science/pith/UTWVZ5QQR564VEWFUIFFXW6GI3/action/author_attestation","sign_citation":"https://pith.science/pith/UTWVZ5QQR564VEWFUIFFXW6GI3/action/citation_signature","submit_replication":"https://pith.science/pith/UTWVZ5QQR564VEWFUIFFXW6GI3/action/replication_record"}},"created_at":"2026-05-20T00:04:40.456754+00:00","updated_at":"2026-05-20T00:04:40.456754+00:00"}