{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EZKV4R5LULR66VMTO5AKA2SKVI","short_pith_number":"pith:EZKV4R5L","schema_version":"1.0","canonical_sha256":"26555e47aba2e3ef55937740a06a4aaa12e57a98de6a8fadc026f9b228c8e95f","source":{"kind":"arxiv","id":"2606.02282","version":1},"attestation_state":"computed","paper":{"title":"POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"\\'Alvaro Guti\\'errez, Annemarie F. Laudanski, Eduardo Rocon, I\\~naki Dellibarda Varela, J.M. Valverde-Garc\\'ia, Manuel Cebrian, Pablo Romero-Sorozabal, R. Sendra-Arranz","submitted_at":"2026-06-01T14:05:35Z","abstract_excerpt":"Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and hallucinations that resist characterisation block their deployment in safety-critical domains -- a gap made legally untenable by emerging AI regulation. Existing evaluation paradigms share a common flaw: centralised judgment creates single points of failure and demands domain-specific expertise. Here we present POIROT, a protocol that repurposes a system's own agents as its diagnostic layer, leveraging the epistemic diversity already present in the ar"},"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":"2606.02282","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T14:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"6875559d026e60cbbf457fa9ca831322bb31ae4f2d7ba4c1231e8dbf7125ffdc","abstract_canon_sha256":"df9c628b88bd7ae5582f5fd0eb2609d69811e40aeba1e2824dbd4a7b0177bd6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:55.029006Z","signature_b64":"rPIb57qK6TEdAcfTD9I74lPyWhm7K99GEqgiupDBiUXLve7w/bepyS9Srn2QwvHBzhsR105YAksTtKhLM8TEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26555e47aba2e3ef55937740a06a4aaa12e57a98de6a8fadc026f9b228c8e95f","last_reissued_at":"2026-06-02T03:04:55.028667Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:55.028667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"\\'Alvaro Guti\\'errez, Annemarie F. Laudanski, Eduardo Rocon, I\\~naki Dellibarda Varela, J.M. Valverde-Garc\\'ia, Manuel Cebrian, Pablo Romero-Sorozabal, R. Sendra-Arranz","submitted_at":"2026-06-01T14:05:35Z","abstract_excerpt":"Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and hallucinations that resist characterisation block their deployment in safety-critical domains -- a gap made legally untenable by emerging AI regulation. Existing evaluation paradigms share a common flaw: centralised judgment creates single points of failure and demands domain-specific expertise. Here we present POIROT, a protocol that repurposes a system's own agents as its diagnostic layer, leveraging the epistemic diversity already present in the ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02282","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/2606.02282/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":"2606.02282","created_at":"2026-06-02T03:04:55.028724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02282v1","created_at":"2026-06-02T03:04:55.028724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02282","created_at":"2026-06-02T03:04:55.028724+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZKV4R5LULR6","created_at":"2026-06-02T03:04:55.028724+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZKV4R5LULR66VMT","created_at":"2026-06-02T03:04:55.028724+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZKV4R5L","created_at":"2026-06-02T03:04:55.028724+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/EZKV4R5LULR66VMTO5AKA2SKVI","json":"https://pith.science/pith/EZKV4R5LULR66VMTO5AKA2SKVI.json","graph_json":"https://pith.science/api/pith-number/EZKV4R5LULR66VMTO5AKA2SKVI/graph.json","events_json":"https://pith.science/api/pith-number/EZKV4R5LULR66VMTO5AKA2SKVI/events.json","paper":"https://pith.science/paper/EZKV4R5L"},"agent_actions":{"view_html":"https://pith.science/pith/EZKV4R5LULR66VMTO5AKA2SKVI","download_json":"https://pith.science/pith/EZKV4R5LULR66VMTO5AKA2SKVI.json","view_paper":"https://pith.science/paper/EZKV4R5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02282&json=true","fetch_graph":"https://pith.science/api/pith-number/EZKV4R5LULR66VMTO5AKA2SKVI/graph.json","fetch_events":"https://pith.science/api/pith-number/EZKV4R5LULR66VMTO5AKA2SKVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZKV4R5LULR66VMTO5AKA2SKVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZKV4R5LULR66VMTO5AKA2SKVI/action/storage_attestation","attest_author":"https://pith.science/pith/EZKV4R5LULR66VMTO5AKA2SKVI/action/author_attestation","sign_citation":"https://pith.science/pith/EZKV4R5LULR66VMTO5AKA2SKVI/action/citation_signature","submit_replication":"https://pith.science/pith/EZKV4R5LULR66VMTO5AKA2SKVI/action/replication_record"}},"created_at":"2026-06-02T03:04:55.028724+00:00","updated_at":"2026-06-02T03:04:55.028724+00:00"}