{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AXVIX2QMK675M4T2MT4IXVC4TY","short_pith_number":"pith:AXVIX2QM","schema_version":"1.0","canonical_sha256":"05ea8bea0c57bfd6727a64f88bd45c9e309117c3e50800a67231b9db070f0d1f","source":{"kind":"arxiv","id":"2607.28317","version":1},"attestation_state":"computed","paper":{"title":"One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alessandro Tommasi, Cesare Zavattari, Giuseppe Prencipe","submitted_at":"2026-07-30T14:52:36Z","abstract_excerpt":"A single human must audit $N$ LLM agents under a budget of $B \\ll N$ audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated errors. We model this as budgeted noisy inspection over a two-level Gaussian copula and locate the miscalibration threshold $\\delta^*$ past which confidence-ranked auditing is \\emph{worse} than random. Two a-priori expectations reverse: $\\delta^*$ \\emph{rises} as the budget shrinks, and cross-family correlation is not low---shared difficulty dominates lineage. Five open-weight LLMs show operationally useless (near-co"},"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":"2607.28317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T14:52:36Z","cross_cats_sorted":[],"title_canon_sha256":"7346a596750a279117e5f4b17eb49ba2b7a205c9f7b71dbcdc3325fca23c1e53","abstract_canon_sha256":"08817b6face136e61981f11868b1b65350333c80749a9f680fa0896185fbc8b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05ea8bea0c57bfd6727a64f88bd45c9e309117c3e50800a67231b9db070f0d1f","last_reissued_at":"2026-07-31T01:37:13.497215Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:13.497215Z"},"graph_snapshot":{"paper":{"title":"One Human, $N$ Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alessandro Tommasi, Cesare Zavattari, Giuseppe Prencipe","submitted_at":"2026-07-30T14:52:36Z","abstract_excerpt":"A single human must audit $N$ LLM agents under a budget of $B \\ll N$ audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated errors. We model this as budgeted noisy inspection over a two-level Gaussian copula and locate the miscalibration threshold $\\delta^*$ past which confidence-ranked auditing is \\emph{worse} than random. Two a-priori expectations reverse: $\\delta^*$ \\emph{rises} as the budget shrinks, and cross-family correlation is not low---shared difficulty dominates lineage. Five open-weight LLMs show operationally useless (near-co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28317","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/2607.28317/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":"2607.28317","created_at":"2026-07-31T01:37:13.500439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28317v1","created_at":"2026-07-31T01:37:13.500439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28317","created_at":"2026-07-31T01:37:13.500439+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXVIX2QMK675","created_at":"2026-07-31T01:37:13.500439+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXVIX2QMK675M4T2","created_at":"2026-07-31T01:37:13.500439+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXVIX2QM","created_at":"2026-07-31T01:37:13.500439+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/AXVIX2QMK675M4T2MT4IXVC4TY","json":"https://pith.science/pith/AXVIX2QMK675M4T2MT4IXVC4TY.json","graph_json":"https://pith.science/api/pith-number/AXVIX2QMK675M4T2MT4IXVC4TY/graph.json","events_json":"https://pith.science/api/pith-number/AXVIX2QMK675M4T2MT4IXVC4TY/events.json","paper":"https://pith.science/paper/AXVIX2QM"},"agent_actions":{"view_html":"https://pith.science/pith/AXVIX2QMK675M4T2MT4IXVC4TY","download_json":"https://pith.science/pith/AXVIX2QMK675M4T2MT4IXVC4TY.json","view_paper":"https://pith.science/paper/AXVIX2QM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28317&json=true","fetch_graph":"https://pith.science/api/pith-number/AXVIX2QMK675M4T2MT4IXVC4TY/graph.json","fetch_events":"https://pith.science/api/pith-number/AXVIX2QMK675M4T2MT4IXVC4TY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXVIX2QMK675M4T2MT4IXVC4TY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXVIX2QMK675M4T2MT4IXVC4TY/action/storage_attestation","attest_author":"https://pith.science/pith/AXVIX2QMK675M4T2MT4IXVC4TY/action/author_attestation","sign_citation":"https://pith.science/pith/AXVIX2QMK675M4T2MT4IXVC4TY/action/citation_signature","submit_replication":"https://pith.science/pith/AXVIX2QMK675M4T2MT4IXVC4TY/action/replication_record"}},"created_at":"2026-07-31T01:37:13.500439+00:00","updated_at":"2026-07-31T01:37:13.500439+00:00"}