{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EZZQM7JXSXZU2ZEGYI7RB5NUFT","short_pith_number":"pith:EZZQM7JX","schema_version":"1.0","canonical_sha256":"2673067d3795f34d6486c23f10f5b42ce8c93f57faf0b238adddecbbf9edaf4f","source":{"kind":"arxiv","id":"2607.20529","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiawei Zheng, Jiazhen Zhang","submitted_at":"2026-07-10T08:47:05Z","abstract_excerpt":"Large Language Model (LLM) ensembles are increasingly used to improve reliability by combining predictions from multiple LLMs. However, existing aggregation methods typically assume that all models are equally trustworthy, overlooking differences in uncertainty quality. This assumption is poorly suited to heterogeneous LLMs, whose reliability and capability vary significantly, making naive aggregation vulnerable to unreliable or adversarial experts. In this work, we formulate multi-LLM aggregation as a problem of uncertainty-aware trust estimation. We adapt structured expert judgment from deci"},"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":"2607.20529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T08:47:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"25917c019f494a3960488f82b1986262447c1081f85d66f05b4392f0e74fb860","abstract_canon_sha256":"e134f178321fee15417501e4ac2934c76d2f18df617929e506c187799094d4ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:20.570974Z","signature_b64":"oQZC9IQCY+kp1NPbgrIRbx0b4fy32BPf1KS0pTfT41CY5d5kKQ43L9JumTgfM7JiI9Kh5dqzmV/qGSlUybCGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2673067d3795f34d6486c23f10f5b42ce8c93f57faf0b238adddecbbf9edaf4f","last_reissued_at":"2026-07-24T00:23:20.570121Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:20.570121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiawei Zheng, Jiazhen Zhang","submitted_at":"2026-07-10T08:47:05Z","abstract_excerpt":"Large Language Model (LLM) ensembles are increasingly used to improve reliability by combining predictions from multiple LLMs. However, existing aggregation methods typically assume that all models are equally trustworthy, overlooking differences in uncertainty quality. This assumption is poorly suited to heterogeneous LLMs, whose reliability and capability vary significantly, making naive aggregation vulnerable to unreliable or adversarial experts. In this work, we formulate multi-LLM aggregation as a problem of uncertainty-aware trust estimation. We adapt structured expert judgment from deci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20529","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/2607.20529/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":"2607.20529","created_at":"2026-07-24T00:23:20.570566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20529v1","created_at":"2026-07-24T00:23:20.570566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20529","created_at":"2026-07-24T00:23:20.570566+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZZQM7JXSXZU","created_at":"2026-07-24T00:23:20.570566+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZZQM7JXSXZU2ZEG","created_at":"2026-07-24T00:23:20.570566+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZZQM7JX","created_at":"2026-07-24T00:23:20.570566+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/EZZQM7JXSXZU2ZEGYI7RB5NUFT","json":"https://pith.science/pith/EZZQM7JXSXZU2ZEGYI7RB5NUFT.json","graph_json":"https://pith.science/api/pith-number/EZZQM7JXSXZU2ZEGYI7RB5NUFT/graph.json","events_json":"https://pith.science/api/pith-number/EZZQM7JXSXZU2ZEGYI7RB5NUFT/events.json","paper":"https://pith.science/paper/EZZQM7JX"},"agent_actions":{"view_html":"https://pith.science/pith/EZZQM7JXSXZU2ZEGYI7RB5NUFT","download_json":"https://pith.science/pith/EZZQM7JXSXZU2ZEGYI7RB5NUFT.json","view_paper":"https://pith.science/paper/EZZQM7JX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20529&json=true","fetch_graph":"https://pith.science/api/pith-number/EZZQM7JXSXZU2ZEGYI7RB5NUFT/graph.json","fetch_events":"https://pith.science/api/pith-number/EZZQM7JXSXZU2ZEGYI7RB5NUFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZZQM7JXSXZU2ZEGYI7RB5NUFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZZQM7JXSXZU2ZEGYI7RB5NUFT/action/storage_attestation","attest_author":"https://pith.science/pith/EZZQM7JXSXZU2ZEGYI7RB5NUFT/action/author_attestation","sign_citation":"https://pith.science/pith/EZZQM7JXSXZU2ZEGYI7RB5NUFT/action/citation_signature","submit_replication":"https://pith.science/pith/EZZQM7JXSXZU2ZEGYI7RB5NUFT/action/replication_record"}},"created_at":"2026-07-24T00:23:20.570566+00:00","updated_at":"2026-07-24T00:23:20.570566+00:00"}