{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A7YV4GCEJNIDDRB2XHUAXCEOO5","short_pith_number":"pith:A7YV4GCE","schema_version":"1.0","canonical_sha256":"07f15e18444b5031c43ab9e80b888e7752330f80e25d7300df3b074580d54db8","source":{"kind":"arxiv","id":"2605.19779","version":1},"attestation_state":"computed","paper":{"title":"Distribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Megan Wang, Yi Ling Yu, Yuxuan Gao","submitted_at":"2026-05-19T12:47:21Z","abstract_excerpt":"We adapt split conformal prediction and adaptive conformal inference (ACI) to continuous AI agent evaluation, providing distribution-free coverage guarantees for forecasted quality scores. Conformal intervals achieve calibration error below 0.02 across all nominal levels at the 24h horizon, while ACI correctly widens intervals by 35% following agent releases then reconverges. We further develop compositional uncertainty bounds for multi-agent pipelines (validated via simulation across inter-stage correlations rho in [-0.5, 0.9]), a conformal abstention rule for pairwise rankings with controlle"},"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":"2605.19779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T12:47:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"819d9fd1ed245e171f5743cecaccc0fc0d1f1437df077c8e6a9fb7efdf72da4b","abstract_canon_sha256":"a107328a5610a4e28b773f5e0facfb8370ff2a84cac57b39621c7192a1b05e79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:13.339166Z","signature_b64":"lh2dgAN6P6SOLiO0kLRidaKoEN9xO6Wdmb9aOvz65wA2FqZg+hqh/V0fKznBDs/NnsRfoG5L8rqsUfM3oGvZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07f15e18444b5031c43ab9e80b888e7752330f80e25d7300df3b074580d54db8","last_reissued_at":"2026-05-20T01:06:13.338454Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:13.338454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Megan Wang, Yi Ling Yu, Yuxuan Gao","submitted_at":"2026-05-19T12:47:21Z","abstract_excerpt":"We adapt split conformal prediction and adaptive conformal inference (ACI) to continuous AI agent evaluation, providing distribution-free coverage guarantees for forecasted quality scores. Conformal intervals achieve calibration error below 0.02 across all nominal levels at the 24h horizon, while ACI correctly widens intervals by 35% following agent releases then reconverges. We further develop compositional uncertainty bounds for multi-agent pipelines (validated via simulation across inter-stage correlations rho in [-0.5, 0.9]), a conformal abstention rule for pairwise rankings with controlle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19779","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/2605.19779/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":"2605.19779","created_at":"2026-05-20T01:06:13.338569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19779v1","created_at":"2026-05-20T01:06:13.338569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19779","created_at":"2026-05-20T01:06:13.338569+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7YV4GCEJNID","created_at":"2026-05-20T01:06:13.338569+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7YV4GCEJNIDDRB2","created_at":"2026-05-20T01:06:13.338569+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7YV4GCE","created_at":"2026-05-20T01:06:13.338569+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/A7YV4GCEJNIDDRB2XHUAXCEOO5","json":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5.json","graph_json":"https://pith.science/api/pith-number/A7YV4GCEJNIDDRB2XHUAXCEOO5/graph.json","events_json":"https://pith.science/api/pith-number/A7YV4GCEJNIDDRB2XHUAXCEOO5/events.json","paper":"https://pith.science/paper/A7YV4GCE"},"agent_actions":{"view_html":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5","download_json":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5.json","view_paper":"https://pith.science/paper/A7YV4GCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19779&json=true","fetch_graph":"https://pith.science/api/pith-number/A7YV4GCEJNIDDRB2XHUAXCEOO5/graph.json","fetch_events":"https://pith.science/api/pith-number/A7YV4GCEJNIDDRB2XHUAXCEOO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/action/storage_attestation","attest_author":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/action/author_attestation","sign_citation":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/action/citation_signature","submit_replication":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/action/replication_record"}},"created_at":"2026-05-20T01:06:13.338569+00:00","updated_at":"2026-05-20T01:06:13.338569+00:00"}