{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A7YV4GCEJNIDDRB2XHUAXCEOO5","short_pith_number":"pith:A7YV4GCE","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"},"canonical_sha256":"07f15e18444b5031c43ab9e80b888e7752330f80e25d7300df3b074580d54db8","source":{"kind":"arxiv","id":"2605.19779","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19779","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19779v1","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19779","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"A7YV4GCEJNID","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"A7YV4GCEJNIDDRB2","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"A7YV4GCE","created_at":"2026-05-20T01:06:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A7YV4GCEJNIDDRB2XHUAXCEOO5","target":"record","payload":{"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"},"canonical_sha256":"07f15e18444b5031c43ab9e80b888e7752330f80e25d7300df3b074580d54db8","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"},"source_kind":"arxiv","source_id":"2605.19779","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DCN6gfjEPB5VUrIf8qwYQ8khjQsuwYyiwW00zZjLIQLd0ZZSiZmRtxYSA4LCKky5vj7C4wkHGkVSHQ2KPoiGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T11:50:43.404766Z"},"content_sha256":"d70f33b6046ffd1b1b79158f9cbaca0dd7864cb2c28cbd2d223958688e426de5","schema_version":"1.0","event_id":"sha256:d70f33b6046ffd1b1b79158f9cbaca0dd7864cb2c28cbd2d223958688e426de5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A7YV4GCEJNIDDRB2XHUAXCEOO5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T01:06:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J/EBmcpFIQ1kvVr0x7/tsFIWpqlON1xIjeJOBn6U6URLBZe1ABmbyAhUa5NK6MwKqjQLG364TE2w2SOGIE2zDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T11:50:43.405563Z"},"content_sha256":"49e3f7161487e7017ad433b1a9ea3a08b7ae92a3975fb04d4795d9726d9b8773","schema_version":"1.0","event_id":"sha256:49e3f7161487e7017ad433b1a9ea3a08b7ae92a3975fb04d4795d9726d9b8773"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/bundle.json","state_url":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T11:50:43Z","links":{"resolver":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5","bundle":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/bundle.json","state":"https://pith.science/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A7YV4GCEJNIDDRB2XHUAXCEOO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A7YV4GCEJNIDDRB2XHUAXCEOO5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a107328a5610a4e28b773f5e0facfb8370ff2a84cac57b39621c7192a1b05e79","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T12:47:21Z","title_canon_sha256":"819d9fd1ed245e171f5743cecaccc0fc0d1f1437df077c8e6a9fb7efdf72da4b"},"schema_version":"1.0","source":{"id":"2605.19779","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19779","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19779v1","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19779","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"pith_short_12","alias_value":"A7YV4GCEJNID","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"pith_short_16","alias_value":"A7YV4GCEJNIDDRB2","created_at":"2026-05-20T01:06:13Z"},{"alias_kind":"pith_short_8","alias_value":"A7YV4GCE","created_at":"2026-05-20T01:06:13Z"}],"graph_snapshots":[{"event_id":"sha256:49e3f7161487e7017ad433b1a9ea3a08b7ae92a3975fb04d4795d9726d9b8773","target":"graph","created_at":"2026-05-20T01:06:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.19779/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Megan Wang, Yi Ling Yu, Yuxuan Gao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T12:47:21Z","title":"Distribution-Free Uncertainty Quantification for Continuous AI Agent Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19779","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d70f33b6046ffd1b1b79158f9cbaca0dd7864cb2c28cbd2d223958688e426de5","target":"record","created_at":"2026-05-20T01:06:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a107328a5610a4e28b773f5e0facfb8370ff2a84cac57b39621c7192a1b05e79","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T12:47:21Z","title_canon_sha256":"819d9fd1ed245e171f5743cecaccc0fc0d1f1437df077c8e6a9fb7efdf72da4b"},"schema_version":"1.0","source":{"id":"2605.19779","kind":"arxiv","version":1}},"canonical_sha256":"07f15e18444b5031c43ab9e80b888e7752330f80e25d7300df3b074580d54db8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07f15e18444b5031c43ab9e80b888e7752330f80e25d7300df3b074580d54db8","first_computed_at":"2026-05-20T01:06:13.338454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:06:13.338454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lh2dgAN6P6SOLiO0kLRidaKoEN9xO6Wdmb9aOvz65wA2FqZg+hqh/V0fKznBDs/NnsRfoG5L8rqsUfM3oGvZCw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:06:13.339166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19779","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d70f33b6046ffd1b1b79158f9cbaca0dd7864cb2c28cbd2d223958688e426de5","sha256:49e3f7161487e7017ad433b1a9ea3a08b7ae92a3975fb04d4795d9726d9b8773"],"state_sha256":"f7f7cc49fc59d2141852b4aacac8b4558425f2bb59ea2bcbfbc2a75dbfda27aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A2MtQYxqpw/9GZkq+dqPeCLMtXLdZOWsJt/Cl6SN4+1CfJ4JTI9tjCH+W/LTcTaPVQzEq+72bjAY4P00lMv1Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T11:50:43.409361Z","bundle_sha256":"ce017f1efc8108bcba44101c89c2a25de37c79f8b8205f3a40d6d11d2ab4ee20"}}