{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2UYC2NPAPLCX7STC5LPK2CBQF5","short_pith_number":"pith:2UYC2NPA","schema_version":"1.0","canonical_sha256":"d5302d35e07ac57fca62eadead08302f4ed598eaab31c82345b4703f69f64f3c","source":{"kind":"arxiv","id":"2101.01739","version":1},"attestation_state":"computed","paper":{"title":"Online Multivalid Learning: Means, Moments, and Prediction Intervals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.GT","econ.EM"],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Christopher Jung, Georgy Noarov, Mallesh M. Pai, Varun Gupta","submitted_at":"2021-01-05T19:08:11Z","abstract_excerpt":"We present a general, efficient technique for providing contextual predictions that are \"multivalid\" in various senses, against an online sequence of adversarially chosen examples $(x,y)$. This means that the resulting estimates correctly predict various statistics of the labels $y$ not just marginally -- as averaged over the sequence of examples -- but also conditionally on $x \\in G$ for any $G$ belonging to an arbitrary intersecting collection of groups $\\mathcal{G}$.\n  We provide three instantiations of this framework. The first is mean prediction, which corresponds to an online algorithm s"},"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":"2101.01739","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-05T19:08:11Z","cross_cats_sorted":["cs.DS","cs.GT","econ.EM"],"title_canon_sha256":"23034376da8a66ec0889a725700adff4a991dff399e8bad2e8fa802b5377391c","abstract_canon_sha256":"04b4c80713a4a9dd2773633322b8f9dc4a70ba6fc665ebd1c40f9c40bac2e8f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:02.933195Z","signature_b64":"4QiQQOYYxUwWNTHSOuhgBXXMNcsuSVy4bley/qLscsFkW8nwFVDmvzkr3UdwZDeeTuC1sLxk1PW9xXy2hLiJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5302d35e07ac57fca62eadead08302f4ed598eaab31c82345b4703f69f64f3c","last_reissued_at":"2026-07-05T05:37:02.932711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:02.932711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Multivalid Learning: Means, Moments, and Prediction Intervals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.GT","econ.EM"],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Christopher Jung, Georgy Noarov, Mallesh M. Pai, Varun Gupta","submitted_at":"2021-01-05T19:08:11Z","abstract_excerpt":"We present a general, efficient technique for providing contextual predictions that are \"multivalid\" in various senses, against an online sequence of adversarially chosen examples $(x,y)$. This means that the resulting estimates correctly predict various statistics of the labels $y$ not just marginally -- as averaged over the sequence of examples -- but also conditionally on $x \\in G$ for any $G$ belonging to an arbitrary intersecting collection of groups $\\mathcal{G}$.\n  We provide three instantiations of this framework. The first is mean prediction, which corresponds to an online algorithm s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01739","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/2101.01739/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":"2101.01739","created_at":"2026-07-05T05:37:02.932774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.01739v1","created_at":"2026-07-05T05:37:02.932774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01739","created_at":"2026-07-05T05:37:02.932774+00:00"},{"alias_kind":"pith_short_12","alias_value":"2UYC2NPAPLCX","created_at":"2026-07-05T05:37:02.932774+00:00"},{"alias_kind":"pith_short_16","alias_value":"2UYC2NPAPLCX7STC","created_at":"2026-07-05T05:37:02.932774+00:00"},{"alias_kind":"pith_short_8","alias_value":"2UYC2NPA","created_at":"2026-07-05T05:37:02.932774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24364","citing_title":"Multicalibration Boosting: Theory, Convergence, and Transferability","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16324","citing_title":"Bi-Level Chaotic Fusion Based Graph Convolutional Network for Stock Market Prediction Interval","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19592","citing_title":"An Efficient Black-Box Reduction from Online Learning to Multicalibration, and a New Route to $\\Phi$-Regret Minimization","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5","json":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5.json","graph_json":"https://pith.science/api/pith-number/2UYC2NPAPLCX7STC5LPK2CBQF5/graph.json","events_json":"https://pith.science/api/pith-number/2UYC2NPAPLCX7STC5LPK2CBQF5/events.json","paper":"https://pith.science/paper/2UYC2NPA"},"agent_actions":{"view_html":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5","download_json":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5.json","view_paper":"https://pith.science/paper/2UYC2NPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.01739&json=true","fetch_graph":"https://pith.science/api/pith-number/2UYC2NPAPLCX7STC5LPK2CBQF5/graph.json","fetch_events":"https://pith.science/api/pith-number/2UYC2NPAPLCX7STC5LPK2CBQF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5/action/storage_attestation","attest_author":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5/action/author_attestation","sign_citation":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5/action/citation_signature","submit_replication":"https://pith.science/pith/2UYC2NPAPLCX7STC5LPK2CBQF5/action/replication_record"}},"created_at":"2026-07-05T05:37:02.932774+00:00","updated_at":"2026-07-05T05:37:02.932774+00:00"}