{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FBKOA47IKSKEC4DMQT4XOLCGSW","short_pith_number":"pith:FBKOA47I","schema_version":"1.0","canonical_sha256":"2854e073e8549441706c84f9772c469590085eb211dc7a0ab2466401e1a3b973","source":{"kind":"arxiv","id":"2606.20557","version":1},"attestation_state":"computed","paper":{"title":"Optimal Deterministic Multicalibration and Omniprediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Georgy Noarov","submitted_at":"2026-06-18T17:59:31Z","abstract_excerpt":"A model is multicalibrated on a collection of group weights $G$ if it is calibrated -- i.e. unbiased even conditional on its prediction -- not just overall, but also after reweighting contexts by each $g \\in G$. It is a useful property for many downstream applications and is a basic desideratum of trustworthy machine learning. Before this work, all predictors known to attain the minimax-optimal $\\widetilde O(\\varepsilon^{-3})$ sample complexity rate for $\\varepsilon$-multicalibration were randomized, while deterministic predictors were known only with substantially worse sample complexity. Whe"},"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":"2606.20557","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T17:59:31Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"15ac5aa854d9a87765e20e995a25e2f82bb761a17789d8cb9bfa1a69d8967042","abstract_canon_sha256":"b6220b971b4351814d2dae042f56705e65b853ace33ac95969a5c749d8ff3bbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:15.282894Z","signature_b64":"NPEokJz7C+1OCoYXXSE54aajGWfoW7pL5BOQaMFYmJjBQAJwl4Gvv0Ty7oR59fnHwCdUK2wGvFXtLYI3XwkGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2854e073e8549441706c84f9772c469590085eb211dc7a0ab2466401e1a3b973","last_reissued_at":"2026-06-19T16:13:15.282546Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:15.282546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Deterministic Multicalibration and Omniprediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Georgy Noarov","submitted_at":"2026-06-18T17:59:31Z","abstract_excerpt":"A model is multicalibrated on a collection of group weights $G$ if it is calibrated -- i.e. unbiased even conditional on its prediction -- not just overall, but also after reweighting contexts by each $g \\in G$. It is a useful property for many downstream applications and is a basic desideratum of trustworthy machine learning. Before this work, all predictors known to attain the minimax-optimal $\\widetilde O(\\varepsilon^{-3})$ sample complexity rate for $\\varepsilon$-multicalibration were randomized, while deterministic predictors were known only with substantially worse sample complexity. Whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20557","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/2606.20557/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":"2606.20557","created_at":"2026-06-19T16:13:15.282600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20557v1","created_at":"2026-06-19T16:13:15.282600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20557","created_at":"2026-06-19T16:13:15.282600+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBKOA47IKSKE","created_at":"2026-06-19T16:13:15.282600+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBKOA47IKSKEC4DM","created_at":"2026-06-19T16:13:15.282600+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBKOA47I","created_at":"2026-06-19T16:13:15.282600+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/FBKOA47IKSKEC4DMQT4XOLCGSW","json":"https://pith.science/pith/FBKOA47IKSKEC4DMQT4XOLCGSW.json","graph_json":"https://pith.science/api/pith-number/FBKOA47IKSKEC4DMQT4XOLCGSW/graph.json","events_json":"https://pith.science/api/pith-number/FBKOA47IKSKEC4DMQT4XOLCGSW/events.json","paper":"https://pith.science/paper/FBKOA47I"},"agent_actions":{"view_html":"https://pith.science/pith/FBKOA47IKSKEC4DMQT4XOLCGSW","download_json":"https://pith.science/pith/FBKOA47IKSKEC4DMQT4XOLCGSW.json","view_paper":"https://pith.science/paper/FBKOA47I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20557&json=true","fetch_graph":"https://pith.science/api/pith-number/FBKOA47IKSKEC4DMQT4XOLCGSW/graph.json","fetch_events":"https://pith.science/api/pith-number/FBKOA47IKSKEC4DMQT4XOLCGSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBKOA47IKSKEC4DMQT4XOLCGSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBKOA47IKSKEC4DMQT4XOLCGSW/action/storage_attestation","attest_author":"https://pith.science/pith/FBKOA47IKSKEC4DMQT4XOLCGSW/action/author_attestation","sign_citation":"https://pith.science/pith/FBKOA47IKSKEC4DMQT4XOLCGSW/action/citation_signature","submit_replication":"https://pith.science/pith/FBKOA47IKSKEC4DMQT4XOLCGSW/action/replication_record"}},"created_at":"2026-06-19T16:13:15.282600+00:00","updated_at":"2026-06-19T16:13:15.282600+00:00"}