{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DOIXCMUEV35ZM7BG6KG57NMTA6","short_pith_number":"pith:DOIXCMUE","schema_version":"1.0","canonical_sha256":"1b91713284aefb967c26f28ddfb59307929d640de3683875a25e6ad5d35bd1d1","source":{"kind":"arxiv","id":"2406.13668","version":3},"attestation_state":"computed","paper":{"title":"Breaking the $T^{2/3}$ Barrier for Sequential Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantinos Daskalakis, Maxwell Fishelson, Noah Golowich, Princewill Okoroafor, Robert Kleinberg, Yuval Dagan","submitted_at":"2024-06-19T16:19:39Z","abstract_excerpt":"A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where that prediction was made. We study the fundamental problem of online calibrated forecasting of binary sequences, which was initially studied by Foster & Vohra (1998). They derived an algorithm with $O(T^{2/3})$ calibration error after $T$ time steps, and showed a lower bound of $\\Omega(T^{1/2})$. These bounds remained stagnant for two decades, until Qiao & Valiant (2021) improved the lower bound to $\\Omega(T^{0.528})$ b"},"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":"2406.13668","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T16:19:39Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"0ee08f54ac46db3fc96b32d37ce38fdd97dde8adb12240965611688ecf9ea7c5","abstract_canon_sha256":"c459ad5a585918df34ca29dec8e630d618b6fb1dc92887a2e8a2e6da3646d743"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:12.643204Z","signature_b64":"zv4/4P7Gl4+5JLBFZPhgBz2pasx19Vd2Dt4uRgnkmnB/Bp/LljzN+NSsU2WnTyR6Dkyd5gEu08Ep7rC+iJsFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b91713284aefb967c26f28ddfb59307929d640de3683875a25e6ad5d35bd1d1","last_reissued_at":"2026-07-05T09:36:12.642704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:12.642704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the $T^{2/3}$ Barrier for Sequential Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Constantinos Daskalakis, Maxwell Fishelson, Noah Golowich, Princewill Okoroafor, Robert Kleinberg, Yuval Dagan","submitted_at":"2024-06-19T16:19:39Z","abstract_excerpt":"A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where that prediction was made. We study the fundamental problem of online calibrated forecasting of binary sequences, which was initially studied by Foster & Vohra (1998). They derived an algorithm with $O(T^{2/3})$ calibration error after $T$ time steps, and showed a lower bound of $\\Omega(T^{1/2})$. These bounds remained stagnant for two decades, until Qiao & Valiant (2021) improved the lower bound to $\\Omega(T^{0.528})$ b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13668","kind":"arxiv","version":3},"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/2406.13668/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":"2406.13668","created_at":"2026-07-05T09:36:12.642767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13668v3","created_at":"2026-07-05T09:36:12.642767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13668","created_at":"2026-07-05T09:36:12.642767+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOIXCMUEV35Z","created_at":"2026-07-05T09:36:12.642767+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOIXCMUEV35ZM7BG","created_at":"2026-07-05T09:36:12.642767+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOIXCMUE","created_at":"2026-07-05T09:36:12.642767+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21460","citing_title":"High-Dimensional Calibration from Swap Regret","ref_index":1982,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6","json":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6.json","graph_json":"https://pith.science/api/pith-number/DOIXCMUEV35ZM7BG6KG57NMTA6/graph.json","events_json":"https://pith.science/api/pith-number/DOIXCMUEV35ZM7BG6KG57NMTA6/events.json","paper":"https://pith.science/paper/DOIXCMUE"},"agent_actions":{"view_html":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6","download_json":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6.json","view_paper":"https://pith.science/paper/DOIXCMUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13668&json=true","fetch_graph":"https://pith.science/api/pith-number/DOIXCMUEV35ZM7BG6KG57NMTA6/graph.json","fetch_events":"https://pith.science/api/pith-number/DOIXCMUEV35ZM7BG6KG57NMTA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6/action/storage_attestation","attest_author":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6/action/author_attestation","sign_citation":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6/action/citation_signature","submit_replication":"https://pith.science/pith/DOIXCMUEV35ZM7BG6KG57NMTA6/action/replication_record"}},"created_at":"2026-07-05T09:36:12.642767+00:00","updated_at":"2026-07-05T09:36:12.642767+00:00"}