{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7NEGOXCXCG6A4VB4APFYMWOB62","short_pith_number":"pith:7NEGOXCX","schema_version":"1.0","canonical_sha256":"fb48675c5711bc0e543c03cb8659c1f69ee35b4f95be9c0642358ffd39e061d9","source":{"kind":"arxiv","id":"2505.21460","version":1},"attestation_state":"computed","paper":{"title":"High-Dimensional Calibration from Swap Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jon Schneider, Maxwell Fishelson, Mehryar Mohri, Noah Golowich","submitted_at":"2025-05-27T17:31:47Z","abstract_excerpt":"We study the online calibration of multi-dimensional forecasts over an arbitrary convex set $\\mathcal{P} \\subset \\mathbb{R}^d$ relative to an arbitrary norm $\\Vert\\cdot\\Vert$. We connect this with the problem of external regret minimization for online linear optimization, showing that if it is possible to guarantee $O(\\sqrt{\\rho T})$ worst-case regret after $T$ rounds when actions are drawn from $\\mathcal{P}$ and losses are drawn from the dual $\\Vert \\cdot \\Vert_*$ unit norm ball, then it is also possible to obtain $\\epsilon$-calibrated forecasts after $T = \\exp(O(\\rho /\\epsilon^2))$ rounds. W"},"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":"2505.21460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T17:31:47Z","cross_cats_sorted":["cs.DS","cs.GT","stat.ML"],"title_canon_sha256":"a3b724a345d02e01bcc9310715dccb2deb994c901344aa5e73c83f8079b0b3c9","abstract_canon_sha256":"ac284bcf0735792681bc1249c7ed32db5cca99bc5f2521f410fed766447456b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:42.337425Z","signature_b64":"/8pdXMJmvZZOA4Y1ZxdPARwewrlQ43t5/H039GxvWlIwXLmYjIXvU0Ttir9o1PZq7gSW/1GB1Snvi6CayKd7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb48675c5711bc0e543c03cb8659c1f69ee35b4f95be9c0642358ffd39e061d9","last_reissued_at":"2026-07-05T11:10:42.336929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:42.336929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Dimensional Calibration from Swap Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jon Schneider, Maxwell Fishelson, Mehryar Mohri, Noah Golowich","submitted_at":"2025-05-27T17:31:47Z","abstract_excerpt":"We study the online calibration of multi-dimensional forecasts over an arbitrary convex set $\\mathcal{P} \\subset \\mathbb{R}^d$ relative to an arbitrary norm $\\Vert\\cdot\\Vert$. We connect this with the problem of external regret minimization for online linear optimization, showing that if it is possible to guarantee $O(\\sqrt{\\rho T})$ worst-case regret after $T$ rounds when actions are drawn from $\\mathcal{P}$ and losses are drawn from the dual $\\Vert \\cdot \\Vert_*$ unit norm ball, then it is also possible to obtain $\\epsilon$-calibrated forecasts after $T = \\exp(O(\\rho /\\epsilon^2))$ rounds. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21460","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/2505.21460/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":"2505.21460","created_at":"2026-07-05T11:10:42.336985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21460v1","created_at":"2026-07-05T11:10:42.336985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21460","created_at":"2026-07-05T11:10:42.336985+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NEGOXCXCG6A","created_at":"2026-07-05T11:10:42.336985+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NEGOXCXCG6A4VB4","created_at":"2026-07-05T11:10:42.336985+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NEGOXCX","created_at":"2026-07-05T11:10:42.336985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02279","citing_title":"Calibration through the Lens of Indistinguishability","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62","json":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62.json","graph_json":"https://pith.science/api/pith-number/7NEGOXCXCG6A4VB4APFYMWOB62/graph.json","events_json":"https://pith.science/api/pith-number/7NEGOXCXCG6A4VB4APFYMWOB62/events.json","paper":"https://pith.science/paper/7NEGOXCX"},"agent_actions":{"view_html":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62","download_json":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62.json","view_paper":"https://pith.science/paper/7NEGOXCX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21460&json=true","fetch_graph":"https://pith.science/api/pith-number/7NEGOXCXCG6A4VB4APFYMWOB62/graph.json","fetch_events":"https://pith.science/api/pith-number/7NEGOXCXCG6A4VB4APFYMWOB62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62/action/storage_attestation","attest_author":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62/action/author_attestation","sign_citation":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62/action/citation_signature","submit_replication":"https://pith.science/pith/7NEGOXCXCG6A4VB4APFYMWOB62/action/replication_record"}},"created_at":"2026-07-05T11:10:42.336985+00:00","updated_at":"2026-07-05T11:10:42.336985+00:00"}