{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N4F3NZQVOSVOSQXFHE4IZIZAXE","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":"874afd35b23b33a17ae1b03cd6acae967942e57ebb3410f1d8e4891dd6fadf9a","cross_cats_sorted":["math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2026-05-11T09:44:02Z","title_canon_sha256":"cb30071320da0b596f3043e477f8defffe786c2574ef374546e9e92848fc3ae2"},"schema_version":"1.0","source":{"id":"2605.10282","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10282","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10282v2","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10282","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"N4F3NZQVOSVO","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"N4F3NZQVOSVOSQXF","created_at":"2026-06-02T03:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"N4F3NZQV","created_at":"2026-06-02T03:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:badd9eaabcc80021dfec3817a398437a8174645ec58064c06077b8995813ba96","target":"graph","created_at":"2026-06-02T03:04:41Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We analyze the minimax regret in the misspecified setting and derive the corresponding optimal universal learner. We propose this formulation as a unified framework for universal learning, applicable to any form of uncertainty in the data-generating process, across both online and batch data arrival modes, as well as supervised and unsupervised learning tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the minimax regret analysis and optimal learner derivation from the well-specified case extend directly to the misspecified case Φ ⊃ Θ without introducing new technical obstacles or requiring additional assumptions on the relationship between Θ and Φ."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Minimax regret is characterized for misspecified universal learning with log-loss, yielding the optimal universal learner as a unified framework for any uncertainty in the data-generating process."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Misspecified universal learning with log-loss admits an optimal learner derived from minimax regret analysis."}],"snapshot_sha256":"f692851c357c9bc8ad8a70bf5e8a5c12aec155dc80367ac7fa6063ebfe3c2a5b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T06:22:00.846301Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:37:14.381885Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:19.312816Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:29:42.503975Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10282/integrity.json","findings":[],"snapshot_sha256":"f6f6ccb91ec99a4d83a4197de3626e8e718c59420589afdd874da2c8f23f9c6b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the problem of universal learning under model misspecification with log-loss. In this setting, the learner operates with a hypothesis class of models denoted by $\\Theta$, while the true data-generating process belongs to a broader class $\\Phi \\supset \\Theta$, and may lie outside the assumed hypothesis space. Classical approaches have characterized the minimax regret and identified optimal universal learners in both the well-specified stochastic and individual deterministic frameworks. The misspecified setting has received comparatively less attention, although several impo","authors_text":"Meir Feder, Shlomi Vituri","cross_cats":["math.IT"],"headline":"Misspecified universal learning with log-loss admits an optimal learner derived from minimax regret analysis.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2026-05-11T09:44:02Z","title":"Misspecified Universal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10282","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T05:06:12.497362Z","id":"45eae2ca-d950-41ab-8e24-6e0c6f4b375c","model_set":{"reader":"grok-4.3"},"one_line_summary":"Minimax regret is characterized for misspecified universal learning with log-loss, yielding the optimal universal learner as a unified framework for any uncertainty in the data-generating process.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Misspecified universal learning with log-loss admits an optimal learner derived from minimax regret analysis.","strongest_claim":"We analyze the minimax regret in the misspecified setting and derive the corresponding optimal universal learner. We propose this formulation as a unified framework for universal learning, applicable to any form of uncertainty in the data-generating process, across both online and batch data arrival modes, as well as supervised and unsupervised learning tasks.","weakest_assumption":"That the minimax regret analysis and optimal learner derivation from the well-specified case extend directly to the misspecified case Φ ⊃ Θ without introducing new technical obstacles or requiring additional assumptions on the relationship between Θ and Φ."}},"verdict_id":"45eae2ca-d950-41ab-8e24-6e0c6f4b375c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fb4ebfc1d4c5f506b84b450f2301613f0afddf13124789b5738c02551b02daf3","target":"record","created_at":"2026-06-02T03:04:41Z","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":"874afd35b23b33a17ae1b03cd6acae967942e57ebb3410f1d8e4891dd6fadf9a","cross_cats_sorted":["math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2026-05-11T09:44:02Z","title_canon_sha256":"cb30071320da0b596f3043e477f8defffe786c2574ef374546e9e92848fc3ae2"},"schema_version":"1.0","source":{"id":"2605.10282","kind":"arxiv","version":2}},"canonical_sha256":"6f0bb6e61574aae942e539388ca320b91a192092acaaa326b085002a1b600e2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f0bb6e61574aae942e539388ca320b91a192092acaaa326b085002a1b600e2a","first_computed_at":"2026-06-02T03:04:41.953126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:41.953126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5EdEuzGXML9Zbaj214SLHQ2Eel+AJFgnRa+JwlRfte0eFSdAmGW/K6/iV2WrhnIaIJIf6vWSyxfD0aGqzWa0Dg==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:41.953491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10282","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb4ebfc1d4c5f506b84b450f2301613f0afddf13124789b5738c02551b02daf3","sha256:badd9eaabcc80021dfec3817a398437a8174645ec58064c06077b8995813ba96"],"state_sha256":"6a2d1d353981ba4767d7ea3acaa8378dbc80a0fee9e0064904104a1a6c786237"}