{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5FJPKEKXATQWBPTM53WR4F5EZ3","short_pith_number":"pith:5FJPKEKX","schema_version":"1.0","canonical_sha256":"e952f5115704e160be6ceeed1e17a4ceec0c7ee1858c2b9372d0690375146bf3","source":{"kind":"arxiv","id":"2604.03146","version":2},"attestation_state":"computed","paper":{"title":"Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"In high-dimensional ERM with non-Gaussian data, the estimator's projection on a test point follows the convolution of a generally non-Gaussian distribution with an independent Gaussian whose variance is set by the trace of the estimator's 2","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chiheb Yaakoubi, Cosme Louart, Malik Tiomoko, Zhenyu Liao","submitted_at":"2026-04-03T16:07:02Z","abstract_excerpt":"We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs. By heuristically extending the Convex Gaussian Min-Max Theorem (CGMT) to non-Gaussian settings, we derive an asymptotic min-max characterization of key statistics, enabling approximation of the mean $\\mu_{\\hat{\\theta}}$ and covariance $C_{\\hat{\\theta}}$ of the ERM estimator $\\hat{\\theta}$.\n  Specifically, under a concentration assumption on the data matrix and standard regularity conditions on the loss and regularizer, we show that for a test covariate $x$ independent of the training dat"},"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":true},"canonical_record":{"source":{"id":"2604.03146","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-04-03T16:07:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0aead56dd7055962032b37ae151118c4662621e6e710fc613814556c293780eb","abstract_canon_sha256":"2ecc7294798a8e729c1c0b7e0d087d728c415c1ba47a41e1c08afe86894a0d55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:03.545256Z","signature_b64":"/qExtqUPpBfJdk5NAOpJHyOl5LuPRUwaL8oZCp3zoQmJA28xrurB5u4GIxz43r3ZKbu2wKP589LIwMGxohDzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e952f5115704e160be6ceeed1e17a4ceec0c7ee1858c2b9372d0690375146bf3","last_reissued_at":"2026-06-08T01:04:03.544438Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:03.544438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"In high-dimensional ERM with non-Gaussian data, the estimator's projection on a test point follows the convolution of a generally non-Gaussian distribution with an independent Gaussian whose variance is set by the trace of the estimator's 2","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chiheb Yaakoubi, Cosme Louart, Malik Tiomoko, Zhenyu Liao","submitted_at":"2026-04-03T16:07:02Z","abstract_excerpt":"We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs. By heuristically extending the Convex Gaussian Min-Max Theorem (CGMT) to non-Gaussian settings, we derive an asymptotic min-max characterization of key statistics, enabling approximation of the mean $\\mu_{\\hat{\\theta}}$ and covariance $C_{\\hat{\\theta}}$ of the ERM estimator $\\hat{\\theta}$.\n  Specifically, under a concentration assumption on the data matrix and standard regularity conditions on the loss and regularizer, we show that for a test covariate $x$ independent of the training dat"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"under a concentration assumption on the data matrix and standard regularity conditions on the loss and regularizer, we show that for a test covariate x independent of the training data, the projection θ̂⊤x approximately follows the convolution of the (generally non-Gaussian) distribution of μ_θ̂⊤x with an independent centered Gaussian variable of variance Tr(C_θ̂ E[xx⊤])","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"the heuristic extension of the Convex Gaussian Min-Max Theorem to non-Gaussian settings under a concentration assumption on the data matrix","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"In high-dimensional convex ERM with non-Gaussian data, the projection of the estimator onto a test covariate asymptotically follows the convolution of a generally non-Gaussian term with an independent centered Gaussian whose variance is the trace of the estimator covariance times the data second-mom","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"In high-dimensional ERM with non-Gaussian data, the estimator's projection on a test point follows the convolution of a generally non-Gaussian distribution with an independent Gaussian whose variance is set by the trace of the estimator's 2","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"45da8ea5e864f82801169551c28b2f9e4a77c0347aea89b7190e96f591fd0d21"},"source":{"id":"2604.03146","kind":"arxiv","version":2},"verdict":{"id":"38f6bd0f-fefd-42f4-928b-7b41d3204007","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T18:25:32.317025Z","strongest_claim":"under a concentration assumption on the data matrix and standard regularity conditions on the loss and regularizer, we show that for a test covariate x independent of the training data, the projection θ̂⊤x approximately follows the convolution of the (generally non-Gaussian) distribution of μ_θ̂⊤x with an independent centered Gaussian variable of variance Tr(C_θ̂ E[xx⊤])","one_line_summary":"In high-dimensional convex ERM with non-Gaussian data, the projection of the estimator onto a test covariate asymptotically follows the convolution of a generally non-Gaussian term with an independent centered Gaussian whose variance is the trace of the estimator covariance times the data second-mom","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"the heuristic extension of the Convex Gaussian Min-Max Theorem to non-Gaussian settings under a concentration assumption on the data matrix","pith_extraction_headline":"In high-dimensional ERM with non-Gaussian data, the estimator's projection on a test point follows the convolution of a generally non-Gaussian distribution with an independent Gaussian whose variance is set by the trace of the estimator's 2"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03146/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":2,"snapshot_sha256":"b42a284ed68de677ce3bee9f3dbbb493bf94deeed93729e420a29fc084c61745"},"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":"2604.03146","created_at":"2026-06-08T01:04:03.544548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.03146v2","created_at":"2026-06-08T01:04:03.544548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.03146","created_at":"2026-06-08T01:04:03.544548+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FJPKEKXATQW","created_at":"2026-06-08T01:04:03.544548+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FJPKEKXATQWBPTM","created_at":"2026-06-08T01:04:03.544548+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FJPKEKX","created_at":"2026-06-08T01:04:03.544548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15688","citing_title":"$\\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3","json":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3.json","graph_json":"https://pith.science/api/pith-number/5FJPKEKXATQWBPTM53WR4F5EZ3/graph.json","events_json":"https://pith.science/api/pith-number/5FJPKEKXATQWBPTM53WR4F5EZ3/events.json","paper":"https://pith.science/paper/5FJPKEKX"},"agent_actions":{"view_html":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3","download_json":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3.json","view_paper":"https://pith.science/paper/5FJPKEKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.03146&json=true","fetch_graph":"https://pith.science/api/pith-number/5FJPKEKXATQWBPTM53WR4F5EZ3/graph.json","fetch_events":"https://pith.science/api/pith-number/5FJPKEKXATQWBPTM53WR4F5EZ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3/action/storage_attestation","attest_author":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3/action/author_attestation","sign_citation":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3/action/citation_signature","submit_replication":"https://pith.science/pith/5FJPKEKXATQWBPTM53WR4F5EZ3/action/replication_record"}},"created_at":"2026-06-08T01:04:03.544548+00:00","updated_at":"2026-06-08T01:04:03.544548+00:00"}