{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JA3CPVDW5WPXYQQYZ2WV72YN5V","short_pith_number":"pith:JA3CPVDW","schema_version":"1.0","canonical_sha256":"483627d476ed9f7c4218cead5feb0ded6e274aafb96ea0a4ddc19d67fabb2100","source":{"kind":"arxiv","id":"1708.03395","version":3},"attestation_state":"computed","paper":{"title":"Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","cs.LG","math-ph","math.IT","math.MP"],"primary_cat":"cs.IT","authors_text":"Florent Krzakala, Jean Barbier, Lenka Zdeborov\\'a, L\\'eo Miolane, Nicolas Macris","submitted_at":"2017-08-10T21:53:40Z","abstract_excerpt":"Generalized linear models (GLMs) arise in high-dimensional machine learning, statistics, communications and signal processing. In this paper we analyze GLMs when the data matrix is random, as relevant in problems such as compressed sensing, error-correcting codes or benchmark models in neural networks. We evaluate the mutual information (or \"free entropy\") from which we deduce the Bayes-optimal estimation and generalization errors. Our analysis applies to the high-dimensional limit where both the number of samples and the dimension are large and their ratio is fixed. Non-rigorous predictions f"},"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":"1708.03395","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2017-08-10T21:53:40Z","cross_cats_sorted":["cond-mat.dis-nn","cs.AI","cs.LG","math-ph","math.IT","math.MP"],"title_canon_sha256":"c3133d4111e9a77a56e81068011aecb8747c909a44e06158b78c767154dbc021","abstract_canon_sha256":"ff1ea884d0bc28892f10c2774eed5ab0c6df439b0baf3f5e5a806f58a803f87a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:57.541954Z","signature_b64":"R6E1RAsQpGW5iwb+MBKIbwCm6FSdnhScVegQuEdTKZSrBU+vmpzh7eeGU+JhFSYtiUvBxyNaMcO+YHmLa3JfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"483627d476ed9f7c4218cead5feb0ded6e274aafb96ea0a4ddc19d67fabb2100","last_reissued_at":"2026-05-17T23:49:57.541083Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:57.541083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.AI","cs.LG","math-ph","math.IT","math.MP"],"primary_cat":"cs.IT","authors_text":"Florent Krzakala, Jean Barbier, Lenka Zdeborov\\'a, L\\'eo Miolane, Nicolas Macris","submitted_at":"2017-08-10T21:53:40Z","abstract_excerpt":"Generalized linear models (GLMs) arise in high-dimensional machine learning, statistics, communications and signal processing. In this paper we analyze GLMs when the data matrix is random, as relevant in problems such as compressed sensing, error-correcting codes or benchmark models in neural networks. We evaluate the mutual information (or \"free entropy\") from which we deduce the Bayes-optimal estimation and generalization errors. Our analysis applies to the high-dimensional limit where both the number of samples and the dimension are large and their ratio is fixed. Non-rigorous predictions f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03395","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":""},"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":"1708.03395","created_at":"2026-05-17T23:49:57.541224+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.03395v3","created_at":"2026-05-17T23:49:57.541224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03395","created_at":"2026-05-17T23:49:57.541224+00:00"},{"alias_kind":"pith_short_12","alias_value":"JA3CPVDW5WPX","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"JA3CPVDW5WPXYQQY","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"JA3CPVDW","created_at":"2026-05-18T12:31:21.493067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22481","citing_title":"When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19712","citing_title":"Ultrametric OGP - parametric RDT \\emph{symmetric} binary perceptron connection","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V","json":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V.json","graph_json":"https://pith.science/api/pith-number/JA3CPVDW5WPXYQQYZ2WV72YN5V/graph.json","events_json":"https://pith.science/api/pith-number/JA3CPVDW5WPXYQQYZ2WV72YN5V/events.json","paper":"https://pith.science/paper/JA3CPVDW"},"agent_actions":{"view_html":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V","download_json":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V.json","view_paper":"https://pith.science/paper/JA3CPVDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.03395&json=true","fetch_graph":"https://pith.science/api/pith-number/JA3CPVDW5WPXYQQYZ2WV72YN5V/graph.json","fetch_events":"https://pith.science/api/pith-number/JA3CPVDW5WPXYQQYZ2WV72YN5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V/action/storage_attestation","attest_author":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V/action/author_attestation","sign_citation":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V/action/citation_signature","submit_replication":"https://pith.science/pith/JA3CPVDW5WPXYQQYZ2WV72YN5V/action/replication_record"}},"created_at":"2026-05-17T23:49:57.541224+00:00","updated_at":"2026-05-17T23:49:57.541224+00:00"}