{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QD67OPHJ7KHWDWLK7HRWMLJGZS","short_pith_number":"pith:QD67OPHJ","schema_version":"1.0","canonical_sha256":"80fdf73ce9fa8f61d96af9e3662d26cc9c274c48d7922bc405032d9f3ac4b637","source":{"kind":"arxiv","id":"1905.12385","version":2},"attestation_state":"computed","paper":{"title":"The spiked matrix model with generative priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP","math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Antoine Maillard, Benjamin Aubin, Bruno Loureiro, Florent Krzakala, Lenka Zdeborov\\'a","submitted_at":"2019-05-29T12:47:05Z","abstract_excerpt":"Using a low-dimensional parametrization of signals is a generic and powerful way to enhance performance in signal processing and statistical inference. A very popular and widely explored type of dimensionality reduction is sparsity; another type is generative modelling of signal distributions. Generative models based on neural networks, such as GANs or variational auto-encoders, are particularly performant and are gaining on applicability. In this paper we study spiked matrix models, where a low-rank matrix is observed through a noisy channel. This problem with sparse structure of the spikes h"},"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":"1905.12385","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2019-05-29T12:47:05Z","cross_cats_sorted":["cs.LG","eess.SP","math.PR","stat.ML","stat.TH"],"title_canon_sha256":"6750dea2e93b541abd7462f41c83499e72acf37d68b5aa8ee718b12b16060cf7","abstract_canon_sha256":"21acad68c8babfb960b218526e581092ac8bb2808c8eb06e022729067ffc958c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:51.772057Z","signature_b64":"9AIW4y4Rc18KYqNqyTlGiysjvcCyBbSBmpxS25PLHlRohaVLktwx7oz+fja7RseyIEV+ZNsWatwB/LLqtIP3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80fdf73ce9fa8f61d96af9e3662d26cc9c274c48d7922bc405032d9f3ac4b637","last_reissued_at":"2026-07-05T00:51:51.771597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:51.771597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The spiked matrix model with generative priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP","math.PR","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Antoine Maillard, Benjamin Aubin, Bruno Loureiro, Florent Krzakala, Lenka Zdeborov\\'a","submitted_at":"2019-05-29T12:47:05Z","abstract_excerpt":"Using a low-dimensional parametrization of signals is a generic and powerful way to enhance performance in signal processing and statistical inference. A very popular and widely explored type of dimensionality reduction is sparsity; another type is generative modelling of signal distributions. Generative models based on neural networks, such as GANs or variational auto-encoders, are particularly performant and are gaining on applicability. In this paper we study spiked matrix models, where a low-rank matrix is observed through a noisy channel. This problem with sparse structure of the spikes h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12385","kind":"arxiv","version":2},"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/1905.12385/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":"1905.12385","created_at":"2026-07-05T00:51:51.771655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12385v2","created_at":"2026-07-05T00:51:51.771655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12385","created_at":"2026-07-05T00:51:51.771655+00:00"},{"alias_kind":"pith_short_12","alias_value":"QD67OPHJ7KHW","created_at":"2026-07-05T00:51:51.771655+00:00"},{"alias_kind":"pith_short_16","alias_value":"QD67OPHJ7KHWDWLK","created_at":"2026-07-05T00:51:51.771655+00:00"},{"alias_kind":"pith_short_8","alias_value":"QD67OPHJ","created_at":"2026-07-05T00:51:51.771655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.07103","citing_title":"Concentration of the matrix-valued minimum mean-square error in optimal Bayesian inference","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS","json":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS.json","graph_json":"https://pith.science/api/pith-number/QD67OPHJ7KHWDWLK7HRWMLJGZS/graph.json","events_json":"https://pith.science/api/pith-number/QD67OPHJ7KHWDWLK7HRWMLJGZS/events.json","paper":"https://pith.science/paper/QD67OPHJ"},"agent_actions":{"view_html":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS","download_json":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS.json","view_paper":"https://pith.science/paper/QD67OPHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12385&json=true","fetch_graph":"https://pith.science/api/pith-number/QD67OPHJ7KHWDWLK7HRWMLJGZS/graph.json","fetch_events":"https://pith.science/api/pith-number/QD67OPHJ7KHWDWLK7HRWMLJGZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS/action/storage_attestation","attest_author":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS/action/author_attestation","sign_citation":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS/action/citation_signature","submit_replication":"https://pith.science/pith/QD67OPHJ7KHWDWLK7HRWMLJGZS/action/replication_record"}},"created_at":"2026-07-05T00:51:51.771655+00:00","updated_at":"2026-07-05T00:51:51.771655+00:00"}