{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5H6ZO2VA66DT4TUYLXYPCHHLYO","short_pith_number":"pith:5H6ZO2VA","schema_version":"1.0","canonical_sha256":"e9fd976aa0f7873e4e985df0f11cebc3ad386961e6a1ebbe6cb0715290d8e0f7","source":{"kind":"arxiv","id":"2309.11516","version":1},"attestation_state":"computed","paper":{"title":"Private Matrix Factorization with Public Item Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.IR","authors_text":"Li Zhang, Mihaela Curmei, Mukund Sundararajan, Walid Krichene","submitted_at":"2023-09-17T11:13:52Z","abstract_excerpt":"We consider the problem of training private recommendation models with access to public item features. Training with Differential Privacy (DP) offers strong privacy guarantees, at the expense of loss in recommendation quality. We show that incorporating public item features during training can help mitigate this loss in quality. We propose a general approach based on collective matrix factorization (CMF), that works by simultaneously factorizing two matrices: the user feedback matrix (representing sensitive data) and an item feature matrix that encodes publicly available (non-sensitive) item i"},"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":"2309.11516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-09-17T11:13:52Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"9b19c2de994ed114d4216b721229e267a9bbb403be6f5c0b75a08b81ffa45072","abstract_canon_sha256":"d941413f8132ed0f6d048ba25901105758105c5ad725510ed83dc80af3b09542"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:51.131006Z","signature_b64":"S/JUrYCP2UYEjA39ACtkvsa9YiXQOLZ3n05WNkOwgCt2B0t7f64Iq48zSZqHzlmWBT6BWRJ2fFwVVrvIx9tmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9fd976aa0f7873e4e985df0f11cebc3ad386961e6a1ebbe6cb0715290d8e0f7","last_reissued_at":"2026-07-05T06:52:51.130566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:51.130566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Private Matrix Factorization with Public Item Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.IR","authors_text":"Li Zhang, Mihaela Curmei, Mukund Sundararajan, Walid Krichene","submitted_at":"2023-09-17T11:13:52Z","abstract_excerpt":"We consider the problem of training private recommendation models with access to public item features. Training with Differential Privacy (DP) offers strong privacy guarantees, at the expense of loss in recommendation quality. We show that incorporating public item features during training can help mitigate this loss in quality. We propose a general approach based on collective matrix factorization (CMF), that works by simultaneously factorizing two matrices: the user feedback matrix (representing sensitive data) and an item feature matrix that encodes publicly available (non-sensitive) item i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11516","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/2309.11516/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":"2309.11516","created_at":"2026-07-05T06:52:51.130623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.11516v1","created_at":"2026-07-05T06:52:51.130623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11516","created_at":"2026-07-05T06:52:51.130623+00:00"},{"alias_kind":"pith_short_12","alias_value":"5H6ZO2VA66DT","created_at":"2026-07-05T06:52:51.130623+00:00"},{"alias_kind":"pith_short_16","alias_value":"5H6ZO2VA66DT4TUY","created_at":"2026-07-05T06:52:51.130623+00:00"},{"alias_kind":"pith_short_8","alias_value":"5H6ZO2VA","created_at":"2026-07-05T06:52:51.130623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO","json":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO.json","graph_json":"https://pith.science/api/pith-number/5H6ZO2VA66DT4TUYLXYPCHHLYO/graph.json","events_json":"https://pith.science/api/pith-number/5H6ZO2VA66DT4TUYLXYPCHHLYO/events.json","paper":"https://pith.science/paper/5H6ZO2VA"},"agent_actions":{"view_html":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO","download_json":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO.json","view_paper":"https://pith.science/paper/5H6ZO2VA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.11516&json=true","fetch_graph":"https://pith.science/api/pith-number/5H6ZO2VA66DT4TUYLXYPCHHLYO/graph.json","fetch_events":"https://pith.science/api/pith-number/5H6ZO2VA66DT4TUYLXYPCHHLYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO/action/storage_attestation","attest_author":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO/action/author_attestation","sign_citation":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO/action/citation_signature","submit_replication":"https://pith.science/pith/5H6ZO2VA66DT4TUYLXYPCHHLYO/action/replication_record"}},"created_at":"2026-07-05T06:52:51.130623+00:00","updated_at":"2026-07-05T06:52:51.130623+00:00"}