{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NHGDVJPXOBR3F62A46QDHYI2SM","short_pith_number":"pith:NHGDVJPX","schema_version":"1.0","canonical_sha256":"69cc3aa5f77063b2fb40e7a033e11a93281fcbd2c96b959bd4752769e5a415be","source":{"kind":"arxiv","id":"2212.08339","version":1},"attestation_state":"computed","paper":{"title":"Generalization Bounds for Inductive Matrix Completion in Low-noise Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antoine Ledent, Marius Kloft, Rodrigo Alves, Yann Guermeur, Yunwen Lei","submitted_at":"2022-12-16T08:30:41Z","abstract_excerpt":"We study inductive matrix completion (matrix completion with side information) under an i.i.d. subgaussian noise assumption at a low noise regime, with uniform sampling of the entries. We obtain for the first time generalization bounds with the following three properties: (1) they scale like the standard deviation of the noise and in particular approach zero in the exact recovery case; (2) even in the presence of noise, they converge to zero when the sample size approaches infinity; and (3) for a fixed dimension of the side information, they only have a logarithmic dependence on the size of th"},"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":"2212.08339","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-16T08:30:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b33b031bfb6b920050df77e4cd338ccfe222718b05c3c7a4295e8836bbfbc7b6","abstract_canon_sha256":"d73afe1fa35fd70150c0640a16c7ee0a239ca04cc0a4791b7b15f382a1be5550"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:55.767096Z","signature_b64":"WXeJ2mEuL3or4in3QQh//uxhUNpa/b9mtFZ3fcuM+C9GG46Fa1eykkOCHgI/UhojgxZ59RR6UN4gHCUJhY2WCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69cc3aa5f77063b2fb40e7a033e11a93281fcbd2c96b959bd4752769e5a415be","last_reissued_at":"2026-07-05T05:25:55.766619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:55.766619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization Bounds for Inductive Matrix Completion in Low-noise Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antoine Ledent, Marius Kloft, Rodrigo Alves, Yann Guermeur, Yunwen Lei","submitted_at":"2022-12-16T08:30:41Z","abstract_excerpt":"We study inductive matrix completion (matrix completion with side information) under an i.i.d. subgaussian noise assumption at a low noise regime, with uniform sampling of the entries. We obtain for the first time generalization bounds with the following three properties: (1) they scale like the standard deviation of the noise and in particular approach zero in the exact recovery case; (2) even in the presence of noise, they converge to zero when the sample size approaches infinity; and (3) for a fixed dimension of the side information, they only have a logarithmic dependence on the size of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08339","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/2212.08339/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":"2212.08339","created_at":"2026-07-05T05:25:55.766678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.08339v1","created_at":"2026-07-05T05:25:55.766678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08339","created_at":"2026-07-05T05:25:55.766678+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHGDVJPXOBR3","created_at":"2026-07-05T05:25:55.766678+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHGDVJPXOBR3F62A","created_at":"2026-07-05T05:25:55.766678+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHGDVJPX","created_at":"2026-07-05T05:25:55.766678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17189","citing_title":"Sample-efficient inductive matrix completion with noise and inexact side-information","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17189","citing_title":"Sample-efficient inductive matrix completion with noise and inexact side-information","ref_index":173,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM","json":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM.json","graph_json":"https://pith.science/api/pith-number/NHGDVJPXOBR3F62A46QDHYI2SM/graph.json","events_json":"https://pith.science/api/pith-number/NHGDVJPXOBR3F62A46QDHYI2SM/events.json","paper":"https://pith.science/paper/NHGDVJPX"},"agent_actions":{"view_html":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM","download_json":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM.json","view_paper":"https://pith.science/paper/NHGDVJPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.08339&json=true","fetch_graph":"https://pith.science/api/pith-number/NHGDVJPXOBR3F62A46QDHYI2SM/graph.json","fetch_events":"https://pith.science/api/pith-number/NHGDVJPXOBR3F62A46QDHYI2SM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM/action/storage_attestation","attest_author":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM/action/author_attestation","sign_citation":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM/action/citation_signature","submit_replication":"https://pith.science/pith/NHGDVJPXOBR3F62A46QDHYI2SM/action/replication_record"}},"created_at":"2026-07-05T05:25:55.766678+00:00","updated_at":"2026-07-05T05:25:55.766678+00:00"}