{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YAPI73K6V7XZTJ7JHEYI53ZDIN","short_pith_number":"pith:YAPI73K6","schema_version":"1.0","canonical_sha256":"c01e8fed5eafef99a7e939308eef23436487cd3c6771092f8f851e9dbfc09b36","source":{"kind":"arxiv","id":"2504.19446","version":1},"attestation_state":"computed","paper":{"title":"Learning High-dimensional Gaussians from Censored Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Arnab Bhattacharyya, Constantinos Daskalakis, Themis Gouleakis, Yuhao Wang","submitted_at":"2025-04-28T03:22:01Z","abstract_excerpt":"We provide efficient algorithms for the problem of distribution learning from high-dimensional Gaussian data where in each sample, some of the variable values are missing. We suppose that the variables are missing not at random (MNAR). The missingness model, denoted by $S(y)$, is the function that maps any point $y$ in $R^d$ to the subsets of its coordinates that are seen. In this work, we assume that it is known. We study the following two settings:\n  (i) Self-censoring: An observation $x$ is generated by first sampling the true value $y$ from a $d$-dimensional Gaussian $N(\\mu*, \\Sigma*)$ wit"},"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":"2504.19446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-28T03:22:01Z","cross_cats_sorted":["cs.CC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"f7e7ffb0b20977c4983aa430d6a284c91ea5d7b6e0b4fb60d4584ad12111b030","abstract_canon_sha256":"f55c45f25184250e39455c73813cadad94ebcc086a413449ef0f725d6b29e1d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:57.708043Z","signature_b64":"hWGXp6/gt7IXil3cCxVeMJRMKXyow0NcOccxdYdnbKrh2YyfTWnieGgzPMBgwqp7ykw9uBpisIaWohATsBufBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c01e8fed5eafef99a7e939308eef23436487cd3c6771092f8f851e9dbfc09b36","last_reissued_at":"2026-07-05T10:54:57.707512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:57.707512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning High-dimensional Gaussians from Censored Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Arnab Bhattacharyya, Constantinos Daskalakis, Themis Gouleakis, Yuhao Wang","submitted_at":"2025-04-28T03:22:01Z","abstract_excerpt":"We provide efficient algorithms for the problem of distribution learning from high-dimensional Gaussian data where in each sample, some of the variable values are missing. We suppose that the variables are missing not at random (MNAR). The missingness model, denoted by $S(y)$, is the function that maps any point $y$ in $R^d$ to the subsets of its coordinates that are seen. In this work, we assume that it is known. We study the following two settings:\n  (i) Self-censoring: An observation $x$ is generated by first sampling the true value $y$ from a $d$-dimensional Gaussian $N(\\mu*, \\Sigma*)$ wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19446","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/2504.19446/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":"2504.19446","created_at":"2026-07-05T10:54:57.707573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19446v1","created_at":"2026-07-05T10:54:57.707573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19446","created_at":"2026-07-05T10:54:57.707573+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAPI73K6V7XZ","created_at":"2026-07-05T10:54:57.707573+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAPI73K6V7XZTJ7J","created_at":"2026-07-05T10:54:57.707573+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAPI73K6","created_at":"2026-07-05T10:54:57.707573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05076","citing_title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05076","citing_title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN","json":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN.json","graph_json":"https://pith.science/api/pith-number/YAPI73K6V7XZTJ7JHEYI53ZDIN/graph.json","events_json":"https://pith.science/api/pith-number/YAPI73K6V7XZTJ7JHEYI53ZDIN/events.json","paper":"https://pith.science/paper/YAPI73K6"},"agent_actions":{"view_html":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN","download_json":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN.json","view_paper":"https://pith.science/paper/YAPI73K6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19446&json=true","fetch_graph":"https://pith.science/api/pith-number/YAPI73K6V7XZTJ7JHEYI53ZDIN/graph.json","fetch_events":"https://pith.science/api/pith-number/YAPI73K6V7XZTJ7JHEYI53ZDIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN/action/storage_attestation","attest_author":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN/action/author_attestation","sign_citation":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN/action/citation_signature","submit_replication":"https://pith.science/pith/YAPI73K6V7XZTJ7JHEYI53ZDIN/action/replication_record"}},"created_at":"2026-07-05T10:54:57.707573+00:00","updated_at":"2026-07-05T10:54:57.707573+00:00"}