{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OTUQJ5O5RT7U2M264FGUY7AM74","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"30241fcb832559868091283d2bec047b61f04085ac028959f0d2a3e203efe328","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-01-31T12:34:10Z","title_canon_sha256":"c49b6be37095185f6b606f14b867e1734923e8b74b919aa2a4ac58f41aa1f443"},"schema_version":"1.0","source":{"id":"2301.13585","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13585","created_at":"2026-07-05T05:37:16Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13585v1","created_at":"2026-07-05T05:37:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13585","created_at":"2026-07-05T05:37:16Z"},{"alias_kind":"pith_short_12","alias_value":"OTUQJ5O5RT7U","created_at":"2026-07-05T05:37:16Z"},{"alias_kind":"pith_short_16","alias_value":"OTUQJ5O5RT7U2M26","created_at":"2026-07-05T05:37:16Z"},{"alias_kind":"pith_short_8","alias_value":"OTUQJ5O5","created_at":"2026-07-05T05:37:16Z"}],"graph_snapshots":[{"event_id":"sha256:9f88c43502e136fec009e8e09939abd075eb194c57ab2cfbd55b56be72bd1efc","target":"graph","created_at":"2026-07-05T05:37:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.13585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Two different approaches exist to handle missing values for prediction: either imputation, prior to fitting any predictive algorithms, or dedicated methods able to natively incorporate missing values. While imputation is widely (and easily) use, it is unfortunately biased when low-capacity predictors (such as linear models) are applied afterward. However, in practice, naive imputation exhibits good predictive performance. In this paper, we study the impact of imputation in a high-dimensional linear model with MCAR missing data. We prove that zero imputation performs an implicit regularization ","authors_text":"Alexis Ayme (LPSM (UMR\\_8001)), Aymeric Dieuleveut (CMAP), Claire Boyer (LPSM (UMR\\_8001)), Erwan Scornet (CMAP)","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-01-31T12:34:10Z","title":"Naive imputation implicitly regularizes high-dimensional linear models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13585","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ca7a4391f35d14357a2c435b9c14daf9eddbec0e00c32139038f9e1d2278d260","target":"record","created_at":"2026-07-05T05:37:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"30241fcb832559868091283d2bec047b61f04085ac028959f0d2a3e203efe328","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2023-01-31T12:34:10Z","title_canon_sha256":"c49b6be37095185f6b606f14b867e1734923e8b74b919aa2a4ac58f41aa1f443"},"schema_version":"1.0","source":{"id":"2301.13585","kind":"arxiv","version":1}},"canonical_sha256":"74e904f5dd8cff4d335ee14d4c7c0cff2c9d1c057d5c890cf39861f945c4b717","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74e904f5dd8cff4d335ee14d4c7c0cff2c9d1c057d5c890cf39861f945c4b717","first_computed_at":"2026-07-05T05:37:16.447496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:37:16.447496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L2dHAfZaf8gBPVoGm17A2JFvMNNRK4cBemVWyD/QU9EvK1xU8T9lcKXFntgsDSFCmtIZNAAfAoW3B0Czg4hUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:37:16.447989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13585","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca7a4391f35d14357a2c435b9c14daf9eddbec0e00c32139038f9e1d2278d260","sha256:9f88c43502e136fec009e8e09939abd075eb194c57ab2cfbd55b56be72bd1efc"],"state_sha256":"ec98964f890c854ecd04a1293b5a30530496bf38fd71feb12b9b1f51e48a496e"}