{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ACVPXVLT47EDSJNVIXQ332VWCK","short_pith_number":"pith:ACVPXVLT","schema_version":"1.0","canonical_sha256":"00aafbd573e7c83925b545e1bdeab6129864311fd4407331ae3322073c5a1ab7","source":{"kind":"arxiv","id":"2605.17778","version":1},"attestation_state":"computed","paper":{"title":"Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Debarghya Mukherjee, Pragya Sur, Radu Lecoiu","submitted_at":"2026-05-18T02:56:57Z","abstract_excerpt":"Self-distillation has emerged as a promising technique for improving model performance in modern machine learning systems. We develop the statistical foundations of self-distillation in spiked covariance models, by introducing and analyzing a broad class of estimators, namely spectral shrinkage estimators. We establish that for spiked covariance matrices with $s$ spikes, $s$-step self-distillation achieves optimal performance among spectral shrinkage estimators, outperforming well-known estimators in statistics and machine learning. Moreover, we show that $s$ steps are necessary for optimality"},"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":"2605.17778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2026-05-18T02:56:57Z","cross_cats_sorted":["cs.LG","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"e178a0b8e605061fc29ab8337e776d76bd77df2b1dbde8e9c442b108a35f82ea","abstract_canon_sha256":"f7fb3c7d379de427082b07899048c58f9c6b97c0842e7536ccde240231115fd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:57.773700Z","signature_b64":"Y1IqzeFvJHhqksOumrnal2/18Q4KN5To1LufoukchfV6F/b0YxKNDZw3C4c0cfKA0KXSS/MVLc1eRj0QrpouBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00aafbd573e7c83925b545e1bdeab6129864311fd4407331ae3322073c5a1ab7","last_reissued_at":"2026-05-20T00:04:57.772906Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:57.772906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Debarghya Mukherjee, Pragya Sur, Radu Lecoiu","submitted_at":"2026-05-18T02:56:57Z","abstract_excerpt":"Self-distillation has emerged as a promising technique for improving model performance in modern machine learning systems. We develop the statistical foundations of self-distillation in spiked covariance models, by introducing and analyzing a broad class of estimators, namely spectral shrinkage estimators. We establish that for spiked covariance matrices with $s$ spikes, $s$-step self-distillation achieves optimal performance among spectral shrinkage estimators, outperforming well-known estimators in statistics and machine learning. Moreover, we show that $s$ steps are necessary for optimality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17778","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/2605.17778/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":"2605.17778","created_at":"2026-05-20T00:04:57.773038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17778v1","created_at":"2026-05-20T00:04:57.773038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17778","created_at":"2026-05-20T00:04:57.773038+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACVPXVLT47ED","created_at":"2026-05-20T00:04:57.773038+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACVPXVLT47EDSJNV","created_at":"2026-05-20T00:04:57.773038+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACVPXVLT","created_at":"2026-05-20T00:04:57.773038+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/ACVPXVLT47EDSJNVIXQ332VWCK","json":"https://pith.science/pith/ACVPXVLT47EDSJNVIXQ332VWCK.json","graph_json":"https://pith.science/api/pith-number/ACVPXVLT47EDSJNVIXQ332VWCK/graph.json","events_json":"https://pith.science/api/pith-number/ACVPXVLT47EDSJNVIXQ332VWCK/events.json","paper":"https://pith.science/paper/ACVPXVLT"},"agent_actions":{"view_html":"https://pith.science/pith/ACVPXVLT47EDSJNVIXQ332VWCK","download_json":"https://pith.science/pith/ACVPXVLT47EDSJNVIXQ332VWCK.json","view_paper":"https://pith.science/paper/ACVPXVLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17778&json=true","fetch_graph":"https://pith.science/api/pith-number/ACVPXVLT47EDSJNVIXQ332VWCK/graph.json","fetch_events":"https://pith.science/api/pith-number/ACVPXVLT47EDSJNVIXQ332VWCK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACVPXVLT47EDSJNVIXQ332VWCK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACVPXVLT47EDSJNVIXQ332VWCK/action/storage_attestation","attest_author":"https://pith.science/pith/ACVPXVLT47EDSJNVIXQ332VWCK/action/author_attestation","sign_citation":"https://pith.science/pith/ACVPXVLT47EDSJNVIXQ332VWCK/action/citation_signature","submit_replication":"https://pith.science/pith/ACVPXVLT47EDSJNVIXQ332VWCK/action/replication_record"}},"created_at":"2026-05-20T00:04:57.773038+00:00","updated_at":"2026-05-20T00:04:57.773038+00:00"}