{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J6TJ6Y4MIS4B2BEDJNU5J23MFE","short_pith_number":"pith:J6TJ6Y4M","schema_version":"1.0","canonical_sha256":"4fa69f638c44b81d04834b69d4eb6c29275334188460b3f407165a32e02f28cd","source":{"kind":"arxiv","id":"2606.01292","version":1},"attestation_state":"computed","paper":{"title":"What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cong Fang, Fangqing Zhang, Haihan Zhang, Wendao Wu","submitted_at":"2026-05-31T15:24:52Z","abstract_excerpt":"Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation (KD) to the emergent phenomenon of Weak-to-Strong (W2S) generalization. While existing studies offer isolated insights, a unified theoretical framework explaining the efficacy of KT across these disparate regimes remains lacking. In this work, we establish a unified spectral analysis of SGD dynamics in high-dimensional linear regression, elucidating the efficiency of KT across seemingly disparate regimes. We characterize KT efficiency through two"},"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":"2606.01292","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T15:24:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ed3d00f972efc769f246f07eba0008a55ce92fdc90325dfe58d954b10ac9891","abstract_canon_sha256":"43deb4e3aedfeafc651efc6c7a00db7629c88c2062cb2ee58bb29d5f892b4f2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:29.236437Z","signature_b64":"il/5Gu56PyqNXk7mOQ4YS3FtJuU4/YN4b/oiXMENV9VoesJBD6SRFHrVNHFp3E1wbt7uXZi5w51o53QpE+A4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fa69f638c44b81d04834b69d4eb6c29275334188460b3f407165a32e02f28cd","last_reissued_at":"2026-06-02T02:04:29.235977Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:29.235977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes a Strong Model? A Unified Spectral Analysis of Knowledge Transfer over High-dimensional Linear Regression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cong Fang, Fangqing Zhang, Haihan Zhang, Wendao Wu","submitted_at":"2026-05-31T15:24:52Z","abstract_excerpt":"Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation (KD) to the emergent phenomenon of Weak-to-Strong (W2S) generalization. While existing studies offer isolated insights, a unified theoretical framework explaining the efficacy of KT across these disparate regimes remains lacking. In this work, we establish a unified spectral analysis of SGD dynamics in high-dimensional linear regression, elucidating the efficiency of KT across seemingly disparate regimes. We characterize KT efficiency through two"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01292","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/2606.01292/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":"2606.01292","created_at":"2026-06-02T02:04:29.236037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01292v1","created_at":"2026-06-02T02:04:29.236037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01292","created_at":"2026-06-02T02:04:29.236037+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6TJ6Y4MIS4B","created_at":"2026-06-02T02:04:29.236037+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6TJ6Y4MIS4B2BED","created_at":"2026-06-02T02:04:29.236037+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6TJ6Y4M","created_at":"2026-06-02T02:04:29.236037+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/J6TJ6Y4MIS4B2BEDJNU5J23MFE","json":"https://pith.science/pith/J6TJ6Y4MIS4B2BEDJNU5J23MFE.json","graph_json":"https://pith.science/api/pith-number/J6TJ6Y4MIS4B2BEDJNU5J23MFE/graph.json","events_json":"https://pith.science/api/pith-number/J6TJ6Y4MIS4B2BEDJNU5J23MFE/events.json","paper":"https://pith.science/paper/J6TJ6Y4M"},"agent_actions":{"view_html":"https://pith.science/pith/J6TJ6Y4MIS4B2BEDJNU5J23MFE","download_json":"https://pith.science/pith/J6TJ6Y4MIS4B2BEDJNU5J23MFE.json","view_paper":"https://pith.science/paper/J6TJ6Y4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01292&json=true","fetch_graph":"https://pith.science/api/pith-number/J6TJ6Y4MIS4B2BEDJNU5J23MFE/graph.json","fetch_events":"https://pith.science/api/pith-number/J6TJ6Y4MIS4B2BEDJNU5J23MFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6TJ6Y4MIS4B2BEDJNU5J23MFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6TJ6Y4MIS4B2BEDJNU5J23MFE/action/storage_attestation","attest_author":"https://pith.science/pith/J6TJ6Y4MIS4B2BEDJNU5J23MFE/action/author_attestation","sign_citation":"https://pith.science/pith/J6TJ6Y4MIS4B2BEDJNU5J23MFE/action/citation_signature","submit_replication":"https://pith.science/pith/J6TJ6Y4MIS4B2BEDJNU5J23MFE/action/replication_record"}},"created_at":"2026-06-02T02:04:29.236037+00:00","updated_at":"2026-06-02T02:04:29.236037+00:00"}