{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FF4XWSKTC7B3LWGBT2SEATH2DV","short_pith_number":"pith:FF4XWSKT","schema_version":"1.0","canonical_sha256":"29797b495317c3b5d8c19ea4404cfa1d5a630b990782a8bd5c5fb9a777648301","source":{"kind":"arxiv","id":"2406.13944","version":2},"attestation_state":"computed","paper":{"title":"Generalization error of min-norm interpolators in transfer learning","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":"Kenneth Gu, Pragya Sur, Sohom Bhattacharya, Yanke Song","submitted_at":"2024-06-20T02:23:28Z","abstract_excerpt":"This paper establishes the generalization error of pooled min-$\\ell_2$-norm interpolation in transfer learning, where data from diverse distributions are available. Min-norm interpolators arise naturally as implicit regularized limits of modern machine learning algorithms. Prior work has characterized their out-of-distribution risk when samples from the test distribution are unavailable during training. In many applications, however, limited test samples may be available at training time, yet properties of min-norm interpolation in this regime remain poorly understood. We address this gap by c"},"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":"2406.13944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2024-06-20T02:23:28Z","cross_cats_sorted":["cs.LG","stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"52619b3eb901993c77bd86a53c6d3d56dfe33ff0fb532ac93f0fce3c6cd5d392","abstract_canon_sha256":"d263d1b3cee71164481a7294a4565fa4a8f1d46c65ee1e2d1b6787fdcf32d206"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:21.742101Z","signature_b64":"1goQ89OKfZG/KHrV+Soaaklgh58j0tcnTTvWf0MBdj9qAQxL0ZpRC+gFofrKcAzI8qSWXoBj+P65i/N8SN+ZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29797b495317c3b5d8c19ea4404cfa1d5a630b990782a8bd5c5fb9a777648301","last_reissued_at":"2026-06-30T01:16:21.741454Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:21.741454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization error of min-norm interpolators in transfer learning","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":"Kenneth Gu, Pragya Sur, Sohom Bhattacharya, Yanke Song","submitted_at":"2024-06-20T02:23:28Z","abstract_excerpt":"This paper establishes the generalization error of pooled min-$\\ell_2$-norm interpolation in transfer learning, where data from diverse distributions are available. Min-norm interpolators arise naturally as implicit regularized limits of modern machine learning algorithms. Prior work has characterized their out-of-distribution risk when samples from the test distribution are unavailable during training. In many applications, however, limited test samples may be available at training time, yet properties of min-norm interpolation in this regime remain poorly understood. We address this gap by c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13944","kind":"arxiv","version":2},"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/2406.13944/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":"2406.13944","created_at":"2026-06-30T01:16:21.741532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13944v2","created_at":"2026-06-30T01:16:21.741532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13944","created_at":"2026-06-30T01:16:21.741532+00:00"},{"alias_kind":"pith_short_12","alias_value":"FF4XWSKTC7B3","created_at":"2026-06-30T01:16:21.741532+00:00"},{"alias_kind":"pith_short_16","alias_value":"FF4XWSKTC7B3LWGB","created_at":"2026-06-30T01:16:21.741532+00:00"},{"alias_kind":"pith_short_8","alias_value":"FF4XWSKT","created_at":"2026-06-30T01:16:21.741532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20105","citing_title":"Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV","json":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV.json","graph_json":"https://pith.science/api/pith-number/FF4XWSKTC7B3LWGBT2SEATH2DV/graph.json","events_json":"https://pith.science/api/pith-number/FF4XWSKTC7B3LWGBT2SEATH2DV/events.json","paper":"https://pith.science/paper/FF4XWSKT"},"agent_actions":{"view_html":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV","download_json":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV.json","view_paper":"https://pith.science/paper/FF4XWSKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13944&json=true","fetch_graph":"https://pith.science/api/pith-number/FF4XWSKTC7B3LWGBT2SEATH2DV/graph.json","fetch_events":"https://pith.science/api/pith-number/FF4XWSKTC7B3LWGBT2SEATH2DV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV/action/storage_attestation","attest_author":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV/action/author_attestation","sign_citation":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV/action/citation_signature","submit_replication":"https://pith.science/pith/FF4XWSKTC7B3LWGBT2SEATH2DV/action/replication_record"}},"created_at":"2026-06-30T01:16:21.741532+00:00","updated_at":"2026-06-30T01:16:21.741532+00:00"}