{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RU4G772KPXNEWADH2LTTEAQU4R","short_pith_number":"pith:RU4G772K","schema_version":"1.0","canonical_sha256":"8d386fff4a7dda4b0067d2e7320214e47ca0f2a9f8cab0adb485705b51b195a5","source":{"kind":"arxiv","id":"2403.06871","version":1},"attestation_state":"computed","paper":{"title":"On the Generalization Ability of Unsupervised Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayu Zhou, Junyuan Hong, Mehrdad Mahdavi, Yuyang Deng","submitted_at":"2024-03-11T16:23:42Z","abstract_excerpt":"Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled dataset affects the generalization of the fine-tuned model is lacking. Existing theoretical research does not adequately account for the heterogeneity of the distribution and tasks in pre-training and fine-tuning stage. To bridge this gap, this paper introduces a novel theoretical framework that illuminates the critical factor influencing the transferability of "},"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":"2403.06871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T16:23:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"15013dd23952aae24cf6babf5881e63feb7297f2ef8f8d609ad77158849a8296","abstract_canon_sha256":"be7d21c65f832d677f88461720f7bbda6778e71a55c90826608118e11e4c2262"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:43.854379Z","signature_b64":"cjr2gUtEGwVNUaFkwz6M+EMeZVitCxtE44hIWzla67IEG0pV71w1cwGXNnGPKL1kWeXuhy+IaHAzz75eDJTFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d386fff4a7dda4b0067d2e7320214e47ca0f2a9f8cab0adb485705b51b195a5","last_reissued_at":"2026-07-05T07:54:43.853978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:43.853978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Generalization Ability of Unsupervised Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayu Zhou, Junyuan Hong, Mehrdad Mahdavi, Yuyang Deng","submitted_at":"2024-03-11T16:23:42Z","abstract_excerpt":"Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled dataset affects the generalization of the fine-tuned model is lacking. Existing theoretical research does not adequately account for the heterogeneity of the distribution and tasks in pre-training and fine-tuning stage. To bridge this gap, this paper introduces a novel theoretical framework that illuminates the critical factor influencing the transferability of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06871","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/2403.06871/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":"2403.06871","created_at":"2026-07-05T07:54:43.854036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06871v1","created_at":"2026-07-05T07:54:43.854036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06871","created_at":"2026-07-05T07:54:43.854036+00:00"},{"alias_kind":"pith_short_12","alias_value":"RU4G772KPXNE","created_at":"2026-07-05T07:54:43.854036+00:00"},{"alias_kind":"pith_short_16","alias_value":"RU4G772KPXNEWADH","created_at":"2026-07-05T07:54:43.854036+00:00"},{"alias_kind":"pith_short_8","alias_value":"RU4G772K","created_at":"2026-07-05T07:54:43.854036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.03532","citing_title":"How Low Can We Go? Minimum Spectroscopic Requirements For Supernova Subtype Classification","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R","json":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R.json","graph_json":"https://pith.science/api/pith-number/RU4G772KPXNEWADH2LTTEAQU4R/graph.json","events_json":"https://pith.science/api/pith-number/RU4G772KPXNEWADH2LTTEAQU4R/events.json","paper":"https://pith.science/paper/RU4G772K"},"agent_actions":{"view_html":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R","download_json":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R.json","view_paper":"https://pith.science/paper/RU4G772K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06871&json=true","fetch_graph":"https://pith.science/api/pith-number/RU4G772KPXNEWADH2LTTEAQU4R/graph.json","fetch_events":"https://pith.science/api/pith-number/RU4G772KPXNEWADH2LTTEAQU4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R/action/storage_attestation","attest_author":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R/action/author_attestation","sign_citation":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R/action/citation_signature","submit_replication":"https://pith.science/pith/RU4G772KPXNEWADH2LTTEAQU4R/action/replication_record"}},"created_at":"2026-07-05T07:54:43.854036+00:00","updated_at":"2026-07-05T07:54:43.854036+00:00"}