{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FOYASESOGO3ENZP5IAYMITJRDD","short_pith_number":"pith:FOYASESO","schema_version":"1.0","canonical_sha256":"2bb009124e33b646e5fd4030c44d3118efda40383bbb49f823235fb443db3cdf","source":{"kind":"arxiv","id":"2409.18685","version":1},"attestation_state":"computed","paper":{"title":"Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhang, Yuan Cao","submitted_at":"2024-09-27T12:19:41Z","abstract_excerpt":"SimCLR is one of the most popular contrastive learning methods for vision tasks. It pre-trains deep neural networks based on a large amount of unlabeled data by teaching the model to distinguish between positive and negative pairs of augmented images. It is believed that SimCLR can pre-train a deep neural network to learn efficient representations that can lead to a better performance of future supervised fine-tuning. Despite its effectiveness, our theoretical understanding of the underlying mechanisms of SimCLR is still limited. In this paper, we theoretically introduce a case study of the Si"},"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":"2409.18685","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-27T12:19:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cdba3fad82372737afe595ce77b3cb24e8d0634978f762fc86bb422cc6fc058e","abstract_canon_sha256":"7306e7a35d3002a8926f72e152d469982da1f14e9bb0ed4df35ec8d20fafd44c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:39.738119Z","signature_b64":"S4zcbI06owko3FlDiUq2nho/ANzoCxoXscyAdzN6G0Z3odNvR3zPOLQ8zFoFA5wKJMaSUFpt2lk+pTCHlQFkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bb009124e33b646e5fd4030c44d3118efda40383bbb49f823235fb443db3cdf","last_reissued_at":"2026-07-05T09:12:39.737650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:39.737650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Benefits of SimCLR Pre-Training in Two-Layer Convolutional Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Zhang, Yuan Cao","submitted_at":"2024-09-27T12:19:41Z","abstract_excerpt":"SimCLR is one of the most popular contrastive learning methods for vision tasks. It pre-trains deep neural networks based on a large amount of unlabeled data by teaching the model to distinguish between positive and negative pairs of augmented images. It is believed that SimCLR can pre-train a deep neural network to learn efficient representations that can lead to a better performance of future supervised fine-tuning. Despite its effectiveness, our theoretical understanding of the underlying mechanisms of SimCLR is still limited. In this paper, we theoretically introduce a case study of the Si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18685","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/2409.18685/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":"2409.18685","created_at":"2026-07-05T09:12:39.737709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18685v1","created_at":"2026-07-05T09:12:39.737709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18685","created_at":"2026-07-05T09:12:39.737709+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOYASESOGO3E","created_at":"2026-07-05T09:12:39.737709+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOYASESOGO3ENZP5","created_at":"2026-07-05T09:12:39.737709+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOYASESO","created_at":"2026-07-05T09:12:39.737709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11152","citing_title":"Latent Space Consistency for Sparse-View CT Reconstruction","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD","json":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD.json","graph_json":"https://pith.science/api/pith-number/FOYASESOGO3ENZP5IAYMITJRDD/graph.json","events_json":"https://pith.science/api/pith-number/FOYASESOGO3ENZP5IAYMITJRDD/events.json","paper":"https://pith.science/paper/FOYASESO"},"agent_actions":{"view_html":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD","download_json":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD.json","view_paper":"https://pith.science/paper/FOYASESO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18685&json=true","fetch_graph":"https://pith.science/api/pith-number/FOYASESOGO3ENZP5IAYMITJRDD/graph.json","fetch_events":"https://pith.science/api/pith-number/FOYASESOGO3ENZP5IAYMITJRDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD/action/storage_attestation","attest_author":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD/action/author_attestation","sign_citation":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD/action/citation_signature","submit_replication":"https://pith.science/pith/FOYASESOGO3ENZP5IAYMITJRDD/action/replication_record"}},"created_at":"2026-07-05T09:12:39.737709+00:00","updated_at":"2026-07-05T09:12:39.737709+00:00"}