{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P3AEUVKAHPIBAR6SHO2TEDNR7M","short_pith_number":"pith:P3AEUVKA","schema_version":"1.0","canonical_sha256":"7ec04a55403bd01047d23bb5320db1fb03855be70cac8b930beb0a16231e9bd9","source":{"kind":"arxiv","id":"2405.15613","version":2},"attestation_state":"computed","paper":{"title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Armand Joulin, Camille Couprie, Herv\\'e J\\'egou, Hugo Touvron, Huy V. Vo, Marc Szafraniec, Maxime Oquab, Nikita Smetanin, Patrick Labatut, Piotr Bojanowski, Th\\'eo Moutakanni, Timoth\\'ee Darcet, Vasil Khalidov","submitted_at":"2024-05-24T14:58:51Z","abstract_excerpt":"Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically require extensive human effort. This manual process has some limitations similar to those encountered in supervised learning, e.g., the crowd-sourced selection of data is costly and time-consuming, preventing scaling the dataset size. In this work, we consider the problem of automatic curation of high-quality datasets for self-supervised pre-training. We posit that such datasets should be large, diverse and balanced, and p"},"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":"2405.15613","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T14:58:51Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"316615354f31474c0e53a4c3252cc00e3dbe58fee41c26785d262cca52ca66b7","abstract_canon_sha256":"3772c7bad53c075d1e7e805d77da2eb0e93fb8e4d4a1bb1fc9c3206278de4d7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:53.263107Z","signature_b64":"W2dg4jVrguhiZd2mJRG26X9egyUntDsTqG69CbuWP6UjOUAdPdlgI93tqvm2aIphyTMuLdFLnVkCqazyDiFsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec04a55403bd01047d23bb5320db1fb03855be70cac8b930beb0a16231e9bd9","last_reissued_at":"2026-07-05T08:37:53.262648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:53.262648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Armand Joulin, Camille Couprie, Herv\\'e J\\'egou, Hugo Touvron, Huy V. Vo, Marc Szafraniec, Maxime Oquab, Nikita Smetanin, Patrick Labatut, Piotr Bojanowski, Th\\'eo Moutakanni, Timoth\\'ee Darcet, Vasil Khalidov","submitted_at":"2024-05-24T14:58:51Z","abstract_excerpt":"Self-supervised features are the cornerstone of modern machine learning systems. They are typically pre-trained on data collections whose construction and curation typically require extensive human effort. This manual process has some limitations similar to those encountered in supervised learning, e.g., the crowd-sourced selection of data is costly and time-consuming, preventing scaling the dataset size. In this work, we consider the problem of automatic curation of high-quality datasets for self-supervised pre-training. We posit that such datasets should be large, diverse and balanced, and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15613","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/2405.15613/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":"2405.15613","created_at":"2026-07-05T08:37:53.262707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15613v2","created_at":"2026-07-05T08:37:53.262707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15613","created_at":"2026-07-05T08:37:53.262707+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3AEUVKAHPIB","created_at":"2026-07-05T08:37:53.262707+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3AEUVKAHPIBAR6S","created_at":"2026-07-05T08:37:53.262707+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3AEUVKA","created_at":"2026-07-05T08:37:53.262707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":292,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":292,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20157","citing_title":"SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08544","citing_title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24762","citing_title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22699","citing_title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08364","citing_title":"MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M","json":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M.json","graph_json":"https://pith.science/api/pith-number/P3AEUVKAHPIBAR6SHO2TEDNR7M/graph.json","events_json":"https://pith.science/api/pith-number/P3AEUVKAHPIBAR6SHO2TEDNR7M/events.json","paper":"https://pith.science/paper/P3AEUVKA"},"agent_actions":{"view_html":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M","download_json":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M.json","view_paper":"https://pith.science/paper/P3AEUVKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15613&json=true","fetch_graph":"https://pith.science/api/pith-number/P3AEUVKAHPIBAR6SHO2TEDNR7M/graph.json","fetch_events":"https://pith.science/api/pith-number/P3AEUVKAHPIBAR6SHO2TEDNR7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M/action/storage_attestation","attest_author":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M/action/author_attestation","sign_citation":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M/action/citation_signature","submit_replication":"https://pith.science/pith/P3AEUVKAHPIBAR6SHO2TEDNR7M/action/replication_record"}},"created_at":"2026-07-05T08:37:53.262707+00:00","updated_at":"2026-07-05T08:37:53.262707+00:00"}