{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P3AEUVKAHPIBAR6SHO2TEDNR7M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3772c7bad53c075d1e7e805d77da2eb0e93fb8e4d4a1bb1fc9c3206278de4d7c","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T14:58:51Z","title_canon_sha256":"316615354f31474c0e53a4c3252cc00e3dbe58fee41c26785d262cca52ca66b7"},"schema_version":"1.0","source":{"id":"2405.15613","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15613","created_at":"2026-07-05T08:37:53Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15613v2","created_at":"2026-07-05T08:37:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15613","created_at":"2026-07-05T08:37:53Z"},{"alias_kind":"pith_short_12","alias_value":"P3AEUVKAHPIB","created_at":"2026-07-05T08:37:53Z"},{"alias_kind":"pith_short_16","alias_value":"P3AEUVKAHPIBAR6S","created_at":"2026-07-05T08:37:53Z"},{"alias_kind":"pith_short_8","alias_value":"P3AEUVKA","created_at":"2026-07-05T08:37:53Z"}],"graph_snapshots":[{"event_id":"sha256:268074d1df39274901a4f3333f9fb4e91051a9e959a4727bdc6d3fad62e87f2b","target":"graph","created_at":"2026-07-05T08:37:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.15613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T14:58:51Z","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15613","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:64bfe44ec3ebd069a0e7adf8c97bef55705af69ae95d5916777e38befc3d6f4e","target":"record","created_at":"2026-07-05T08:37:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3772c7bad53c075d1e7e805d77da2eb0e93fb8e4d4a1bb1fc9c3206278de4d7c","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T14:58:51Z","title_canon_sha256":"316615354f31474c0e53a4c3252cc00e3dbe58fee41c26785d262cca52ca66b7"},"schema_version":"1.0","source":{"id":"2405.15613","kind":"arxiv","version":2}},"canonical_sha256":"7ec04a55403bd01047d23bb5320db1fb03855be70cac8b930beb0a16231e9bd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec04a55403bd01047d23bb5320db1fb03855be70cac8b930beb0a16231e9bd9","first_computed_at":"2026-07-05T08:37:53.262648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:53.262648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W2dg4jVrguhiZd2mJRG26X9egyUntDsTqG69CbuWP6UjOUAdPdlgI93tqvm2aIphyTMuLdFLnVkCqazyDiFsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:53.263107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15613","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64bfe44ec3ebd069a0e7adf8c97bef55705af69ae95d5916777e38befc3d6f4e","sha256:268074d1df39274901a4f3333f9fb4e91051a9e959a4727bdc6d3fad62e87f2b"],"state_sha256":"d9e62d890d534819853453cbb9ce3a010db994d2c2d921f380e3104c22b7027d"}