{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5IEVLLHVL6CERV2W3RSDSPWRYX","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":"e3feec5f144010ed79cbc368fd3603e3ae35ed8bb09a16ea9b246e77c23e1fff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-17T17:59:03Z","title_canon_sha256":"10af960e526959812a9cd44782af28643fcdcdb2488203c1b6b279bd2edc0f29"},"schema_version":"1.0","source":{"id":"2105.08054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08054","created_at":"2026-07-05T02:40:47Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08054v1","created_at":"2026-07-05T02:40:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08054","created_at":"2026-07-05T02:40:47Z"},{"alias_kind":"pith_short_12","alias_value":"5IEVLLHVL6CE","created_at":"2026-07-05T02:40:47Z"},{"alias_kind":"pith_short_16","alias_value":"5IEVLLHVL6CERV2W","created_at":"2026-07-05T02:40:47Z"},{"alias_kind":"pith_short_8","alias_value":"5IEVLLHV","created_at":"2026-07-05T02:40:47Z"}],"graph_snapshots":[{"event_id":"sha256:9cde31c0540c96e057d6bedee1e53d98ff49ff5f020902d4011ee94a51e051b1","target":"graph","created_at":"2026-07-05T02:40:47Z","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/2105.08054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning holds promise in leveraging large amounts of unlabeled data, however much of its progress has thus far been limited to highly curated pre-training data such as ImageNet. We explore the effects of contrastive learning from larger, less-curated image datasets such as YFCC, and find there is indeed a large difference in the resulting representation quality. We hypothesize that this curation gap is due to a shift in the distribution of image classes -- which is more diverse and heavy-tailed -- resulting in less relevant negative samples to learn from. We test this hypothes","authors_text":"Aaron van den Oord, Olivier J. Henaff, Yonglong Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-17T17:59:03Z","title":"Divide and Contrast: Self-supervised Learning from Uncurated Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08054","kind":"arxiv","version":1},"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":"sha256:6c4b2ede21b1ac629136ca2cfecca8667d13430a23f33f617abb6d3ff4fe7909","target":"record","created_at":"2026-07-05T02:40:47Z","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":"e3feec5f144010ed79cbc368fd3603e3ae35ed8bb09a16ea9b246e77c23e1fff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-17T17:59:03Z","title_canon_sha256":"10af960e526959812a9cd44782af28643fcdcdb2488203c1b6b279bd2edc0f29"},"schema_version":"1.0","source":{"id":"2105.08054","kind":"arxiv","version":1}},"canonical_sha256":"ea0955acf55f8448d756dc64393ed1c5d9f09ceba8b6c7262f0274783e419d33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea0955acf55f8448d756dc64393ed1c5d9f09ceba8b6c7262f0274783e419d33","first_computed_at":"2026-07-05T02:40:47.335126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:47.335126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L3Sy6PEx9fCiPhRrP8Qgr/6IFFL9J7T8HkMvfWZB9xYuarZVEm6xVwIMGOnqw8WJsfm7f6jPU6IjIgJaoCR7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:47.335668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.08054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c4b2ede21b1ac629136ca2cfecca8667d13430a23f33f617abb6d3ff4fe7909","sha256:9cde31c0540c96e057d6bedee1e53d98ff49ff5f020902d4011ee94a51e051b1"],"state_sha256":"99ce831e328c4aa8b23f0851696245c8969ef4f134a11862c8282f32dcdb8ee1"}