{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LRW2ZKR4HSDZORU4ZUMQG2D3JT","short_pith_number":"pith:LRW2ZKR4","schema_version":"1.0","canonical_sha256":"5c6dacaa3c3c8797469ccd1903687b4cc12b8dd4d99b4fadfb33ab6e0c859c82","source":{"kind":"arxiv","id":"2304.12210","version":2},"attestation_state":"computed","paper":{"title":"A Cookbook of Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Adrien Bardes, Amir Bar, Andrew Gordon Wilson, Ari Morcos, Avi Schwarzschild, Florian Bordes, Gregoire Mialon, Hamed Pirsiavash, Jonas Geiping, Mark Ibrahim, Micah Goldblum, Pierre Fernandez, Quentin Garrido, Randall Balestriero, Shashank Shekhar, Tom Goldstein, Vlad Sobal, Yann LeCun, Yuandong Tian","submitted_at":"2023-04-24T15:49:53Z","abstract_excerpt":"Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art with a high barrier to entry. While many components are familiar, successfully training a SSL method involves a dizzying set of choices from the pretext tasks to training hyper-parameters. Our goal is to lower the barrier to entry into SSL research by laying the foundations and latest SSL recipes in the style of a cookbook. We hope to empower the curious researcher to navigate the terrain of methods, understand the rol"},"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":"2304.12210","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-24T15:49:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b3f6df6e3f5606729df846490485708100916a207041da8e92e1410684f4150e","abstract_canon_sha256":"04f2135b15369bb0a6c8f503da0b066463526743a2f1bb49272eb4c6578d4198"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:41.190443Z","signature_b64":"kTAF1TS9w8vQ3Y1cpsTGuwccoE0Aa4otTCOgDa4siz3eksMCcLaggwljf5XYctoQr2txd97HotraRkY6ugyoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c6dacaa3c3c8797469ccd1903687b4cc12b8dd4d99b4fadfb33ab6e0c859c82","last_reissued_at":"2026-07-05T06:25:41.189892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:41.189892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Cookbook of Self-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Adrien Bardes, Amir Bar, Andrew Gordon Wilson, Ari Morcos, Avi Schwarzschild, Florian Bordes, Gregoire Mialon, Hamed Pirsiavash, Jonas Geiping, Mark Ibrahim, Micah Goldblum, Pierre Fernandez, Quentin Garrido, Randall Balestriero, Shashank Shekhar, Tom Goldstein, Vlad Sobal, Yann LeCun, Yuandong Tian","submitted_at":"2023-04-24T15:49:53Z","abstract_excerpt":"Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art with a high barrier to entry. While many components are familiar, successfully training a SSL method involves a dizzying set of choices from the pretext tasks to training hyper-parameters. Our goal is to lower the barrier to entry into SSL research by laying the foundations and latest SSL recipes in the style of a cookbook. We hope to empower the curious researcher to navigate the terrain of methods, understand the rol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12210","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/2304.12210/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":"2304.12210","created_at":"2026-07-05T06:25:41.189957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12210v2","created_at":"2026-07-05T06:25:41.189957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12210","created_at":"2026-07-05T06:25:41.189957+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRW2ZKR4HSDZ","created_at":"2026-07-05T06:25:41.189957+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRW2ZKR4HSDZORU4","created_at":"2026-07-05T06:25:41.189957+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRW2ZKR4","created_at":"2026-07-05T06:25:41.189957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20886","citing_title":"Toward Parking Spot Occupancy Recognition: A Self-Supervised Approach","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27538","citing_title":"Self-Supervised Learning of Plant Image Representations","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27734","citing_title":"Learn from your own latents and not from tokens: A sample-complexity theory","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29122","citing_title":"Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2511.05963","citing_title":"Next-Latent Prediction Transformers Learn Compact World Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2410.08559","citing_title":"Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2501.07571","citing_title":"Statistical learnability of smooth boundaries via pairwise binary classification with deep ReLU networks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00867","citing_title":"Self-supervised neural operator for solving partial differential equations","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08544","citing_title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02509","citing_title":"Rapidly deploying on-device eye tracking by distilling visual foundation models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17878","citing_title":"RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11291","citing_title":"Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27538","citing_title":"Self-Supervised Learning of Plant Image Representations","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21691","citing_title":"There Will Be a Scientific Theory of Deep Learning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17878","citing_title":"RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05614","citing_title":"Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT","json":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT.json","graph_json":"https://pith.science/api/pith-number/LRW2ZKR4HSDZORU4ZUMQG2D3JT/graph.json","events_json":"https://pith.science/api/pith-number/LRW2ZKR4HSDZORU4ZUMQG2D3JT/events.json","paper":"https://pith.science/paper/LRW2ZKR4"},"agent_actions":{"view_html":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT","download_json":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT.json","view_paper":"https://pith.science/paper/LRW2ZKR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12210&json=true","fetch_graph":"https://pith.science/api/pith-number/LRW2ZKR4HSDZORU4ZUMQG2D3JT/graph.json","fetch_events":"https://pith.science/api/pith-number/LRW2ZKR4HSDZORU4ZUMQG2D3JT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT/action/storage_attestation","attest_author":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT/action/author_attestation","sign_citation":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT/action/citation_signature","submit_replication":"https://pith.science/pith/LRW2ZKR4HSDZORU4ZUMQG2D3JT/action/replication_record"}},"created_at":"2026-07-05T06:25:41.189957+00:00","updated_at":"2026-07-05T06:25:41.189957+00:00"}