{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GOU7GOAZQQMXN2QV4GCRUR3MIV","short_pith_number":"pith:GOU7GOAZ","schema_version":"1.0","canonical_sha256":"33a9f33819841976ea15e1851a476c45696bd3b5c93517206a745f183222ec5e","source":{"kind":"arxiv","id":"2006.07733","version":3},"attestation_state":"computed","paper":{"title":"Bootstrap your own latent: A new approach to self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernardo Avila Pires, Bilal Piot, Carl Doersch, Corentin Tallec, Elena Buchatskaya, Florent Altch\\'e, Florian Strub, Jean-bastien Grill, Koray Kavukcuoglu, Michal Valko, Mohammad Gheshlaghi Azar, Pierre H. Richemond, R\\'emi Munos, Zhaohan Daniel Guo","submitted_at":"2020-06-13T22:35:21Z","abstract_excerpt":"We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods rely on negative pairs, BYOL achieves a new state of the art without them. BYOL"},"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":"2006.07733","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T22:35:21Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"391bfe4a981ae8f1d5162859ef1ce688d6fb6cb83772f06988d593b7223fdcc8","abstract_canon_sha256":"72138df6b47cc83ca02fff85d76a7b8e99eb455cd45ff2db80f39eb131d2a0f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:23.219706Z","signature_b64":"/c/p3ApjDCw/37vMBFDXy835Un7BY1eCDZ0y9ZqsneGSBNE4xaQxkWmpfDknHT6MZBCjaR9mLot8/wzXeLmnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33a9f33819841976ea15e1851a476c45696bd3b5c93517206a745f183222ec5e","last_reissued_at":"2026-07-05T01:34:23.219208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:23.219208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrap your own latent: A new approach to self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernardo Avila Pires, Bilal Piot, Carl Doersch, Corentin Tallec, Elena Buchatskaya, Florent Altch\\'e, Florian Strub, Jean-bastien Grill, Koray Kavukcuoglu, Michal Valko, Mohammad Gheshlaghi Azar, Pierre H. Richemond, R\\'emi Munos, Zhaohan Daniel Guo","submitted_at":"2020-06-13T22:35:21Z","abstract_excerpt":"We introduce Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning. BYOL relies on two neural networks, referred to as online and target networks, that interact and learn from each other. From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view. At the same time, we update the target network with a slow-moving average of the online network. While state-of-the art methods rely on negative pairs, BYOL achieves a new state of the art without them. BYOL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07733","kind":"arxiv","version":3},"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/2006.07733/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":"2006.07733","created_at":"2026-07-05T01:34:23.219268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07733v3","created_at":"2026-07-05T01:34:23.219268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07733","created_at":"2026-07-05T01:34:23.219268+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOU7GOAZQQMX","created_at":"2026-07-05T01:34:23.219268+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOU7GOAZQQMXN2QV","created_at":"2026-07-05T01:34:23.219268+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOU7GOAZ","created_at":"2026-07-05T01:34:23.219268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06629","citing_title":"STST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture For EEG Self-Supervised Learning","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00052","citing_title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07775","citing_title":"DALE-CT: Depth-Aware Foundation Models for Computed Tomography","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00958","citing_title":"LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01145","citing_title":"Hierarchical Self-Supervised Representation Learning Framework for Multivariate Time Series Grounded in ECG Analysis","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01443","citing_title":"UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00229","citing_title":"Continuous Reasoning for Vision-Language-Action","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26059","citing_title":"A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16416","citing_title":"SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15394","citing_title":"Representation Without Reward: A JEPA Audit for LLM Fine-Tuning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2506.10137","citing_title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2110.04627","citing_title":"Vector-quantized Image Modeling with Improved VQGAN","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2208.03299","citing_title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2010.02193","citing_title":"Mastering Atari with Discrete World Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02430","citing_title":"Self-Directed Task Identification","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11718","citing_title":"Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2112.09118","citing_title":"Unsupervised Dense Information Retrieval with Contrastive Learning","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2404.08471","citing_title":"Revisiting Feature Prediction for Learning Visual Representations from Video","ref_index":242,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06266","citing_title":"ZScribbleSeg: A comprehensive segmentation framework with modeling of efficient annotation and maximization of scribble supervision","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04527","citing_title":"Velox: Learning Representations of 4D Geometry and Appearance","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10333","citing_title":"Zero-shot World Models Are Developmentally Efficient Learners","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV","json":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV.json","graph_json":"https://pith.science/api/pith-number/GOU7GOAZQQMXN2QV4GCRUR3MIV/graph.json","events_json":"https://pith.science/api/pith-number/GOU7GOAZQQMXN2QV4GCRUR3MIV/events.json","paper":"https://pith.science/paper/GOU7GOAZ"},"agent_actions":{"view_html":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV","download_json":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV.json","view_paper":"https://pith.science/paper/GOU7GOAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07733&json=true","fetch_graph":"https://pith.science/api/pith-number/GOU7GOAZQQMXN2QV4GCRUR3MIV/graph.json","fetch_events":"https://pith.science/api/pith-number/GOU7GOAZQQMXN2QV4GCRUR3MIV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV/action/storage_attestation","attest_author":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV/action/author_attestation","sign_citation":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV/action/citation_signature","submit_replication":"https://pith.science/pith/GOU7GOAZQQMXN2QV4GCRUR3MIV/action/replication_record"}},"created_at":"2026-07-05T01:34:23.219268+00:00","updated_at":"2026-07-05T01:34:23.219268+00:00"}