{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZCXIWH2ZUMEDH7XKQ63R3REKTH","short_pith_number":"pith:ZCXIWH2Z","schema_version":"1.0","canonical_sha256":"c8ae8b1f59a30833feea87b71dc48a99f35b264ee081a3e1f897164466b30e3e","source":{"kind":"arxiv","id":"1906.05849","version":5},"attestation_state":"computed","paper":{"title":"Contrastive Multiview Coding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dilip Krishnan, Phillip Isola, Yonglong Tian","submitted_at":"2019-06-13T17:49:20Z","abstract_excerpt":"Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right ear. Each view is noisy and incomplete, but important factors, such as physics, geometry, and semantics, tend to be shared between all views (e.g., a \"dog\" can be seen, heard, and felt). We investigate the classic hypothesis that a powerful representation is one that models view-invariant factors. We study this hypothesis under the framework of multiview contrastive learning, where we learn a representation that aims "},"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":"1906.05849","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-06-13T17:49:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"86354b4df59e7ced18205767758fc84fe28e441027e210653efcd9d68d985551","abstract_canon_sha256":"3b065e036037842c789a7329b608c6b106b8f991cedb13c323918d6a2b9d521c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:29.013273Z","signature_b64":"CvntvJD/yQbCENYws8woustVM581QLGumEImOccIK02BuHobpejjFLqgb50qZK8J9VwbCLV2PFTBPGhpYQDFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8ae8b1f59a30833feea87b71dc48a99f35b264ee081a3e1f897164466b30e3e","last_reissued_at":"2026-07-05T02:00:29.012874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:29.012874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Multiview Coding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dilip Krishnan, Phillip Isola, Yonglong Tian","submitted_at":"2019-06-13T17:49:20Z","abstract_excerpt":"Humans view the world through many sensory channels, e.g., the long-wavelength light channel, viewed by the left eye, or the high-frequency vibrations channel, heard by the right ear. Each view is noisy and incomplete, but important factors, such as physics, geometry, and semantics, tend to be shared between all views (e.g., a \"dog\" can be seen, heard, and felt). We investigate the classic hypothesis that a powerful representation is one that models view-invariant factors. We study this hypothesis under the framework of multiview contrastive learning, where we learn a representation that aims "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05849","kind":"arxiv","version":5},"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/1906.05849/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":"1906.05849","created_at":"2026-07-05T02:00:29.012926+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05849v5","created_at":"2026-07-05T02:00:29.012926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05849","created_at":"2026-07-05T02:00:29.012926+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCXIWH2ZUMED","created_at":"2026-07-05T02:00:29.012926+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCXIWH2ZUMEDH7XK","created_at":"2026-07-05T02:00:29.012926+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCXIWH2Z","created_at":"2026-07-05T02:00:29.012926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01443","citing_title":"UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2105.04906","citing_title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14521","citing_title":"Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2002.05709","citing_title":"A Simple Framework for Contrastive Learning of Visual Representations","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2003.04297","citing_title":"Improved Baselines with Momentum Contrastive Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11870","citing_title":"Information theoretic underpinning of self-supervised learning by clustering","ref_index":127,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH","json":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH.json","graph_json":"https://pith.science/api/pith-number/ZCXIWH2ZUMEDH7XKQ63R3REKTH/graph.json","events_json":"https://pith.science/api/pith-number/ZCXIWH2ZUMEDH7XKQ63R3REKTH/events.json","paper":"https://pith.science/paper/ZCXIWH2Z"},"agent_actions":{"view_html":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH","download_json":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH.json","view_paper":"https://pith.science/paper/ZCXIWH2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05849&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCXIWH2ZUMEDH7XKQ63R3REKTH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCXIWH2ZUMEDH7XKQ63R3REKTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH/action/storage_attestation","attest_author":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH/action/author_attestation","sign_citation":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH/action/citation_signature","submit_replication":"https://pith.science/pith/ZCXIWH2ZUMEDH7XKQ63R3REKTH/action/replication_record"}},"created_at":"2026-07-05T02:00:29.012926+00:00","updated_at":"2026-07-05T02:00:29.012926+00:00"}