{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CVBYXWMXFLMB7EOWH34TMMJFCP","short_pith_number":"pith:CVBYXWMX","schema_version":"1.0","canonical_sha256":"15438bd9972ad81f91d63ef936312513faafa4a1052f40aa92d8b4168738d558","source":{"kind":"arxiv","id":"2210.09304","version":1},"attestation_state":"computed","paper":{"title":"Non-Contrastive Learning Meets Language-Image Pre-Training","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Furu Wei, Jinghao Zhou, Li Dong, Lijuan Wang, Zhe Gan","submitted_at":"2022-10-17T17:57:46Z","abstract_excerpt":"Contrastive language-image pre-training (CLIP) serves as a de-facto standard to align images and texts. Nonetheless, the loose correlation between images and texts of web-crawled data renders the contrastive objective data inefficient and craving for a large training batch size. In this work, we explore the validity of non-contrastive language-image pre-training (nCLIP), and study whether nice properties exhibited in visual self-supervised models can emerge. We empirically observe that the non-contrastive objective nourishes representation learning while sufficiently underperforming under zero"},"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":"2210.09304","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T17:57:46Z","cross_cats_sorted":[],"title_canon_sha256":"8251c18fec307f986c7b75ca9a6095bbab1e74a684f4c996351347e329ff5d41","abstract_canon_sha256":"b6635e47fed64b300ec89f776c91332c9f2eb48a22f96b5b9c73f38d9d66128b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:21.170557Z","signature_b64":"vuXLzyDgFIvRLJxQaru/5bLRhWnVx1CaaHS1jNiCOWAVSCX0Nt2g2WJGyWsCMFag3Z7xSx7plZQKlcRjH3bjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15438bd9972ad81f91d63ef936312513faafa4a1052f40aa92d8b4168738d558","last_reissued_at":"2026-07-05T05:07:21.170115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:21.170115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Contrastive Learning Meets Language-Image Pre-Training","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Furu Wei, Jinghao Zhou, Li Dong, Lijuan Wang, Zhe Gan","submitted_at":"2022-10-17T17:57:46Z","abstract_excerpt":"Contrastive language-image pre-training (CLIP) serves as a de-facto standard to align images and texts. Nonetheless, the loose correlation between images and texts of web-crawled data renders the contrastive objective data inefficient and craving for a large training batch size. In this work, we explore the validity of non-contrastive language-image pre-training (nCLIP), and study whether nice properties exhibited in visual self-supervised models can emerge. We empirically observe that the non-contrastive objective nourishes representation learning while sufficiently underperforming under zero"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09304","kind":"arxiv","version":1},"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/2210.09304/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":"2210.09304","created_at":"2026-07-05T05:07:21.170188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09304v1","created_at":"2026-07-05T05:07:21.170188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09304","created_at":"2026-07-05T05:07:21.170188+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVBYXWMXFLMB","created_at":"2026-07-05T05:07:21.170188+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVBYXWMXFLMB7EOW","created_at":"2026-07-05T05:07:21.170188+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVBYXWMX","created_at":"2026-07-05T05:07:21.170188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08254","citing_title":"UniCoRN: Unified Commented Retrieval Network with LMMs","ref_index":98,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP","json":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP.json","graph_json":"https://pith.science/api/pith-number/CVBYXWMXFLMB7EOWH34TMMJFCP/graph.json","events_json":"https://pith.science/api/pith-number/CVBYXWMXFLMB7EOWH34TMMJFCP/events.json","paper":"https://pith.science/paper/CVBYXWMX"},"agent_actions":{"view_html":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP","download_json":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP.json","view_paper":"https://pith.science/paper/CVBYXWMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09304&json=true","fetch_graph":"https://pith.science/api/pith-number/CVBYXWMXFLMB7EOWH34TMMJFCP/graph.json","fetch_events":"https://pith.science/api/pith-number/CVBYXWMXFLMB7EOWH34TMMJFCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP/action/storage_attestation","attest_author":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP/action/author_attestation","sign_citation":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP/action/citation_signature","submit_replication":"https://pith.science/pith/CVBYXWMXFLMB7EOWH34TMMJFCP/action/replication_record"}},"created_at":"2026-07-05T05:07:21.170188+00:00","updated_at":"2026-07-05T05:07:21.170188+00:00"}