{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U526TVI4DHJUOP2KHRAGTP7RVY","short_pith_number":"pith:U526TVI4","schema_version":"1.0","canonical_sha256":"a775e9d51c19d3473f4a3c4069bff1ae09bc34ed5f5b6125b9874900bf44aa1d","source":{"kind":"arxiv","id":"2312.17742","version":1},"attestation_state":"computed","paper":{"title":"Learning Vision from Models Rivals Learning Vision from Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dilip Krishnan, Dina Katabi, Kaifeng Chen, Lijie Fan, Phillip Isola, Yonglong Tian","submitted_at":"2023-12-28T18:59:55Z","abstract_excerpt":"We introduce SynCLR, a novel approach for learning visual representations exclusively from synthetic images and synthetic captions, without any real data. We synthesize a large dataset of image captions using LLMs, then use an off-the-shelf text-to-image model to generate multiple images corresponding to each synthetic caption. We perform visual representation learning on these synthetic images via contrastive learning, treating images sharing the same caption as positive pairs. The resulting representations transfer well to many downstream tasks, competing favorably with other general-purpose"},"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":"2312.17742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-28T18:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"d53301e9c649648c8af14caf3b2eaf32a314998c729060dba9e9936d4612cd40","abstract_canon_sha256":"a893eb0b3554ee3a64f725bcde7b7ab7c0f9ce8188be150c5893066f967d2d33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:56.044405Z","signature_b64":"9J4Rqrh92NzDE5DyW9yzs8ZzT+S3yLirdTY1fKhBLmr6Tp23qFzkgTZnMRw524M6m6PSe1lw+UDXnxSogDRLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a775e9d51c19d3473f4a3c4069bff1ae09bc34ed5f5b6125b9874900bf44aa1d","last_reissued_at":"2026-07-05T07:28:56.043971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:56.043971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Vision from Models Rivals Learning Vision from Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dilip Krishnan, Dina Katabi, Kaifeng Chen, Lijie Fan, Phillip Isola, Yonglong Tian","submitted_at":"2023-12-28T18:59:55Z","abstract_excerpt":"We introduce SynCLR, a novel approach for learning visual representations exclusively from synthetic images and synthetic captions, without any real data. We synthesize a large dataset of image captions using LLMs, then use an off-the-shelf text-to-image model to generate multiple images corresponding to each synthetic caption. We perform visual representation learning on these synthetic images via contrastive learning, treating images sharing the same caption as positive pairs. The resulting representations transfer well to many downstream tasks, competing favorably with other general-purpose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17742","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/2312.17742/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":"2312.17742","created_at":"2026-07-05T07:28:56.044033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17742v1","created_at":"2026-07-05T07:28:56.044033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17742","created_at":"2026-07-05T07:28:56.044033+00:00"},{"alias_kind":"pith_short_12","alias_value":"U526TVI4DHJU","created_at":"2026-07-05T07:28:56.044033+00:00"},{"alias_kind":"pith_short_16","alias_value":"U526TVI4DHJUOP2K","created_at":"2026-07-05T07:28:56.044033+00:00"},{"alias_kind":"pith_short_8","alias_value":"U526TVI4","created_at":"2026-07-05T07:28:56.044033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26353","citing_title":"Personalized Generative Models for Contextual Debiasing","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY","json":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY.json","graph_json":"https://pith.science/api/pith-number/U526TVI4DHJUOP2KHRAGTP7RVY/graph.json","events_json":"https://pith.science/api/pith-number/U526TVI4DHJUOP2KHRAGTP7RVY/events.json","paper":"https://pith.science/paper/U526TVI4"},"agent_actions":{"view_html":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY","download_json":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY.json","view_paper":"https://pith.science/paper/U526TVI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17742&json=true","fetch_graph":"https://pith.science/api/pith-number/U526TVI4DHJUOP2KHRAGTP7RVY/graph.json","fetch_events":"https://pith.science/api/pith-number/U526TVI4DHJUOP2KHRAGTP7RVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY/action/storage_attestation","attest_author":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY/action/author_attestation","sign_citation":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY/action/citation_signature","submit_replication":"https://pith.science/pith/U526TVI4DHJUOP2KHRAGTP7RVY/action/replication_record"}},"created_at":"2026-07-05T07:28:56.044033+00:00","updated_at":"2026-07-05T07:28:56.044033+00:00"}