{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MCWWR6O4QH6CFN5DQANWTOUHHF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4330917f154a93f876982a1b240e92cc97d6790238aa1dd241959ea1d7427c2e","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-07T16:25:18Z","title_canon_sha256":"febcc0c521eb29c436b021797b6fbc734af8776221bee19ba9927c448e0a9a94"},"schema_version":"1.0","source":{"id":"2304.03717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03717","created_at":"2026-07-05T05:58:59Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03717v1","created_at":"2026-07-05T05:58:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03717","created_at":"2026-07-05T05:58:59Z"},{"alias_kind":"pith_short_12","alias_value":"MCWWR6O4QH6C","created_at":"2026-07-05T05:58:59Z"},{"alias_kind":"pith_short_16","alias_value":"MCWWR6O4QH6CFN5D","created_at":"2026-07-05T05:58:59Z"},{"alias_kind":"pith_short_8","alias_value":"MCWWR6O4","created_at":"2026-07-05T05:58:59Z"}],"graph_snapshots":[{"event_id":"sha256:fcce0ca0d6a2111c0c84d3aa8243cf0499dbd516f647ec52bc30bb764042759a","target":"graph","created_at":"2026-07-05T05:58:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.03717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, contrastive learning approaches (e.g., CLIP (Radford et al., 2021)) have received huge success in multimodal learning, where the model tries to minimize the distance between the representations of different views (e.g., image and its caption) of the same data point while keeping the representations of different data points away from each other. However, from a theoretical perspective, it is unclear how contrastive learning can learn the representations from different views efficiently, especially when the data is not isotropic. In this work, we analyze the training dynamics of a simp","authors_text":"Yuanzhi Li, Yunwei Ren","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-07T16:25:18Z","title":"On the Importance of Contrastive Loss in Multimodal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03717","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fef84bb620e3e200665cd8f7f3c9151960678449f66b8137894285ca71b21487","target":"record","created_at":"2026-07-05T05:58:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4330917f154a93f876982a1b240e92cc97d6790238aa1dd241959ea1d7427c2e","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-07T16:25:18Z","title_canon_sha256":"febcc0c521eb29c436b021797b6fbc734af8776221bee19ba9927c448e0a9a94"},"schema_version":"1.0","source":{"id":"2304.03717","kind":"arxiv","version":1}},"canonical_sha256":"60ad68f9dc81fc22b7a3801b69ba873956f12a66be69b29e8737042938b6dad3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60ad68f9dc81fc22b7a3801b69ba873956f12a66be69b29e8737042938b6dad3","first_computed_at":"2026-07-05T05:58:59.335562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:59.335562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jyjQ3xGGVRpkjONCI25ZM9lfO8loK+L3M/PoKRR/FUn0CdAfIq0RE1XAGpWjlDsZqQQS7OWziBn+I18rAABLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:59.336087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fef84bb620e3e200665cd8f7f3c9151960678449f66b8137894285ca71b21487","sha256:fcce0ca0d6a2111c0c84d3aa8243cf0499dbd516f647ec52bc30bb764042759a"],"state_sha256":"bffb683597906f70fd2b195e5303ecb177ec4634a7d8a0a0b0058d2180a4cf74"}