{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3NO6CUIOPM7TJZYXWGVJOL3WNS","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":"3f7c911837a35e319e60525a302571597e0b44b24c317d4f9441d51fd6489347","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-16T18:52:27Z","title_canon_sha256":"09b6d37bd5de353c50ec06e18e2dfbf1be07d947c92c0ea68b81d977b08e5dd7"},"schema_version":"1.0","source":{"id":"2401.08567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08567","created_at":"2026-07-05T07:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08567v1","created_at":"2026-07-05T07:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08567","created_at":"2026-07-05T07:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"3NO6CUIOPM7T","created_at":"2026-07-05T07:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"3NO6CUIOPM7TJZYX","created_at":"2026-07-05T07:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"3NO6CUIO","created_at":"2026-07-05T07:34:13Z"}],"graph_snapshots":[{"event_id":"sha256:fd0fd5e32c5a8872cb57a56db79ffe2d7b1aaf330d4eb966b4954510bb41f88c","target":"graph","created_at":"2026-07-05T07:34:13Z","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/2401.08567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building cross-modal applications is challenging due to limited paired multi-modal data. Recent works have shown that leveraging a pre-trained multi-modal contrastive representation space enables cross-modal tasks to be learned from uni-modal data. This is based on the assumption that contrastive optimization makes embeddings from different modalities interchangeable. However, this assumption is under-explored due to the poorly understood geometry of the multi-modal contrastive space, where a modality gap exists. In our study, we provide a theoretical explanation of this space's geometry and i","authors_text":"Elaine Sui, Serena Yeung-Levy, Yuhui Zhang","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-16T18:52:27Z","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08567","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":"sha256:014da48cb26a343fba24771327afc42f6add9bde9830fd5e1a38ef13291d3ecf","target":"record","created_at":"2026-07-05T07:34:13Z","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":"3f7c911837a35e319e60525a302571597e0b44b24c317d4f9441d51fd6489347","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-16T18:52:27Z","title_canon_sha256":"09b6d37bd5de353c50ec06e18e2dfbf1be07d947c92c0ea68b81d977b08e5dd7"},"schema_version":"1.0","source":{"id":"2401.08567","kind":"arxiv","version":1}},"canonical_sha256":"db5de1510e7b3f34e717b1aa972f766cbceff24bb01abecaead6357aec6fbb4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db5de1510e7b3f34e717b1aa972f766cbceff24bb01abecaead6357aec6fbb4a","first_computed_at":"2026-07-05T07:34:13.505052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:13.505052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vi2vJdyrpyO5rl99HqASVxhv42P5+jZ8QGRHmxKQtM7wlokGyUpAjUPEg1TnS0PRu0xQyh3L2MKEjb85WqTuAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:13.505483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08567","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:014da48cb26a343fba24771327afc42f6add9bde9830fd5e1a38ef13291d3ecf","sha256:fd0fd5e32c5a8872cb57a56db79ffe2d7b1aaf330d4eb966b4954510bb41f88c"],"state_sha256":"f7de9f138c049e347e7eb424e67d170bbf0568fddedbb4ee56b43ad40f8d8435"}