{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PX22RPVBQX5BOAKLCJO5ECX4E6","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":"0e9e015c59a033d8f014bcfd84c815587d96ff8fceb18a89e4a98220284bc8a4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T18:20:12Z","title_canon_sha256":"9c2514e63042f2a0129d390445f3038248093a79fd7c1dd8f7f668804a580a04"},"schema_version":"1.0","source":{"id":"2005.03687","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.03687","created_at":"2026-07-05T01:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"2005.03687v2","created_at":"2026-07-05T01:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03687","created_at":"2026-07-05T01:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"PX22RPVBQX5B","created_at":"2026-07-05T01:05:27Z"},{"alias_kind":"pith_short_16","alias_value":"PX22RPVBQX5BOAKL","created_at":"2026-07-05T01:05:27Z"},{"alias_kind":"pith_short_8","alias_value":"PX22RPVB","created_at":"2026-07-05T01:05:27Z"}],"graph_snapshots":[{"event_id":"sha256:94d26600b86b4254bce80261fe1beec4c9a6bed82cb580022ae03141d9e05ebd","target":"graph","created_at":"2026-07-05T01:05:27Z","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/2005.03687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are a wide range of applications that involve multi-modal data, such as cross-modal retrieval, visual question-answering, and image captioning. Such applications are primarily dependent on aligned distributions of the different constituent modalities. Existing approaches generate latent embeddings for each modality in a joint fashion by representing them in a common manifold. However these joint embedding spaces fail to sufficiently reduce the modality gap, which affects the performance in downstream tasks. We hypothesize that these embeddings retain the intra-class relationships but are","authors_text":"Abhishek Maiti, Deepak Srivatsav, Rajiv Ratn Shah, Suryatej Reddy Vyalla, Vishaal Udandarao, Yifang Yin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T18:20:12Z","title":"COBRA: Contrastive Bi-Modal Representation Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03687","kind":"arxiv","version":2},"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":"sha256:2597e40452c77279ea3b5eaa9670a3e518d198f01b2e0db57db858748a48d45f","target":"record","created_at":"2026-07-05T01:05:27Z","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":"0e9e015c59a033d8f014bcfd84c815587d96ff8fceb18a89e4a98220284bc8a4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-07T18:20:12Z","title_canon_sha256":"9c2514e63042f2a0129d390445f3038248093a79fd7c1dd8f7f668804a580a04"},"schema_version":"1.0","source":{"id":"2005.03687","kind":"arxiv","version":2}},"canonical_sha256":"7df5a8bea185fa17014b125dd20afc279d71b45142f712eb699df0391cc41bd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7df5a8bea185fa17014b125dd20afc279d71b45142f712eb699df0391cc41bd1","first_computed_at":"2026-07-05T01:05:27.346993Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:05:27.346993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RATBsotkRb5T8PBHadH/LVeboGSRLtANyBV+TAD0ja70NbQfyJFBnGXuEUZoN2h/PnCnKpMIWNxpXSUp1E8RBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:05:27.347491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.03687","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2597e40452c77279ea3b5eaa9670a3e518d198f01b2e0db57db858748a48d45f","sha256:94d26600b86b4254bce80261fe1beec4c9a6bed82cb580022ae03141d9e05ebd"],"state_sha256":"de0c0915d87906d2e08f95e0d6241ef08ff9ea31f12313e9626e8a3f4fc5e7dc"}