{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TI7HPQGMBMYGYKI2WOG436P3YI","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":"b6eb2f912fec8d8b1426944a6ce9906c1e23f858acdd83a9ef208e2ae9d06968","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-15T12:34:47Z","title_canon_sha256":"ea47934e9885a0c3b47c9a0a9106bfac2603aafb0eb76ac040c25dfc649c21b8"},"schema_version":"1.0","source":{"id":"2204.07441","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.07441","created_at":"2026-07-05T04:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"2204.07441v2","created_at":"2026-07-05T04:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.07441","created_at":"2026-07-05T04:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"TI7HPQGMBMYG","created_at":"2026-07-05T04:24:59Z"},{"alias_kind":"pith_short_16","alias_value":"TI7HPQGMBMYGYKI2","created_at":"2026-07-05T04:24:59Z"},{"alias_kind":"pith_short_8","alias_value":"TI7HPQGM","created_at":"2026-07-05T04:24:59Z"}],"graph_snapshots":[{"event_id":"sha256:83dafe7a6997694a7373693dc44ea6dfcf479e1a58da3d1c1611ed2b842ebfff","target":"graph","created_at":"2026-07-05T04:24:59Z","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/2204.07441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high inference efficiency have also shown promising performance, however, they only consider instance-level alignment between the two streams (thus there is still room for improvement). To overcome these limitations, we propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval by enhancing cross-modal interaction. In ","authors_text":"Haoyu Lu, Ji-Rong Wen, Nanyi Fei, Yizhao Gao, Yuqi Huo, Zhiwu Lu","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-15T12:34:47Z","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.07441","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:b0c7cf4db934e7a227b1525b96f1d8a47ceb7ee9b2d63a37aad70be8136ca2e8","target":"record","created_at":"2026-07-05T04:24:59Z","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":"b6eb2f912fec8d8b1426944a6ce9906c1e23f858acdd83a9ef208e2ae9d06968","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-15T12:34:47Z","title_canon_sha256":"ea47934e9885a0c3b47c9a0a9106bfac2603aafb0eb76ac040c25dfc649c21b8"},"schema_version":"1.0","source":{"id":"2204.07441","kind":"arxiv","version":2}},"canonical_sha256":"9a3e77c0cc0b306c291ab38dcdf9fbc20b99c997cc3fd85d3f5c29001b75b0e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a3e77c0cc0b306c291ab38dcdf9fbc20b99c997cc3fd85d3f5c29001b75b0e4","first_computed_at":"2026-07-05T04:24:59.223063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:59.223063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rFK22PglZ00uJe3a65xgsE+W3nbZqrpCf4IM3eH0SUAITPEskQWKX3J/Jau6MQFqMLpRSS+oQai04L4PngNfDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:59.223492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.07441","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0c7cf4db934e7a227b1525b96f1d8a47ceb7ee9b2d63a37aad70be8136ca2e8","sha256:83dafe7a6997694a7373693dc44ea6dfcf479e1a58da3d1c1611ed2b842ebfff"],"state_sha256":"ce007dea75968b25a8a449157464171f67432b63b02074bdb6f4aad2b901ecae"}