{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2TBMA3DPZ237JAFIGVKT6JRXXK","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":"fba68b622019054894d59c6c8e4143c40eb45f61155a01fcdced0c2e9379b0a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T17:57:32Z","title_canon_sha256":"91e3466fd38423c07a743fa665e1013de26a89cdd7b792c9f50526eb3ee21f90"},"schema_version":"1.0","source":{"id":"2409.19425","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19425","created_at":"2026-07-05T10:37:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19425v2","created_at":"2026-07-05T10:37:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19425","created_at":"2026-07-05T10:37:34Z"},{"alias_kind":"pith_short_12","alias_value":"2TBMA3DPZ237","created_at":"2026-07-05T10:37:34Z"},{"alias_kind":"pith_short_16","alias_value":"2TBMA3DPZ237JAFI","created_at":"2026-07-05T10:37:34Z"},{"alias_kind":"pith_short_8","alias_value":"2TBMA3DP","created_at":"2026-07-05T10:37:34Z"}],"graph_snapshots":[{"event_id":"sha256:a020c4538503efdc9a02a9c2d14395dd3d1ec09834abb8dc306a1a99c88cc87f","target":"graph","created_at":"2026-07-05T10:37:34Z","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/2409.19425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent contrastive multimodal vision-language models like CLIP have demonstrated robust open-world semantic understanding, becoming the standard image backbones for vision-language applications. However, recent findings suggest high semantic similarity between well-trained unimodal encoders, which raises a key question: Is there a plausible way to connect unimodal backbones for vision-language tasks? To this end, we propose a novel framework that aligns vision and language using frozen unimodal encoders. It involves selecting semantically similar encoders in the latent space, curating a concep","authors_text":"Ankit Singh, Mayug Maniparambil, Noel E. O'Connor, Raiymbek Akshulakov, Sanath Narayan, Yasser Abdelaziz Dahou Djilali","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T17:57:32Z","title":"Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19425","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":"sha256:61414680874acc70d4a9f5262ac9dd0765a39b73e2b921df6b04ad3d9e5a250a","target":"record","created_at":"2026-07-05T10:37:34Z","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":"fba68b622019054894d59c6c8e4143c40eb45f61155a01fcdced0c2e9379b0a8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T17:57:32Z","title_canon_sha256":"91e3466fd38423c07a743fa665e1013de26a89cdd7b792c9f50526eb3ee21f90"},"schema_version":"1.0","source":{"id":"2409.19425","kind":"arxiv","version":2}},"canonical_sha256":"d4c2c06c6fceb7f480a835553f2637baafe9c159558d497cdbd5a5698f85e47f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4c2c06c6fceb7f480a835553f2637baafe9c159558d497cdbd5a5698f85e47f","first_computed_at":"2026-07-05T10:37:34.460242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:34.460242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"553zlMJioNSdGECzwDO289h8PdHRsj8kgfI9t7usCcVbWYVDyMa0LbdnX02lbQweGr5ufhMezQ3G1pOculxRBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:34.461021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19425","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61414680874acc70d4a9f5262ac9dd0765a39b73e2b921df6b04ad3d9e5a250a","sha256:a020c4538503efdc9a02a9c2d14395dd3d1ec09834abb8dc306a1a99c88cc87f"],"state_sha256":"24d95905a2be3e095e189d7abeb69cb3de08fdfb2a4b889fc16e22691f3657b9"}