{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OGIK6SXOO2OEYXF25EVOU4KWZH","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":"615f1c8d27097ec546d452f0b7ecd12f8680e12d6b5f9333885c0b01d0a975f9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T17:58:59Z","title_canon_sha256":"ac195d937874794b85c8e8cd343b80160b635f7af02cca3e4c4f69b58a51a4bc"},"schema_version":"1.0","source":{"id":"2502.04263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.04263","created_at":"2026-07-05T10:10:35Z"},{"alias_kind":"arxiv_version","alias_value":"2502.04263v1","created_at":"2026-07-05T10:10:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04263","created_at":"2026-07-05T10:10:35Z"},{"alias_kind":"pith_short_12","alias_value":"OGIK6SXOO2OE","created_at":"2026-07-05T10:10:35Z"},{"alias_kind":"pith_short_16","alias_value":"OGIK6SXOO2OEYXF2","created_at":"2026-07-05T10:10:35Z"},{"alias_kind":"pith_short_8","alias_value":"OGIK6SXO","created_at":"2026-07-05T10:10:35Z"}],"graph_snapshots":[{"event_id":"sha256:78449a9f20d9db7d557d3c965744d78ac4371dfa756fac51ec84dad80a2e63cd","target":"graph","created_at":"2026-07-05T10:10:35Z","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/2502.04263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for a variety of applications. In this paper, we show that the common practice of individually exploiting the text or image encoders of these powerful multi-modal models is highly suboptimal for intra-modal tasks like image-to-image retrieval. We argue that this is inherently due to the CLIP-style inter-modal contrastive loss that does not enforce any intra-modal constraints, leading to what we call intra-modal misalignment. To demonstrate this, we leverage two optimization-based modality inversion technique","authors_text":"Alberto Baldrati, Andrew D. Bagdanov, Lorenzo Agnolucci, Marco Bertini, Marco Mistretta","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T17:58:59Z","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04263","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":"sha256:6c41dfc2d25e0ffd2dfc982f76a518fa730e41cb932e327f601197674fa5e110","target":"record","created_at":"2026-07-05T10:10:35Z","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":"615f1c8d27097ec546d452f0b7ecd12f8680e12d6b5f9333885c0b01d0a975f9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-06T17:58:59Z","title_canon_sha256":"ac195d937874794b85c8e8cd343b80160b635f7af02cca3e4c4f69b58a51a4bc"},"schema_version":"1.0","source":{"id":"2502.04263","kind":"arxiv","version":1}},"canonical_sha256":"7190af4aee769c4c5cbae92aea7156c9d61b666bb715e254e54f3f434865ae53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7190af4aee769c4c5cbae92aea7156c9d61b666bb715e254e54f3f434865ae53","first_computed_at":"2026-07-05T10:10:35.932376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:35.932376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5RueVxdLfEAGSJ1aWgluAp04tV0li4t7+RzaMzvn6J05ickjDv5bBsImu1ESC0WVG46vxUKqYm1Y6es6NqIbDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:35.932810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.04263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c41dfc2d25e0ffd2dfc982f76a518fa730e41cb932e327f601197674fa5e110","sha256:78449a9f20d9db7d557d3c965744d78ac4371dfa756fac51ec84dad80a2e63cd"],"state_sha256":"ad6198a476af9c090e7f568fc6510654e086233eab78504651501eb124c44d2c"}