{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AQY45A6AB7R2FP7AKIILPS4EDJ","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":"3042f67c4084d107fdcd29ade49dfff4e51c8e9aeb5f7aafb6f9ff6c860ddc34","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T17:24:41Z","title_canon_sha256":"50e8600404ce61d4b6d158599e2dffc4642e95698ca5b91609c6efce2d986520"},"schema_version":"1.0","source":{"id":"2505.03703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03703","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03703v1","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03703","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"AQY45A6AB7R2","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"AQY45A6AB7R2FP7A","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"AQY45A6A","created_at":"2026-07-05T10:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:0a864839493c0c3b7349c57c027a3192ea34fa42a90613ef14ba072fa1299a5a","target":"graph","created_at":"2026-07-05T10:59:20Z","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/2505.03703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) allow to embed texts and images in a shared representation space. However, it has been shown that these models are subject to a modality gap phenomenon meaning there exists a clear separation between the embeddings from one modality and another in the embedding space. While this misalignment is detrimental for downstream tasks such as multimodal retrieval, multimodal clustering or zero-shot classification, etc. no generic and practical methods have so far been proposed to assess it precisely and even reduce it. We therefore propose novel measures and effective tec","authors_text":"Fran\\c{c}ois Role, S\\'ebastien Meyer, Victor Amblard","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T17:24:41Z","title":"Fill the Gap: Quantifying and Reducing the Modality Gap in Image-Text Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03703","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":"sha256:86b4a99b62f0c9dec92d27712912d1a710c11147a49e171187d968c755137c21","target":"record","created_at":"2026-07-05T10:59:20Z","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":"3042f67c4084d107fdcd29ade49dfff4e51c8e9aeb5f7aafb6f9ff6c860ddc34","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-06T17:24:41Z","title_canon_sha256":"50e8600404ce61d4b6d158599e2dffc4642e95698ca5b91609c6efce2d986520"},"schema_version":"1.0","source":{"id":"2505.03703","kind":"arxiv","version":1}},"canonical_sha256":"0431ce83c00fe3a2bfe05210b7cb841a77c9b65865dd9b0d2eacc3394d41251d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0431ce83c00fe3a2bfe05210b7cb841a77c9b65865dd9b0d2eacc3394d41251d","first_computed_at":"2026-07-05T10:59:20.792486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:20.792486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2xYuc4zX0ERHSvDRVOnMwGQyX8xFtx5EVyKyCGjnWpA2zOKs0AfqXODDW97FSncMp2Ex8M0n8rgzCYE8M/SBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:20.792990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86b4a99b62f0c9dec92d27712912d1a710c11147a49e171187d968c755137c21","sha256:0a864839493c0c3b7349c57c027a3192ea34fa42a90613ef14ba072fa1299a5a"],"state_sha256":"f8c5b89a0b8547103536d680e604e049f27ec12131dcbbc2840ef4cf2d2fb14a"}