{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P4ZH5VYV6PYERKUSI3F6PZZV5C","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":"4744d7a7e205867f05722193f31397358b387226fc2aeea5ca280cb89b6a5b89","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-20T11:25:55Z","title_canon_sha256":"ec9472f3bcc7e82a91017c1c5a98c75a72cbe0fb06e850b2d7cf50d731779b0a"},"schema_version":"1.0","source":{"id":"2603.19862","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.19862","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2603.19862v2","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.19862","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"P4ZH5VYV6PYE","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"P4ZH5VYV6PYERKUS","created_at":"2026-06-01T01:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"P4ZH5VYV","created_at":"2026-06-01T01:03:51Z"}],"graph_snapshots":[{"event_id":"sha256:edbf7fb35536c259ce497013b9bba97576c65bd1c37293903535db92043a129d","target":"graph","created_at":"2026-06-01T01:03:51Z","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/2603.19862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models like CLIP are extensively used for inter-modal tasks which involve both visual and text modalities. However, when the individual modality encoders are applied to inherently intra-modal tasks like image-to-image retrieval, their performance suffers from the intra-modal misalignment. In this paper we study intra-modal misalignment in CLIP with a focus on the role of the projectors that map pre-projection image and text embeddings into the shared embedding space. By analyzing the form of the cosine similarity applied to projected features, and its interaction with the contr","authors_text":"Andrew D. Bagdanov, Bart{\\l}omiej Twardowski, Dipam Goswami, Joost Van De Weijer, Marco Mistretta, Simone Magistri","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-20T11:25:55Z","title":"IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.19862","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":"sha256:76feec1b92e5c80cadf45a4ae6c975907f84ca7daf743e4923d89ec514ca175b","target":"record","created_at":"2026-06-01T01:03:51Z","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":"4744d7a7e205867f05722193f31397358b387226fc2aeea5ca280cb89b6a5b89","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-20T11:25:55Z","title_canon_sha256":"ec9472f3bcc7e82a91017c1c5a98c75a72cbe0fb06e850b2d7cf50d731779b0a"},"schema_version":"1.0","source":{"id":"2603.19862","kind":"arxiv","version":2}},"canonical_sha256":"7f327ed715f3f048aa9246cbe7e735e89d4a14c451cc6b722e4dc395617ba6ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f327ed715f3f048aa9246cbe7e735e89d4a14c451cc6b722e4dc395617ba6ea","first_computed_at":"2026-06-01T01:03:51.997946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:51.997946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fi8TqvmwRIWVJMb434IrxlAejGx4xSX0TQJ571LXaZ3JVDNPLYXzfqkrljWrPoC56y+G1CdQVWGv8sWyZkL/BQ==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:51.999136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.19862","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76feec1b92e5c80cadf45a4ae6c975907f84ca7daf743e4923d89ec514ca175b","sha256:edbf7fb35536c259ce497013b9bba97576c65bd1c37293903535db92043a129d"],"state_sha256":"c62c67cfdac030ce21e318ed9d8b13cc8ae4bc5fc679be994ebe61e61e23e995"}