{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6T67V6P3I6PVYUWV5YLYP7NQOG","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":"4d7758c20525adbafb334c145ba7d0fb94576cf966786f07af055018769fb6a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T15:00:01Z","title_canon_sha256":"264c1dbaaf1da2172de187325494ae63a5e42144a11c99790ce1b87273d11514"},"schema_version":"1.0","source":{"id":"2503.24182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.24182","created_at":"2026-07-05T10:42:05Z"},{"alias_kind":"arxiv_version","alias_value":"2503.24182v1","created_at":"2026-07-05T10:42:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.24182","created_at":"2026-07-05T10:42:05Z"},{"alias_kind":"pith_short_12","alias_value":"6T67V6P3I6PV","created_at":"2026-07-05T10:42:05Z"},{"alias_kind":"pith_short_16","alias_value":"6T67V6P3I6PVYUWV","created_at":"2026-07-05T10:42:05Z"},{"alias_kind":"pith_short_8","alias_value":"6T67V6P3","created_at":"2026-07-05T10:42:05Z"}],"graph_snapshots":[{"event_id":"sha256:daa4f9e84b66984a7b0aac01a171f45ecf039698fd2d9515df1b8085ea2f7b8a","target":"graph","created_at":"2026-07-05T10:42:05Z","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/2503.24182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success in cross-modal tasks such as zero-shot image classification and text-image retrieval by effectively aligning visual and textual representations. However, the theoretical foundations underlying CLIP's strong generalization remain unclear. In this work, we address this gap by proposing the Cross-modal Information Bottleneck (CIB) framework. CIB offers a principled interpretation of CLIP's contrastive learning objective as an implicit Information Bottleneck optimization. Under this view, the model maximizes shared cross","authors_text":"Aokun Liang, Chenrui Ma, Gaofei Chen, Hao Xu, Jiansheng Chen, Lijing Zhu, Xi Xiao, Yingrui Ji","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T15:00:01Z","title":"CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.24182","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":"sha256:116241b6a759b9b59b0965da12d4f02c7949b9d5804984f5ae5892a13c1c3c0b","target":"record","created_at":"2026-07-05T10:42:05Z","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":"4d7758c20525adbafb334c145ba7d0fb94576cf966786f07af055018769fb6a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T15:00:01Z","title_canon_sha256":"264c1dbaaf1da2172de187325494ae63a5e42144a11c99790ce1b87273d11514"},"schema_version":"1.0","source":{"id":"2503.24182","kind":"arxiv","version":1}},"canonical_sha256":"f4fdfaf9fb479f5c52d5ee1787fdb07185a4fde4c85ce4f53e3217d6e78c1619","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4fdfaf9fb479f5c52d5ee1787fdb07185a4fde4c85ce4f53e3217d6e78c1619","first_computed_at":"2026-07-05T10:42:05.965475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:05.965475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNA6JAHIYKpbioM6pSDqhJzSAy3eiTJCuQNto56oTWYfgYNtP9XH9Kxy6LIy2oFQwE3Tmb3nCFvE+TmXOQAkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:05.965888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.24182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:116241b6a759b9b59b0965da12d4f02c7949b9d5804984f5ae5892a13c1c3c0b","sha256:daa4f9e84b66984a7b0aac01a171f45ecf039698fd2d9515df1b8085ea2f7b8a"],"state_sha256":"b6e951b392bc92ff2f17c3a3f4236f85470a38c15661fcbf11f5af0dee58cf9c"}