{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VXRE7C6VL46Q3E5YUV5A23LALF","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":"1e1378566541ebe5fb7d67a852d519595a3350aa1a18e579d75229491f38e9c5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-11T10:44:52Z","title_canon_sha256":"f54c9a98e5dd860e71afe1505a1714b394f019bbf0ea64a743b8f884f2d5994b"},"schema_version":"1.0","source":{"id":"2505.06934","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06934","created_at":"2026-07-05T11:01:39Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06934v1","created_at":"2026-07-05T11:01:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06934","created_at":"2026-07-05T11:01:39Z"},{"alias_kind":"pith_short_12","alias_value":"VXRE7C6VL46Q","created_at":"2026-07-05T11:01:39Z"},{"alias_kind":"pith_short_16","alias_value":"VXRE7C6VL46Q3E5Y","created_at":"2026-07-05T11:01:39Z"},{"alias_kind":"pith_short_8","alias_value":"VXRE7C6V","created_at":"2026-07-05T11:01:39Z"}],"graph_snapshots":[{"event_id":"sha256:1e4e10b37d5c764dad646dedd9de1761f84d8b573eda3aaaace29fef5e2baaa0","target":"graph","created_at":"2026-07-05T11:01:39Z","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/2505.06934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Likelihood approximations for images are not trivial to compute and can be useful in many applications. We examine the use of Contrastive Language-Image Pre-training (CLIP) to assess the likelihood of images and captions. We introduce \\textit{Whitened CLIP}, a novel transformation of the CLIP latent space via an invertible linear operation. This transformation ensures that each feature in the embedding space has zero mean, unit standard deviation, and no correlation with all other features, resulting in an identity covariance matrix. We show that the whitened embeddings statistics can be well ","authors_text":"Guy Gilboa, Meir Yossef Levi, Roy Betser","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-11T10:44:52Z","title":"Whitened CLIP as a Likelihood Surrogate of Images and Captions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06934","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:bbfdf3dcec12b02fcf8412c6d75ddfe02d98a20d9a27fd1ad07b7365c193801b","target":"record","created_at":"2026-07-05T11:01:39Z","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":"1e1378566541ebe5fb7d67a852d519595a3350aa1a18e579d75229491f38e9c5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2025-05-11T10:44:52Z","title_canon_sha256":"f54c9a98e5dd860e71afe1505a1714b394f019bbf0ea64a743b8f884f2d5994b"},"schema_version":"1.0","source":{"id":"2505.06934","kind":"arxiv","version":1}},"canonical_sha256":"ade24f8bd55f3d0d93b8a57a0d6d60597121e69d07b4819351b88fbc6135dbba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ade24f8bd55f3d0d93b8a57a0d6d60597121e69d07b4819351b88fbc6135dbba","first_computed_at":"2026-07-05T11:01:39.586062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:39.586062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dpZXpLv5aKgZmVpCPjB9saE8G1FEDzI1IVMMYMKqHRx8qxZ6FQddCZWuAuazSUF7+1d8dLFfHiBGNlkwjTutAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:39.586518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06934","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbfdf3dcec12b02fcf8412c6d75ddfe02d98a20d9a27fd1ad07b7365c193801b","sha256:1e4e10b37d5c764dad646dedd9de1761f84d8b573eda3aaaace29fef5e2baaa0"],"state_sha256":"af40e710aefb84cdf8a024a52eeebfc9166e5c7308db0933e84ff60794d551df"}