{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MNGI4ESBYOSSYQN3ZLXIL7NJIX","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":"ff852fd118975e45166e6ee4d3d1680a5bf9010c07484a0acdd715a88e1a6e18","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T21:14:29Z","title_canon_sha256":"d5bc315abd33e3decfa5a2aaea89d0dd25e6f456e8e0235ed1fc51dadb142023"},"schema_version":"1.0","source":{"id":"2607.22919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22919","created_at":"2026-07-28T00:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22919v1","created_at":"2026-07-28T00:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22919","created_at":"2026-07-28T00:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"MNGI4ESBYOSS","created_at":"2026-07-28T00:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"MNGI4ESBYOSSYQN3","created_at":"2026-07-28T00:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"MNGI4ESB","created_at":"2026-07-28T00:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:e38d80af615dfb8ac5962d1e188174f9db3591b1b7a63c186d7dccf880c2314d","target":"graph","created_at":"2026-07-28T00:22:02Z","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/2607.22919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal embedding spaces in models like CLIP enable powerful capabilities such as semantic similarity retrieval and cross-modal zero-shot classification. These embeddings compress high-level semantics into a single vector, which comes at the cost of primarily expressing a dominant semantics like main object while suppressing other important attributes such as camera angle or color tone. We propose a text-conditioned transformation of visual embeddings that makes such attributes explicitly accessible. Given a natural language description of an attribute category (e.g., \"color\" or \"art style\"","authors_text":"Fabian Caba Heilbron, Joseph Fioresi, Kushal Kafle, Mubarak Shah, Pankaj Nathani","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T21:14:29Z","title":"Controlling Embedding Spaces with Text-Conditioned Transformations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22919","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":"sha256:09edb9c21af925f0dacb64ccc6ab3da945f37e0a2b06ab320cb50d390af52e8f","target":"record","created_at":"2026-07-28T00:22:02Z","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":"ff852fd118975e45166e6ee4d3d1680a5bf9010c07484a0acdd715a88e1a6e18","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T21:14:29Z","title_canon_sha256":"d5bc315abd33e3decfa5a2aaea89d0dd25e6f456e8e0235ed1fc51dadb142023"},"schema_version":"1.0","source":{"id":"2607.22919","kind":"arxiv","version":1}},"canonical_sha256":"634c8e1241c3a52c41bbcaee85fda945fd672ecabcb380c86c71ffc7517747bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"634c8e1241c3a52c41bbcaee85fda945fd672ecabcb380c86c71ffc7517747bb","first_computed_at":"2026-07-28T00:22:02.135966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:22:02.135966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ekwxHEsQP0s3jBzTzZd9k0fcb/QNXuauO/ZQTrnOKhhnToAdEb/Rr34Jmpc1oKv4QVWWiSbq2KlsxkRl3uWCg==","signature_status":"signed_v1","signed_at":"2026-07-28T00:22:02.136869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09edb9c21af925f0dacb64ccc6ab3da945f37e0a2b06ab320cb50d390af52e8f","sha256:e38d80af615dfb8ac5962d1e188174f9db3591b1b7a63c186d7dccf880c2314d"],"state_sha256":"ef2825a1bd13364857f012a55db0e9339179945720f80351e10ab3a8f2f1425e"}