{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MNGI4ESBYOSSYQN3ZLXIL7NJIX","short_pith_number":"pith:MNGI4ESB","schema_version":"1.0","canonical_sha256":"634c8e1241c3a52c41bbcaee85fda945fd672ecabcb380c86c71ffc7517747bb","source":{"kind":"arxiv","id":"2607.22919","version":1},"attestation_state":"computed","paper":{"title":"Controlling Embedding Spaces with Text-Conditioned Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fabian Caba Heilbron, Joseph Fioresi, Kushal Kafle, Mubarak Shah, Pankaj Nathani","submitted_at":"2026-07-24T21:14:29Z","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\""},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.22919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T21:14:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5bc315abd33e3decfa5a2aaea89d0dd25e6f456e8e0235ed1fc51dadb142023","abstract_canon_sha256":"ff852fd118975e45166e6ee4d3d1680a5bf9010c07484a0acdd715a88e1a6e18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:02.136869Z","signature_b64":"3ekwxHEsQP0s3jBzTzZd9k0fcb/QNXuauO/ZQTrnOKhhnToAdEb/Rr34Jmpc1oKv4QVWWiSbq2KlsxkRl3uWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"634c8e1241c3a52c41bbcaee85fda945fd672ecabcb380c86c71ffc7517747bb","last_reissued_at":"2026-07-28T00:22:02.135966Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:02.135966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Embedding Spaces with Text-Conditioned Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fabian Caba Heilbron, Joseph Fioresi, Kushal Kafle, Mubarak Shah, Pankaj Nathani","submitted_at":"2026-07-24T21:14:29Z","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\""},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22919","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.22919/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.22919","created_at":"2026-07-28T00:22:02.136423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22919v1","created_at":"2026-07-28T00:22:02.136423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22919","created_at":"2026-07-28T00:22:02.136423+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNGI4ESBYOSS","created_at":"2026-07-28T00:22:02.136423+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNGI4ESBYOSSYQN3","created_at":"2026-07-28T00:22:02.136423+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNGI4ESB","created_at":"2026-07-28T00:22:02.136423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX","json":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX.json","graph_json":"https://pith.science/api/pith-number/MNGI4ESBYOSSYQN3ZLXIL7NJIX/graph.json","events_json":"https://pith.science/api/pith-number/MNGI4ESBYOSSYQN3ZLXIL7NJIX/events.json","paper":"https://pith.science/paper/MNGI4ESB"},"agent_actions":{"view_html":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX","download_json":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX.json","view_paper":"https://pith.science/paper/MNGI4ESB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22919&json=true","fetch_graph":"https://pith.science/api/pith-number/MNGI4ESBYOSSYQN3ZLXIL7NJIX/graph.json","fetch_events":"https://pith.science/api/pith-number/MNGI4ESBYOSSYQN3ZLXIL7NJIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX/action/storage_attestation","attest_author":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX/action/author_attestation","sign_citation":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX/action/citation_signature","submit_replication":"https://pith.science/pith/MNGI4ESBYOSSYQN3ZLXIL7NJIX/action/replication_record"}},"created_at":"2026-07-28T00:22:02.136423+00:00","updated_at":"2026-07-28T00:22:02.136423+00:00"}