{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KWI77SKGYOWI5T6UVJZF2FIXU6","short_pith_number":"pith:KWI77SKG","schema_version":"1.0","canonical_sha256":"5591ffc946c3ac8ecfd4aa725d1517a7a3b2a2e836bef7bdd4b4e1538f8f5595","source":{"kind":"arxiv","id":"2503.08455","version":1},"attestation_state":"computed","paper":{"title":"Controlling Latent Diffusion Using Latent CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV","stat.ML"],"primary_cat":"cs.CV","authors_text":"Christian Wressnegger, Chris Wendler, Jason Becker, Peter Baylies, Robert West","submitted_at":"2025-03-11T14:04:29Z","abstract_excerpt":"Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more efficient processing at reduced computational costs. However, while the diffusion process has moved to the latent space, the contrastive language-image pre-training (CLIP) models, as used in many image processing tasks, still operate in pixel space. Doing so requires costly VAE-decoding of latent images before they can be processed. In this paper, we introduce Latent-CLIP, a CLIP model that operates directly in the latent"},"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":"2503.08455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T14:04:29Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV","stat.ML"],"title_canon_sha256":"9c699892f5fc97611165143469797b2c3a396bc70cff54d81c78c6c1131b6fcb","abstract_canon_sha256":"30f4aba4fabcd472672ed8884e16808652525483344437782d989b14171ff9cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:59.809230Z","signature_b64":"TdIqUyDOQc9X41B/7XpE5z7k134R6+pNGfdsdE9uh1s6OhAdYo4vs9sVOyqOS02qXRcFYixmZNF9NuOWMeKBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5591ffc946c3ac8ecfd4aa725d1517a7a3b2a2e836bef7bdd4b4e1538f8f5595","last_reissued_at":"2026-07-05T10:28:59.808348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:59.808348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controlling Latent Diffusion Using Latent CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV","stat.ML"],"primary_cat":"cs.CV","authors_text":"Christian Wressnegger, Chris Wendler, Jason Becker, Peter Baylies, Robert West","submitted_at":"2025-03-11T14:04:29Z","abstract_excerpt":"Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more efficient processing at reduced computational costs. However, while the diffusion process has moved to the latent space, the contrastive language-image pre-training (CLIP) models, as used in many image processing tasks, still operate in pixel space. Doing so requires costly VAE-decoding of latent images before they can be processed. In this paper, we introduce Latent-CLIP, a CLIP model that operates directly in the latent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08455","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/2503.08455/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":"2503.08455","created_at":"2026-07-05T10:28:59.808461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08455v1","created_at":"2026-07-05T10:28:59.808461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08455","created_at":"2026-07-05T10:28:59.808461+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWI77SKGYOWI","created_at":"2026-07-05T10:28:59.808461+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWI77SKGYOWI5T6U","created_at":"2026-07-05T10:28:59.808461+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWI77SKG","created_at":"2026-07-05T10:28:59.808461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.03151","citing_title":"Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6","json":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6.json","graph_json":"https://pith.science/api/pith-number/KWI77SKGYOWI5T6UVJZF2FIXU6/graph.json","events_json":"https://pith.science/api/pith-number/KWI77SKGYOWI5T6UVJZF2FIXU6/events.json","paper":"https://pith.science/paper/KWI77SKG"},"agent_actions":{"view_html":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6","download_json":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6.json","view_paper":"https://pith.science/paper/KWI77SKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08455&json=true","fetch_graph":"https://pith.science/api/pith-number/KWI77SKGYOWI5T6UVJZF2FIXU6/graph.json","fetch_events":"https://pith.science/api/pith-number/KWI77SKGYOWI5T6UVJZF2FIXU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6/action/storage_attestation","attest_author":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6/action/author_attestation","sign_citation":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6/action/citation_signature","submit_replication":"https://pith.science/pith/KWI77SKGYOWI5T6UVJZF2FIXU6/action/replication_record"}},"created_at":"2026-07-05T10:28:59.808461+00:00","updated_at":"2026-07-05T10:28:59.808461+00:00"}