{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KWI77SKGYOWI5T6UVJZF2FIXU6","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":"30f4aba4fabcd472672ed8884e16808652525483344437782d989b14171ff9cf","cross_cats_sorted":["cs.AI","cs.LG","eess.IV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T14:04:29Z","title_canon_sha256":"9c699892f5fc97611165143469797b2c3a396bc70cff54d81c78c6c1131b6fcb"},"schema_version":"1.0","source":{"id":"2503.08455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08455","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08455v1","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08455","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"KWI77SKGYOWI","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"KWI77SKGYOWI5T6U","created_at":"2026-07-05T10:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"KWI77SKG","created_at":"2026-07-05T10:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:08ee580506f9501fea68e3e2437da4b7304042dc6a48cf233653cca963f3e9da","target":"graph","created_at":"2026-07-05T10:28:59Z","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/2503.08455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Christian Wressnegger, Chris Wendler, Jason Becker, Peter Baylies, Robert West","cross_cats":["cs.AI","cs.LG","eess.IV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T14:04:29Z","title":"Controlling Latent Diffusion Using Latent CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08455","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:d9a4063a5d0eeb5d20e631794927b4851fa5c81ba58cd3586c68bd90a60b5106","target":"record","created_at":"2026-07-05T10:28:59Z","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":"30f4aba4fabcd472672ed8884e16808652525483344437782d989b14171ff9cf","cross_cats_sorted":["cs.AI","cs.LG","eess.IV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T14:04:29Z","title_canon_sha256":"9c699892f5fc97611165143469797b2c3a396bc70cff54d81c78c6c1131b6fcb"},"schema_version":"1.0","source":{"id":"2503.08455","kind":"arxiv","version":1}},"canonical_sha256":"5591ffc946c3ac8ecfd4aa725d1517a7a3b2a2e836bef7bdd4b4e1538f8f5595","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5591ffc946c3ac8ecfd4aa725d1517a7a3b2a2e836bef7bdd4b4e1538f8f5595","first_computed_at":"2026-07-05T10:28:59.808348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:59.808348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TdIqUyDOQc9X41B/7XpE5z7k134R6+pNGfdsdE9uh1s6OhAdYo4vs9sVOyqOS02qXRcFYixmZNF9NuOWMeKBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:59.809230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9a4063a5d0eeb5d20e631794927b4851fa5c81ba58cd3586c68bd90a60b5106","sha256:08ee580506f9501fea68e3e2437da4b7304042dc6a48cf233653cca963f3e9da"],"state_sha256":"9f88e4943cef3df960962f4b5400cbba45240a1bd2d08d904909c93ceafe4f45"}