{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4MQPZPV42FM6IAH6VCVCJMG2Q7","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":"ebb3c49cea31254cc11e7946f17c78f6c1b13a850011c44157f0713c349383de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T04:34:59Z","title_canon_sha256":"dd0460740240771dc7dec3d79f228ec4c9d6b582c301c2fe5e4c093c0fb47db9"},"schema_version":"1.0","source":{"id":"2403.14944","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14944","created_at":"2026-07-05T07:59:28Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14944v1","created_at":"2026-07-05T07:59:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14944","created_at":"2026-07-05T07:59:28Z"},{"alias_kind":"pith_short_12","alias_value":"4MQPZPV42FM6","created_at":"2026-07-05T07:59:28Z"},{"alias_kind":"pith_short_16","alias_value":"4MQPZPV42FM6IAH6","created_at":"2026-07-05T07:59:28Z"},{"alias_kind":"pith_short_8","alias_value":"4MQPZPV4","created_at":"2026-07-05T07:59:28Z"}],"graph_snapshots":[{"event_id":"sha256:f5b85240685d950b781b76425c2ba52f53de66da2f336a8de6f770de1fbbc2c5","target":"graph","created_at":"2026-07-05T07:59:28Z","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/2403.14944/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been a significant progress in text conditional image generation models. Recent advancements in this field depend not only on improvements in model structures, but also vast quantities of text-image paired datasets. However, creating these kinds of datasets is very costly and requires a substantial amount of labor. Famous face datasets don't have corresponding text captions, making it difficult to develop text conditional image generation models on these datasets. Some research has focused on developing text to image generation models using only images without text captions. Here, we","authors_text":"Joohee Kim, Seungdae Han","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T04:34:59Z","title":"CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusion model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14944","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:fe5030a3f058d4db6c05a6b13009397de83810df841188177818a1f24c55f49c","target":"record","created_at":"2026-07-05T07:59:28Z","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":"ebb3c49cea31254cc11e7946f17c78f6c1b13a850011c44157f0713c349383de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T04:34:59Z","title_canon_sha256":"dd0460740240771dc7dec3d79f228ec4c9d6b582c301c2fe5e4c093c0fb47db9"},"schema_version":"1.0","source":{"id":"2403.14944","kind":"arxiv","version":1}},"canonical_sha256":"e320fcbebcd159e400fea8aa24b0da87f716f2a6331e7622064eb4b806ed379b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e320fcbebcd159e400fea8aa24b0da87f716f2a6331e7622064eb4b806ed379b","first_computed_at":"2026-07-05T07:59:28.040932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:28.040932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3NljojgLHCXwVpXuSzIpBVnp9OqfF18NO0UEqP6mg68SR0KVrQPJYfRXB1mEN3M+cvDzyRckPFwkED88EvW9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:28.041357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14944","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe5030a3f058d4db6c05a6b13009397de83810df841188177818a1f24c55f49c","sha256:f5b85240685d950b781b76425c2ba52f53de66da2f336a8de6f770de1fbbc2c5"],"state_sha256":"4348d89e6f3d4b02a5432e98f69945c64a839d59b35abbe7f4a973f78916d003"}