{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ADCGUUYLJINKKNEVOVVNQWMEMG","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":"e2319ae95ae1fb33a3d98af2b4f98c4be8e0aeeb601c72f05a04eda1f29fefe1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-27T01:54:45Z","title_canon_sha256":"9905f4c75168f5f1c48fa28af2de3587039244b8ad538636ef51e7a95fe56f93"},"schema_version":"1.0","source":{"id":"2111.13792","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.13792","created_at":"2026-07-05T04:08:04Z"},{"alias_kind":"arxiv_version","alias_value":"2111.13792v3","created_at":"2026-07-05T04:08:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13792","created_at":"2026-07-05T04:08:04Z"},{"alias_kind":"pith_short_12","alias_value":"ADCGUUYLJINK","created_at":"2026-07-05T04:08:04Z"},{"alias_kind":"pith_short_16","alias_value":"ADCGUUYLJINKKNEV","created_at":"2026-07-05T04:08:04Z"},{"alias_kind":"pith_short_8","alias_value":"ADCGUUYL","created_at":"2026-07-05T04:08:04Z"}],"graph_snapshots":[{"event_id":"sha256:5d4222673c8e40eb917d9a0861fa51ba115f8d11421f663af3613a97783354e0","target":"graph","created_at":"2026-07-05T04:08:04Z","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/2111.13792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the major challenges in training text-to-image generation models is the need of a large number of high-quality image-text pairs. While image samples are often easily accessible, the associated text descriptions typically require careful human captioning, which is particularly time- and cost-consuming. In this paper, we propose the first work to train text-to-image generation models without any text data. Our method leverages the well-aligned multi-modal semantic space of the powerful pre-trained CLIP model: the requirement of text-conditioning is seamlessly alleviated via generating tex","authors_text":"Changyou Chen, Chris Tensmeyer, Chunyuan Li, Jinhui Xu, Jiuxiang Gu, Ruiyi Zhang, Tong Sun, Tong Yu, Yufan Zhou","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-27T01:54:45Z","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13792","kind":"arxiv","version":3},"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":"sha256:8703f840da4e927dbf611cef11c0f4824915cc5a7568b9e4fc03b86776b64508","target":"record","created_at":"2026-07-05T04:08:04Z","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":"e2319ae95ae1fb33a3d98af2b4f98c4be8e0aeeb601c72f05a04eda1f29fefe1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-27T01:54:45Z","title_canon_sha256":"9905f4c75168f5f1c48fa28af2de3587039244b8ad538636ef51e7a95fe56f93"},"schema_version":"1.0","source":{"id":"2111.13792","kind":"arxiv","version":3}},"canonical_sha256":"00c46a530b4a1aa53495756ad8598461ae4ffc61cdb8b4ddb3435be900d793aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00c46a530b4a1aa53495756ad8598461ae4ffc61cdb8b4ddb3435be900d793aa","first_computed_at":"2026-07-05T04:08:04.513094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:04.513094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YeakEky8gWbdwuA0WPtrGfmRrd+pNdDA1sC4+2D8sJajUacwQANGe+T12l8BaJShy0p0jb36zsa8HXg6+f6pBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:04.513504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.13792","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8703f840da4e927dbf611cef11c0f4824915cc5a7568b9e4fc03b86776b64508","sha256:5d4222673c8e40eb917d9a0861fa51ba115f8d11421f663af3613a97783354e0"],"state_sha256":"e776c772bc3cd15f7e2fe7e63707024001d9f6f1c9488b05e81281c40b5c67c8"}