{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3VNTYY2A25BLYA473IVH7C3M26","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":"21e83f5e5b696770cb271153cb715dd8017fae0ce35971a36a14af36fd76126b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:31Z","title_canon_sha256":"15930e87fa97519048c9a989768f19a5ffb559c8e61afdc47f6bc5e4ece706f9"},"schema_version":"1.0","source":{"id":"2412.07767","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07767","created_at":"2026-07-05T10:37:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07767v3","created_at":"2026-07-05T10:37:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07767","created_at":"2026-07-05T10:37:39Z"},{"alias_kind":"pith_short_12","alias_value":"3VNTYY2A25BL","created_at":"2026-07-05T10:37:39Z"},{"alias_kind":"pith_short_16","alias_value":"3VNTYY2A25BLYA47","created_at":"2026-07-05T10:37:39Z"},{"alias_kind":"pith_short_8","alias_value":"3VNTYY2A","created_at":"2026-07-05T10:37:39Z"}],"graph_snapshots":[{"event_id":"sha256:a009f3e9103161eb5ea4fb3d00db83fb9276b0b28df0eb2b66b718f2395ac8f4","target":"graph","created_at":"2026-07-05T10:37:39Z","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/2412.07767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although text-to-image (T2I) models have recently thrived as visual generative priors, their reliance on high-quality text-image pairs makes scaling up expensive. We argue that grasping the cross-modality alignment is not a necessity for a sound visual generative prior, whose focus should be on texture modeling. Such a philosophy inspires us to study image-to-image (I2I) generation, where models can learn from in-the-wild images in a self-supervised manner. We first develop a pure vision-based training framework, Lumos, and confirm the feasibility and the scalability of learning I2I models. We","authors_text":"Biao Gong, Chen-Wei Xie, Fan Lu, Jiapeng Zhu, Kecheng Zheng, Shuailei Ma, Wei Wu, Yifei Zhang, Ying Wei, Yujun Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:31Z","title":"Learning Visual Generative Priors without Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07767","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":"sha256:0f16950d218d6abdcccd368b1a150cb2e8752192d9330f6ff0a7ba92f5628131","target":"record","created_at":"2026-07-05T10:37:39Z","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":"21e83f5e5b696770cb271153cb715dd8017fae0ce35971a36a14af36fd76126b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:31Z","title_canon_sha256":"15930e87fa97519048c9a989768f19a5ffb559c8e61afdc47f6bc5e4ece706f9"},"schema_version":"1.0","source":{"id":"2412.07767","kind":"arxiv","version":3}},"canonical_sha256":"dd5b3c6340d742bc039fda2a7f8b6cd7bd04255435bae4322328102eeead2218","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd5b3c6340d742bc039fda2a7f8b6cd7bd04255435bae4322328102eeead2218","first_computed_at":"2026-07-05T10:37:39.892433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:39.892433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y78+RQ4hG9t92yqk/Nd8L0659duaci4R1UYUlUMFTKV+5irKzHMFu+iAwgKzhOELPda34ibhKDbf5CmscD5KBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:39.893167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07767","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f16950d218d6abdcccd368b1a150cb2e8752192d9330f6ff0a7ba92f5628131","sha256:a009f3e9103161eb5ea4fb3d00db83fb9276b0b28df0eb2b66b718f2395ac8f4"],"state_sha256":"95c39205d4b1873ea5453eb67757bfe4e8d85102ea32474215a0ea1706fe8542"}