{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5R3RMP4FDVBBI74S2KQJROUIRP","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":"704f1b4a592dcef76da08cb297c88d86ac76de7eaaa87756b6e9805504337f2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-02T11:03:22Z","title_canon_sha256":"8e46df438b0e2de73a0993d438be69292ca5f497012dfd424b77e6ff70090012"},"schema_version":"1.0","source":{"id":"2408.01181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01181","created_at":"2026-07-05T08:51:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01181v1","created_at":"2026-07-05T08:51:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01181","created_at":"2026-07-05T08:51:28Z"},{"alias_kind":"pith_short_12","alias_value":"5R3RMP4FDVBB","created_at":"2026-07-05T08:51:28Z"},{"alias_kind":"pith_short_16","alias_value":"5R3RMP4FDVBBI74S","created_at":"2026-07-05T08:51:28Z"},{"alias_kind":"pith_short_8","alias_value":"5R3RMP4F","created_at":"2026-07-05T08:51:28Z"}],"graph_snapshots":[{"event_id":"sha256:25a7d9a30c8da917a82d0873ac81ca8ca0ab529f7f9de071671e71c3324eff23","target":"graph","created_at":"2026-07-05T08:51:28Z","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/2408.01181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"VAR is a new generation paradigm that employs 'next-scale prediction' as opposed to 'next-token prediction'. This innovative transformation enables auto-regressive (AR) transformers to rapidly learn visual distributions and achieve robust generalization. However, the original VAR model is constrained to class-conditioned synthesis, relying solely on textual captions for guidance. In this paper, we introduce VAR-CLIP, a novel text-to-image model that integrates Visual Auto-Regressive techniques with the capabilities of CLIP. The VAR-CLIP framework encodes captions into text embeddings, which ar","authors_text":"Ninghua Yang, Qian Zhang, Xiang An, Xiangzi Dai, Xingyu Ren, Ziyong Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-02T11:03:22Z","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01181","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":"sha256:2f60f2983330f84a01652ef13ae52b04b0fd2495bab3a4fefac07b15f8847f9b","target":"record","created_at":"2026-07-05T08:51:28Z","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":"704f1b4a592dcef76da08cb297c88d86ac76de7eaaa87756b6e9805504337f2c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-02T11:03:22Z","title_canon_sha256":"8e46df438b0e2de73a0993d438be69292ca5f497012dfd424b77e6ff70090012"},"schema_version":"1.0","source":{"id":"2408.01181","kind":"arxiv","version":1}},"canonical_sha256":"ec77163f851d42147f92d2a098ba888bf4877c887ce0219753cc8dce629ccc9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec77163f851d42147f92d2a098ba888bf4877c887ce0219753cc8dce629ccc9d","first_computed_at":"2026-07-05T08:51:28.074126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:28.074126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twM4Wb5sNRN9Dmw5mKzURmIvp3PJpbO8vEtpgkSI9zMsjVVY5p0WFxAuOTYuqh/dGlmZrwQLXZakwBRy8rhtAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:28.074559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f60f2983330f84a01652ef13ae52b04b0fd2495bab3a4fefac07b15f8847f9b","sha256:25a7d9a30c8da917a82d0873ac81ca8ca0ab529f7f9de071671e71c3324eff23"],"state_sha256":"f20e9e45305b2133bd00997f212080284f509a4d81072cbd9d0bafbb823ffc48"}