{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5R3RMP4FDVBBI74S2KQJROUIRP","short_pith_number":"pith:5R3RMP4F","schema_version":"1.0","canonical_sha256":"ec77163f851d42147f92d2a098ba888bf4877c887ce0219753cc8dce629ccc9d","source":{"kind":"arxiv","id":"2408.01181","version":1},"attestation_state":"computed","paper":{"title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ninghua Yang, Qian Zhang, Xiang An, Xiangzi Dai, Xingyu Ren, Ziyong Feng","submitted_at":"2024-08-02T11:03:22Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2408.01181","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-02T11:03:22Z","cross_cats_sorted":[],"title_canon_sha256":"8e46df438b0e2de73a0993d438be69292ca5f497012dfd424b77e6ff70090012","abstract_canon_sha256":"704f1b4a592dcef76da08cb297c88d86ac76de7eaaa87756b6e9805504337f2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:28.074559Z","signature_b64":"twM4Wb5sNRN9Dmw5mKzURmIvp3PJpbO8vEtpgkSI9zMsjVVY5p0WFxAuOTYuqh/dGlmZrwQLXZakwBRy8rhtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec77163f851d42147f92d2a098ba888bf4877c887ce0219753cc8dce629ccc9d","last_reissued_at":"2026-07-05T08:51:28.074126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:28.074126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ninghua Yang, Qian Zhang, Xiang An, Xiangzi Dai, Xingyu Ren, Ziyong Feng","submitted_at":"2024-08-02T11:03:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01181","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.01181/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2408.01181","created_at":"2026-07-05T08:51:28.074182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01181v1","created_at":"2026-07-05T08:51:28.074182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01181","created_at":"2026-07-05T08:51:28.074182+00:00"},{"alias_kind":"pith_short_12","alias_value":"5R3RMP4FDVBB","created_at":"2026-07-05T08:51:28.074182+00:00"},{"alias_kind":"pith_short_16","alias_value":"5R3RMP4FDVBBI74S","created_at":"2026-07-05T08:51:28.074182+00:00"},{"alias_kind":"pith_short_8","alias_value":"5R3RMP4F","created_at":"2026-07-05T08:51:28.074182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30124","citing_title":"SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP","json":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP.json","graph_json":"https://pith.science/api/pith-number/5R3RMP4FDVBBI74S2KQJROUIRP/graph.json","events_json":"https://pith.science/api/pith-number/5R3RMP4FDVBBI74S2KQJROUIRP/events.json","paper":"https://pith.science/paper/5R3RMP4F"},"agent_actions":{"view_html":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP","download_json":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP.json","view_paper":"https://pith.science/paper/5R3RMP4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01181&json=true","fetch_graph":"https://pith.science/api/pith-number/5R3RMP4FDVBBI74S2KQJROUIRP/graph.json","fetch_events":"https://pith.science/api/pith-number/5R3RMP4FDVBBI74S2KQJROUIRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP/action/storage_attestation","attest_author":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP/action/author_attestation","sign_citation":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP/action/citation_signature","submit_replication":"https://pith.science/pith/5R3RMP4FDVBBI74S2KQJROUIRP/action/replication_record"}},"created_at":"2026-07-05T08:51:28.074182+00:00","updated_at":"2026-07-05T08:51:28.074182+00:00"}