{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q63UJ2TYM2RFDNEEEDB5Y5JXOD","short_pith_number":"pith:Q63UJ2TY","schema_version":"1.0","canonical_sha256":"87b744ea7866a251b48420c3dc753770f37133a86ab6964f6c1d8b007abec30f","source":{"kind":"arxiv","id":"2411.10433","version":1},"attestation_state":"computed","paper":{"title":"M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Cihang Xie, Feng Wang, Nataniel Ruiz, Sucheng Ren, Yaodong Yu","submitted_at":"2024-11-15T18:54:42Z","abstract_excerpt":"There exists recent work in computer vision, named VAR, that proposes a new autoregressive paradigm for image generation. Diverging from the vanilla next-token prediction, VAR structurally reformulates the image generation into a coarse to fine next-scale prediction. In this paper, we show that this scale-wise autoregressive framework can be effectively decoupled into \\textit{intra-scale modeling}, which captures local spatial dependencies within each scale, and \\textit{inter-scale modeling}, which models cross-scale relationships progressively from coarse-to-fine scales. This decoupling struc"},"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":"2411.10433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T18:54:42Z","cross_cats_sorted":[],"title_canon_sha256":"42196612ceb4daa8b8c8dc5fa3614675d03d6547b0931ed774ea28dc02660e5f","abstract_canon_sha256":"78aa0374365c3dfb2c601507fd01d6658ef97c0d4dbcfdb8ea2e9e77b60e76b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:05.415178Z","signature_b64":"rwG2b5roBWPnKXVgo8U8fi0g6PlW/CokhR6DAVGdbbZOIehMO7dYTuzPRVBJTPWXfhyoa/2J5tXfxeVW84W7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87b744ea7866a251b48420c3dc753770f37133a86ab6964f6c1d8b007abec30f","last_reissued_at":"2026-07-05T09:36:05.414608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:05.414608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Cihang Xie, Feng Wang, Nataniel Ruiz, Sucheng Ren, Yaodong Yu","submitted_at":"2024-11-15T18:54:42Z","abstract_excerpt":"There exists recent work in computer vision, named VAR, that proposes a new autoregressive paradigm for image generation. Diverging from the vanilla next-token prediction, VAR structurally reformulates the image generation into a coarse to fine next-scale prediction. In this paper, we show that this scale-wise autoregressive framework can be effectively decoupled into \\textit{intra-scale modeling}, which captures local spatial dependencies within each scale, and \\textit{inter-scale modeling}, which models cross-scale relationships progressively from coarse-to-fine scales. This decoupling struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10433","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/2411.10433/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":"2411.10433","created_at":"2026-07-05T09:36:05.414676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10433v1","created_at":"2026-07-05T09:36:05.414676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10433","created_at":"2026-07-05T09:36:05.414676+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q63UJ2TYM2RF","created_at":"2026-07-05T09:36:05.414676+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q63UJ2TYM2RFDNEE","created_at":"2026-07-05T09:36:05.414676+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q63UJ2TY","created_at":"2026-07-05T09:36:05.414676+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08302","citing_title":"HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06078","citing_title":"Knowledge Distillation for Visual Autoregressive Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15521","citing_title":"Frequency-Aware Flow Matching for High-Quality Image Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17286","citing_title":"Depth Adaptive Efficient Visual Autoregressive Modeling","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD","json":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD.json","graph_json":"https://pith.science/api/pith-number/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/graph.json","events_json":"https://pith.science/api/pith-number/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/events.json","paper":"https://pith.science/paper/Q63UJ2TY"},"agent_actions":{"view_html":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD","download_json":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD.json","view_paper":"https://pith.science/paper/Q63UJ2TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10433&json=true","fetch_graph":"https://pith.science/api/pith-number/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/graph.json","fetch_events":"https://pith.science/api/pith-number/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/action/storage_attestation","attest_author":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/action/author_attestation","sign_citation":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/action/citation_signature","submit_replication":"https://pith.science/pith/Q63UJ2TYM2RFDNEEEDB5Y5JXOD/action/replication_record"}},"created_at":"2026-07-05T09:36:05.414676+00:00","updated_at":"2026-07-05T09:36:05.414676+00:00"}