{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V2FKCNN5PZM5QCLZCTDLFZCOSF","short_pith_number":"pith:V2FKCNN5","schema_version":"1.0","canonical_sha256":"ae8aa135bd7e59d8097914c6b2e44e91684ba8ae06817bf91bc1a6cb04be0693","source":{"kind":"arxiv","id":"2501.18993","version":1},"attestation_state":"computed","paper":{"title":"Visual Autoregressive Modeling for Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhou, Jinhua Hao, Kai Zhao, Kun Yuan, Ming Sun, Qizhi Xie, Yunpeng Qu","submitted_at":"2025-01-31T09:53:47Z","abstract_excerpt":"Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also posed limitations on their application. Building upon the tremendous success of autoregressive models in the language domain, we propose \\textbf{VARSR}, a novel visual autoregressive modeling for ISR framework with the form of next-scale prediction. To effectively integrate and preserve semantic information in low-resolution images, we propose using prefix t"},"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":"2501.18993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T09:53:47Z","cross_cats_sorted":[],"title_canon_sha256":"7d5c570df7bf5d5d389f6851f5335f947d4ab2dff77157af1ab22941607f703f","abstract_canon_sha256":"cd7b07d9458bb95acce07540b4b25e7a709c830956d59bcf81d854b3cdedf60d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:54.623299Z","signature_b64":"tN/zQXYLe8k5gGiYZ0XukT1Psywndl5L6Y85fUTlfTrPuczf1DEWVgtUGuHaZhL43ks4CABdJOzMY+f75BdNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae8aa135bd7e59d8097914c6b2e44e91684ba8ae06817bf91bc1a6cb04be0693","last_reissued_at":"2026-07-05T10:07:54.622811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:54.622811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Autoregressive Modeling for Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Zhou, Jinhua Hao, Kai Zhao, Kun Yuan, Ming Sun, Qizhi Xie, Yunpeng Qu","submitted_at":"2025-01-31T09:53:47Z","abstract_excerpt":"Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also posed limitations on their application. Building upon the tremendous success of autoregressive models in the language domain, we propose \\textbf{VARSR}, a novel visual autoregressive modeling for ISR framework with the form of next-scale prediction. To effectively integrate and preserve semantic information in low-resolution images, we propose using prefix t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18993","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/2501.18993/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":"2501.18993","created_at":"2026-07-05T10:07:54.622869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18993v1","created_at":"2026-07-05T10:07:54.622869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18993","created_at":"2026-07-05T10:07:54.622869+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2FKCNN5PZM5","created_at":"2026-07-05T10:07:54.622869+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2FKCNN5PZM5QCLZ","created_at":"2026-07-05T10:07:54.622869+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2FKCNN5","created_at":"2026-07-05T10:07:54.622869+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":30,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16796","citing_title":"RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21450","citing_title":"VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolution","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10546","citing_title":"Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF","json":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF.json","graph_json":"https://pith.science/api/pith-number/V2FKCNN5PZM5QCLZCTDLFZCOSF/graph.json","events_json":"https://pith.science/api/pith-number/V2FKCNN5PZM5QCLZCTDLFZCOSF/events.json","paper":"https://pith.science/paper/V2FKCNN5"},"agent_actions":{"view_html":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF","download_json":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF.json","view_paper":"https://pith.science/paper/V2FKCNN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18993&json=true","fetch_graph":"https://pith.science/api/pith-number/V2FKCNN5PZM5QCLZCTDLFZCOSF/graph.json","fetch_events":"https://pith.science/api/pith-number/V2FKCNN5PZM5QCLZCTDLFZCOSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF/action/storage_attestation","attest_author":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF/action/author_attestation","sign_citation":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF/action/citation_signature","submit_replication":"https://pith.science/pith/V2FKCNN5PZM5QCLZCTDLFZCOSF/action/replication_record"}},"created_at":"2026-07-05T10:07:54.622869+00:00","updated_at":"2026-07-05T10:07:54.622869+00:00"}