{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3UVWFHCBYDAHQDJXBUMUA7J75W","short_pith_number":"pith:3UVWFHCB","schema_version":"1.0","canonical_sha256":"dd2b629c41c0c0780d370d19407d3fed874fee8d53816d8b69023cf1e956b9f8","source":{"kind":"arxiv","id":"2501.04299","version":1},"attestation_state":"computed","paper":{"title":"Circuit Complexity Bounds for Visual Autoregressive Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaoyu Li, Yekun Ke, Yingyu Liang, Zhao Song, Zhenmei Shi","submitted_at":"2025-01-08T06:07:33Z","abstract_excerpt":"Understanding the expressive ability of a specific model is essential for grasping its capacity limitations. Recently, several studies have established circuit complexity bounds for Transformer architecture. Besides, the Visual AutoRegressive (VAR) model has risen to be a prominent method in the field of image generation, outperforming previous techniques, such as Diffusion Transformers, in generating high-quality images. We investigate the circuit complexity of the VAR model and establish a bound in this study. Our primary result demonstrates that the VAR model is equivalent to a simulation b"},"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":"2501.04299","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-01-08T06:07:33Z","cross_cats_sorted":["cs.AI","cs.CC","cs.CL","cs.LG"],"title_canon_sha256":"cb1c0b7110ab224484f882d52a7bd7c6c6a309d196a79cc062ef230a4d034e59","abstract_canon_sha256":"d122b9d90c7b4e1c4fb9aa37e9feba9406ef5080b8395da21385fd3b0e45fac9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:33.013683Z","signature_b64":"tbv3jIayqpfDbFgkSJbkCg+lRaqb55J7Qozi8mn3LR5hadY/Azicin6KUNyIwIqo1B4QEiyk/W5iY6/At6B0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd2b629c41c0c0780d370d19407d3fed874fee8d53816d8b69023cf1e956b9f8","last_reissued_at":"2026-07-05T09:58:33.013207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:33.013207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Circuit Complexity Bounds for Visual Autoregressive Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CC","cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaoyu Li, Yekun Ke, Yingyu Liang, Zhao Song, Zhenmei Shi","submitted_at":"2025-01-08T06:07:33Z","abstract_excerpt":"Understanding the expressive ability of a specific model is essential for grasping its capacity limitations. Recently, several studies have established circuit complexity bounds for Transformer architecture. Besides, the Visual AutoRegressive (VAR) model has risen to be a prominent method in the field of image generation, outperforming previous techniques, such as Diffusion Transformers, in generating high-quality images. We investigate the circuit complexity of the VAR model and establish a bound in this study. Our primary result demonstrates that the VAR model is equivalent to a simulation b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04299","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/2501.04299/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":"2501.04299","created_at":"2026-07-05T09:58:33.013265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04299v1","created_at":"2026-07-05T09:58:33.013265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04299","created_at":"2026-07-05T09:58:33.013265+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UVWFHCBYDAH","created_at":"2026-07-05T09:58:33.013265+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UVWFHCBYDAHQDJX","created_at":"2026-07-05T09:58:33.013265+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UVWFHCB","created_at":"2026-07-05T09:58:33.013265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08150","citing_title":"Force Matching with Relativistic Constraints: A Physics-Inspired Approach to Stable and Efficient Generative Modeling","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W","json":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W.json","graph_json":"https://pith.science/api/pith-number/3UVWFHCBYDAHQDJXBUMUA7J75W/graph.json","events_json":"https://pith.science/api/pith-number/3UVWFHCBYDAHQDJXBUMUA7J75W/events.json","paper":"https://pith.science/paper/3UVWFHCB"},"agent_actions":{"view_html":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W","download_json":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W.json","view_paper":"https://pith.science/paper/3UVWFHCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04299&json=true","fetch_graph":"https://pith.science/api/pith-number/3UVWFHCBYDAHQDJXBUMUA7J75W/graph.json","fetch_events":"https://pith.science/api/pith-number/3UVWFHCBYDAHQDJXBUMUA7J75W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W/action/storage_attestation","attest_author":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W/action/author_attestation","sign_citation":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W/action/citation_signature","submit_replication":"https://pith.science/pith/3UVWFHCBYDAHQDJXBUMUA7J75W/action/replication_record"}},"created_at":"2026-07-05T09:58:33.013265+00:00","updated_at":"2026-07-05T09:58:33.013265+00:00"}