{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EZA3UDX4RF3P2PCHRKXHYGJUGD","short_pith_number":"pith:EZA3UDX4","schema_version":"1.0","canonical_sha256":"2641ba0efc8976fd3c478aae7c193430d778883165165a2ecb63a1a8b7697d7c","source":{"kind":"arxiv","id":"2410.10511","version":1},"attestation_state":"computed","paper":{"title":"Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Le Zhuo, Peng Gao, Sheng Xia, Wenze Liu, Xiangyu Yue, Yi Xin","submitted_at":"2024-10-14T13:49:06Z","abstract_excerpt":"We introduce a new paradigm for AutoRegressive (AR) image generation, termed Set AutoRegressive Modeling (SAR). SAR generalizes the conventional AR to the next-set setting, i.e., splitting the sequence into arbitrary sets containing multiple tokens, rather than outputting each token in a fixed raster order. To accommodate SAR, we develop a straightforward architecture termed Fully Masked Transformer. We reveal that existing AR variants correspond to specific design choices of sequence order and output intervals within the SAR framework, with AR and Masked AR (MAR) as two extreme instances. Not"},"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":"2410.10511","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T13:49:06Z","cross_cats_sorted":[],"title_canon_sha256":"4bfef573e0fa9c28dd216c0866d784082ace3ac29d688152f7936102d33791af","abstract_canon_sha256":"c11c08024baf66abe7c907983f5d90b11d064b4f150f5d948f5819dce542c121"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:17.321636Z","signature_b64":"g89KJ3vHr/hITFpKCnfN+uGn3oO4Yh6uHs02U+km5NIfhSAzH/UHZDbHV5GosMMC2zJmsvzpazg7ncCcj5Z0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2641ba0efc8976fd3c478aae7c193430d778883165165a2ecb63a1a8b7697d7c","last_reissued_at":"2026-07-05T09:20:17.321096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:17.321096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Le Zhuo, Peng Gao, Sheng Xia, Wenze Liu, Xiangyu Yue, Yi Xin","submitted_at":"2024-10-14T13:49:06Z","abstract_excerpt":"We introduce a new paradigm for AutoRegressive (AR) image generation, termed Set AutoRegressive Modeling (SAR). SAR generalizes the conventional AR to the next-set setting, i.e., splitting the sequence into arbitrary sets containing multiple tokens, rather than outputting each token in a fixed raster order. To accommodate SAR, we develop a straightforward architecture termed Fully Masked Transformer. We reveal that existing AR variants correspond to specific design choices of sequence order and output intervals within the SAR framework, with AR and Masked AR (MAR) as two extreme instances. Not"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10511","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/2410.10511/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":"2410.10511","created_at":"2026-07-05T09:20:17.321164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10511v1","created_at":"2026-07-05T09:20:17.321164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10511","created_at":"2026-07-05T09:20:17.321164+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZA3UDX4RF3P","created_at":"2026-07-05T09:20:17.321164+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZA3UDX4RF3P2PCH","created_at":"2026-07-05T09:20:17.321164+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZA3UDX4","created_at":"2026-07-05T09:20:17.321164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00371","citing_title":"MEPA: Multi-Scale Representation Alignment for Visual Autoregressive Modeling with Mixture of Experts","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD","json":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD.json","graph_json":"https://pith.science/api/pith-number/EZA3UDX4RF3P2PCHRKXHYGJUGD/graph.json","events_json":"https://pith.science/api/pith-number/EZA3UDX4RF3P2PCHRKXHYGJUGD/events.json","paper":"https://pith.science/paper/EZA3UDX4"},"agent_actions":{"view_html":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD","download_json":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD.json","view_paper":"https://pith.science/paper/EZA3UDX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10511&json=true","fetch_graph":"https://pith.science/api/pith-number/EZA3UDX4RF3P2PCHRKXHYGJUGD/graph.json","fetch_events":"https://pith.science/api/pith-number/EZA3UDX4RF3P2PCHRKXHYGJUGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD/action/storage_attestation","attest_author":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD/action/author_attestation","sign_citation":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD/action/citation_signature","submit_replication":"https://pith.science/pith/EZA3UDX4RF3P2PCHRKXHYGJUGD/action/replication_record"}},"created_at":"2026-07-05T09:20:17.321164+00:00","updated_at":"2026-07-05T09:20:17.321164+00:00"}