{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PMFP7YDYIJ5GJEFGQJFWP2PC4Q","short_pith_number":"pith:PMFP7YDY","schema_version":"1.0","canonical_sha256":"7b0affe078427a6490a6824b67e9e2e417c1628b2a2f8511e33906bd7472f560","source":{"kind":"arxiv","id":"2506.07999","version":1},"attestation_state":"computed","paper":{"title":"MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Junhao Chen, Xiaochuang Han, Yulia Tsvetkov","submitted_at":"2025-06-09T17:59:01Z","abstract_excerpt":"Recent progress in multimodal generation has increasingly combined autoregressive (AR) and diffusion-based approaches, leveraging their complementary strengths: AR models capture long-range dependencies and produce fluent, context-aware outputs, while diffusion models operate in continuous latent spaces to refine high-fidelity visual details. However, existing hybrids often lack systematic guidance on how and why to allocate model capacity between these paradigms. In this work, we introduce MADFormer, a Mixed Autoregressive and Diffusion Transformer that serves as a testbed for analyzing AR-di"},"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":"2506.07999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2a3ff73c085b5e9550032115ad84f535ba7f54e28f1267ff2b25790dfc911c9e","abstract_canon_sha256":"d7207c57f60c46f05585fcbded9fdbb40e6879c47f181bb330fe3ec62e45a447"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:36.989822Z","signature_b64":"ZYL3ddjA0GHbqemfsrGepYQzdzGIvg4OmENI2ikAr7HuCbTNf06vx19gn69HKETPedLipneDdX8K6qpmLg4NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b0affe078427a6490a6824b67e9e2e417c1628b2a2f8511e33906bd7472f560","last_reissued_at":"2026-07-05T11:18:36.989434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:36.989434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Junhao Chen, Xiaochuang Han, Yulia Tsvetkov","submitted_at":"2025-06-09T17:59:01Z","abstract_excerpt":"Recent progress in multimodal generation has increasingly combined autoregressive (AR) and diffusion-based approaches, leveraging their complementary strengths: AR models capture long-range dependencies and produce fluent, context-aware outputs, while diffusion models operate in continuous latent spaces to refine high-fidelity visual details. However, existing hybrids often lack systematic guidance on how and why to allocate model capacity between these paradigms. In this work, we introduce MADFormer, a Mixed Autoregressive and Diffusion Transformer that serves as a testbed for analyzing AR-di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07999","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/2506.07999/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":"2506.07999","created_at":"2026-07-05T11:18:36.989491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07999v1","created_at":"2026-07-05T11:18:36.989491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07999","created_at":"2026-07-05T11:18:36.989491+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMFP7YDYIJ5G","created_at":"2026-07-05T11:18:36.989491+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMFP7YDYIJ5GJEFG","created_at":"2026-07-05T11:18:36.989491+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMFP7YDY","created_at":"2026-07-05T11:18:36.989491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q","json":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q.json","graph_json":"https://pith.science/api/pith-number/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/graph.json","events_json":"https://pith.science/api/pith-number/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/events.json","paper":"https://pith.science/paper/PMFP7YDY"},"agent_actions":{"view_html":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q","download_json":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q.json","view_paper":"https://pith.science/paper/PMFP7YDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07999&json=true","fetch_graph":"https://pith.science/api/pith-number/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/action/storage_attestation","attest_author":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/action/author_attestation","sign_citation":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/action/citation_signature","submit_replication":"https://pith.science/pith/PMFP7YDYIJ5GJEFGQJFWP2PC4Q/action/replication_record"}},"created_at":"2026-07-05T11:18:36.989491+00:00","updated_at":"2026-07-05T11:18:36.989491+00:00"}