{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PMFP7YDYIJ5GJEFGQJFWP2PC4Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d7207c57f60c46f05585fcbded9fdbb40e6879c47f181bb330fe3ec62e45a447","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:01Z","title_canon_sha256":"2a3ff73c085b5e9550032115ad84f535ba7f54e28f1267ff2b25790dfc911c9e"},"schema_version":"1.0","source":{"id":"2506.07999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07999","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07999v1","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07999","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"PMFP7YDYIJ5G","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"PMFP7YDYIJ5GJEFG","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"PMFP7YDY","created_at":"2026-07-05T11:18:36Z"}],"graph_snapshots":[{"event_id":"sha256:ece587f12b8e8dbbc870582f95abe58de6f0f221fb99b8591f0fd7176f391ce9","target":"graph","created_at":"2026-07-05T11:18:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.07999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Junhao Chen, Xiaochuang Han, Yulia Tsvetkov","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:01Z","title":"MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07999","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6a47a5d38d94ebbfb60df0f59d9ccaee4493e4a8024c4009c842d8f50d6976ee","target":"record","created_at":"2026-07-05T11:18:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d7207c57f60c46f05585fcbded9fdbb40e6879c47f181bb330fe3ec62e45a447","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-09T17:59:01Z","title_canon_sha256":"2a3ff73c085b5e9550032115ad84f535ba7f54e28f1267ff2b25790dfc911c9e"},"schema_version":"1.0","source":{"id":"2506.07999","kind":"arxiv","version":1}},"canonical_sha256":"7b0affe078427a6490a6824b67e9e2e417c1628b2a2f8511e33906bd7472f560","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b0affe078427a6490a6824b67e9e2e417c1628b2a2f8511e33906bd7472f560","first_computed_at":"2026-07-05T11:18:36.989434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:36.989434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZYL3ddjA0GHbqemfsrGepYQzdzGIvg4OmENI2ikAr7HuCbTNf06vx19gn69HKETPedLipneDdX8K6qpmLg4NAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:36.989822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a47a5d38d94ebbfb60df0f59d9ccaee4493e4a8024c4009c842d8f50d6976ee","sha256:ece587f12b8e8dbbc870582f95abe58de6f0f221fb99b8591f0fd7176f391ce9"],"state_sha256":"53a6bb8bf591f3a8ee08f1819f0b7bc8dd3a6b3de36b45265a4647c7720b2fc9"}