{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A4NLSGG3CJJDGVNKWZA4HMDUQV","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":"5a3f4775bfd8815ff410a257b1bbe1270add412a49c732ac0f1f69f8c0ca855b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T17:51:04Z","title_canon_sha256":"f37ca8f7e51b60ff605751c4a4e2ae48e6994f9e3895f2899d0a6684d3b77caa"},"schema_version":"1.0","source":{"id":"2409.16280","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16280","created_at":"2026-07-05T09:11:18Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16280v1","created_at":"2026-07-05T09:11:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16280","created_at":"2026-07-05T09:11:18Z"},{"alias_kind":"pith_short_12","alias_value":"A4NLSGG3CJJD","created_at":"2026-07-05T09:11:18Z"},{"alias_kind":"pith_short_16","alias_value":"A4NLSGG3CJJDGVNK","created_at":"2026-07-05T09:11:18Z"},{"alias_kind":"pith_short_8","alias_value":"A4NLSGG3","created_at":"2026-07-05T09:11:18Z"}],"graph_snapshots":[{"event_id":"sha256:95f089fc66a39692d7f1f5a6a92259e3b1de7bf3edb5212690c881b2891ad513","target":"graph","created_at":"2026-07-05T09:11:18Z","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/2409.16280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for both text and visual generation. In this paper, we propose to study a simple idea: share one transformer for both autoregression and diffusion. The feasibility comes from two main aspects: (i) Transformer is successfully applied to diffusion for visual generation, and (ii) transformer training for autoregression and diffusion is very similar, and the differenc","authors_text":"Chuyang Zhao, Errui Ding, Haocheng Feng, Jingdong Wang, Wenhao Wang, Xinyan Xiao, Yifan Sun, Yuxing Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T17:51:04Z","title":"MonoFormer: One Transformer for Both Diffusion and Autoregression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16280","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:d8a29c2352e7f16f617d99b4fd21483ba16306c7c74f7783dc90f11e3ba96c0a","target":"record","created_at":"2026-07-05T09:11:18Z","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":"5a3f4775bfd8815ff410a257b1bbe1270add412a49c732ac0f1f69f8c0ca855b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T17:51:04Z","title_canon_sha256":"f37ca8f7e51b60ff605751c4a4e2ae48e6994f9e3895f2899d0a6684d3b77caa"},"schema_version":"1.0","source":{"id":"2409.16280","kind":"arxiv","version":1}},"canonical_sha256":"071ab918db12523355aab641c3b074855510b6977f2508257528742f46cf4b9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"071ab918db12523355aab641c3b074855510b6977f2508257528742f46cf4b9f","first_computed_at":"2026-07-05T09:11:18.378056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:18.378056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBJJ0nn9GWZFZf5e3gPg39l0hsUpN1E04TR0SFNCj1MMhsBY47rCy4sWPEdEAYZd1h2epIiN6xN5kl2FVVN5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:18.378588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16280","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8a29c2352e7f16f617d99b4fd21483ba16306c7c74f7783dc90f11e3ba96c0a","sha256:95f089fc66a39692d7f1f5a6a92259e3b1de7bf3edb5212690c881b2891ad513"],"state_sha256":"81c54bbfa5285ef2fb5ec05d57ce26cbed5204830f6a866f1d5d6d0da7bda270"}