{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2O74O6U5WGWUWJLRPO3DQFB7JB","short_pith_number":"pith:2O74O6U5","canonical_record":{"source":{"id":"2410.08159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:41:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0987dbc1891e5cc8027a62d4cbfca13f201e1f3723982416751f01bbd421d3fb","abstract_canon_sha256":"f99de061ff28bf6161aa2b2e2452b5ad2adfbdcbb74e0e427d041acb97e4e6db"},"schema_version":"1.0"},"canonical_sha256":"d3bfc77a9db1ad4b25717bb638143f48472ba5f51737089d72d6773726bd6c70","source":{"kind":"arxiv","id":"2410.08159","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08159","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08159v2","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08159","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"2O74O6U5WGWU","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"2O74O6U5WGWUWJLR","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"2O74O6U5","created_at":"2026-07-05T10:04:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2O74O6U5WGWUWJLRPO3DQFB7JB","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:41:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0987dbc1891e5cc8027a62d4cbfca13f201e1f3723982416751f01bbd421d3fb","abstract_canon_sha256":"f99de061ff28bf6161aa2b2e2452b5ad2adfbdcbb74e0e427d041acb97e4e6db"},"schema_version":"1.0"},"canonical_sha256":"d3bfc77a9db1ad4b25717bb638143f48472ba5f51737089d72d6773726bd6c70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:18.493505Z","signature_b64":"DWx3zaw2lklhLFHnc6EtY+hKb/Isb6aokT2g8IYBMox1P0J6aDMhXvzxr2+jk4S1E9p0l4drh+dIu4B/XhVfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3bfc77a9db1ad4b25717bb638143f48472ba5f51737089d72d6773726bd6c70","last_reissued_at":"2026-07-05T10:04:18.493018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:18.493018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08159","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yA6N+1cMlNLby0kbxOxu0jhLNZeWNfHIK4yzsNeRJWIlwsI+rwBxRTNQb7WpOlmxlwTOdQ2N5QujnrB5FBUoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:55:34.727554Z"},"content_sha256":"d770c2407a068b025cf02218c3c676f34a4ee2161cb180cf257bb1f40154f1a0","schema_version":"1.0","event_id":"sha256:d770c2407a068b025cf02218c3c676f34a4ee2161cb180cf257bb1f40154f1a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2O74O6U5WGWUWJLRPO3DQFB7JB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Dinghuai Zhang, Jiatao Gu, Josh Susskind, Navdeep Jaitly, Qihang Zhang, Shuangfei Zhai, Yizhe Zhang, Yuyang Wang","submitted_at":"2024-10-10T17:41:54Z","abstract_excerpt":"Diffusion models have become the dominant approach for visual generation. They are trained by denoising a Markovian process which gradually adds noise to the input. We argue that the Markovian property limits the model's ability to fully utilize the generation trajectory, leading to inefficiencies during training and inference. In this paper, we propose DART, a transformer-based model that unifies autoregressive (AR) and diffusion within a non-Markovian framework. DART iteratively denoises image patches spatially and spectrally using an AR model that has the same architecture as standard langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08159","kind":"arxiv","version":2},"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/2410.08159/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:04:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DSvaswEjiKtUisjwDyDTovlJatem1Q82vG5qtgSYHDr2C9SwpQEqUFLNOrBSe1XPGd6ddOsBhTcdk/0fOjGpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:55:34.728067Z"},"content_sha256":"fc8f0cfc6221ac635a0487e5b51336329681f6f6820229b3812e7de7dd682eed","schema_version":"1.0","event_id":"sha256:fc8f0cfc6221ac635a0487e5b51336329681f6f6820229b3812e7de7dd682eed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2O74O6U5WGWUWJLRPO3DQFB7JB/bundle.json","state_url":"https://pith.science/pith/2O74O6U5WGWUWJLRPO3DQFB7JB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2O74O6U5WGWUWJLRPO3DQFB7JB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T22:55:34Z","links":{"resolver":"https://pith.science/pith/2O74O6U5WGWUWJLRPO3DQFB7JB","bundle":"https://pith.science/pith/2O74O6U5WGWUWJLRPO3DQFB7JB/bundle.json","state":"https://pith.science/pith/2O74O6U5WGWUWJLRPO3DQFB7JB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2O74O6U5WGWUWJLRPO3DQFB7JB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2O74O6U5WGWUWJLRPO3DQFB7JB","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":"f99de061ff28bf6161aa2b2e2452b5ad2adfbdcbb74e0e427d041acb97e4e6db","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:41:54Z","title_canon_sha256":"0987dbc1891e5cc8027a62d4cbfca13f201e1f3723982416751f01bbd421d3fb"},"schema_version":"1.0","source":{"id":"2410.08159","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08159","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08159v2","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08159","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"2O74O6U5WGWU","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"2O74O6U5WGWUWJLR","created_at":"2026-07-05T10:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"2O74O6U5","created_at":"2026-07-05T10:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:fc8f0cfc6221ac635a0487e5b51336329681f6f6820229b3812e7de7dd682eed","target":"graph","created_at":"2026-07-05T10:04:18Z","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/2410.08159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have become the dominant approach for visual generation. They are trained by denoising a Markovian process which gradually adds noise to the input. We argue that the Markovian property limits the model's ability to fully utilize the generation trajectory, leading to inefficiencies during training and inference. In this paper, we propose DART, a transformer-based model that unifies autoregressive (AR) and diffusion within a non-Markovian framework. DART iteratively denoises image patches spatially and spectrally using an AR model that has the same architecture as standard langu","authors_text":"Dinghuai Zhang, Jiatao Gu, Josh Susskind, Navdeep Jaitly, Qihang Zhang, Shuangfei Zhai, Yizhe Zhang, Yuyang Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:41:54Z","title":"DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08159","kind":"arxiv","version":2},"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:d770c2407a068b025cf02218c3c676f34a4ee2161cb180cf257bb1f40154f1a0","target":"record","created_at":"2026-07-05T10:04:18Z","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":"f99de061ff28bf6161aa2b2e2452b5ad2adfbdcbb74e0e427d041acb97e4e6db","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:41:54Z","title_canon_sha256":"0987dbc1891e5cc8027a62d4cbfca13f201e1f3723982416751f01bbd421d3fb"},"schema_version":"1.0","source":{"id":"2410.08159","kind":"arxiv","version":2}},"canonical_sha256":"d3bfc77a9db1ad4b25717bb638143f48472ba5f51737089d72d6773726bd6c70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3bfc77a9db1ad4b25717bb638143f48472ba5f51737089d72d6773726bd6c70","first_computed_at":"2026-07-05T10:04:18.493018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:18.493018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DWx3zaw2lklhLFHnc6EtY+hKb/Isb6aokT2g8IYBMox1P0J6aDMhXvzxr2+jk4S1E9p0l4drh+dIu4B/XhVfAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:18.493505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08159","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d770c2407a068b025cf02218c3c676f34a4ee2161cb180cf257bb1f40154f1a0","sha256:fc8f0cfc6221ac635a0487e5b51336329681f6f6820229b3812e7de7dd682eed"],"state_sha256":"39f3121c94b949bbed7f82a92ea218720678fe4ca627c306bb0d51ec45b9899f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YeOdHgNUl4e7iEFQxfi6N+gT4kAvgmsP2VZZKcIk19qppCavDiVOoZ0ornAgOQ/j0UBMHjapmwJ7D7hdIDB1AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:55:34.732781Z","bundle_sha256":"3e3e729c95f607309b7b892e009866a712381ee52db45646ecee61ff70651d9b"}}