{"as_of":"2026-08-19T20:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b9ddf301fcab8445cf420085d64066ec18bac034e4246e66ca2b8c748c8f908","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T17:28:10.698216Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.09438/citation-record","integrity":"/paper/2608.09438/integrity","json":"/paper/2608.09438/citation-record.json","paper":"/paper/2608.09438"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.395822Z","title":"Scalable diffusion models with transformers,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.395822Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:4876328107b4be995fb61a00a7307153be15f0cddb1c852944ca05885006e394","observation_id":"061bb80a-c590-4375-90b0-e3f8c620a997","resolution":{"observed_at":"2026-08-11T17:28:10.395822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.401656Z","title":"Diffusion models beat gans on image synthesis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.401656Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:b70759305d86672a3c4ab4d00b5090f8ca192be77758cfdab50cfe195695cdc5","observation_id":"251f7c84-6d6e-4e3a-b4e4-c28d71aa0bdc","resolution":{"observed_at":"2026-08-11T17:28:10.401656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.407116Z","title":"High- resolution image synthesis with latent diffusion models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.407116Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:78f91cd08fb5c503fde0d1a02952bfc37fea7d53326d0e92d75bc3d1431594c3","observation_id":"de54c5e0-0bf7-4f58-82ab-7f91154bc4e8","resolution":{"observed_at":"2026-08-11T17:28:10.407116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.595463Z","title":"Visionllama: A unified llama backbone for vision tasks,","venue":null,"work_id":"d4334a6c-c237-4817-914d-39b6333198a8","year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.412656Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:3606aceec7d3212df93c5023e63498da427298a2b09590a79724286a32797002","observation_id":"5ecc1ac5-e21d-4bd9-a239-a4adaea37b2f","resolution":{"observed_at":"2026-08-11T17:28:11.600923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08740","last_updated":"2024-09-23T15:59:41Z","snapshot_observed_at":"2026-08-18T20:56:40.841401Z","submitted_at":"2024-01-16T18:55:25Z","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08740","snapshot_observed_at":"2026-08-11T17:28:10.417934Z","title":"Sit: Exploring flow and diffusion-based gen- erative models with scalable interpolant transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.417934Z"},"links":{"cited_paper":"/paper/2401.08740","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:0091a9eabebd1fdc6041d1d1dcc7ede14e4b40fa53cdd3f900ff133294a8f062","observation_id":"3f0696c6-4660-4bf0-89cb-8c2041a364fe","resolution":{"observed_at":"2026-08-11T17:28:10.417934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12376","last_updated":"2024-10-15T02:51:00Z","snapshot_observed_at":"2026-08-18T14:41:50.960509Z","submitted_at":"2024-02-19T18:59:07Z","title":"FiT: Flexible Vision Transformer for Diffusion Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12376","snapshot_observed_at":"2026-08-11T17:28:10.423769Z","title":"Fit: Flexible vision transformer for diffusion model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.423769Z"},"links":{"cited_paper":"/paper/2402.12376","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:155aecb54df39fce142b6db25a6de5098c746c2c0ad698b3c588291c9933a5bb","observation_id":"5c3b62ea-04aa-4a51-8926-770b6c977864","resolution":{"observed_at":"2026-08-11T17:28:10.423769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.02730","last_updated":"2024-10-30T16:13:42Z","snapshot_observed_at":"2026-08-16T13:55:23.420832Z","submitted_at":"2024-05-04T18:27:29Z","title":"U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.02730","snapshot_observed_at":"2026-08-11T17:28:10.430901Z","title":"U-dits: Downsample tokens in u-shaped diffusion transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.430901Z"},"links":{"cited_paper":"/paper/2405.02730","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:7057f23a56f95e9a98651ae638fd67e6bd90624918ab388b965d6f7dd7628c9c","observation_id":"bc7b16dc-c0ac-46b1-bd7e-49fca75e54a7","resolution":{"observed_at":"2026-08-11T17:28:10.430901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17004","last_updated":"2024-03-25T17:59:35Z","snapshot_observed_at":"2026-08-17T21:58:24.442620Z","submitted_at":"2024-03-25T17:59:35Z","title":"SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer","version":1},"cited_work":{"arxiv_id":"2403.17004","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.17004","snapshot_observed_at":"2026-08-11T17:28:10.935647Z","title":"SD-DiT: Unleashing the Power of Self-supervised Discrimination in Diffusion Transformer","venue":"cs.CV","work_id":"88b0c4d1-2175-4b57-9298-06057877eca7","year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.437338Z"},"links":{"cited_paper":"/paper/2403.17004","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:135670509cbd84c14fb682e9a908bba61a7c5b8da91a205c73f2888a85bcea4f","observation_id":"0794aa2f-8f14-4b1e-a22d-8d6be3c961da","resolution":{"observed_at":"2026-08-11T17:28:10.943650Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.577543Z","title":"Fasterdit: Towards faster diffusion transformers training without architecture modification,","venue":null,"work_id":"4b5ac89c-7ad6-4011-8f14-a4d1b37aa77b","year":null},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.442614Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:5df9827f774deda900835d8bd54d15eba067b5e59a7616ba1ad47d0be2010c68","observation_id":"105c9fff-c547-4890-a506-c56eef937d1c","resolution":{"observed_at":"2026-08-11T17:28:11.583458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.447470Z","title":"Roformer: En- hanced transformer with rotary position embedding,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.447470Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:d8670513d1965c19a3f71dd76e6bbcb7ffaa7a2fdc1ee3c4e5e67ad32e78d876","observation_id":"507def2c-5769-4e7b-af3f-4ee686484d78","resolution":{"observed_at":"2026-08-11T17:28:10.447470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05202","last_updated":"2020-02-12T19:57:13Z","snapshot_observed_at":"2026-08-11T06:21:56.129166Z","submitted_at":"2020-02-12T19:57:13Z","title":"GLU Variants Improve Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05202","snapshot_observed_at":"2026-08-11T17:28:10.452729Z","title":"Glu variants improve transformer,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.452729Z"},"links":{"cited_paper":"/paper/2002.05202","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:d74716e5d1d07c5bb44308ebe70fe4b3ba810d9592fb3b32a478592468be8211","observation_id":"8b48fed9-7234-4260-8cab-63dbb8cd73ec","resolution":{"observed_at":"2026-08-11T17:28:10.452729Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.460303Z","title":"Scaling rectified flow transformers for high-resolution image synthesis,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.460303Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:5e4a225fe8e110f7adb8c4ea4222cf92360c5b1438f061c6a53fad09eafe33e2","observation_id":"e54686e1-e60c-4641-9687-a56b61026eee","resolution":{"observed_at":"2026-08-11T17:28:10.460303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00426","last_updated":"2023-12-29T16:42:08Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-30T16:18:00Z","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00426","snapshot_observed_at":"2026-08-11T17:28:10.471021Z","title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.471021Z"},"links":{"cited_paper":"/paper/2310.00426","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:80da051e54ccfe62933e3ae392c3a23547a8939b37c6077cb926cb571f91dd4c","observation_id":"d9ac4349-ff52-4e6e-b14e-aae591407678","resolution":{"observed_at":"2026-08-11T17:28:10.471021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04692","last_updated":"2024-03-17T16:59:25Z","snapshot_observed_at":"2026-08-16T14:11:52.899972Z","submitted_at":"2024-03-07T17:41:37Z","title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04692","snapshot_observed_at":"2026-08-11T17:28:10.476889Z","title":"Pixart-\\sigma: Weak-to-strong training of dif- fusion transformer for 4k text-to-image generation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.476889Z"},"links":{"cited_paper":"/paper/2403.04692","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:80eb333b53f51e0671b05a4acaefba1659c1525aa75e21c032740df275084f70","observation_id":"f9ae9c13-e2b3-401b-a033-d541c301d334","resolution":{"observed_at":"2026-08-11T17:28:10.476889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11831","last_updated":"2024-12-05T04:06:09Z","snapshot_observed_at":"2026-08-16T13:42:07.744224Z","submitted_at":"2024-06-17T17:59:43Z","title":"Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11831","snapshot_observed_at":"2026-08-11T17:28:10.483402Z","title":"Exploring the role of large language models in prompt encoding for diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.483402Z"},"links":{"cited_paper":"/paper/2406.11831","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:4f5bb4ef8c66f0e79453867a9a4985d4a1400d0493d8ffacb65b197685d9877f","observation_id":"e820df1c-10d1-48cf-bad1-ad64a454f49e","resolution":{"observed_at":"2026-08-11T17:28:10.483402Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08748","last_updated":"2024-05-14T16:33:25Z","snapshot_observed_at":"2026-07-06T18:14:16.386835Z","submitted_at":"2024-05-14T16:33:25Z","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.08748","snapshot_observed_at":"2026-08-11T17:28:10.489850Z","title":"Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chinese understanding,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.489850Z"},"links":{"cited_paper":"/paper/2405.08748","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:71aea3ebccc235ef5d958c25819268b10d9f150b251b445dd431a2be955317b5","observation_id":"afd46162-1fac-4e4e-986d-9b26b782e77b","resolution":{"observed_at":"2026-08-11T17:28:10.489850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.495350Z","title":"Elucidating the design space of diffusion-based generative models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.495350Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:1789dbbf0a87fbce9b120c358c215fccb93f27510e4314b4c41fdee81abed8ee","observation_id":"7317b5f6-4696-4ad3-9233-0a380e0d8100","resolution":{"observed_at":"2026-08-11T17:28:10.495350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.503141Z","title":"Analyzing and improving the training dynamics of diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.503141Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:bf663244716fbd5761b8c36222ad77ec1d4c01f7ace65405b94e6bffacd81ff4","observation_id":"de197934-a01c-4ce8-9818-7f0dcee8bff1","resolution":{"observed_at":"2026-08-11T17:28:10.503141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.506181Z","title":"Mole: En- hancing human-centric text-to-image diffusion via mixture of low-rank experts,","venue":null,"work_id":"5526ee5f-e2a1-4ba2-9a55-0911550a3a38","year":null},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.509275Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:457e15756fd0408a296dfc71576527423a0318606118481aa6606c54d838c16f","observation_id":"2be22698-9134-4eef-b249-2e715f53a515","resolution":{"observed_at":"2026-08-11T17:28:11.512504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.516365Z","title":"Squeeze-and-excitation networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.516365Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:fdfb23f6687e97ce745ef102590ccc5cd7609b8b259a2dca0877bc8211ce8aa9","observation_id":"87ff3248-00d9-47b4-a4d0-b950456f6adb","resolution":{"observed_at":"2026-08-11T17:28:10.516365Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.470650Z","title":"ImageNet Large Scale Visual Recognition Challenge,","venue":null,"work_id":"f22b3b68-fd9c-4624-b59e-38fbb3ede74c","year":2015},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.522562Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:9158266a068cdf2fc04c925101ba7e73b3773e313166fae2a6b4271a18ccb523","observation_id":"91e40c70-db90-4377-a6f3-c9c5648b9a7a","resolution":{"observed_at":"2026-08-11T17:28:11.476773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.532180Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.532180Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:7206c1f22e5b9d20a1fcc65b5dbb418af7735f180f5bee694566352d7a56892e","observation_id":"ccafd034-3784-4ff1-889e-e84ea4c2b207","resolution":{"observed_at":"2026-08-11T17:28:10.532180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-11T17:28:10.537502Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.537502Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:336c83aafb691c4f2001c159bf768ff906f62569d8b8fd8317163eb1bbbfa5fe","observation_id":"c19fe0f3-3aa8-48f3-b96c-f3d7ce0f7739","resolution":{"observed_at":"2026-08-11T17:28:10.537502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.437723Z","title":"Layoutdm: Transformer-based diffusion model for layout generation,","venue":null,"work_id":"2a2018cd-3725-4e17-964b-6a667a90d64a","year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.542807Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:675e021583a0365e44ce09ee6a4e0e8666fbaade2130c9f000cc799bd1cca50e","observation_id":"a52863e7-6876-4f6f-adca-f23f5c454a1e","resolution":{"observed_at":"2026-08-11T17:28:11.443939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.417463Z","title":"Masked diffusion trans- former is a strong image synthesizer,","venue":null,"work_id":"ae6dc9c8-3dd8-4121-82b1-ab360ea4e7e7","year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.547911Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:876a33a0a0e18373fe821d04a546604b0415516314c94e1c708ace263a854013","observation_id":"15b7a432-fbb3-47a8-ad03-87a8d59631e0","resolution":{"observed_at":"2026-08-11T17:28:11.424526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.396681Z","title":"Dit- 3d: Exploring plain diffusion transformers for 3d shape generation,","venue":null,"work_id":"0c3598ca-a332-4a05-a0e2-7396bc98ca70","year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.553685Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:ef9c8f47d5fc9342e54ae5f421e9126f80c53b0d8e9a860976fc3115a2a8d273","observation_id":"09d3f644-b9d8-4f65-9f54-1e98aa18e327","resolution":{"observed_at":"2026-08-11T17:28:11.402841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.375195Z","title":"Diffuser: efficient transformers with multi-hop attention diffusion for long sequences,","venue":null,"work_id":"a0bad31a-65fe-4018-a215-a580843bf275","year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.558832Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:67a139c65f582c8b006eb66e7025abb3bc7b78a1518f7cc6d322b0af8404a80d","observation_id":"19c2ac9f-712d-4e66-9faf-750b3569e1ea","resolution":{"observed_at":"2026-08-11T17:28:11.381371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.564858Z","title":"Latent diffusion transformer for probabilistic time series forecasting,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.564858Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:741e8525ee0d7f4a20a5fdffecca8980ea976018998f6ad178ddf0d49f6e9d7d","observation_id":"fd4c7915-d2a9-42fa-b001-f528e73d7015","resolution":{"observed_at":"2026-08-11T17:28:10.564858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.337232Z","title":"All are worth words: A vit backbone for diffusion models,","venue":null,"work_id":"6fe2a11a-e834-4983-813e-18a1eb8b6744","year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.571639Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:983e5d8e36fedb9b1726710ff8630f45addc785e49175b673cf08b487b6549d6","observation_id":"2680193e-7ff4-43a5-9651-5f72ea0b2730","resolution":{"observed_at":"2026-08-11T17:28:11.344359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.11633","last_updated":"2024-09-09T02:17:12Z","snapshot_observed_at":"2026-08-16T13:33:48.508986Z","submitted_at":"2024-07-16T11:55:23Z","title":"Scaling Diffusion Transformers to 16 Billion Parameters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.11633","snapshot_observed_at":"2026-08-11T17:28:10.577443Z","title":"Scaling diffusion transformers to 16 billion parameters,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.577443Z"},"links":{"cited_paper":"/paper/2407.11633","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:e65fde5ffdbf3f3bc02ccdbed1f377a3c5b91ed28a7f62b372fe3d237b7ee08f","observation_id":"a1f85d73-3157-4120-bf24-4a8da04d9465","resolution":{"observed_at":"2026-08-11T17:28:10.577443Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.313094Z","title":"Gentron: Diffusion transformers for image and video generation,","venue":null,"work_id":"6dc0759a-d3c6-4e42-a8e3-2fc7135314d6","year":2024},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.583147Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:c629af477c431db38318716a0f4131bcb85e9ad9f66a31f979e11395d0e34c1e","observation_id":"4c0fd045-4c5d-497a-bb18-a5593a0b96eb","resolution":{"observed_at":"2026-08-11T17:28:11.319253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.294789Z","title":"Dlt: Conditioned layout generation with joint discrete-continuous diffusion layout trans- former,","venue":null,"work_id":"1aaa4dd9-48a9-4126-a3bd-68219697f29a","year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.588496Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:6e28aa515996b73492470561c191b02b0745e2fd32bec7bfa0b16da59907a1af","observation_id":"ae7c37f3-ecfb-44e0-bc8d-6be1610439a2","resolution":{"observed_at":"2026-08-11T17:28:11.300516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.274440Z","title":"Scalable high-resolution pixel-space image synthesis JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 12 with hourglass diffusion transformers,","venue":null,"work_id":"bf49449f-e51c-4da2-a64d-f3b800fe195c","year":2021},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.593549Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:1fa3e9e6810bc80eb3568b8ba47c68d0dbd3c4b395cb5d0d9f2a8683b9a73484","observation_id":"895a01e5-0261-4da0-adb7-9dc54f4b0266","resolution":{"observed_at":"2026-08-11T17:28:11.280699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.02139","last_updated":"2024-08-29T03:09:40Z","snapshot_observed_at":"2026-08-19T17:10:29.872518Z","submitted_at":"2023-12-04T18:57:01Z","title":"DiffiT: Diffusion Vision Transformers for Image Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.02139","snapshot_observed_at":"2026-08-11T17:28:10.599022Z","title":"Diffit: Diffusion vision transformers for image generation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.599022Z"},"links":{"cited_paper":"/paper/2312.02139","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:e5b4fb52ec44d25b2b3751fadb462b5907161949867dcd71449b6be8ef925b88","observation_id":"61fc9032-92ce-4441-bfc0-f94dfcd8a9af","resolution":{"observed_at":"2026-08-11T17:28:10.599022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.255389Z","title":"A review on weight initialization strategies for neural networks,","venue":null,"work_id":"7ae49f40-4397-474d-b76b-faf72aef63f5","year":2022},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.604834Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:a8c80eff699cfd32e94eb56bb90ade2e437e5df33a19728187e0f3236726932b","observation_id":"58b0722d-5e34-410d-9706-972ca5d2ce00","resolution":{"observed_at":"2026-08-11T17:28:11.261375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.610119Z","title":"Understanding the difficulty of training deep feedforward neural networks,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.610119Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:57727b568d4c192b712d5d9324d04484cb1e93d1e73406834422d740dd9727a9","observation_id":"90a4af35-6bc0-49e4-ac6e-7a54a0294f4a","resolution":{"observed_at":"2026-08-11T17:28:10.610119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.224259Z","title":"Caffe: Convolutional architecture for fast feature embedding,","venue":null,"work_id":"ee6f995e-aa44-4c15-abcb-517d6af3c997","year":2014},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.615053Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:0e4e33844c06fed04535a265ad6da4a48ba3856f190cc5004ff9bb80e2722d9f","observation_id":"f595ad9f-c04e-4b75-adc4-545f25f2f0a3","resolution":{"observed_at":"2026-08-11T17:28:11.231253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.620289Z","title":"Rectified linear units improve restricted boltz- mann machines,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.620289Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:913e01bb33b835a94a4a464370d7b50a61587dd338b0606d3fa9e8b6a70be61a","observation_id":"a34fe535-60c4-4fbd-8ddb-9836132b9f37","resolution":{"observed_at":"2026-08-11T17:28:10.620289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.625337Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.625337Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:99d0cfef8f78ea3bcd31448dd554929b47996f186d6a9b48c3878c6dcdc51491","observation_id":"c1cc095d-5b98-4da8-adf7-f6ec233d2052","resolution":{"observed_at":"2026-08-11T17:28:10.625337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.02677","last_updated":"2018-04-30T21:53:41Z","snapshot_observed_at":"2026-08-09T05:23:26.365677Z","submitted_at":"2017-06-08T16:51:53Z","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.02677","snapshot_observed_at":"2026-08-11T17:28:10.630942Z","title":"Accurate, large minibatch sgd: Training imagenet in 1 hour,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.630942Z"},"links":{"cited_paper":"/paper/1706.02677","citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:783e5ba30b1ad059a57c041a257f4545e5a4928d3f64c59069b6515f5dc7a338","observation_id":"40c66c7a-a3c3-4c1c-9203-6212df09a8ab","resolution":{"observed_at":"2026-08-11T17:28:10.630942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.637180Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.637180Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:e782f26ba5416130e31e6aaaa18c8999285c83c22c0ab029bb4a3d83905314fe","observation_id":"a151ddb2-2731-40ba-bd41-1cc325918bb1","resolution":{"observed_at":"2026-08-11T17:28:10.637180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.642669Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.642669Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:f95913c96c6ee8e78fb14dab9cbabed3130774604ab6e870729e23dc33786174","observation_id":"134a75a0-7c9e-41d5-b10a-81d38524ac3d","resolution":{"observed_at":"2026-08-11T17:28:10.642669Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.647678Z","title":"Improved techniques for training gans,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.647678Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:239ff755b553c79f29545545f7f75b29ace2ce7212f9206f93c0e18d76618891","observation_id":"31802955-c79a-4cbf-88f8-606ffd796018","resolution":{"observed_at":"2026-08-11T17:28:10.647678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.653387Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.653387Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:2d140a250e3bf7b1dac6db6330b87df3250258602876be19ec774f39f04555c2","observation_id":"1d2ce698-cd38-444b-b357-9e47d87409e5","resolution":{"observed_at":"2026-08-11T17:28:10.653387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.658781Z","title":"Adding conditional control to text-to-image diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.658781Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:d74ffe861d064c2fcaeff17125346860e8ac78dfaaa217c5de7e2822a2cdbc3a","observation_id":"7cbb087e-8197-4b5a-bb17-50c2f75a3bfa","resolution":{"observed_at":"2026-08-11T17:28:10.658781Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.113578Z","title":"Generating images with sparse representations,","venue":null,"work_id":"04a84b94-2da0-42ed-9d2e-50f1b5d5d8cc","year":2021},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.663610Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:92eafe14352f7e62dff8c0cf75558d167cfe1471dc4f20cd9dac44693c5bafef","observation_id":"3417ffa1-5259-4da2-a92f-33387b4b5533","resolution":{"observed_at":"2026-08-11T17:28:11.119542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.093354Z","title":"Im- proved precision and recall metric for assessing generative models,","venue":null,"work_id":"975612d6-c8a6-4178-8f69-2d854045703b","year":2019},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.668649Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:4e2eaf6a4c1fcb98294593d6aa722829a83f9d483b7a324abb070e9f23cdf6d9","observation_id":"065a4afb-52ec-4918-b1ea-dffa9ba29b52","resolution":{"observed_at":"2026-08-11T17:28:11.099214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.674408Z","title":"Tiny imagenet visual recognition challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.674408Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:f25f17858cb76c0ae39c7230a40f76b249e3ca6518eb391958b326eb0a85f8a8","observation_id":"118883e8-95bd-4b2d-8d17-290a5fade379","resolution":{"observed_at":"2026-08-11T17:28:10.674408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.679517Z","title":"Stargan v2: Diverse image synthesis for multiple domains,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.679517Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:8e4112da127cccab75c6cbee3fa05453954ef9dd81e8af143a6253208fc05c6c","observation_id":"389130ee-8d74-40e7-9fdd-047d6a596db3","resolution":{"observed_at":"2026-08-11T17:28:10.679517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.047022Z","title":"Progressive growing of GANs for improved quality, stability, and variation,","venue":null,"work_id":"8b6c0974-0c63-4043-bff9-434eb3132adc","year":2018},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.686685Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:d3663e5490704d9e0a4c36438e58c7b8b36a73a12e04cb5e631ddfdf3acba3ad","observation_id":"216c6694-e4ad-4bdf-bee9-74b02eb57fa4","resolution":{"observed_at":"2026-08-11T17:28:11.052943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:10.692421Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.692421Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:0e3b68450c2d31ea89d214402db99ae3e909015f74f567a58800a35c7a57ac53","observation_id":"e13e0729-63b6-4a3f-a552-a72066a03088","resolution":{"observed_at":"2026-08-11T17:28:10.692421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:28:11.016907Z","title":"Computing higher order deriva- tives of matrix and tensor expressions,","venue":null,"work_id":"15fb645e-3157-421b-b2ec-728a62c02277","year":2018},"citing_paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T17:28:10.698216Z"},"links":{"citing_paper":"/paper/2608.09438"},"observation_digest":"sha256:44001ce78515a0b38bbfd77c6a334342b55fd1aea11892663dc6ede6d56b7c0c","observation_id":"a4632e3f-44c6-4a2c-9ca2-d589f0168fe9","resolution":{"observed_at":"2026-08-11T17:28:11.022420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.09438","last_updated":"2026-08-10T11:12:17Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T03:55:58.934123Z","submitted_at":"2026-08-10T11:12:17Z","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":33,"verified_exact":1,"verified_fuzzy":18},"total_outbound_references":52},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 0 inbound Pith citation observations for arXiv:2608.09438."}