{"as_of":"2026-08-09T18:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a7e34cd6e6c3323c5ca30a8194fbd8cbf9bec23e201aeaf62b4debdb9c28c604","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T18:04:46.887194Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2604.09022/citation-record","integrity":"/paper/2604.09022/integrity","json":"/paper/2604.09022/citation-record.json","paper":"/paper/2604.09022"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Baraniuk","venue":null,"work_id":"086c66c6-3bf2-449e-ba2d-06f78114a6a5","year":2023},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:88709930a8f4f35a7ce1b0ad65337b4f5eac79e514a76e901d17aa598f8d84c6","observation_id":"3104cc5f-9e76-45f7-b2f5-99dccbc30152","resolution":{"observed_at":"2026-05-17T07:21:38.689674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"8 Baraniuk","venue":null,"work_id":"ebe798d1-daee-49db-aa93-153f75af211e","year":2025},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:ae3b8fce7690a1d65c141592cb07c0b7d7cb3c4cb454299b6c40e1f62f3105f3","observation_id":"1e8ca63d-a4b3-45fd-83ff-76413125596c","resolution":{"observed_at":"2026-05-17T07:21:38.699359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Dragon: A large-scale dataset of realistic images generated by diffusion models","venue":null,"work_id":"e4c92156-65d1-4cd0-98fa-d393774d969f","year":2025},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:97386f90148f0c3b7cbc89be65eef580092bf20bd84c20526095372c1fea1147","observation_id":"6fd5c73e-9d7c-4844-9d6c-c44ee18c9306","resolution":{"observed_at":"2026-05-17T07:21:38.709532Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Objaverse: A universe of annotated 3d objects","venue":null,"work_id":"021adcad-3a7d-4029-90c5-27d352205962","year":2022},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:c6a929df4fa2ea9fff5612c2f5bc001d6c0f430c57e03802be3c4401cb9f8af9","observation_id":"b191cbc2-807b-4cfc-95c5-91c46cea66a7","resolution":{"observed_at":"2026-05-17T07:21:38.693369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Objaverse-xl: A universe of 10m+ 3d objects","venue":null,"work_id":"11ab0902-fe32-4f07-864a-190ab541a369","year":2023},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:fcbaad3e0cde533df0fe5d04b420d48bcc3b8dffa526a9e8caec0528cccd0012","observation_id":"aa7b56a9-7bff-41f9-ba4e-d7cea0cae811","resolution":{"observed_at":"2026-05-17T07:21:38.696454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"16bc314d-d452-48e2-9577-8b5628e34304","year":2009},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:89e83fbda86e5abdf78c537abdfb68fa09170008a2aa203871515a4ad3045260","observation_id":"47757f14-387f-4ed3-99d3-5650b15a7e8d","resolution":{"observed_at":"2026-05-17T07:21:38.702638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Blender- proc","venue":null,"work_id":"ed0349d0-8289-4c53-83ce-4e3d56eb237b","year":2019},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:a97ccdf039dbb18ac75d043e16c2d6f0ca2ed753032a160ec40a34eb15c959fe","observation_id":"2db19166-5933-4229-9c14-5c51f320617e","resolution":{"observed_at":"2026-05-17T07:21:38.683202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"The farthest point strategy for progressive image sampling.IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 6:1305– 15","venue":null,"work_id":"f9b4de69-9191-481d-a005-c9d7f32d2fec","year":1997},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:7517093286662dfea05d8ecaeddae3b77512016c99d573f3dbd700cc87d087f3","observation_id":"c6d59e4f-65cf-4387-9f49-bbeb9a8b5c7e","resolution":{"observed_at":"2026-05-17T07:21:38.552495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.08803","last_updated":"2025-05-10T22:42:29Z","snapshot_observed_at":"2026-08-07T15:48:11.044824Z","submitted_at":"2025-05-10T22:42:29Z","title":"Multi-modal Synthetic Data Training and Model Collapse: Insights from VLMs and Diffusion Models","version":1},"cited_work":{"arxiv_id":"2505.08803","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.08803","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multi-modal synthetic data training and model collapse: Insights from vlms and diffusion models","venue":null,"work_id":"464857f6-c358-4ef9-ab6a-05b9d3e00682","year":2025},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"cited_paper":"/paper/2505.08803","citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:6bd2554075b16eccd4d8e621c8eb5c8f170fb255f74803402d49882e40f53bfb","observation_id":"3fb4107f-cf0c-4bc3-b020-6a281999e315","resolution":{"observed_at":"2026-05-11T05:31:01.102097Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Unreal engine sun temple, open research content archive (orca)","venue":null,"work_id":"00e2722e-cfac-4b9f-9387-1d266395185c","year":2017},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:55e47fd95dc6f2a2ba1d6a240b5698df33db5e14f026067823f2b0c94f0c6c82","observation_id":"84658533-6d4c-4093-85e2-5258e00eb6e0","resolution":{"observed_at":"2026-05-17T07:21:38.672189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Uncurated image-text datasets: Shedding light on demographic bias","venue":null,"work_id":"2d6dca9a-d245-4d7d-b9bf-1cedde1b2ed9","year":2023},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:642749f46fff39ae0cfcc2f1f2dc0d44fffd541d9371515d4dd143655b1a65a2","observation_id":"89507979-40f3-4568-943c-9745341ce7ef","resolution":{"observed_at":"2026-05-17T07:21:38.676132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b58a19f7-4521-4faa-ad3f-e07563c0fbba","year":2024},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:02a5ebc8e311ca821f49bb31aec510bfd736042e639a7231293b8d245b74bf18","observation_id":"20a161aa-cd77-43ed-9371-b1698b6b3c25","resolution":{"observed_at":"2026-05-17T07:21:38.679491Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"a4d9ebaf-3dde-4704-bcec-918de9490f82","year":2022},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:7dedb14132c8b79bd7cc31b0e4fda91409c4ca4ae6517426ffbe4b7f2e99f0ca","observation_id":"a324d20e-2368-4cd1-bebb-70d012c0464b","resolution":{"observed_at":"2026-05-17T07:21:38.664457Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Transi- tioning from real to synthetic data: Quantifying the bias in model","venue":null,"work_id":"7b8f04b6-fcd6-4fb0-bff6-65b73bb83ae3","year":2021},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:ef11c72cd07e7f2ba0db07440ea25306f8d3545eace77d078557466801dccd6f","observation_id":"2c47eb69-83c7-47f8-b0cb-bddc6d31f5f6","resolution":{"observed_at":"2026-05-17T07:21:38.657723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Clipscore: A reference-free evaluation met- ric for image captioning","venue":null,"work_id":"908f7b06-4f9a-4849-bdb8-17567e453556","year":2022},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:b495d3ebc4721a418e06a0d0e00d388a44d8b0fbb807d886311c5f1e990517c6","observation_id":"c83accc4-c4f6-4f2f-9eb1-e603d957189f","resolution":{"observed_at":"2026-05-17T07:21:38.660885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-07-09T07:06:04.158752Z","title":"Denoising diffu- sion probabilistic models","venue":null,"work_id":"e2b19783-b26f-40e8-ad60-dbe8f7ca807e","year":2020},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:5b440ed716e36f4d159fa55151bfa863711baeeee54133211f02905ec4917b7d","observation_id":"09ac9ac2-df5b-4ed0-85a0-b894180e390c","resolution":{"observed_at":"2026-05-17T07:21:38.668279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Releasing re-laion-5b: transparent iteration on laion-5b with additional safety fixes.https://laion","venue":null,"work_id":"110aec37-dc23-46bf-b518-2adb348681ba","year":2024},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:41190e72775806d2476e38099277b529e6ec2c5670b798270588989bf6257fc6","observation_id":"36af3592-4bc5-4dee-8a17-e4019ed1a392","resolution":{"observed_at":"2026-05-17T07:21:38.642804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Lawrence Zitnick, and Piotr Doll ´ar","venue":null,"work_id":"6d5e843a-e6c2-4c18-a58d-4491db78de62","year":2015},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:5b058af55c07e7fce174e4eb373eae95beab2ebc54c33b804083898dd8c99833","observation_id":"353acc3c-9f82-4681-ac48-df61a033419f","resolution":{"observed_at":"2026-05-17T07:21:38.664138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Amazon lumberyard bistro, open research content archive (orca)","venue":null,"work_id":"0a6dce92-2dd4-40e4-9477-9dc2d8f1375b","year":2017},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:b9ac71bd256f846dd59a620f6d772952e39b9fe0c3b974d26942488dae83cdac","observation_id":"67ff8e91-13f9-4fef-8217-6879b1c8fc74","resolution":{"observed_at":"2026-05-17T07:21:38.650368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Scalable 3d captioning with pretrained models","venue":null,"work_id":"c050e6d5-7959-4ed6-b26c-eab2368cd4a7","year":2023},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:7f5e4a3d6fc22eb79ebf5fbacb81c908263becd186e2f06fa62e596195ab8049","observation_id":"0244a912-c9fa-4fd4-abcf-140979bf16cd","resolution":{"observed_at":"2026-05-17T07:21:38.585253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"View selec- tion for 3d captioning via diffusion ranking","venue":null,"work_id":"a491adde-58de-48a5-8ba9-31d2b1f7e076","year":2025},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:679091488cfe61020e49f6f397fcab6fbc7691ad9aa0eaf78a43e8e311f60349","observation_id":"170baad4-32e2-4cfc-a859-ce33d726761f","resolution":{"observed_at":"2026-05-17T07:21:38.686434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Improved denoising dif- fusion probabilistic models","venue":null,"work_id":"372131eb-2bf8-44a7-957c-c73cc0802c14","year":2021},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:95b60de9e8321436310a88dd391ea458d43524be6463ec17afd586cd2dd96966","observation_id":"3c656bcc-445c-45c2-af6c-78c481deb6e6","resolution":{"observed_at":"2026-05-17T07:21:38.706186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Nvidia emerald square, open research content archive (orca)","venue":null,"work_id":"ecd3b19d-7bfd-4c7f-8005-7bb8728fa74a","year":2017},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:1836b881e09b6b043a70b603a13bc5655c1d205841d3814ea0c6a221ea46f4e1","observation_id":"85e52c27-d256-42a3-82d8-745a76d1f0a6","resolution":{"observed_at":"2026-05-17T07:21:38.713003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Dinov2: Learning robust visual features with- out supervision","venue":null,"work_id":"9738848f-6d65-4fb6-860b-0b3a6e374262","year":2024},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:1ba7f3fa8dedb3b943ccfd793ee5fb47f45bf025f5026a2f80cac17e2209bfb6","observation_id":"a5823b36-3c91-4f5c-b1a5-bc511f3554f0","resolution":{"observed_at":"2026-05-17T07:21:38.657938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"The consis- tency critic: Correcting inconsistencies in generated images via reference-guided attentive alignment","venue":null,"work_id":"dbde4770-fa3d-4e69-9dd6-a9ff25ddd11b","year":2025},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:c4e04af951b96091b1462731680e3b246465c7547275debbf05a21603ae1b4c1","observation_id":"dfdb5474-31b3-4627-ac3b-ec320b21ac32","resolution":{"observed_at":"2026-05-17T07:21:38.601840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01952","last_updated":"2023-07-04T23:04:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-04T23:04:57Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":"2307.01952","doi":"10.48500/arxiv.2307.01952","metadata_source":"pith","pith_arxiv_id":"2307.01952","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","venue":"cs.CV","work_id":"8034c587-fba6-4941-87ba-c98f2ac962cb","year":2023},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:2c3e111f72edaf4fde9bd86baa64a72a92eeb5c75f2e292fc797a29f7aafe895","observation_id":"7c500413-7a1c-4575-980b-4211d4d6833b","resolution":{"observed_at":"2026-05-11T05:31:01.111398Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":"0083ae45-e2d1-4c2e-88b2-508ed85f3557","year":2021},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:d43a262916268549b6da3cefe52ea05c97b19b7d351faf718da51087d172e3e6","observation_id":"c747279c-27a1-4e18-9ff8-4cda3ecd9efe","resolution":{"observed_at":"2026-05-17T07:21:38.661081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Richter, Vibhav Vineet, Stefan Roth, and Vladlen Koltun","venue":null,"work_id":"012f29df-3be0-40df-94d9-9fd33fa998e1","year":2016},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:922d4562e6efcfe300ce5402bf442fa2139da3a4fcc51aa0eb2787b2f27a4644","observation_id":"92be0995-1298-44e0-bf8b-ce589a2a2623","resolution":{"observed_at":"2026-05-17T07:21:38.647447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":"e0839a6d-7f1f-40bb-8608-306bf898e823","year":2022},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:e25d75a502b9c4475e68bbfe5b1b1c906ebd884cea7027c289c3a9eb0b93da76","observation_id":"2c191abf-c538-4360-a309-f4f8ee30c4f7","resolution":{"observed_at":"2026-05-17T07:21:38.619861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"9d6af5a7-12c5-4070-9dfa-d59edea7e0c6","year":null},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:76e9ffb2d9529c989570c9ef7ad182e9808eef2d49d0b7adc0b3bb8dbd90671e","observation_id":"7cf14e9d-50ba-44b9-91cb-47ff7e54213c","resolution":{"observed_at":"2026-05-17T07:21:38.597866Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho, David J Fleet, and Mohammad Norouzi","venue":null,"work_id":"aa3e175b-40e6-4b1c-8215-5811fb089e26","year":2022},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:eab329e84e4013d6ba5db4ed8b987a2229fa1ad6e9ffa7e831fbe941fc37789f","observation_id":"8a964409-9bb2-4f88-a588-a07eeafcd189","resolution":{"observed_at":"2026-05-17T07:21:38.628284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Using dif- fusion models to generate synthetic labelled data for medical image segmentation","venue":null,"work_id":"db6fdda9-e064-4f42-b836-0dc5fa2fb42c","year":2024},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:e5365bf6ad23ef6f36193be64cdee7a9c3f3205c3d39fd25294d493328213a19","observation_id":"9385dc3f-33f7-4792-9494-8f5b0941bb4c","resolution":{"observed_at":"2026-05-17T07:21:38.582015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Laion-aesthetics.https : / / laion.ai/blog/laion-aesthetics/","venue":null,"work_id":"e8f4fe6e-7219-45ab-b4b9-879359b042f2","year":2022},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:5e4793ef0027df10c2985178035b6ad5480b7dcf9ab653a51edd48cb1f81a0e4","observation_id":"109ce520-7816-464a-8ecf-1022c1e641eb","resolution":{"observed_at":"2026-05-17T07:21:38.654030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models","venue":null,"work_id":"c84620a1-3070-4f3a-8042-b700713e0b79","year":2022},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:075bc77f2164b9951074114c2a5ad2b2d740a336e0d9d62c1484cae4f01a2400","observation_id":"74375ac9-7734-46af-b618-5bd84b31d8dd","resolution":{"observed_at":"2026-05-17T07:21:38.626917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Conceptual captions: A cleaned, hypernymed, im- age alt-text dataset for automatic image captioning","venue":null,"work_id":"25f27af6-3211-437f-9300-3de8e0a0b16d","year":2018},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:2c0bc44cdfabe75a98b57497acf6dd72db0e8a67820f95378588338c0a18f01c","observation_id":"acfa6a4c-48ef-4da9-b66f-2a8b92ee88a4","resolution":{"observed_at":"2026-05-17T07:21:38.634241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"The curse of recur- sion: Training on generated data makes models forget","venue":null,"work_id":"05c64b87-51fa-4246-8bb5-fc884f311d13","year":2024},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:3873c6172ac9eb2e9d6d81a391b317233c24814575d1e66bbd2e006d9f109e0c","observation_id":"82c93205-fa42-4cf6-ac80-e3d05472ab41","resolution":{"observed_at":"2026-05-17T07:21:38.675892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Qwen3 technical report","venue":null,"work_id":"f2cfcb40-fa0f-4c13-9929-97aee2a10ea7","year":2025},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:c6acdc330b8e60df9b31d471d95b064ec47aa0eb0ef11f699d49a0f5426f8174","observation_id":"7c39f8c9-ea8d-4606-862a-d6f358571879","resolution":{"observed_at":"2026-05-17T07:21:38.618848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Falling things: A synthetic dataset for 3d object detection and pose estimation","venue":null,"work_id":"a465e875-8aa7-4aa2-b2d2-ef76254f076a","year":2018},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:a45f76083e73c4cb183a943f1ed0696cc18622f9657b9b972cd26126eebc92b6","observation_id":"5d24e411-4dbb-43ba-a504-567043d32d35","resolution":{"observed_at":"2026-05-17T07:21:38.592310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Wang, Evan Montoya, David Munechika, Haoyang Yang, Benjamin Hoover, and Duen Horng Chau","venue":null,"work_id":"67425084-d5ed-4286-83f9-09e5b5a960ba","year":2023},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:6136e1cecbcf73571d965b035a39f6c46793ef815353b489492579e5ad6487ba","observation_id":"b054d564-82bc-4a93-9bda-b8c63608c082","resolution":{"observed_at":"2026-05-17T07:21:38.574208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"Datasetdm: Synthesizing data with perception anno- tations using diffusion models","venue":null,"work_id":"4bd3a521-4721-4730-b60c-3cdfb4b3ae95","year":2023},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:1e5d59b9ec5e32272dfe89394ef62e07cda142fb0fe1de83601feae0133f0a63","observation_id":"6d4a5f3d-3451-4e9c-8127-242030ba26ff","resolution":{"observed_at":"2026-05-17T07:21:38.673023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"GOOD: <brief factual reason>","venue":null,"work_id":"22832d5d-bddb-4396-be65-1b21c25d54e7","year":2023},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:9c3c9e349c00d00b39e310ddb510b89fc597ba1d6e29011d81f1f8175a16a843","observation_id":"8c12fd9d-314c-40c2-bb23-c88e9e5e62ab","resolution":{"observed_at":"2026-05-17T07:21:38.569963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"- BAD if the frame is dominated by a single surface/part (e.g., cheek, wall, texture) without context","venue":null,"work_id":"9e0f1a40-8b40-484d-93b4-5132a6fd1b91","year":null},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:b000e82460165d9bd349197d5e9e6088ea3bc3870fde6eabe7276f909b3d3d72","observation_id":"6e8abaf8-9e7b-474e-89e7-c86891d870e3","resolution":{"observed_at":"2026-05-17T07:21:38.577929Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"9d61a1f2-e5e3-4397-9272-faeae2ee9575","year":null},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:4d433c1f7db1a72e59a1a020f0e844b49a71d60ef00b698a07ba4acd75e8ff9e","observation_id":"36c96138-0058-4496-8bcb-d5c3be34f584","resolution":{"observed_at":"2026-05-17T07:21:38.590169Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"3b84e031-d38f-4f96-b270-da189c616bc0","year":null},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:48ba0aaf8305b67c0992e8899a4e12e52862d8a7b07998414e2a7a4e1624fad0","observation_id":"f6d56709-dbac-44fd-a25f-30d7b50a3d39","resolution":{"observed_at":"2026-05-17T07:21:38.670171Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-06-05T21:23:00.469572Z","title":"close-up of a clock face","venue":null,"work_id":"32b06b40-0566-41fa-b6ff-31b6b8cd53b1","year":null},"citing_paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-10T18:04:46.887194Z"},"links":{"citing_paper":"/paper/2604.09022"},"observation_digest":"sha256:189453721d72bea7e03eaad6b53571bf0b68cd2f9a4c6deeefa951f8ce3f6422","observation_id":"47693bce-b6a9-4fab-8668-23547ef8c881","resolution":{"observed_at":"2026-05-17T07:21:38.654269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.09022","last_updated":"2026-04-10T06:36:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T22:57:59.555972Z","submitted_at":"2026-04-10T06:36:38Z","title":"BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":2,"verified_fuzzy":38},"total_outbound_references":45},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2604.09022."}