{"as_of":"2026-08-20T18:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b7e7349712f6c7ac543db4bf89d64511fd9bd3df3059ddcf523c41e70c53da53","coverage":[{"denominator":77,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":77,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:25:31.306591Z","state":"measured"},{"denominator":85,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":85,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":8,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":8,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T10:19:54.482983Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T10:11:01.756825Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07447","snapshot_observed_at":"2026-08-05T10:19:54.482983Z","title":"Unified continuous gener- ative models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.04394","last_updated":"2025-09-04T17:05:59Z","snapshot_observed_at":"2026-08-16T13:24:04.947329Z","submitted_at":"2025-09-04T17:05:59Z","title":"Transition Models: Rethinking the Generative Learning Objective","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T10:19:54.482983Z"},"links":{"cited_paper":"/paper/2505.07447","citing_paper":"/paper/2509.04394"},"observation_digest":"sha256:c9267c62237e5594d38e16f99c3d0afb92905d70c46b6b6b3ac84a6852b7febb","observation_id":"013941b4-868a-44bf-966b-d9b4378790f2","resolution":{"observed_at":"2026-08-05T10:19:54.482983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07447","snapshot_observed_at":"2026-08-03T10:35:06.599060Z","title":"Unified continuous generative models.arXiv preprint arXiv:2505.07447, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.09881","last_updated":"2026-07-09T22:49:12Z","snapshot_observed_at":"2026-08-09T17:44:11.904091Z","submitted_at":"2026-01-14T21:30:03Z","title":"Transition Matching Distillation for Fast Video Generation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T10:35:06.599060Z"},"links":{"cited_paper":"/paper/2505.07447","citing_paper":"/paper/2601.09881"},"observation_digest":"sha256:8e3e0d8af809a28a44f36ad7047588b0c834090a0881de9ef92bceca565b1db5","observation_id":"0611a257-3859-4b29-a303-08abf920d6f7","resolution":{"observed_at":"2026-08-03T10:35:06.599060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07447","snapshot_observed_at":"2026-08-03T06:33:25.026644Z","title":"vt(xt|x)−F θ(xt;t, s) + (s−t)· d dt Fθ− (xt;t, s) 2 2 # =∇ θE","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2601.22679","last_updated":"2026-06-20T05:34:10Z","snapshot_observed_at":"2026-08-18T01:16:55.110539Z","submitted_at":"2026-01-30T07:51:55Z","title":"Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation","version":2},"reference_index":6851,"source":"pdf_text","source_observed_at":"2026-08-03T06:33:25.026644Z"},"links":{"cited_paper":"/paper/2505.07447","citing_paper":"/paper/2601.22679"},"observation_digest":"sha256:e65db6b37648b159bf89b2e54eb3dd6d51b556a375ed338a856764c9a8fa11ef","observation_id":"df2a2ba1-251c-4ded-85c3-2da0c3cdb4e2","resolution":{"observed_at":"2026-08-03T06:33:25.026644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"cited_work":{"arxiv_id":"2505.07447","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.07447","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"GitHub repository","venue":null,"work_id":"61a75e54-e7b0-46ad-9379-c1a66f430487","year":null},"citing_paper":{"arxiv_id":"2604.12322","last_updated":"2026-04-14T05:54:33Z","snapshot_observed_at":"2026-08-15T01:51:39.927374Z","submitted_at":"2026-04-14T05:54:33Z","title":"Self-Adversarial One Step Generation via Condition Shifting","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T15:37:36.994169Z"},"links":{"cited_paper":"/paper/2505.07447","citing_paper":"/paper/2604.12322"},"observation_digest":"sha256:34fbdf1c4eaad1b9d382a374857946e02c393aed4c0ad2a38d6bb04358924876","observation_id":"7b194ae7-4857-420d-9e05-34282f6b6f50","resolution":{"observed_at":"2026-05-11T10:11:01.760247Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"cited_work":{"arxiv_id":"2505.07447","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.07447","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"GitHub repository","venue":null,"work_id":"61a75e54-e7b0-46ad-9379-c1a66f430487","year":null},"citing_paper":{"arxiv_id":"2604.20796","last_updated":"2026-04-22T17:20:42Z","snapshot_observed_at":"2026-08-17T00:56:18.717007Z","submitted_at":"2026-04-22T17:20:42Z","title":"LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-10T00:49:38.156237Z"},"links":{"cited_paper":"/paper/2505.07447","citing_paper":"/paper/2604.20796"},"observation_digest":"sha256:b870432c3c03b383ba324b236b43c3d7be9cb6d947a72609c5ed4bcdcee237d6","observation_id":"acf92aee-f3a4-4b3a-8348-b4d9862dfa14","resolution":{"observed_at":"2026-05-10T00:49:48.322712Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07447","snapshot_observed_at":"2026-08-01T15:49:34.306071Z","title":"Unified continuous generative models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18198","last_updated":"2026-07-20T17:38:12Z","snapshot_observed_at":"2026-08-20T07:41:31.919026Z","submitted_at":"2026-07-20T17:38:12Z","title":"Three-Body Scattering for Generative Modeling","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-01T15:49:34.306071Z"},"links":{"cited_paper":"/paper/2505.07447","citing_paper":"/paper/2607.18198"},"observation_digest":"sha256:41bbe17a5b003952f5089012837d8739cf75c6aa679da051d833a94b8ad538c4","observation_id":"429aa4a3-ea4b-46be-b6f0-ba7e3a6cc9b4","resolution":{"observed_at":"2026-08-01T15:49:34.306071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07447","snapshot_observed_at":"2026-07-30T18:58:28.186475Z","title":"arXiv preprint arXiv:2505.07447 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26860","last_updated":"2026-07-29T12:44:19Z","snapshot_observed_at":"2026-08-12T23:39:20.547745Z","submitted_at":"2026-07-29T12:44:19Z","title":"Amortized Moment Matching for Visual Generation","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-07-30T18:58:28.186475Z"},"links":{"cited_paper":"/paper/2505.07447","citing_paper":"/paper/2607.26860"},"observation_digest":"sha256:866bd08ce9cce58122243a66e9d3e720e0463b89a7eb83c38895204b3cece6c8","observation_id":"e2f72065-b2b4-44a6-861b-4b6816f0ab1a","resolution":{"observed_at":"2026-07-30T18:58:28.186475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07447","snapshot_observed_at":"2026-08-04T06:04:05.398635Z","title":"arXiv preprint arXiv:2505.07447 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.02502","last_updated":"2026-08-03T17:04:43Z","snapshot_observed_at":"2026-08-18T14:03:12.886032Z","submitted_at":"2026-08-03T17:04:43Z","title":"CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T06:04:05.398635Z"},"links":{"cited_paper":"/paper/2505.07447","citing_paper":"/paper/2608.02502"},"observation_digest":"sha256:d63d3fbf9f5aa19d7ae0051e24cf7cb0781281b77fbe108d97998c1cb69a24fe","observation_id":"52574316-9c96-4a09-993e-de09bc29a79e","resolution":{"observed_at":"2026-08-04T06:04:05.398635Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.07447/citation-record","integrity":"/paper/2505.07447/integrity","json":"/paper/2505.07447/citation-record.json","paper":"/paper/2505.07447"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:30.971580Z","title":"All are worth words: A vit backbone for diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:30.971580Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:bc167de2348a599a539c41f5395fd15a0b13d6a392992a76e6136ee7520d7670","observation_id":"76fce76b-5633-41f1-88b1-96d4e4f2f802","resolution":{"observed_at":"2026-08-15T22:25:30.971580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.11096","last_updated":"2019-02-25T21:32:06Z","snapshot_observed_at":"2026-07-06T07:04:57.275371Z","submitted_at":"2018-09-28T15:38:49Z","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.11096","snapshot_observed_at":"2026-08-15T22:25:30.977134Z","title":"Large scale gan training for high fidelity natural image synthesis","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:30.977134Z"},"links":{"cited_paper":"/paper/1809.11096","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:eda2b07b513afda694d381d633cae62893e16d3bd464cdb3d2fa56d4c032a166","observation_id":"42fe7a0f-c2a7-4ab3-8a37-9a5b611db4c6","resolution":{"observed_at":"2026-08-15T22:25:30.977134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10733","last_updated":"2025-05-18T21:17:22Z","snapshot_observed_at":"2026-08-18T11:02:33.658704Z","submitted_at":"2024-10-14T17:15:07Z","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10733","snapshot_observed_at":"2026-08-15T22:25:30.981927Z","title":"Deep compression autoencoder for efficient high-resolution diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:30.981927Z"},"links":{"cited_paper":"/paper/2410.10733","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:db690ca4d29f8ba78841c0ceb526841f32380684dc28abf51569696b539dd78c","observation_id":"9c48ab1f-e7fc-46b8-ad48-fa0c810c4c96","resolution":{"observed_at":"2026-08-15T22:25:30.981927Z","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":"2026-08-15T22:25:30.986643Z","title":"Sana-sprint: One-step diffusion with continuous-time consistency distillation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:30.986643Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:bc309120e43528c39d16b0d3978ddd75609cae8f15a23b8e682bc758ad302574","observation_id":"f44a794a-f461-410b-8d6f-fc9d24a7d2b1","resolution":{"observed_at":"2026-08-15T22:25:30.986643Z","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":"2026-08-15T22:25:30.991114Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:30.991114Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:5c0d5974fe97b9716f893fbab9af229a045fabc0daec09ce46ee71b29f7dc4f7","observation_id":"95149909-4900-4e2f-89c1-81c38096a664","resolution":{"observed_at":"2026-08-15T22:25:30.991114Z","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":"2026-08-15T22:25:30.995068Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:30.995068Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:e1523517417617bc0b9e045a6c1766d2159088600f9a864bc0bbaa458e5330b0","observation_id":"29694af2-7a47-4673-9f2c-c3185c7e92ed","resolution":{"observed_at":"2026-08-15T22:25:30.995068Z","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":"2026-08-15T22:25:30.999076Z","title":"Taming transformers for high-resolution image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:30.999076Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:450dbbed369d7ef639ba19d4a67d61a61fa373a80cb7dd3349bb4cc5685e4333","observation_id":"1c43c5de-2773-4c60-a7ce-99ef0da53eb4","resolution":{"observed_at":"2026-08-15T22:25:30.999076Z","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":"2026-08-15T22:25:31.003552Z","title":"Scaling rectified flow trans- formers for high-resolution image synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.003552Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:aeb7489d7b684dcca87b9dd169b8ca7cf41b6ca0c5fda04c41dfdebddc5c59b5","observation_id":"badfca7c-0833-4b8d-a818-da90b4e1bfae","resolution":{"observed_at":"2026-08-15T22:25:31.003552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12557","last_updated":"2025-06-23T14:26:35Z","snapshot_observed_at":"2026-08-17T08:09:05.115467Z","submitted_at":"2024-10-16T13:34:40Z","title":"One Step Diffusion via Shortcut Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12557","snapshot_observed_at":"2026-08-15T22:25:31.007338Z","title":"One step diffusion via shortcut models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.007338Z"},"links":{"cited_paper":"/paper/2410.12557","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:67e550683df15726525e9670e65c6ae3896926c948a63d3d5add4a5521c07090","observation_id":"ca134af3-facf-41df-8e99-9d99bd7256d6","resolution":{"observed_at":"2026-08-15T22:25:31.007338Z","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":"2026-08-15T22:25:31.011572Z","title":"Masked diffusion transformer is a strong image synthesizer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.011572Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:96f1d888e4511a514b647b89edbb7783247959b5284560f268fc3c0c2b488edb","observation_id":"97b362ec-e2be-421e-96bb-c0137dbbefbc","resolution":{"observed_at":"2026-08-15T22:25:31.011572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14548","last_updated":"2024-10-10T21:59:49Z","snapshot_observed_at":"2026-08-18T08:57:58.907249Z","submitted_at":"2024-06-20T17:56:02Z","title":"Consistency Models Made Easy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14548","snapshot_observed_at":"2026-08-15T22:25:31.017024Z","title":"Consistency models made easy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.017024Z"},"links":{"cited_paper":"/paper/2406.14548","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:f46eb126b85ffd2d41fb1e7f30c152b67132006ece4c7bfe0a4edf377127b23c","observation_id":"efa300df-5898-434d-b732-5864eb4a0ff7","resolution":{"observed_at":"2026-08-15T22:25:31.017024Z","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":"2026-08-15T22:25:31.022059Z","title":"Generative adversarial networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.022059Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:98dd964a0308e838e3ee40dd037932e0d5cf3043605e4caca479f3dd2d62ca84","observation_id":"92c4cbed-9331-463c-bbd7-9e8d80c00bec","resolution":{"observed_at":"2026-08-15T22:25:31.022059Z","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":"2026-08-15T22:25:31.025817Z","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":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.025817Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:703bd37a2f27d4c6cb59d1f941371415262decbbe28db3853c993b9b3bbaeff9","observation_id":"72c48230-f3b7-4e25-96b7-47416543edff","resolution":{"observed_at":"2026-08-15T22:25:31.025817Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-08-14T06:37:15.299690Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-15T22:25:31.029758Z","title":"Classifier-free diffusion guidance","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.029758Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:c3daa77bf85205bd28a89a4ed000fe5ea98f8e2543cd853da65fc0c68b4f5602","observation_id":"e5d8116d-f07e-45b7-be24-2449a9c91cbd","resolution":{"observed_at":"2026-08-15T22:25:31.029758Z","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":"2026-08-15T22:25:31.033848Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.033848Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:0f43b29bac7c1193ede8fa84adad1d7ee1108d68d7d3ec0e129b9ef39a8146ed","observation_id":"37d4c355-24ad-4883-9cbc-084d56d2a629","resolution":{"observed_at":"2026-08-15T22:25:31.033848Z","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":"2026-08-15T22:25:31.037576Z","title":"Video diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.037576Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:f308f94bbfe1c660684581483abd540fae909a8dc884974cfb7ae1208e6284ef","observation_id":"b29c6a82-81c8-4770-8946-1ffd193c2e68","resolution":{"observed_at":"2026-08-15T22:25:31.037576Z","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":"2026-08-15T22:25:32.488311Z","title":"Scaling up gans for text-to-image synthesis","venue":null,"work_id":"fd144398-fbeb-4bdc-bf84-4eec614cf9e5","year":2023},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.041074Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:9da0c1e61c5d1af72271d3196c63a124592b22416a5928aa276a39d7a6d07545","observation_id":"da9e9a5f-c013-4d41-8169-b144e7ab16d7","resolution":{"observed_at":"2026-08-15T22:25:32.493353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:31.045003Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.045003Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:70052c001734df134d3fb45f889c16abb7796bb4ad32bd7639643084434d4cf9","observation_id":"6b3db73d-75e4-4e88-b880-0382ed65d0f8","resolution":{"observed_at":"2026-08-15T22:25:31.045003Z","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":"2026-08-15T22:25:31.049048Z","title":"Guiding a diffusion model with a bad version of itself","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.049048Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:ad046e3462b5be8793a401607a3b685077145503db7ab06dcd3ee1c2650d1f46","observation_id":"24bed9a7-8d34-4c26-a241-1fe3c879f6ac","resolution":{"observed_at":"2026-08-15T22:25:31.049048Z","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":"2026-08-15T22:25:31.053837Z","title":"Analyzing and improving the training dynamics of diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.053837Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:c013e2ee7d2c3cc9d51cf3f4aef502a224facd91d276804dccb8f12e8087d007","observation_id":"9a48af75-5792-46a3-bd3c-cfa78f4df662","resolution":{"observed_at":"2026-08-15T22:25:31.053837Z","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":"2026-08-15T22:25:31.057464Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.057464Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:eb91533089dab0c50ab6ab826809787fb2d8c413c307f79b6abc559ba64bbab4","observation_id":"5aa17244-a1b2-42cd-8f34-b1b3f1cf00f5","resolution":{"observed_at":"2026-08-15T22:25:31.057464Z","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":"2026-08-15T22:25:32.436728Z","title":"Cifar-10 and cifar-100 datasets","venue":null,"work_id":"dc126fe9-97ce-435a-82c1-3c9fdf22513b","year":2009},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.061278Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:778f6b1ffeec15a7b1fb188a09367ce6db7ca981016be9fdce37aa29a5bb704e","observation_id":"1b62f498-99d3-451d-b8b7-a40a41f2ed63","resolution":{"observed_at":"2026-08-15T22:25:32.441197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:31.064551Z","title":"Repa-e: Unlocking vae for end-to-end tuning with latent diffusion transformers","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.064551Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:6c6600db548ebe524dbde16bb28cefb8b220ab6eabb5e6ac40b72928735431aa","observation_id":"6511fc48-0ec9-4bf8-81bb-04ee51bf3c65","resolution":{"observed_at":"2026-08-15T22:25:31.064551Z","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":"2026-08-15T22:25:31.067791Z","title":"Autoregressive image generation without vector quantization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.067791Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:4b4065d99b5098c5da1497ed0d28c1b7b51379eeae700fcf7ef57a00457d3c88","observation_id":"348fa4d1-42d1-4294-825b-598851c23b63","resolution":{"observed_at":"2026-08-15T22:25:31.067791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-16T02:30:42.660030Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-15T22:25:31.072298Z","title":"Flow matching for generative modeling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.072298Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:9e3dd37f4ca2c78ff6192eca9e1f16833c4f9beae2c8ca7d90c5036eca6a9c2d","observation_id":"e9c56877-1522-4882-bcc6-d1bf2daaf180","resolution":{"observed_at":"2026-08-15T22:25:31.072298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.03265","last_updated":"2021-10-26T02:48:30Z","snapshot_observed_at":"2026-08-19T14:20:48.530093Z","submitted_at":"2019-08-08T20:51:17Z","title":"On the Variance of the Adaptive Learning Rate and Beyond","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.03265","snapshot_observed_at":"2026-08-15T22:25:31.076238Z","title":"On the variance of the adaptive learning rate and beyond","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.076238Z"},"links":{"cited_paper":"/paper/1908.03265","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:299552cc3df7118d09b6953c297a5ae5a3c14c8b2ecac56a349961e101a0221f","observation_id":"2544e12b-bf62-438b-bdca-1dcf81fcfbba","resolution":{"observed_at":"2026-08-15T22:25:31.076238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.03003","last_updated":"2022-09-07T08:59:55Z","snapshot_observed_at":"2026-07-06T13:49:40.974495Z","submitted_at":"2022-09-07T08:59:55Z","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.03003","snapshot_observed_at":"2026-08-15T22:25:31.079495Z","title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.079495Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:d146996d81f44e3bb0bdc0f556bf5a54ea3f6ec21cddf87ecf09e87bd82e9140","observation_id":"2ed92b07-e33c-46e3-a4e8-33b1629d12ae","resolution":{"observed_at":"2026-08-15T22:25:31.079495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-15T22:25:31.083770Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.083770Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:f2b2be843088cedf3cfcd137afe9d23f4d5203f8921936286984a7328992d1d8","observation_id":"c0db0787-a25e-48ff-94f8-fc1ff07b40ae","resolution":{"observed_at":"2026-08-15T22:25:31.083770Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.11081","last_updated":"2025-03-01T09:52:49Z","snapshot_observed_at":"2026-08-17T22:37:34.780172Z","submitted_at":"2024-10-14T20:43:25Z","title":"Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.11081","snapshot_observed_at":"2026-08-15T22:25:31.087392Z","title":"Simplifying, stabilizing and scaling continuous-time consistency models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.087392Z"},"links":{"cited_paper":"/paper/2410.11081","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:89e67ec4abed136efa326b31bbfe781b554fca0d841afed93e32dd9a8999091c","observation_id":"f71b1497-b999-4bc8-bbbb-d5887467712f","resolution":{"observed_at":"2026-08-15T22:25:31.087392Z","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":"2026-08-15T22:25:31.092074Z","title":"Sit: Exploring flow and diffusion-based generative models with scalable interpolant transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.092074Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:041a78d09180438a43a11ffb7abd60c1865c398732dadc0c4385231dea489392","observation_id":"ecf0bd49-d0c3-40af-8835-6cba3fc23e2d","resolution":{"observed_at":"2026-08-15T22:25:31.092074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01703","last_updated":"2019-12-03T22:06:05Z","snapshot_observed_at":"2026-07-06T08:41:49.632205Z","submitted_at":"2019-12-03T22:06:05Z","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01703","snapshot_observed_at":"2026-08-15T22:25:31.095578Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.095578Z"},"links":{"cited_paper":"/paper/1912.01703","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:5549b6a63b5ca3f330f956b140f39f898182b4a9764f0644c70c78c3b45fb898","observation_id":"8e9b0b37-c5c6-4f68-bb3a-8ca9ba3adfeb","resolution":{"observed_at":"2026-08-15T22:25:31.095578Z","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":"2026-08-15T22:25:31.099282Z","title":"Scikit- learn: Machine learning in python","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.099282Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:3cab979b1fe053311e371c73d703ead07db20950a9cdada97d68eac55d3d5fda","observation_id":"0bf0ff08-e2eb-4b15-83b3-bee8d43449ac","resolution":{"observed_at":"2026-08-15T22:25:31.099282Z","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":"2026-08-15T22:25:31.102965Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.102965Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:0e975e0023f420c49916c7533c589eeebd68259b6810d86edab5f6e2fe58ad53","observation_id":"0531a1df-d56e-4673-94c6-d00ea139c434","resolution":{"observed_at":"2026-08-15T22:25:31.102965Z","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":"2026-08-15T22:25:31.106751Z","title":"High- resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.106751Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:bf604b304dfd656713c4b83361f351d5f343c94fc21828c74dc6951c3c696c50","observation_id":"ead167ad-f3d9-4ae1-b2d9-9c9ef6359d14","resolution":{"observed_at":"2026-08-15T22:25:31.106751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.00512","last_updated":"2022-06-07T09:17:35Z","snapshot_observed_at":"2026-08-12T01:14:44.484432Z","submitted_at":"2022-02-01T16:07:25Z","title":"Progressive Distillation for Fast Sampling of Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.00512","snapshot_observed_at":"2026-08-15T22:25:31.110898Z","title":"Progressive distillation for fast sampling of diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.110898Z"},"links":{"cited_paper":"/paper/2202.00512","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:a9e8bb90f1ddc4fd7097a3c08e7f7a3bfdcdd89c09ada18f017a0a2f50d1aa2a","observation_id":"66e61149-366c-4acf-a385-b8bb070a0284","resolution":{"observed_at":"2026-08-15T22:25:31.110898Z","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":"2026-08-15T22:25:31.114678Z","title":"Stylegan-xl: Scaling stylegan to large diverse datasets","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.114678Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:b7b5d7b6e1ba33e1c1890c8ae904d3cdd0303f000db1cedbfc4a30c02a5688ed","observation_id":"f6429375-fb6c-4c83-aac7-a92aaa18d301","resolution":{"observed_at":"2026-08-15T22:25:31.114678Z","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":"2026-08-15T22:25:31.118650Z","title":"Glu variants improve transformer","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.118650Z"},"links":{"cited_paper":"/paper/2002.05202","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:a7c7e7df02c2d40d5ebf3398709461d667aea3fb8af6ef7fc63cae2895dde8b0","observation_id":"9e6dbddf-ac28-48cd-a967-b4b9f3c7f04b","resolution":{"observed_at":"2026-08-15T22:25:31.118650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-15T22:25:31.124818Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.124818Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:b0e577924daac9bd6f452772b4a1d3ccaf6c38caf44cf76bae9505dc007b86a3","observation_id":"87da8f22-3539-4318-b26b-89a85b660d96","resolution":{"observed_at":"2026-08-15T22:25:31.124818Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14189","last_updated":"2023-10-22T05:33:38Z","snapshot_observed_at":"2026-08-17T19:16:27.766862Z","submitted_at":"2023-10-22T05:33:38Z","title":"Improved Techniques for Training Consistency Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14189","snapshot_observed_at":"2026-08-15T22:25:31.128850Z","title":"Improved techniques for training consistency models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.128850Z"},"links":{"cited_paper":"/paper/2310.14189","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:879eceec00044b6ad3cc8fa2ffa03a8c05886cd9e2ae65e4f614ef4fab87001d","observation_id":"fd832200-8325-42a3-9306-b0649d64f2ce","resolution":{"observed_at":"2026-08-15T22:25:31.128850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-15T22:25:31.133303Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.133303Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:5c069edaeb222c4de4db4443a2153a080bacecd6b460fb88b421c82da27cafe9","observation_id":"ff28a573-f204-459b-accd-722c620067dd","resolution":{"observed_at":"2026-08-15T22:25:31.133303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.01469","last_updated":"2023-05-31T06:17:10Z","snapshot_observed_at":"2026-08-15T07:00:23.337991Z","submitted_at":"2023-03-02T18:30:16Z","title":"Consistency Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.01469","snapshot_observed_at":"2026-08-15T22:25:31.137687Z","title":"Consistency models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.137687Z"},"links":{"cited_paper":"/paper/2303.01469","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:9729fa8e61f34674191d879f8604d3e3f6e01bed345c838d7563230e3dc0790c","observation_id":"faf2da6f-0e8f-4684-b3a7-70fffc3af96d","resolution":{"observed_at":"2026-08-15T22:25:31.137687Z","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":"2026-08-15T22:25:31.142216Z","title":"Roformer: Enhanced transformer with rotary position embedding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.142216Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:fa6f0d4b7d4e01de4e8696d25806d4b763b177f819c4372cef035dbdf1709e13","observation_id":"76719e43-e141-44d4-b1a2-10c4532b8add","resolution":{"observed_at":"2026-08-15T22:25:31.142216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06525","last_updated":"2024-06-10T17:59:52Z","snapshot_observed_at":"2026-08-13T22:05:34.844117Z","submitted_at":"2024-06-10T17:59:52Z","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06525","snapshot_observed_at":"2026-08-15T22:25:31.146052Z","title":"Autoregressive model beats diffusion: Llama for scalable image generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.146052Z"},"links":{"cited_paper":"/paper/2406.06525","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:6b2d5b5eed7586a154c29278a64077ba646a4a042ad64086c09104eae1b2af5a","observation_id":"cfc6ac1a-5c65-4eaf-8895-99eff2189c62","resolution":{"observed_at":"2026-08-15T22:25:31.146052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.12154","last_updated":"2025-02-17T18:59:50Z","snapshot_observed_at":"2026-08-16T12:57:35.496151Z","submitted_at":"2025-02-17T18:59:50Z","title":"Diffusion Models without Classifier-free Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.12154","snapshot_observed_at":"2026-08-15T22:25:31.151125Z","title":"Diffusion models without classifier- free guidance","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.151125Z"},"links":{"cited_paper":"/paper/2502.12154","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:d0f276824534b5be148ce2f0a71188a5856453794a860ec1099e3c53520215ab","observation_id":"041a4eb8-01a1-4866-b8f0-dc0dbe30cabb","resolution":{"observed_at":"2026-08-15T22:25:31.151125Z","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":"2026-08-15T22:25:31.155073Z","title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.155073Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:3eab1deeaceb61f91fb5126dfc63e13c4d6503ec2b2f32d6bc6b5ba48aa722e7","observation_id":"ccc0a91f-729f-4d1e-9afd-a1b15776c590","resolution":{"observed_at":"2026-08-15T22:25:31.155073Z","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":"2026-08-15T22:25:31.158674Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.158674Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:aa18f7dcacd20f73cca02558da8b6fd3779795a426cb123c4ad284495a7dcded","observation_id":"100290b2-4ae6-4eba-b515-94fdb5110543","resolution":{"observed_at":"2026-08-15T22:25:31.158674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.05741","last_updated":"2025-04-09T04:23:38Z","snapshot_observed_at":"2026-08-20T13:13:18.546061Z","submitted_at":"2025-04-08T07:17:45Z","title":"DDT: Decoupled Diffusion Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.05741","snapshot_observed_at":"2026-08-15T22:25:31.163002Z","title":"Ddt: Decoupled diffusion transformer","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.163002Z"},"links":{"cited_paper":"/paper/2504.05741","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:895961d0b633e0922ed798f9802798657881fdedf74fe929c4c6d6774a383f4b","observation_id":"190cdce3-095a-48de-8f25-6205f44f7cbc","resolution":{"observed_at":"2026-08-15T22:25:31.163002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.10629","last_updated":"2024-10-20T14:35:31Z","snapshot_observed_at":"2026-08-20T10:31:24.549119Z","submitted_at":"2024-10-14T15:36:42Z","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.10629","snapshot_observed_at":"2026-08-15T22:25:31.168313Z","title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.168313Z"},"links":{"cited_paper":"/paper/2410.10629","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:51d5cfc02a46c9b891692038b6094ff9b76bcc48a1abbf9aa844574c266c00e4","observation_id":"b67293da-88fe-4a96-a970-90ae06d44fc4","resolution":{"observed_at":"2026-08-15T22:25:31.168313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01423","last_updated":"2025-03-10T11:43:42Z","snapshot_observed_at":"2026-08-15T15:57:30.372623Z","submitted_at":"2025-01-02T18:59:40Z","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01423","snapshot_observed_at":"2026-08-15T22:25:31.172575Z","title":"Reconstruction vs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.172575Z"},"links":{"cited_paper":"/paper/2501.01423","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:71975eb400ebfad6e6c140f05a4b5f73e446230910d8a521ecaaf70421a5921d","observation_id":"18bc2b63-b362-4392-bff1-31668749423e","resolution":{"observed_at":"2026-08-15T22:25:31.172575Z","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":"2026-08-15T22:25:31.177648Z","title":"One-step diffusion with distribution matching distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.177648Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:0645d22e0ec8709e8961c21bd0e19a01eb54b84a45cb2b40d82da358c7e83966","observation_id":"98239ee6-29a5-48a9-b61b-c2a630a53899","resolution":{"observed_at":"2026-08-15T22:25:31.177648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05737","last_updated":"2024-03-29T17:44:41Z","snapshot_observed_at":"2026-08-02T18:23:02.746177Z","submitted_at":"2023-10-09T14:10:29Z","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05737","snapshot_observed_at":"2026-08-15T22:25:31.182489Z","title":"Language model beats diffusion–tokenizer is key to visual generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.182489Z"},"links":{"cited_paper":"/paper/2310.05737","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:bef3bc4c82ca1bc140ca5e913c50c12f5c4e3bc54d8dfedfefba585121d4d85d","observation_id":"c7a35704-d2d8-4a63-b808-1dae1387dba7","resolution":{"observed_at":"2026-08-15T22:25:31.182489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06940","last_updated":"2025-06-18T04:35:42Z","snapshot_observed_at":"2026-07-06T19:30:26.233621Z","submitted_at":"2024-10-09T14:34:53Z","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.06940","snapshot_observed_at":"2026-08-15T22:25:31.186217Z","title":"Representation alignment for generation: Training diffusion transformers is easier than you think","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.186217Z"},"links":{"cited_paper":"/paper/2410.06940","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:27b87808b344fd9e1cab51fad8ffe435f73be8407d7bbc719804224dae601685","observation_id":"43ff8770-ff37-4a3d-9b42-e03bf46e657f","resolution":{"observed_at":"2026-08-15T22:25:31.186217Z","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":"2026-08-15T22:25:31.190554Z","title":"Root mean square layer normalization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.190554Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:f148eceefa5b9f720aa6d42d07e73fb78e9da48498a8af76306e52c172f30295","observation_id":"8edd8015-e594-4401-83fb-cdcd54bac2eb","resolution":{"observed_at":"2026-08-15T22:25:31.190554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09305","last_updated":"2024-03-05T01:10:18Z","snapshot_observed_at":"2026-08-16T15:23:34.823593Z","submitted_at":"2023-06-15T17:38:48Z","title":"Fast Training of Diffusion Models with Masked Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09305","snapshot_observed_at":"2026-08-15T22:25:31.194888Z","title":"Fast training of diffusion models with masked transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.194888Z"},"links":{"cited_paper":"/paper/2306.09305","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:6c524853ff80d8774c1e51dd83a5f922cea6715556f5efc49e6f506c8a0790c1","observation_id":"4dc694ad-a1c2-4541-93fb-e29b7e2ef43b","resolution":{"observed_at":"2026-08-15T22:25:31.194888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.07565","last_updated":"2025-05-14T19:11:44Z","snapshot_observed_at":"2026-08-16T12:51:25.226336Z","submitted_at":"2025-03-10T17:37:39Z","title":"Inductive Moment Matching","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.07565","snapshot_observed_at":"2026-08-15T22:25:31.199381Z","title":"Inductive moment matching","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.199381Z"},"links":{"cited_paper":"/paper/2503.07565","citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:f7f82f7930216de5a046b90b9f6f7645859cd1fb0360c35cd2e1bcc4dce13b8e","observation_id":"9fd710db-991a-4246-9558-818b6333bfb0","resolution":{"observed_at":"2026-08-15T22:25:31.199381Z","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":"2026-08-15T22:25:32.336966Z","title":"C.1.3 Detailed Implementation Details Experiments were conducted on a cluster equipped with 8 H800 GPUs, each with 80 GB of VRAM","venue":null,"work_id":"bf9fe0fe-5f61-46b2-b1e6-db2ec0f06ea8","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.204595Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:3b085e7bee295b864145a4544d59ee270f28f9fc7eeb8d860e9d340bdb3e10c1","observation_id":"5e04583d-00fc-4b05-b9ed-87b36884a29c","resolution":{"observed_at":"2026-08-15T22:25:32.341456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.322503Z","title":"TrigLinear","venue":null,"work_id":"49ba870a-a85e-4cd9-b788-b3bb7c70778e","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.209086Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:9390dcb18f046b38bd8c0956ae5cad38d40e26ed4f54daf01b390dfab6daf0d0","observation_id":"fe99cc99-72fa-43ef-973d-c6573579213d","resolution":{"observed_at":"2026-08-15T22:25:32.328798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.306280Z","title":null,"venue":null,"work_id":"e396ed7d-92d7-4658-9fbf-fd4c94ddc8bb","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.213974Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:4667d9bb3ffb946bf005b207e91fed77864a34a3cd4b055332b3ce6e775a082b","observation_id":"ecc7f79b-09f3-4a63-9bcc-05e7714dd669","resolution":{"observed_at":"2026-08-15T22:25:32.313916Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.289179Z","title":null,"venue":null,"work_id":"aed92e8d-0260-4c6a-9bb3-c9ccabcdb2cd","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.219331Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:af84ae9927fead7844ac90ffc580bdb26efdb6443d342412d1fa18f2ff7b6222","observation_id":"c29019d6-6668-4b0f-acff-61ff3adf6b1b","resolution":{"observed_at":"2026-08-15T22:25:32.295900Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.274096Z","title":null,"venue":null,"work_id":"f7fccb81-e8e3-47c2-9797-8a06a409fa7e","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.223521Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:4aac3c990c164dacd4c804c62b1cc3aa0973edf6ea5573574a335d17dd373fa0","observation_id":"50a02311-764c-4f93-97f8-ca326ca13c4d","resolution":{"observed_at":"2026-08-15T22:25:32.278670Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.258131Z","title":null,"venue":null,"work_id":"169a7d2b-69f3-4542-8213-0a1226754c1b","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.228371Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:ab5f80314c36a0e2d0c9c48198e32e3572f19bd2f83b302bd035293f10444a1d","observation_id":"1f00345e-a7af-425d-a42d-244541b02416","resolution":{"observed_at":"2026-08-15T22:25:32.262356Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.246276Z","title":null,"venue":null,"work_id":"aa11c611-15e1-4cfd-a9af-f686305e9574","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.233785Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:6cb5d354f7919ad9a830197d3303a0e159f13a182bcd0fd61521d384df0b9b21","observation_id":"b205e732-fbeb-417c-b5eb-6a4d6d06ed59","resolution":{"observed_at":"2026-08-15T22:25:32.250347Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.232504Z","title":"Additionally, we also include autoregressive models [ 24, 45, 51] as the baselines, which generate data sequentially, often in discrete domains","venue":null,"work_id":"0c7844cb-3888-467e-9e14-faff6e0d2ee3","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.238205Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:106be517a838bd90cc9261ff2a9cb9c9b0862db4f253014dd2a4c8780ba1f70a","observation_id":"20da5c4d-08c7-467c-8022-a00e9760398f","resolution":{"observed_at":"2026-08-15T22:25:32.237566Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.216548Z","title":"Since z and x are independent, E[xt| x0 = x] = γ(t) x","venue":null,"work_id":"85dd012f-8b6c-49e3-ad90-3e95e2377b3f","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.244513Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:1e170c4bb5ff60980465bcccb7cb1ec6b797dde59ca73cc01468b37f933390d7","observation_id":"a5dea9ff-626d-4cbd-8fc3-2a22aae2b9d4","resolution":{"observed_at":"2026-08-15T22:25:32.221443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.200913Z","title":"The covariance of xt given x0 is Var(xt| x0) =α(t)2 Id","venue":null,"work_id":"213d4a29-a04f-40af-b6e5-7bcdf279e211","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.249356Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:2dd5832f641b43edd5b81e1553f0aa911a7337bff71e11705c2b24786aedcc0d","observation_id":"04f68ea4-7538-4ac2-885e-c0e1a5f3d23a","resolution":{"observed_at":"2026-08-15T22:25:32.205985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.183710Z","title":"By general theory (see, e.g., de Bortoli et al.), the probability flow ODE associated with the SDE dxt = f(xt,t ) dt +g(t) dwt is d xt dt = f(xt,t ) − 1 2g(t)2∇xt logpt(xt)","venue":null,"work_id":"d20c38f9-7cf4-4853-93fe-27c835374ab6","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.255894Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:69674e03cee7b02b900f96d066ba908addb2094129a972c906f286da496e0bff","observation_id":"38ae8d1a-b7e8-4c44-b5ef-e3404d27d740","resolution":{"observed_at":"2026-08-15T22:25:32.189334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.169638Z","title":null,"venue":null,"work_id":"cf27f17e-f0f6-48ea-8fdc-cb4173950226","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.261239Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:f5da32ca4d4166fdf9c857a2608fe154fb415733e8f4dad75a30bf27533bc094","observation_id":"115d2d6a-2657-4b12-9e30-5cf5c0f99c13","resolution":{"observed_at":"2026-08-15T22:25:32.174201Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.150476Z","title":null,"venue":null,"work_id":"e032d9eb-f1d9-4369-a946-a3fa0cc361e7","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.267129Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:a07b8afb0c736f83d34f2ad0bdab6926e7989fea68ec5fa2e31cec0537f0ebc0","observation_id":"0af6d3f3-ebdf-4173-8997-47bc3bf503ae","resolution":{"observed_at":"2026-08-15T22:25:32.155425Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.130486Z","title":null,"venue":null,"work_id":"4036a97e-5e40-4c0a-94ee-2b33f730f40b","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.272090Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:751d6e4a82d490e21ba1d3072d7fd68fec1731ed4cd8f0fb4d8948cecbedf4f3","observation_id":"f108b026-02b2-46f7-8479-2982df37e105","resolution":{"observed_at":"2026-08-15T22:25:32.135807Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.113740Z","title":"Substituting these into the general drift gives dxt dt =− xt 1−t + t (1−t) Σt h xt−m (1−t) tanh m (1−t) Σt xt i , which is the claimed closed-form Probability-Flow ODE","venue":null,"work_id":"0276771c-9328-44a0-9e20-589695086976","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.277382Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:0ae79704881ae88271308147d4a02704055a9854ae21fb1154d025502674ed72","observation_id":"f48b3543-59ae-4616-a2d0-7f7c82e6fc81","resolution":{"observed_at":"2026-08-15T22:25:32.120076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.100001Z","title":null,"venue":null,"work_id":"43dceda8-23d8-40ed-83d5-f3df5e2babc7","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.282383Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:288062f77d4ad43bbe4776a3512469d2032abceec064cea7418e56f465b9c566","observation_id":"43946f21-7803-4f45-90a1-605c5e61e7ae","resolution":{"observed_at":"2026-08-15T22:25:32.104870Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.084897Z","title":null,"venue":null,"work_id":"87b19510-c223-4727-9b55-644d59c5dba2","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.286105Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:2032972f686901d69568379b48ad6ef14bb7f17a0c3a5335865cdd06c8850d0d","observation_id":"4403fa7f-e271-4f6e-be60-23c99039547c","resolution":{"observed_at":"2026-08-15T22:25:32.089539Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.054634Z","title":"44 0.0 0.2 0.4 0.6 0.8 1.0 Time t 0.0 0.5 1.0 1.5 2.0 2.5 3.0 3.5Prob","venue":null,"work_id":"b8ea5cce-6263-40ac-992d-e2f1a848fff9","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.290586Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:474f6c48ee06fcacab9bc32869cfe9f83fc813cbd6ba5b20b98c21869a1f82f2","observation_id":"3af68b8a-1812-4bca-8a19-bcd75e06e2c1","resolution":{"observed_at":"2026-08-15T22:25:32.060679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.038230Z","title":"Replacing x(ti) by ˜xi in the leading terms gives x(ti+1) = ˜xi +h vi + h2 2 v′(˜xi,ti) +O(h3)","venue":null,"work_id":"13c8b355-155f-437e-9561-35fd876838f6","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.294055Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:3930c89ae341eff89dff5e796b0e115ecb89d53c517e92d3d5a764795427be11","observation_id":"e923a75f-9cdb-4784-b5a8-58fccbe43e77","resolution":{"observed_at":"2026-08-15T22:25:32.044078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.023824Z","title":"base point","venue":null,"work_id":"8bae90f4-e5f6-4353-a130-fbfe4eb9d556","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.298001Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:cfd847608dc3162c87b2c916463d42f037caafc9f24340896443726a568728a1","observation_id":"d2266423-2a20-46a5-978c-b0aa873a3769","resolution":{"observed_at":"2026-08-15T22:25:32.028942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:32.000423Z","title":"By the Implicit Function Theorem, for each fixed (t1,t 0,t 2) near ( 1 4, 1 2, 3","venue":null,"work_id":"18e83b34-1a59-407e-b115-85f0a46c8a84","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.302227Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:85ccc69a4c2677226dbb92511121cf44474f420e2bcd878003307f4b9b1d6b08","observation_id":"6a5bcfa4-3a07-4df8-8307-57767ba00275","resolution":{"observed_at":"2026-08-15T22:25:32.010615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T22:25:31.977820Z","title":"subtract-then-scale","venue":null,"work_id":"d812dbe7-bb2e-4f35-a883-20e6606859c9","year":null},"citing_paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-15T22:25:31.306591Z"},"links":{"citing_paper":"/paper/2505.07447"},"observation_digest":"sha256:9013e1aabf8c5b53e831fd2002ebcbe2db924cbb893ad702ecc9f99c638e9469","observation_id":"f9723611-34d8-4604-9375-99f0fc64c558","resolution":{"observed_at":"2026-08-15T22:25:31.984756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.07447","last_updated":"2025-05-20T12:27:53Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T02:13:44.077914Z","submitted_at":"2025-05-12T11:15:39Z","title":"Unified Continuous Generative Models"},"reference_resolution":{"displayed":77,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":3,"unresolved":60,"verified_exact":0,"verified_fuzzy":13},"total_outbound_references":77},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 77 of 77 outbound references and 8 inbound Pith citation observations for arXiv:2505.07447."}