{"as_of":"2026-08-08T02:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8f10931cabba1b2626a5e98196ba5851eb309bbfd77497d1d454f71bd6de0ade","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:34:06.057829Z","state":"measured"},{"denominator":70,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":70,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-01T05:35:48.896721Z","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":"2026-07-01T10:25:41.145492Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"cited_work":{"arxiv_id":"2506.02221","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.02221","snapshot_observed_at":"2026-07-01T10:25:41.145492Z","title":"Diff2flow: Training flow matching models via diffusion model alignment, 2025.https://arxiv.org/abs/2506.02221","venue":null,"work_id":"8da548ea-694d-4f7d-85be-fc914d30896a","year":2025},"citing_paper":{"arxiv_id":"2604.28185","last_updated":"2026-04-30T17:59:02Z","snapshot_observed_at":"2026-07-06T23:13:29.310140Z","submitted_at":"2026-04-30T17:59:02Z","title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-07T06:38:04.459129Z"},"links":{"cited_paper":"/paper/2506.02221","citing_paper":"/paper/2604.28185"},"observation_digest":"sha256:0ac8d93b825ef444829a38b4a1d413cc7bc8cd92a84b3cb47ad2276d42885239","observation_id":"f0180740-5d93-476b-8863-53d1152ef251","resolution":{"observed_at":"2026-05-12T10:16:28.982692Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"cited_work":{"arxiv_id":"2506.02221","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.02221","snapshot_observed_at":"2026-07-01T10:25:41.145492Z","title":"Diff2flow: Training flow matching models via diffusion model alignment, 2025.https://arxiv.org/abs/2506.02221","venue":null,"work_id":"8da548ea-694d-4f7d-85be-fc914d30896a","year":2025},"citing_paper":{"arxiv_id":"2606.32020","last_updated":"2026-06-30T17:51:26Z","snapshot_observed_at":"2026-08-03T10:16:58.559510Z","submitted_at":"2026-06-30T17:51:26Z","title":"Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-01T05:35:48.896721Z"},"links":{"cited_paper":"/paper/2506.02221","citing_paper":"/paper/2606.32020"},"observation_digest":"sha256:1d5428aac12a6bc8943d43e5d87a4dc4d70eb0c637ffac30ed0d900b7fd1f03f","observation_id":"dd3f2424-bdf2-40b5-b989-5e8586110d37","resolution":{"observed_at":"2026-07-01T10:25:41.147057Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.02221/citation-record","integrity":"/paper/2506.02221/integrity","json":"/paper/2506.02221/citation-record.json","paper":"/paper/2506.02221"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08797","last_updated":"2025-10-09T00:43:44Z","snapshot_observed_at":"2026-07-06T15:03:52.079498Z","submitted_at":"2023-03-15T17:43:42Z","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08797","snapshot_observed_at":"2026-08-07T11:33:57.630120Z","title":"Stochastic interpolants: A unifying framework for flows and diffusions","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:57.630120Z"},"links":{"cited_paper":"/paper/2303.08797","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:559484cf8b8543b3b0650471985dbf71f7a21b0c55f2e4ff4bfc0166e624954b","observation_id":"4c884881-ca4a-4c4a-b7a2-c16487079f9f","resolution":{"observed_at":"2026-08-07T11:33:57.630120Z","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":"2026-08-07T11:34:15.456405Z","title":"Lora learns less and forgets less","venue":null,"work_id":"c6933707-aca9-4b9d-ae5a-a4de2fab9dea","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:57.723681Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:2bd58a94aa550f497769143cae6084f4cfd940341d2ac11b77bf0e407d789c89","observation_id":"09f73fc6-c10a-408d-96ee-5763796ad1a5","resolution":{"observed_at":"2026-08-07T11:34:15.593051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:15.194849Z","title":"Align your latents: High-resolution video synthesis with la- tent diffusion models","venue":null,"work_id":"88556110-aea3-4b87-99ca-f401ae3be9c3","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:57.893588Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:500d24d3f3c023c853de0630c7e6a632320f9a8f9a10ebeda28ad4ce72aa4b33","observation_id":"c6bfefd8-8e32-4699-b119-e06682f1ac7e","resolution":{"observed_at":"2026-08-07T11:34:15.325378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:14.917844Z","title":"Vir- tual kitti 2, 2020","venue":null,"work_id":"6c45f34b-3fbf-41b2-9151-662526ceb715","year":2020},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:58.018451Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:be4eccda69a8c350efb1c84aadfea2d6f153c2715288cf0ff422cb140511cebe","observation_id":"24483d94-5ec4-48be-afe0-e669d2009361","resolution":{"observed_at":"2026-08-07T11:34:15.027331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:14.651778Z","title":"Chang, Manolis Savva, Maciej Hal- ber, Thomas Funkhouser, and Matthias Nießner","venue":null,"work_id":"059f2eab-0dff-4b2e-8f0c-7b24d2e7737e","year":2017},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:58.155108Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:45e211f06b2a148ab9cee30c00b48f68460d1cc25bce7df1b142d07642a4ef57","observation_id":"ffc2993e-3895-4bdd-b35f-6aa6d17f41e3","resolution":{"observed_at":"2026-08-07T11:34:14.793462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15807","last_updated":"2023-09-27T17:30:19Z","snapshot_observed_at":"2026-08-02T11:54:13.342379Z","submitted_at":"2023-09-27T17:30:19Z","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15807","snapshot_observed_at":"2026-08-07T11:33:58.280467Z","title":"Emu: Enhanc- ing image generation models using photogenic needles in a haystack","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:58.280467Z"},"links":{"cited_paper":"/paper/2309.15807","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:2a5db1a920ca7a8691b8c111437a15cb8b7259d17a8cd35fa8336e6ccad1afba","observation_id":"3893c0ab-624b-4fb3-9fa7-6c360ff1166d","resolution":{"observed_at":"2026-08-07T11:33:58.280467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.17137","last_updated":"2024-10-16T07:08:57Z","snapshot_observed_at":"2026-08-07T10:14:22.700975Z","submitted_at":"2023-11-28T18:59:02Z","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17137","snapshot_observed_at":"2026-08-07T11:33:58.437845Z","title":"Generative models: What do they know? do they know things? let’s find out! arXiv preprint arXiv:2311.17137, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:58.437845Z"},"links":{"cited_paper":"/paper/2311.17137","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:445a9d21b8b837fbc20f8a5362508e75d0754c492bec69579194464417fe0544","observation_id":"ed575bf2-ea23-4aaa-b78b-9c3f66bfe943","resolution":{"observed_at":"2026-08-07T11:33:58.437845Z","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":"2026-08-07T11:34:14.368885Z","title":"Scaling recti- fied flow transformers for high-resolution image synthesis","venue":null,"work_id":"65761412-7836-4f0c-8e54-97896d248ea9","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:58.567457Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:d39cb9a9a1e1b2bf998e8c85d9c33cd0872a7ccacae6a98431a6a6ce877ca5c9","observation_id":"06706ecd-5d37-42f6-ac4a-c63adb71ee98","resolution":{"observed_at":"2026-08-07T11:34:14.520352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:14.117590Z","title":"Geowiz- ard: Unleashing the diffusion priors for 3d geometry estima- tion from a single image","venue":null,"work_id":"ca6342f5-1c4c-48d5-af15-1d2bc543cb7f","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:58.656501Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:fa6e60ad17f5246dcf4d4b5988bee3b9e16b498cc7ef4481c2c8da94f899e83b","observation_id":"90a15785-eee4-4375-baf7-1765d3c82d9d","resolution":{"observed_at":"2026-08-07T11:34:14.228704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.00783","last_updated":"2024-06-30T17:59:58Z","snapshot_observed_at":"2026-08-03T19:11:51.277524Z","submitted_at":"2024-06-30T17:59:58Z","title":"Diffusion Models and Representation Learning: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.00783","snapshot_observed_at":"2026-08-07T11:33:58.810974Z","title":"Diffusion mod- els and representation learning: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:58.810974Z"},"links":{"cited_paper":"/paper/2407.00783","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:9c3b96c870819448168e09b4fd4ca23dcfe024db08d404ecfacf2173b9261644","observation_id":"0d733709-b4b8-4a50-8da9-47e6f88a046f","resolution":{"observed_at":"2026-08-07T11:33:58.810974Z","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":"2026-08-07T11:34:13.886279Z","title":"Distillation of diffusion features for semantic correspondence","venue":null,"work_id":"76ba7fe5-1791-4c54-8621-d5e3ea80ac02","year":2025},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:58.966709Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:b222fc18a38e0f6b5d67311e318469d70ede8eb9c1955f5ab31fe383ab0eee19","observation_id":"566b0b82-812c-4702-b9b3-746829ef90fe","resolution":{"observed_at":"2026-08-07T11:34:13.998848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.12092","last_updated":"2023-11-27T08:29:54Z","snapshot_observed_at":"2026-07-06T16:50:10.189504Z","submitted_at":"2023-11-20T18:59:01Z","title":"Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.12092","snapshot_observed_at":"2026-08-07T11:33:59.076521Z","title":"Concept sliders: Lora adap- tors for precise control in diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:59.076521Z"},"links":{"cited_paper":"/paper/2311.12092","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:6325bafa8d4453d6efb45458047250cfa720e86489ba65aed23321cedf2b9572","observation_id":"041b8f47-16d5-4425-8dfc-5107e5f5f772","resolution":{"observed_at":"2026-08-07T11:33:59.076521Z","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":"2026-08-07T11:33:59.188884Z","title":"Vision meets robotics: The kitti dataset","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:59.188884Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:5f69c50398e309b579d22a95d5b75f803a32bf3c8613126159802e35157d5292","observation_id":"955ad597-ed1a-4109-99d3-a508a3e85145","resolution":{"observed_at":"2026-08-07T11:33:59.188884Z","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":"2026-08-07T11:34:13.615030Z","title":"Depthfm: Fast monocular depth estimation with flow matching","venue":null,"work_id":"443168a0-e92e-4331-a8e6-d33b9de49970","year":2025},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:59.323082Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:7823c0d54e7acfa9b2ade768b47516f55e963ca4eb9d9ae730b872e26941960d","observation_id":"ef40478a-da26-4d50-8a52-055132e27f34","resolution":{"observed_at":"2026-08-07T11:34:13.713098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:33:59.397096Z","title":"Animatediff: Animate your personalized text-to- image diffusion models without specific tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:59.397096Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:7eac4ee2feac31988e05b3ec58fcc4546c7e6a4c30360e39565c5569e137bdd2","observation_id":"46b866d4-f5a1-4184-9df7-2f40c0b3dfda","resolution":{"observed_at":"2026-08-07T11:33:59.397096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18124","last_updated":"2025-01-18T20:14:54Z","snapshot_observed_at":"2026-08-04T16:50:25.699602Z","submitted_at":"2024-09-26T17:58:55Z","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18124","snapshot_observed_at":"2026-08-07T11:33:59.540350Z","title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:59.540350Z"},"links":{"cited_paper":"/paper/2409.18124","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:d69cd3324ad6b650e0dda756a7959768a388e6d7569de4937155d004da1cd24b","observation_id":"30127671-5022-4262-aebe-6db07d384c1d","resolution":{"observed_at":"2026-08-07T11:33:59.540350Z","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":"2026-08-07T11:34:13.323465Z","title":"Scalecrafter: Tuning-free higher- resolution visual generation with diffusion models","venue":null,"work_id":"80f935e2-5a22-4403-9bc8-5390a74e1ba2","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:59.658359Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:4ae4b349dd31755b4fb7234ca442fc788ebd093b26a3ed021f3f1adc1faf36bd","observation_id":"055273bd-b2c2-4752-967b-2ccf86bf6c2a","resolution":{"observed_at":"2026-08-07T11:34:13.499803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:13.055620Z","title":"Classifier-free diffusion guidance","venue":null,"work_id":"e67b5b89-e3ff-46e2-81e1-df42e9bbb2e9","year":2021},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:59.796870Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:a99ea985326c628eaef2d0cb2a07add57ee6e489f9c20b39e06af7eae230482c","observation_id":"14b2b457-1036-49ed-9538-63bbf83bb551","resolution":{"observed_at":"2026-08-07T11:34:13.166177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:12.796416Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":"b3c4264d-6d78-47c1-9513-136e7077e476","year":2020},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:33:59.960055Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:884c5fd2d2fa53ce687261d0431db40a9b38ea516b97631102946f6c08db618f","observation_id":"ce8f5b7a-f7fa-4d9c-a7d4-fa17f89f0648","resolution":{"observed_at":"2026-08-07T11:34:12.913159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:00.071018Z","title":"Video dif- fusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:00.071018Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:230f1f1f3b884eadf6ad2367f04610f0e2040ae82d4c627c0af0ed4b26126720","observation_id":"4467fa8f-e1d0-4cfc-8eb9-b720e18bd923","resolution":{"observed_at":"2026-08-07T11:34:00.071018Z","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":"2026-08-07T11:34:12.542903Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":"59744e7e-dd6a-422e-86d2-19134bd35936","year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:00.194593Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:e1b9a8a3bcd5f551e0af1d5d60ccd838d9115fb8e800b0e7799dd0809681700a","observation_id":"63699cd7-05c4-4f73-b785-43fcb7be7244","resolution":{"observed_at":"2026-08-07T11:34:12.657054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15506","last_updated":"2025-01-03T15:39:16Z","snapshot_observed_at":"2026-07-06T18:04:42.102581Z","submitted_at":"2024-03-22T02:30:46Z","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15506","snapshot_observed_at":"2026-08-07T11:34:00.312873Z","title":"Metric3d v2: A versatile monocular geomet- ric foundation model for zero-shot metric depth and surface 9 normal estimation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:00.312873Z"},"links":{"cited_paper":"/paper/2404.15506","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:dcfc233c01d3f3d917176dda8b571bc106cca2e737d1ca935e3827f758a54ad6","observation_id":"e47a2a94-5b3d-4d74-91c0-f467b6acf5ab","resolution":{"observed_at":"2026-08-07T11:34:00.312873Z","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":"2026-08-07T11:34:00.433847Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:00.433847Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:d98f4859932313402374f80b30e42c9722122615f3ea18c8f11b8a0b498d7a8e","observation_id":"5b262491-79a5-4f11-ba1b-6e9472945dda","resolution":{"observed_at":"2026-08-07T11:34:00.433847Z","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":"2026-08-07T11:34:12.223853Z","title":"Repurpos- ing diffusion-based image generators for monocular depth estimation","venue":null,"work_id":"84adfd21-9a84-4b95-b20e-7cf9d35c56d0","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:00.580884Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:55bae2ccad4b8ebdbfdb4319f0bb22165c2c82e6c9e77ddd829b35a39907d120","observation_id":"5a8188f3-3090-4a80-88c1-2d695987005c","resolution":{"observed_at":"2026-08-07T11:34:12.374917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:11.984205Z","title":"Understanding diffu- sion objectives as the elbo with simple data augmentation","venue":null,"work_id":"776eddbe-7a7b-4018-8b2e-0f1b6eae0d0a","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:00.715793Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:8a786d67300c2b046af02ad4494529d401ee707a348c041d1c81c089dd9a601b","observation_id":"c6df2a8a-af85-4e11-b4dc-c271c82d854d","resolution":{"observed_at":"2026-08-07T11:34:12.092308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:11.723634Z","title":null,"venue":null,"work_id":"e0b816e0-3e74-47a3-855f-eb190da73fc0","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:00.816159Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:87b6516ecf7ef99a73caafd4d663b392c358b72b0f5aeca05fa74870b901179d","observation_id":"182072cb-a137-437d-b425-98584247c792","resolution":{"observed_at":"2026-08-07T11:34:11.860273Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:11.435826Z","title":"Improving the training of rectified flows","venue":null,"work_id":"5861b92a-b4de-4c3d-bf23-e04215cada41","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:00.944316Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:85f37684a7c032b99f1cccbf914ff98a639be065cdb34b2a0fa7d168035a3b62","observation_id":"69fb86f0-a302-4e5e-b21d-1aabb7b03387","resolution":{"observed_at":"2026-08-07T11:34:11.559543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:11.164818Z","title":"Common diffusion noise schedules and sample steps are flawed","venue":null,"work_id":"194766e2-ef16-4abb-b8eb-5c29b7717359","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:01.071040Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:18d48392692f3f15fb5817ea2255bf78a2106e9092698a362f3257edbcd25847","observation_id":"1133d6c4-0cbd-40e3-9519-60684f9a1341","resolution":{"observed_at":"2026-08-07T11:34:11.300820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:10.908318Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"748cb47e-8b32-4b24-bd94-5ae561fc674a","year":2014},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:01.233435Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:31e56aec3e5b589e058009ee15e6da084803ad14765e5e74dca8837bb83c4a39","observation_id":"0fd5534e-50c3-4f34-9280-8a73e6223725","resolution":{"observed_at":"2026-08-07T11:34:11.004246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-02T18:24:58.914589Z","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":"2026-08-07T11:34:01.376255Z","title":"Flow matching for generative mod- eling","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:01.376255Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:4bcc240bbe60b3710424eb17b8537efcebd2ac13c140fc61227ec925b51d0de2","observation_id":"93703b74-7ac5-495d-9005-3311b3a5f20f","resolution":{"observed_at":"2026-08-07T11:34:01.376255Z","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":"2026-08-07T11:34:10.645317Z","title":"Au- dioldm: Text-to-audio generation with latent diffusion mod- els","venue":null,"work_id":"1c2a075e-b1c9-4c42-88b5-80232432bf1c","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:01.508657Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:93839e850a4fdf4671638832021b94674c7e2b4eea8c811262c0b78ff22538ce","observation_id":"4c52cdeb-7932-49ff-b4ef-ac7ff4676e34","resolution":{"observed_at":"2026-08-07T11:34:10.764958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-07T11:34:01.622130Z","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":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:01.622130Z"},"links":{"cited_paper":"/paper/2209.03003","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:ec5a6262e58050f00dd45fc2b86bd88eedd062ffdf0900c36b0d6e411df7bfa1","observation_id":"a9288bda-7f85-4e5b-b272-501676b62165","resolution":{"observed_at":"2026-08-07T11:34:01.622130Z","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":"2026-08-07T11:34:01.753289Z","title":"Instaflow: One step is enough for high-quality diffusion- based text-to-image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:01.753289Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:a5dff9377737741c02073d5532ed6d311d2f917a112809ae138fc4f018894c93","observation_id":"42803282-daac-4045-a954-5a33b89917bd","resolution":{"observed_at":"2026-08-07T11:34:01.753289Z","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":"2026-08-07T11:34:01.865671Z","title":"Dpm-solver: A fast ode solver for diffusion probabilistic model sampling in around 10 steps","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:01.865671Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:9bdced251e6d49bd42b395e6f99cf854417daa6cb920079b11ae427cff39e0cd","observation_id":"f7a3e0c4-e90e-4652-9153-5ffbb70139f4","resolution":{"observed_at":"2026-08-07T11:34:01.865671Z","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":"2026-08-07T11:34:10.425539Z","title":"Diffusion hyperfeatures: searching through time and space for semantic correspondence","venue":null,"work_id":"fde8dcd3-1290-4d8c-9c60-0912737f3cd1","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:01.968388Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:8f1ed6031db7be017bc9591a2e0867e919cd3c9833ef95f253205f05e6daebbe","observation_id":"31fa962c-2337-41e2-aac2-1fd287387479","resolution":{"observed_at":"2026-08-07T11:34:10.527746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05556","last_updated":"2023-11-09T18:04:15Z","snapshot_observed_at":"2026-07-06T16:45:20.005195Z","submitted_at":"2023-11-09T18:04:15Z","title":"LCM-LoRA: A Universal Stable-Diffusion Acceleration Module","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05556","snapshot_observed_at":"2026-08-07T11:34:02.106675Z","title":"Lcm-lora: A universal stable-diffusion acceleration module","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:02.106675Z"},"links":{"cited_paper":"/paper/2311.05556","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:5810e998408bb033f08dce3dcac829c8a7b23b6ff5dcd59207d7795c0494d5e9","observation_id":"5bc9a9ad-6133-478f-8300-e7f51e93a804","resolution":{"observed_at":"2026-08-07T11:34:02.106675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08740","last_updated":"2024-09-23T15:59:41Z","snapshot_observed_at":"2026-08-07T23:50:09.060564Z","submitted_at":"2024-01-16T18:55:25Z","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08740","snapshot_observed_at":"2026-08-07T11:34:02.216529Z","title":"Sit: Explor- ing flow and diffusion-based generative models with scalable interpolant transformers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:02.216529Z"},"links":{"cited_paper":"/paper/2401.08740","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:5b1e6c8aaf5a57238e425add8d0f9338aa0a07e354ef4020add6dc548250fb49","observation_id":"fd4c6d52-7a06-46d3-a29b-333bc1ac5793","resolution":{"observed_at":"2026-08-07T11:34:02.216529Z","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":"2026-08-07T11:34:10.251598Z","title":"Fine-tuning image-conditional diffusion models is easier than you think","venue":null,"work_id":"fcd45017-0959-4e2d-9832-cd74e860e28d","year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:02.359009Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:96b8e572f17902faef5a35cfff497896353c17184c5b7e87f4d7d66d3811a394","observation_id":"3054d0a8-5d02-4817-9ca8-474fe10b2f04","resolution":{"observed_at":"2026-08-07T11:34:10.327087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:02.489052Z","title":"On distillation of guided diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:02.489052Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:616fa398dffcbc11c347fd18802055abfb99048339f470b87e106da7239167ba","observation_id":"52679af6-5c98-470a-9d41-1985177411e3","resolution":{"observed_at":"2026-08-07T11:34:02.489052Z","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":"2026-08-07T11:34:10.034360Z","title":"Indoor segmentation and support inference from rgbd images","venue":null,"work_id":"36e1a022-fcd3-426c-8ad4-97812627944d","year":2012},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:02.618331Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:165d16116d7de2f0e4a309d4dfcb466da68013691b43a8405eed292507c8bcc2","observation_id":"96d4537b-f846-417d-a521-aa3a9a2ab92b","resolution":{"observed_at":"2026-08-07T11:34:10.105627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:09.844020Z","title":"Glide: Towards photorealis- tic image generation and editing with text-guided diffusion models","venue":null,"work_id":"4ee06b88-955e-4ef1-aa22-1fbad5f37895","year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:02.766180Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:315553ef3f298544a6a5d721f91faa7e67bfca089b62894eb9c39d4095704912","observation_id":"61e2bea4-75f7-41e0-9d24-1dcff0759871","resolution":{"observed_at":"2026-08-07T11:34:09.946784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:02.883059Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:02.883059Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:943bdb87460d0f219105c06744ef5607566a2fb029cbddbd40476c65ce3c14de","observation_id":"fb33c966-5050-48a6-b74e-4b48f4d2980a","resolution":{"observed_at":"2026-08-07T11:34:02.883059Z","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":"2026-08-07T11:34:09.590000Z","title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":"48f427b9-86ca-42eb-b654-119b62387380","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:02.988081Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:30725d15caa8e7a23e23076f70f36ecb37cace2da383a31864fd028714b497f7","observation_id":"010479a1-0213-4a40-956c-5c9dc29de2ac","resolution":{"observed_at":"2026-08-07T11:34:09.720622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-07T11:34:03.095241Z","title":"Hierarchical text-conditional image gen- eration with clip latents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:03.095241Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:07382934fd31012052b93ef4ac89933fd9901afd1aca8f9a70ce89b7fdefa10a","observation_id":"0b59607d-31c9-4f0d-9ad9-918f9dd02bc9","resolution":{"observed_at":"2026-08-07T11:34:03.095241Z","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":"2026-08-07T11:34:03.195615Z","title":"Susskind","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:03.195615Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:33d9d62aefe236bb381e0c3c38788398589cc36751800daef2882e90f775eaee","observation_id":"f5365c08-cfd2-49ef-90d9-e1c90a50ba8c","resolution":{"observed_at":"2026-08-07T11:34:03.195615Z","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":"2026-08-07T11:34:09.325375Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"14e9ce61-a5d3-4ad4-a7b5-4e9e269c3fc9","year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:03.322025Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:5a14e8606d966b7c0c51fd957034fa33da2e866af1f2133fd67559fa135db671","observation_id":"a22a4fbb-72a8-4617-abdd-543f4221ccad","resolution":{"observed_at":"2026-08-07T11:34:09.453738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:09.144025Z","title":"Low-rank adaptation for fast text- to-image diffusion fine-tuning","venue":null,"work_id":"5aa0a0d5-65b2-4225-abf1-d67958306bbe","year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:03.471645Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:9b91120f0cac847b5cbe579efb2a10c6bdbcfbe0cac46f7824580b691abab0ec","observation_id":"d245481c-2358-4167-87af-d99d4ad24d66","resolution":{"observed_at":"2026-08-07T11:34:09.234129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:08.915964Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":"63c28e38-8aeb-49cd-811a-0359e0fc32b0","year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:03.584269Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:36d9725d8cf4edb3419b196a2d6fe14a0d776702e3c8f7f111b6915d08a63108","observation_id":"dde4719c-5170-4d7b-a41c-f0c684e5051b","resolution":{"observed_at":"2026-08-07T11:34:09.027062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:03.667772Z","title":"Progressive distillation for fast sampling of diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:03.667772Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:e78afcb9f27a2be43e0ed20d8aaa101eb6752511f6ed095f23ddac45d3e961bf","observation_id":"cead7f1f-7032-477e-b3c8-9ae3e366852b","resolution":{"observed_at":"2026-08-07T11:34:03.667772Z","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":"2026-08-07T11:34:03.788564Z","title":"Adversarial diffusion distillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:03.788564Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:d6afff4807ac4981270851ad9260b94e898dae2a82a582e976d95274145275bf","observation_id":"e51e8f78-9113-4390-9b9b-37b51c542c3a","resolution":{"observed_at":"2026-08-07T11:34:03.788564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.14816","last_updated":"2023-02-28T18:08:21Z","snapshot_observed_at":"2026-08-05T15:26:54.980348Z","submitted_at":"2023-02-28T18:08:21Z","title":"Monocular Depth Estimation using Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.14816","snapshot_observed_at":"2026-08-07T11:34:03.910640Z","title":"Monocular depth estimation using diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:03.910640Z"},"links":{"cited_paper":"/paper/2302.14816","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:b49c743f1bf2c82768f95d83f75f20b306b3e9070f9dfa5f5c5498cf58660978","observation_id":"f62b748c-a7e3-4957-b59b-14089bf70a18","resolution":{"observed_at":"2026-08-07T11:34:03.910640Z","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":"2026-08-07T11:34:08.677137Z","title":"A multi-view stereo benchmark with high- resolution images and multi-camera videos","venue":null,"work_id":"65438073-d9b5-40af-9c27-b34818594464","year":2017},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.035802Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:a378a562d3f1bb2b231649abc194f6641ae481915a6626c6bd1e33b167210d47","observation_id":"3292057f-e716-4294-874b-a0e052c37ba0","resolution":{"observed_at":"2026-08-07T11:34:08.798622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:08.426153Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models","venue":null,"work_id":"664fd719-4b36-4683-864a-e33baf778f5b","year":2022},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.190227Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:be448d219ad0eb705a3dc0cd2ff6e6c246310628eaf42b643b2c1bedd251acc1","observation_id":"a5c544ad-6120-4e69-b739-1cd475547ba1","resolution":{"observed_at":"2026-08-07T11:34:08.529539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:08.228575Z","title":"Boosting latent diffusion with flow match- ing","venue":null,"work_id":"af8ccadb-1769-4ec3-bcbf-37ca3e251038","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.279419Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:1ee9d67de29da9e769b1f4df942edaf4ddc5c3b6a6b9cf07ff218790a7087c0d","observation_id":"2d1c8ad0-5bb5-4bf6-bfa0-dab3aaee1a71","resolution":{"observed_at":"2026-08-07T11:34:08.340180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.19075","last_updated":"2023-10-29T16:58:31Z","snapshot_observed_at":"2026-07-06T16:40:08.030032Z","submitted_at":"2023-10-29T16:58:31Z","title":"Bespoke Solvers for Generative Flow Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19075","snapshot_observed_at":"2026-08-07T11:34:04.386658Z","title":"Bespoke solvers for genera- tive flow models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.386658Z"},"links":{"cited_paper":"/paper/2310.19075","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:35c1f43666d0aa18450de67cbcf4631678dd2b73158337705450f81f67a2cfbe","observation_id":"d9779b2e-53c0-4f18-8bd2-14a708ad5230","resolution":{"observed_at":"2026-08-07T11:34:04.386658Z","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":"2026-08-07T11:34:04.521602Z","title":"Denois- ing diffusion implicit models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.521602Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:ebb646595f56c2f8a7aa36a8047b1a188387dbb49c9a0590b9f98fcbf56827f0","observation_id":"c3332ee6-5cb1-4f4a-a2ae-5ac67bb8d792","resolution":{"observed_at":"2026-08-07T11:34:04.521602Z","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":"2026-08-07T11:34:04.679153Z","title":"Score-based generative modeling through stochastic differential equa- tions","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.679153Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:c23116561d78c0c811c488480dbad1fc73a300d975ac3d2d7f84afa2dd331ffd","observation_id":"2a658d97-a691-42cb-9d4d-6987d014a980","resolution":{"observed_at":"2026-08-07T11:34:04.679153Z","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":"2026-08-07T11:34:07.977397Z","title":"Consistency models","venue":null,"work_id":"7215b923-1930-4d5b-85c8-6f8809cf0b15","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.795451Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:6e07269ee7ad5c0c320943d3df74a20992501983cbb4f36557ee601d516caac1","observation_id":"73550a7a-9b08-4887-9ac7-bf600b94e075","resolution":{"observed_at":"2026-08-07T11:34:08.099595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07913","last_updated":"2024-10-08T15:14:29Z","snapshot_observed_at":"2026-07-31T15:34:00.016832Z","submitted_at":"2024-05-13T16:46:44Z","title":"CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07913","snapshot_observed_at":"2026-08-07T11:34:04.864808Z","title":"Ctrloralter: Con- ditional loradapter for efficient 0-shot control & altering of t2i models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.864808Z"},"links":{"cited_paper":"/paper/2405.07913","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:d5c525210b3fc90193204153a6de69aa21d962bbd8f839f6efa5b94cee94bd48","observation_id":"cdedb216-4f22-4e79-9202-ef095ca9fd34","resolution":{"observed_at":"2026-08-07T11:34:04.864808Z","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":"2026-08-07T11:34:07.745382Z","title":"Emergent correspondence from im- age diffusion","venue":null,"work_id":"a62fe9b2-e44e-41f7-ad10-d9b357c8b075","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:04.983292Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:69dfb2bd8859cc1dd86a53f94381511e0fe268dd2b47afd1738047368a007991","observation_id":"ad02aebd-de39-40dc-9a9d-33b3408882a3","resolution":{"observed_at":"2026-08-07T11:34:07.842580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:07.504270Z","title":"Improving and generalizing flow-based gen- erative models with minibatch optimal transport","venue":null,"work_id":"1ab3f12e-3887-4166-848c-860aebe4fde3","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:05.092925Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:67f565ea31b166c2c169da064712437fadd841444ffd2ad0a408143dd9630b99","observation_id":"4642e35f-dad1-4c71-918e-c92347fa758c","resolution":{"observed_at":"2026-08-07T11:34:07.620005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:07.245994Z","title":"Dai, Andrea F","venue":null,"work_id":"b0fecc0a-8a6d-46e9-aa7b-c732fb9d8a42","year":2019},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:05.190794Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:bf11b70feef7849fd08bc1920e5e0962113d6fd71c721c36a509fd6bdcbd4765","observation_id":"14ac07bd-4129-4399-aa56-68c8f75bc536","resolution":{"observed_at":"2026-08-07T11:34:07.365097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:07.033742Z","title":"Open-vocabulary panop- tic segmentation with text-to-image diffusion models","venue":null,"work_id":"4b090773-39a4-4947-9e39-5b47130bee66","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:05.357414Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:8568f4381d868ddd11a2d5200b7666673f2fe1a5ec6c0a8b8842b8495b793538","observation_id":"6d58f621-00be-4cbb-847b-87f84cacab1c","resolution":{"observed_at":"2026-08-07T11:34:07.126883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:06.816351Z","title":"Perflow: Piecewise rectified flow as universal plug-and-play accelerator, 2024","venue":null,"work_id":"687c6408-856d-4fd5-93de-070a4d8fc2ff","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:05.474230Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:a41520ce91d38cdf94506f92535ae501089f86952adcfa29c17618a9945c3b2e","observation_id":"09d023ca-7e5a-4dc7-9541-028ff014344b","resolution":{"observed_at":"2026-08-07T11:34:06.921645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T11:34:06.605192Z","title":"Depth anything: Unleashing the power of large-scale unlabeled data","venue":null,"work_id":"0a77d388-1ed9-45ec-bd4c-cc5d5cde2679","year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:05.623240Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:d3346896ae18b14ae6dea6b5c8f022e6d74202f09b7d582b1e41ae944e2743a9","observation_id":"da54b21e-18f7-4472-ac26-439596bd0d4b","resolution":{"observed_at":"2026-08-07T11:34:06.717559Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09414","last_updated":"2024-10-20T11:24:09Z","snapshot_observed_at":"2026-07-06T18:30:32.982860Z","submitted_at":"2024-06-13T17:59:56Z","title":"Depth Anything V2","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09414","snapshot_observed_at":"2026-08-07T11:34:05.787660Z","title":"Depth any- thing v2","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:05.787660Z"},"links":{"cited_paper":"/paper/2406.09414","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:5ed2432d142d4f4969ba2fc4526a8a03a8ad013e9dec82e33fe41c0b6b16d8da","observation_id":"74412f08-06d0-4ffd-a2a3-b61b6aca16ac","resolution":{"observed_at":"2026-08-07T11:34:05.787660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06721","last_updated":"2023-08-13T08:34:51Z","snapshot_observed_at":"2026-07-06T16:05:39.158819Z","submitted_at":"2023-08-13T08:34:51Z","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06721","snapshot_observed_at":"2026-08-07T11:34:05.953733Z","title":"Ip- adapter: Text compatible image prompt adapter for text-to- image diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:05.953733Z"},"links":{"cited_paper":"/paper/2308.06721","citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:443968f0bfbf6ed86e1b1d8ef0d6dcde724040e73d854214e7584ab1e6897dc2","observation_id":"87d761b5-1a3d-47cf-8cc1-f9181fbca22e","resolution":{"observed_at":"2026-08-07T11:34:05.953733Z","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":"2026-08-07T11:34:06.394287Z","title":"LoRA base","venue":null,"work_id":"fb94ed5d-f8a8-42e2-9573-6fbe2f38c7a1","year":2023},"citing_paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T11:34:06.057829Z"},"links":{"citing_paper":"/paper/2506.02221"},"observation_digest":"sha256:2005aada15accfbfe41db8ed8a1df5aea1733e02f154d726dacece8fb6ab3061","observation_id":"0a61bb08-d273-4344-87e2-5971c583c968","resolution":{"observed_at":"2026-08-07T11:34:06.486250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.02221","last_updated":"2025-06-02T20:05:05Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T11:25:53.363429Z","submitted_at":"2025-06-02T20:05:05Z","title":"Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":0,"verified_fuzzy":37},"total_outbound_references":68},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 2 inbound Pith citation observations for arXiv:2506.02221."}