{"as_of":"2026-08-10T04:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9525c478baccde64913d82aa5a5f5ab73e6b315d656a257015f7497cedae7930","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T15:20:57.772970Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T12:43:31.615735Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-14T23:48:19.353564Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.01441","snapshot_observed_at":"2026-08-05T12:43:31.615735Z","title":"Improved training technique for latent consistency models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.01492","last_updated":"2025-09-01T14:11:59Z","snapshot_observed_at":"2026-08-08T16:21:56.627652Z","submitted_at":"2025-09-01T14:11:59Z","title":"A Continuous-Time Consistency Model for 3D Point Cloud Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T12:43:31.615735Z"},"links":{"cited_paper":"/paper/2502.01441","citing_paper":"/paper/2509.01492"},"observation_digest":"sha256:acc9d32e2ea3a9831fa52eeba419ee437be360c13050d5782b30883e7fa23f47","observation_id":"ff8072be-53b3-4d3f-bbcd-f62107582bac","resolution":{"observed_at":"2026-08-05T12:43:31.615735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"cited_work":{"arxiv_id":"2502.01441","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01441","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improved training technique for latent consistency models","venue":null,"work_id":"d230cc85-3a16-4b30-a001-33dcd0756cc1","year":2025},"citing_paper":{"arxiv_id":"2603.26357","last_updated":"2026-04-04T00:36:49Z","snapshot_observed_at":"2026-07-31T15:31:41.723690Z","submitted_at":"2026-03-27T12:30:10Z","title":"MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-14T23:46:25.197344Z"},"links":{"cited_paper":"/paper/2502.01441","citing_paper":"/paper/2603.26357"},"observation_digest":"sha256:d6642173405b7049ee781a4de9df64a583a51e5f2ae5f4c53d3d0810c63626d4","observation_id":"aa60b309-4459-4c29-8b14-257ee24980e2","resolution":{"observed_at":"2026-05-14T23:48:19.359351Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"cited_work":{"arxiv_id":"2502.01441","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01441","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improved training technique for latent consistency models","venue":null,"work_id":"d230cc85-3a16-4b30-a001-33dcd0756cc1","year":2025},"citing_paper":{"arxiv_id":"2604.08837","last_updated":"2026-04-10T00:25:44Z","snapshot_observed_at":"2026-07-06T22:57:50.266735Z","submitted_at":"2026-04-10T00:25:44Z","title":"Discrete Meanflow Training Curriculum","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T18:15:51.900778Z"},"links":{"cited_paper":"/paper/2502.01441","citing_paper":"/paper/2604.08837"},"observation_digest":"sha256:90556a5275fad95c0b762faf82b27470e5c9f2f378ab10606a9c8670877a307d","observation_id":"dee5886e-a505-4206-92ef-a0cb14332d0f","resolution":{"observed_at":"2026-05-11T05:10:55.581103Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"cited_work":{"arxiv_id":"2502.01441","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.01441","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improved training technique for latent consistency models","venue":null,"work_id":"d230cc85-3a16-4b30-a001-33dcd0756cc1","year":2025},"citing_paper":{"arxiv_id":"2604.15911","last_updated":"2026-04-17T10:11:39Z","snapshot_observed_at":"2026-07-06T23:03:21.422544Z","submitted_at":"2026-04-17T10:11:39Z","title":"Efficient Video Diffusion Models: Advancements and Challenges","version":1},"reference_index":250,"source":"pdf_text","source_observed_at":"2026-05-10T08:28:29.706249Z"},"links":{"cited_paper":"/paper/2502.01441","citing_paper":"/paper/2604.15911"},"observation_digest":"sha256:11c7abafe58ebca3cc2a41261228f042d84bb511c6a3a2189469b0784abec4fe","observation_id":"2afdef9f-3c79-49f7-a664-f06d82810aaa","resolution":{"observed_at":"2026-05-10T09:03:26.086951Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.01441/citation-record","integrity":"/paper/2502.01441/integrity","json":"/paper/2502.01441/citation-record.json","paper":"/paper/2502.01441"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2412.16906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T15:20:59.404011Z","title":"Self-corrected flow distillation for consistent one-step and few-step text-to-image generation","venue":null,"work_id":"3441b6ab-e594-4a79-b6d5-ab7af00709d8","year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.517017Z"},"links":{"citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:0877ba58c4d7ecc09f2a29cf011959bac66dc78ca28abbd70a74d4e1963007df","observation_id":"1b58bbe3-c826-4d6a-891f-a86b4003c963","resolution":{"observed_at":"2026-08-09T15:20:59.411396Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.06807","last_updated":"2024-11-19T14:31:02Z","snapshot_observed_at":"2026-08-03T11:30:00.885783Z","submitted_at":"2024-03-11T15:26:34Z","title":"Multistep Consistency Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.06807","snapshot_observed_at":"2026-08-09T15:20:57.572858Z","title":"Multistep consistency models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.572858Z"},"links":{"cited_paper":"/paper/2403.06807","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:6e61e51d52e7eb1524f197a4f096dcc2cc88fdfb46f10a2d904e3a4c34768feb","observation_id":"d931c44c-73c9-4665-b0b7-63ddb5e74975","resolution":{"observed_at":"2026-08-09T15:20:57.572858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.14097","last_updated":"2024-03-28T17:59:06Z","snapshot_observed_at":"2026-08-05T15:53:31.800541Z","submitted_at":"2023-11-23T16:49:06Z","title":"ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models","version":3},"cited_work":{"arxiv_id":"2311.14097","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.14097","snapshot_observed_at":"2026-08-09T15:20:58.037976Z","title":"ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models","venue":"cs.CV","work_id":"afedc1a1-e592-449b-bd4a-0d5438bc59cb","year":2023},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.597287Z"},"links":{"cited_paper":"/paper/2311.14097","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:de3c54321c3687291b68b2a50bc0550209bb8a24fb8f75dd01ccc5b5a7cd2542","observation_id":"5a64b7be-06b0-4ba7-9241-c721967df208","resolution":{"observed_at":"2026-08-09T15:20:58.044609Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T15:20:59.496443Z","title":"Multi-concept customization of text-to-image diffusion","venue":null,"work_id":"4d2bde33-feda-46b2-b0b3-1b0cfa050101","year":1931},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.601755Z"},"links":{"citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:7ea96cb04cf68e15c065a3a489460ed755a2f28532658e6d1b4de908b4105b0e","observation_id":"bc9f7c7a-ccfe-4407-99bf-0f9d9e37f1cb","resolution":{"observed_at":"2026-08-09T15:20:59.500955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12003","last_updated":"2023-05-25T11:33:13Z","snapshot_observed_at":"2026-08-07T23:56:02.237466Z","submitted_at":"2023-01-27T21:52:03Z","title":"Minimizing Trajectory Curvature of ODE-based Generative Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.12003","snapshot_observed_at":"2026-08-09T15:20:57.606197Z","title":"Minimizing trajectory curvature of ode-based gen- erative models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.606197Z"},"links":{"cited_paper":"/paper/2301.12003","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:a902f5637ca83520dcced2097f9d2f71c1eeedf9cc044c539dde1d327f4c18e7","observation_id":"83b9fb2a-06fc-440a-8352-4bbc78e5e551","resolution":{"observed_at":"2026-08-09T15:20:57.606197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.01073","last_updated":"2022-01-05T00:07:35Z","snapshot_observed_at":"2026-08-08T06:35:17.078531Z","submitted_at":"2021-08-02T17:59:47Z","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.01073","snapshot_observed_at":"2026-08-09T15:20:57.611217Z","title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.611217Z"},"links":{"cited_paper":"/paper/2108.01073","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:4e47e6984e74d52ace1a45e8102942f4cf4478dca2a8f1ea901bd33bccb3fec0","observation_id":"007a99a9-326d-4d68-b574-7c8b3bba4a31","resolution":{"observed_at":"2026-08-09T15:20:57.611217Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.09797","last_updated":"2020-06-28T20:37:50Z","snapshot_observed_at":"2026-08-09T23:44:47.022108Z","submitted_at":"2020-02-23T00:50:01Z","title":"Reliable Fidelity and Diversity Metrics for Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.09797","snapshot_observed_at":"2026-08-09T15:20:57.615892Z","title":"Reliable fidelity and diversity metrics for generative models.ArXiv, abs/2002.09797,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.615892Z"},"links":{"cited_paper":"/paper/2002.09797","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:e4c5badf9889a4d8d6f77b3954a37e26e1714238668f236fda46db1f48c31d27","observation_id":"9d65057c-9e11-4789-8e9b-1c407741fb17","resolution":{"observed_at":"2026-08-09T15:20:57.615892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12517","last_updated":"2024-03-20T11:24:06Z","snapshot_observed_at":"2026-07-06T17:19:14.478786Z","submitted_at":"2024-01-23T06:21:34Z","title":"DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12517","snapshot_observed_at":"2026-08-09T15:20:57.620623Z","title":"12 Published as a conference paper at ICLR 2025 Dogyun Park, Sihyeon Kim, Sojin Lee, and Hyunwoo J Kim","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.620623Z"},"links":{"cited_paper":"/paper/2401.12517","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:545a289db805db7f6999f21ac4ddf4a7aceee4d5adfca4752fc6b9bf00f6be27","observation_id":"0321ab73-6b40-43d8-b7c8-d2d1777eb41e","resolution":{"observed_at":"2026-08-09T15:20:57.620623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.04168","last_updated":"2025-04-10T23:29:21Z","snapshot_observed_at":"2026-08-02T01:13:22.950483Z","submitted_at":"2024-11-06T18:59:17Z","title":"DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.04168","snapshot_observed_at":"2026-08-09T15:20:57.625514Z","title":"Dimsum: Diffu- sion mamba–a scalable and unified spatial-frequency method for image generation.arXiv preprint arXiv:2411.04168,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.625514Z"},"links":{"cited_paper":"/paper/2411.04168","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:b0725155a175826e1cc388f0d5d5c6612c1368731ea6a773c96e527ed42636d8","observation_id":"b5bea0f2-d4ed-4741-9637-f1e9789cb13b","resolution":{"observed_at":"2026-08-09T15:20:57.625514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.14772","last_updated":"2023-05-24T18:17:17Z","snapshot_observed_at":"2026-08-09T01:57:21.665743Z","submitted_at":"2023-04-28T11:33:08Z","title":"Multisample Flow Matching: Straightening Flows with Minibatch Couplings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.14772","snapshot_observed_at":"2026-08-09T15:20:57.630435Z","title":"Multisample flow matching: Straightening flows with minibatch cou- plings","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.630435Z"},"links":{"cited_paper":"/paper/2304.14772","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:d5eb008aa9d60f1a200f311ab04049030f25835ea0b31534cf55c0ee213c763a","observation_id":"1db0df69-a7a7-4b45-a195-045acc03f433","resolution":{"observed_at":"2026-08-09T15:20:57.630435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.13686","last_updated":"2024-11-04T13:24:18Z","snapshot_observed_at":"2026-08-04T05:24:37.569197Z","submitted_at":"2024-04-21T15:16:05Z","title":"Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13686","snapshot_observed_at":"2026-08-09T15:20:57.635217Z","title":"Hyper-sd: Trajectory segmented consistency model for efficient image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.635217Z"},"links":{"cited_paper":"/paper/2404.13686","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:48e7f81bc9c401902d04f0ca3740662424c8a726f2a3baab66992ce657613495","observation_id":"b414525b-8957-471b-8f6d-5fc575c640c7","resolution":{"observed_at":"2026-08-09T15:20:57.635217Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.17042","last_updated":"2023-11-28T18:53:24Z","snapshot_observed_at":"2026-07-06T16:53:58.875152Z","submitted_at":"2023-11-28T18:53:24Z","title":"Adversarial Diffusion Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17042","snapshot_observed_at":"2026-08-09T15:20:57.648480Z","title":"Adversarial diffusion dis- tillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.648480Z"},"links":{"cited_paper":"/paper/2311.17042","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:475532670af97f6f4b51df3cb1f500c6c87a8e8962f14012cae9dda2b9d4bbfa","observation_id":"0eb120a5-9824-4423-9b60-27e5752e4088","resolution":{"observed_at":"2026-08-09T15:20:57.648480Z","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":"2026-08-09T15:20:57.692326Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.692326Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:170ebca9f45f8193f9fc797568b211f224f0e0b297fd045d465fcfd4bf9c67f9","observation_id":"aa48c951-1b9c-44e8-bfdc-cf39b79fd7a6","resolution":{"observed_at":"2026-08-09T15:20:57.692326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.01469","last_updated":"2023-05-31T06:17:10Z","snapshot_observed_at":"2026-07-06T14:58:02.852672Z","submitted_at":"2023-03-02T18:30:16Z","title":"Consistency Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.01469","snapshot_observed_at":"2026-08-09T15:20:57.714155Z","title":"Consistency models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.714155Z"},"links":{"cited_paper":"/paper/2303.01469","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:7ff65e70d6cf16d172a5938089305a80f605eab9569b09a8509bc9c616e54b16","observation_id":"de642e40-2aad-4e73-9d0a-70a49204b668","resolution":{"observed_at":"2026-08-09T15:20:57.714155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.03350","last_updated":"2023-09-04T15:00:33Z","snapshot_observed_at":"2026-08-10T01:54:02.067073Z","submitted_at":"2023-09-04T15:00:33Z","title":"Relay Diffusion: Unifying diffusion process across resolutions for image synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.03350","snapshot_observed_at":"2026-08-09T15:20:57.734244Z","title":"Relay diffusion: Unifying diffusion process across resolutions for image synthesis.arXiv preprint arXiv:2309.03350,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.734244Z"},"links":{"cited_paper":"/paper/2309.03350","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:cf7e5318ef8aeaa9e2603a5b6cbba196db98985d41ddfe70dc5348676a31aaf6","observation_id":"2186e0d5-ffee-487f-a51e-21137e03cdc5","resolution":{"observed_at":"2026-08-09T15:20:57.734244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.00482","last_updated":"2024-03-11T14:27:48Z","snapshot_observed_at":"2026-07-06T14:47:04.817434Z","submitted_at":"2023-02-01T14:47:17Z","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.00482","snapshot_observed_at":"2026-08-09T15:20:57.745792Z","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.745792Z"},"links":{"cited_paper":"/paper/2302.00482","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:9c644c2a1fff3c13a23d0d42b1d4995ff4f63ac9f9ffc12872fb6542f8f33dea","observation_id":"7cfe6197-9ad4-45d4-b737-42373a06cc19","resolution":{"observed_at":"2026-08-09T15:20:57.745792Z","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":"2026-08-09T15:20:59.481704Z","title":"Pro- lificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","venue":null,"work_id":"5907f64b-a85c-424e-8780-9e1b077af710","year":2025},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.750449Z"},"links":{"citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:85a69646c3008fdaf61e80dda4ba375e984ed76e41bc9a76f838afe897e8c720","observation_id":"c7fcb881-1201-4804-8ed5-8807d376e748","resolution":{"observed_at":"2026-08-09T15:20:59.486477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07804","last_updated":"2022-04-04T18:55:28Z","snapshot_observed_at":"2026-08-10T01:50:09.823474Z","submitted_at":"2021-12-15T00:09:38Z","title":"Tackling the Generative Learning Trilemma with Denoising Diffusion GANs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07804","snapshot_observed_at":"2026-08-09T15:20:57.754574Z","title":"Tackling the generative learning trilemma with denoising diffusion gans","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.754574Z"},"links":{"cited_paper":"/paper/2112.07804","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:0ac773cf7262fe2dd53b87454e9831432138b9421dcc83b06c785939f3085ef7","observation_id":"0e8e0a83-80e6-49cd-9d02-2e3516c69ad8","resolution":{"observed_at":"2026-08-09T15:20:57.754574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1506.03365","last_updated":"2016-06-04T09:51:30Z","snapshot_observed_at":"2026-08-08T13:26:17.517503Z","submitted_at":"2015-06-10T15:38:47Z","title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.03365","snapshot_observed_at":"2026-08-09T15:20:57.759908Z","title":"Lsun: Construction of a large- scale image dataset using deep learning with humans in the loop","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.759908Z"},"links":{"cited_paper":"/paper/1506.03365","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:ed407efefb0a3bf726b7a5de7a78ddf6e88822c2b6139d60cf980c59f1717293","observation_id":"a2b365f2-74dd-4976-85a8-b1f2053963c0","resolution":{"observed_at":"2026-08-09T15:20:57.759908Z","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":"2026-08-09T15:20:59.466897Z","title":"Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, and Qing Qu","venue":null,"work_id":"52b7cfe6-66de-4162-9f86-7d1a1568cd78","year":2024},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.764722Z"},"links":{"citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:8fa4d2eb67698c8455429e5e4087c6097a3d09efcdbfe909e946a28219679624","observation_id":"86cd1421-8efd-4478-b62b-c43af3d1fa65","resolution":{"observed_at":"2026-08-09T15:20:59.471776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.19159","last_updated":"2024-04-15T13:51:17Z","snapshot_observed_at":"2026-08-04T12:42:29.134022Z","submitted_at":"2024-02-29T13:44:14Z","title":"Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.19159","snapshot_observed_at":"2026-08-09T15:20:57.768825Z","title":"Trajectory consistency distillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.768825Z"},"links":{"cited_paper":"/paper/2402.19159","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:ebd5e3f31a6f6a1a82de4aad93f704f077c2359e338ada5e54fe9ca5ff408afb","observation_id":"17d41b41-6792-4eea-ab75-af96df8df365","resolution":{"observed_at":"2026-08-09T15:20:57.768825Z","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":"2026-08-09T15:20:59.452875Z","title":"We also provide additional uncurated samples of our models on CelebaA-HQ trained with L2 loss (12) and E-LatentLPIPS loss (13)","venue":null,"work_id":"57195af4-79e1-49bc-bfa2-9c9546743e25","year":2025},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.772970Z"},"links":{"citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:73f3c095ce831a3760ba3ba6695a72e58c4699cc791f175489066f52a2c9db86","observation_id":"3d3f59ba-4e0a-42b2-9d5c-6e78366cffc4","resolution":{"observed_at":"2026-08-09T15:20:59.457418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14548","last_updated":"2024-10-10T21:59:49Z","snapshot_observed_at":"2026-08-09T07:18:02.667044Z","submitted_at":"2024-06-20T17:56:02Z","title":"Consistency Models Made Easy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14548","snapshot_observed_at":"2026-08-09T15:20:57.543979Z","title":"Consistency models made easy","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":1986,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.543979Z"},"links":{"cited_paper":"/paper/2406.14548","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:4785965380fab022a47ab56bdc2a47b2bc4197295382b74c9cc3d869dcb08e0d","observation_id":"ad1ee258-a005-426e-8104-f417a2468e52","resolution":{"observed_at":"2026-08-09T15:20:57.543979Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14189","last_updated":"2023-10-22T05:33:38Z","snapshot_observed_at":"2026-08-03T16:40:35.231838Z","submitted_at":"2023-10-22T05:33:38Z","title":"Improved Techniques for Training Consistency Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14189","snapshot_observed_at":"2026-08-09T15:20:57.665419Z","title":"Improved techniques for training consistency models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.665419Z"},"links":{"cited_paper":"/paper/2310.14189","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:615a934ffdb3d261eb03c223d326066ff13cdbab8812dabb875bc678cb07aa3a","observation_id":"5c56e939-d74b-4936-a2d5-41fa09e84e63","resolution":{"observed_at":"2026-08-09T15:20:57.665419Z","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":"2026-08-09T15:20:59.510935Z","title":"Inbar Huberman-Spiegelglas, Vladimir Kulikov, and Tomer Michaeli","venue":null,"work_id":"0cc3a7ed-bb1c-43d7-978c-2c63ece31690","year":2018},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.582837Z"},"links":{"citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:05be16c875cb5f735ec2bee50c8774cc1c50870417d942846ad27fc7e79134f0","observation_id":"53376941-f8be-4f59-8a69-f7c65aea3744","resolution":{"observed_at":"2026-08-09T15:20:59.515725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.04248","last_updated":"2023-03-07T21:46:15Z","snapshot_observed_at":"2026-08-09T12:22:44.106674Z","submitted_at":"2023-03-07T21:46:15Z","title":"TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.04248","snapshot_observed_at":"2026-08-09T15:20:57.439955Z","title":"Tract: Denoising diffusion models with transitive closure time-distillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.439955Z"},"links":{"cited_paper":"/paper/2303.04248","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:8e65a3d2856dade1d7c28d9f1ff645a0e2f31d330a85b493de235738e18ec3d3","observation_id":"b935c1fb-1327-417f-aef3-d5e7c4d1b04b","resolution":{"observed_at":"2026-08-09T15:20:57.439955Z","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":"2026-08-09T15:20:59.526482Z","title":"Introvae: In- trospective variational autoencoders for photographic image synthesis","venue":null,"work_id":"84d5a9ce-d095-4c9b-bdf4-693a79a94db0","year":2025},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.578463Z"},"links":{"citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:78fff5607f16b0f7f947a6d2dc3cfbcb2d206dcc23e612e972a03b1909aab0be","observation_id":"75c60ace-4881-408f-bb7a-731130cc0b26","resolution":{"observed_at":"2026-08-09T15:20:59.531437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02279","last_updated":"2024-03-30T06:29:48Z","snapshot_observed_at":"2026-07-06T16:27:18.829052Z","submitted_at":"2023-10-01T05:07:17Z","title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02279","snapshot_observed_at":"2026-08-09T15:20:57.592553Z","title":"Consistency trajectory models: Learning proba- bility flow ode trajectory of diffusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.592553Z"},"links":{"cited_paper":"/paper/2310.02279","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:c19fc07d8e5e1b9be16e27dea2f845f592ff5a827dd289966416e8fa93a09c9f","observation_id":"8bedf3ff-82d5-48cc-8f62-cef11edb3ae7","resolution":{"observed_at":"2026-08-09T15:20:57.592553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.05527","last_updated":"2022-06-11T02:36:37Z","snapshot_observed_at":"2026-07-06T11:17:52.032348Z","submitted_at":"2021-06-10T06:30:16Z","title":"Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.05527","snapshot_observed_at":"2026-08-09T15:20:57.587398Z","title":"Soft truncation: A universal training technique of score-based diffusion model for high precision score estimation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.587398Z"},"links":{"cited_paper":"/paper/2106.05527","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:45e6c1a437ba36874e18e23e162bea487e2c234466904ae831a02ca2241fa95f","observation_id":"915e723c-44fb-457a-9b67-c05583af4f8f","resolution":{"observed_at":"2026-08-09T15:20:57.587398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08698","last_updated":"2023-07-17T17:57:56Z","snapshot_observed_at":"2026-08-04T12:09:15.933692Z","submitted_at":"2023-07-17T17:57:56Z","title":"Flow Matching in Latent Space","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08698","snapshot_observed_at":"2026-08-09T15:20:57.486031Z","title":"Flow matching in latent space","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.486031Z"},"links":{"cited_paper":"/paper/2307.08698","citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:6801e12d0a403a4413dcb73632daf3bf26c220d9b5d8049198cff4f69b98fb98","observation_id":"8a81bfd6-8fd0-48a0-a897-d5171c2c6229","resolution":{"observed_at":"2026-08-09T15:20:57.486031Z","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":"2026-08-09T15:20:57.568240Z","title":"Dice: Discrete inversion enabling controllable editing for multinomial diffusion and masked generative models.arXiv preprint arXiv:2410.08207,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T15:20:57.568240Z"},"links":{"citing_paper":"/paper/2502.01441"},"observation_digest":"sha256:721d1e90bd9e2a22405a1a0eb216582f1e03b92d6d8c8c173560a8547372e0bb","observation_id":"2d6811b2-8400-490b-9f03-f432129fb741","resolution":{"observed_at":"2026-08-09T15:20:57.568240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.01441","last_updated":"2025-03-25T03:30:17Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T15:14:30.967776Z","submitted_at":"2025-02-03T15:25:58Z","title":"Improved Training Technique for Latent Consistency Models"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":2,"verified_fuzzy":6},"total_outbound_references":31},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 4 inbound Pith citation observations for arXiv:2502.01441."}