{"as_of":"2026-08-14T14:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2cde470b9ac206936905d8d0eb785d81b85de51cd762db0e0ef130cbff8275a3","coverage":[{"denominator":19,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":19,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T18:29:41.220560Z","state":"measured"},{"denominator":19,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":19,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.07972/citation-record","integrity":"/paper/2412.07972/integrity","json":"/paper/2412.07972/citation-record.json","paper":"/paper/2412.07972"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:29:41.532391Z","title":null,"venue":null,"work_id":"cd40cf3a-c268-47d1-a74e-ff4d55d7a88b","year":2024},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:41.155964Z"},"links":{"citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:9d175e1bc33e4521f6f2688685524e8a2583891d33e9ffeecc355176c305ea29","observation_id":"1672933e-c56f-486f-8eee-fdd65ccf74ec","resolution":{"observed_at":"2026-08-11T18:29:41.536873Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T18:29:40.902495Z","title":"doi: 10.1088/1742-5468/acf8ba","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.902495Z"},"links":{"citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:1ecd9c6734cb12955cc866e1251afc85dc46220c3c12d651cb44cbbc8dc6ae92","observation_id":"a2783b6e-88ee-4394-b365-d6d4ca656114","resolution":{"observed_at":"2026-08-11T18:29:40.902495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18491","last_updated":"2024-02-28T17:19:26Z","snapshot_observed_at":"2026-08-13T12:17:01.113663Z","submitted_at":"2024-02-28T17:19:26Z","title":"Dynamical Regimes of Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18491","snapshot_observed_at":"2026-08-11T18:29:40.908792Z","title":"Sitan Chen, Sinho Chewi, Holden Lee, Yuanzhi Li, Jianfeng Lu, and Adil Salim","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.908792Z"},"links":{"cited_paper":"/paper/2402.18491","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:bb75f85dbf6e6a5879990d1dde7e26a26cba0a223cc44d5f59648e73bf370f81","observation_id":"58d2d4c0-5cbe-41b1-af55-0accb5d0cb39","resolution":{"observed_at":"2026-08-11T18:29:40.908792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11798","last_updated":"2023-05-19T16:33:05Z","snapshot_observed_at":"2026-08-13T11:38:35.407101Z","submitted_at":"2023-05-19T16:33:05Z","title":"The probability flow ODE is provably fast","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.11798","snapshot_observed_at":"2026-08-11T18:29:40.914246Z","title":"Hugo Cui, Florent Krzakala, Eric Vanden-Eijnden, and Lenka Zdeborov ´a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.914246Z"},"links":{"cited_paper":"/paper/2305.11798","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:02f7442a1536d126d7c22ab0f470a63dfce157b3da90454afc070f3f3a7ef977","observation_id":"ad806647-f19a-4c67-bab7-04e23c15585c","resolution":{"observed_at":"2026-08-11T18:29:40.914246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03575","last_updated":"2024-06-25T16:32:20Z","snapshot_observed_at":"2026-08-13T05:56:47.624549Z","submitted_at":"2023-10-05T14:53:40Z","title":"Analysis of learning a flow-based generative model from limited sample complexity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03575","snapshot_observed_at":"2026-08-11T18:29:40.920453Z","title":"org/abs/2310.03575","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.920453Z"},"links":{"cited_paper":"/paper/2310.03575","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:e3942c4e50be5016b8603f7fa4916135d415c33981d1c0b6a6f0e340b27bd585","observation_id":"538bc8b5-e609-4dd5-a91d-363a39e1f9ff","resolution":{"observed_at":"2026-08-11T18:29:40.920453Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18869","last_updated":"2025-03-04T15:36:34Z","snapshot_observed_at":"2026-08-13T00:19:17.149678Z","submitted_at":"2024-04-29T17:00:20Z","title":"Learning Mixtures of Gaussians Using Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18869","snapshot_observed_at":"2026-08-11T18:29:40.925775Z","title":"10 Jonathan Ho, Ajay Jain, and Pieter Abbeel","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.925775Z"},"links":{"cited_paper":"/paper/2404.18869","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:b3affe3f80f3f888722e23715619eae5f6f82cb58cf01ae0e1e713d8f9abe975","observation_id":"82cd1320-5bbd-4faf-bc0d-6c9424c4ee0e","resolution":{"observed_at":"2026-08-11T18:29:40.925775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16834","last_updated":"2024-06-06T21:06:44Z","snapshot_observed_at":"2026-07-06T16:38:29.188225Z","submitted_at":"2023-10-25T17:59:12Z","title":"Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16834","snapshot_observed_at":"2026-08-11T18:29:40.946373Z","title":"Andrea Montanari","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.946373Z"},"links":{"cited_paper":"/paper/2310.16834","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:06282026045ca902cb74f99e9b31c20b89c92a11d3147de134ffadbfad0f2c85","observation_id":"f0b0e368-a102-4cc3-ac33-248431df2aeb","resolution":{"observed_at":"2026-08-11T18:29:40.946373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10690","last_updated":"2025-09-02T12:50:49Z","snapshot_observed_at":"2026-08-13T11:39:47.008248Z","submitted_at":"2023-05-18T04:01:40Z","title":"Sampling, Diffusions, and Stochastic Localization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10690","snapshot_observed_at":"2026-08-11T18:29:40.985060Z","title":"Gabriel Raya and Luca Ambrogioni","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.985060Z"},"links":{"cited_paper":"/paper/2305.10690","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:a5cc669d019ef477d52dd44e885db15eb7aa706154c11c721885418657f9e75c","observation_id":"9fa6ef64-d058-4acd-aa96-8eedb1551351","resolution":{"observed_at":"2026-08-11T18:29:40.985060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19693","last_updated":"2023-10-26T16:02:56Z","snapshot_observed_at":"2026-08-14T10:27:50.993703Z","submitted_at":"2023-05-31T09:36:34Z","title":"Spontaneous Symmetry Breaking in Generative Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.19693","snapshot_observed_at":"2026-08-11T18:29:41.040956Z","title":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:41.040956Z"},"links":{"cited_paper":"/paper/2305.19693","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:00c495690e18e8f09b8e1a8838358cf3c5c85d9f3194004885aa14563109cd63","observation_id":"ca380fe1-704e-4ab5-afae-4bc84c57eb06","resolution":{"observed_at":"2026-08-11T18:29:41.040956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1505.04597","last_updated":"2015-05-18T11:28:37Z","snapshot_observed_at":"2026-08-14T05:43:53.421538Z","submitted_at":"2015-05-18T11:28:37Z","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.04597","snapshot_observed_at":"2026-08-11T18:29:41.073919Z","title":"Antonio Sclocchi, Alessandro Favero, and Matthieu Wyart","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:41.073919Z"},"links":{"cited_paper":"/paper/1505.04597","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:2f54b64b15b5d0d83dd2db0f9b25a4126e6164ee5ea5df3e2a8ecf17dc40b389","observation_id":"42db066e-67bb-4090-b58d-0057473ccce9","resolution":{"observed_at":"2026-08-11T18:29:41.073919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.05600","last_updated":"2020-10-10T07:46:19Z","snapshot_observed_at":"2026-08-01T16:44:46.833530Z","submitted_at":"2019-07-12T07:37:26Z","title":"Generative Modeling by Estimating Gradients of the Data Distribution","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.05600","snapshot_observed_at":"2026-08-11T18:29:41.080111Z","title":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:41.080111Z"},"links":{"cited_paper":"/paper/1907.05600","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:c7d4ca8c377e229fe245b70f7c17462ad2f6caab0a68b4ab08ecde50ffb8e02e","observation_id":"45611f0c-2f79-4fbe-b30a-c3c1001e08ad","resolution":{"observed_at":"2026-08-11T18:29:41.080111Z","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":"2026-08-11T18:29:41.515827Z","title":"D E XPERIMENTAL DETAILS The model used for the MNIST experiment consists of a U-Net architecture (Ronneberger et al","venue":null,"work_id":"6f6be4b4-1f4a-4cd6-a02f-377f772fba6d","year":2015},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:41.215091Z"},"links":{"citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:f8043e9b0026a01d961791c8fa8f706ef7e9a482a2ff9b81ea9d525e000443a5","observation_id":"44e8cfa5-9c2d-4d12-8ccf-e73680261daf","resolution":{"observed_at":"2026-08-11T18:29:41.521183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-11T18:29:41.493563Z","title":"Then with ηt(ν) = E[Z|mt = ν] we have ˙νt = νt t − ηt(νt) t 21 Proof","venue":null,"work_id":"025126ca-9e58-4fb5-a5aa-9237cb58c2bd","year":2023},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:41.220560Z"},"links":{"citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:357df4b5d3389361e59af0d26ae4d307aa22a9de80b668cf253207fa7bc205cd","observation_id":"fb78f32c-0696-436a-89a0-b4ea7f76b2a9","resolution":{"observed_at":"2026-08-11T18:29:41.500714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-11T18:29:40.936222Z","title":"Farley Knight","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.936222Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:836906cae7915b64a26c61dec75491af4ead9fd153d2d1dad4eb8bfcac1656c1","observation_id":"9bc34c9c-6a74-41c5-85d4-990a7b3450a9","resolution":{"observed_at":"2026-08-11T18:29:40.936222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11239","last_updated":"2020-12-16T21:15:05Z","snapshot_observed_at":"2026-08-10T05:21:27.485481Z","submitted_at":"2020-06-19T17:24:44Z","title":"Denoising Diffusion Probabilistic Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.11239","snapshot_observed_at":"2026-08-11T18:29:40.931462Z","title":"Diederik P","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.931462Z"},"links":{"cited_paper":"/paper/2006.11239","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:6a169226c40a58ef857f6612b35c6af3bb9a8741f4545c927b1da85b2c858c1d","observation_id":"2ba1777b-2573-4796-b24a-0679d2af2b4a","resolution":{"observed_at":"2026-08-11T18:29:40.931462Z","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":"2026-08-11T18:29:41.547064Z","title":"11 A P ROOF OF PROPOSITION 1 To prove Proposition 1, we will use the following three Lemmas that follow directly from Albergo et al","venue":null,"work_id":"349ac405-1598-4d7a-85f5-01bfe31c2430","year":2023},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:41.109506Z"},"links":{"citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:afac0f2d71cbd340dafad573c062ba4ba337d81574fdd0c1352d0e17e7d3dfc0","observation_id":"43d205f8-b58f-43e1-a54f-99b12e95de81","resolution":{"observed_at":"2026-08-11T18:29:41.551956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01633","last_updated":"2024-05-24T20:35:38Z","snapshot_observed_at":"2026-08-13T04:04:31.913906Z","submitted_at":"2024-03-03T22:43:47Z","title":"Critical windows: non-asymptotic theory for feature emergence in diffusion models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01633","snapshot_observed_at":"2026-08-11T18:29:40.941207Z","title":"Marvin Li and Sitan Chen","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.941207Z"},"links":{"cited_paper":"/paper/2403.01633","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:f835a56831b2a39e1f1f1aa57f3bc64f771668f29344c800c6bd55cab783aaac","observation_id":"110789b7-e10e-4b33-ab64-28e122ce189f","resolution":{"observed_at":"2026-08-11T18:29:40.941207Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17467","last_updated":"2024-06-20T08:39:11Z","snapshot_observed_at":"2026-08-13T09:20:18.756860Z","submitted_at":"2023-10-26T15:15:01Z","title":"The statistical thermodynamics of generative diffusion models: Phase transitions, symmetry breaking and critical instability","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.17467","snapshot_observed_at":"2026-08-11T18:29:40.863451Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.863451Z"},"links":{"cited_paper":"/paper/2310.17467","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:50c60750a2cacf5816786806c2246a7781f9a52c93b3b3371e8a8c6fe05c4484","observation_id":"a687acef-c485-4ae7-81fd-e3db7e300a9a","resolution":{"observed_at":"2026-08-11T18:29:40.863451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03686","last_updated":"2024-03-06T00:41:30Z","snapshot_observed_at":"2026-08-13T10:39:15.108238Z","submitted_at":"2023-08-07T16:01:14Z","title":"Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03686","snapshot_observed_at":"2026-08-11T18:29:40.896799Z","title":"Giulio Biroli and Marc M´ezard","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models","version":4},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-11T18:29:40.896799Z"},"links":{"cited_paper":"/paper/2308.03686","citing_paper":"/paper/2412.07972"},"observation_digest":"sha256:2e04a4a7686d93fa46003554463c68349f8898bf07fb39c38b25e89f3b8aec86","observation_id":"1e4f7c69-79df-428c-ac13-1c4ed4cdab88","resolution":{"observed_at":"2026-08-11T18:29:40.896799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.07972","last_updated":"2025-02-09T16:59:28Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T15:20:15.333597Z","submitted_at":"2024-12-10T23:21:04Z","title":"Phase-aware Training Schedule Simplifies Learning in Flow-Based Generative Models"},"reference_resolution":{"displayed":19,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":19},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 19 of 19 outbound references and 0 inbound Pith citation observations for arXiv:2412.07972."}