{"as_of":"2026-08-22T05:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cca4d2d4ef6e6ade7c4a3a6f4c1b9400a143b1a0b21e9d68afd146749f7fd799","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T20:56:10.361807Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2501.06999/citation-record","integrity":"/paper/2501.06999/integrity","json":"/paper/2501.06999/citation-record.json","paper":"/paper/2501.06999"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:56:10.909758Z","title":"According to (Ho et al., 2020), the likelihood bound Eq","venue":null,"work_id":"8b390ab2-9f73-4abb-baa9-0f708e938222","year":2020},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.343498Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:8be60c82399c5be1ab2993e478a0bd88d5081bca0975d1cb6e35165aba4e4cde","observation_id":"3977dbc2-9c8d-4110-8563-89b62c980667","resolution":{"observed_at":"2026-08-10T20:56:10.914690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.04933","last_updated":"2019-10-08T17:55:59Z","snapshot_observed_at":"2026-08-18T18:58:34.709115Z","submitted_at":"2019-03-06T22:13:52Z","title":"Hierarchical Autoregressive Image Models with Auxiliary Decoders","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.04933","snapshot_observed_at":"2026-08-10T20:56:10.198582Z","title":"Hierarchical autoregressive image models with auxiliary decoders","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.198582Z"},"links":{"cited_paper":"/paper/1903.04933","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:b4fc4ace770d168b2c35a29a4bd00ece7fbe5e8294a6a0ec5187f651f552ca37","observation_id":"7e5d9191-4e82-4178-a689-d4d8419b394b","resolution":{"observed_at":"2026-08-10T20:56:10.198582Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1410.8516","last_updated":"2015-04-10T12:27:56Z","snapshot_observed_at":"2026-08-12T12:07:47.951486Z","submitted_at":"2014-10-30T19:44:20Z","title":"NICE: Non-linear Independent Components Estimation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1410.8516","snapshot_observed_at":"2026-08-10T20:56:10.203821Z","title":"Nice: Non-linear independent components estimation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.203821Z"},"links":{"cited_paper":"/paper/1410.8516","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:80625e01ce379ff697205e5c323c9d10c9225995ca2bff1fe22b64db3d40351a","observation_id":"61dbabec-01bb-4826-af2e-45cf56df1cff","resolution":{"observed_at":"2026-08-10T20:56:10.203821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.08125","last_updated":"2021-03-27T06:35:56Z","snapshot_observed_at":"2026-08-21T10:32:56.674761Z","submitted_at":"2020-12-15T07:09:02Z","title":"Learning Energy-Based Models by Diffusion Recovery Likelihood","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.08125","snapshot_observed_at":"2026-08-10T20:56:10.213555Z","title":"Learning energy-based models by diffusion recovery likelihood","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.213555Z"},"links":{"cited_paper":"/paper/2012.08125","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:be4db7da31b85a1024b463702ffbc4a9ee4703b34c367dc0d47496ce505f7b0c","observation_id":"741e5ecd-8a4a-43f0-94fe-4a7985943407","resolution":{"observed_at":"2026-08-10T20:56:10.213555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.05003","last_updated":"2022-08-09T19:13:34Z","snapshot_observed_at":"2026-08-20T11:30:32.235094Z","submitted_at":"2022-08-09T19:13:34Z","title":"Wavelet Score-Based Generative Modeling","version":1},"cited_work":{"arxiv_id":"2208.05003","doi":null,"metadata_source":"pith","pith_arxiv_id":"2208.05003","snapshot_observed_at":"2026-08-10T20:56:10.690983Z","title":"Wavelet Score-Based Generative Modeling","venue":"cs.LG","work_id":"ef6c9da6-15f0-4f46-9ddc-eba484ddbeec","year":2022},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.223344Z"},"links":{"cited_paper":"/paper/2208.05003","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:5ab722484fc6236e78eb22e793201ee5935c833079de1c37d61692872584463b","observation_id":"8877d213-6e07-4e8a-bb1f-7f33bf32ce1c","resolution":{"observed_at":"2026-08-10T20:56:10.696272Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.04606","last_updated":"2019-01-28T20:34:44Z","snapshot_observed_at":"2026-08-14T17:45:07.132382Z","submitted_at":"2018-12-11T18:49:50Z","title":"Deep Anomaly Detection with Outlier Exposure","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.04606","snapshot_observed_at":"2026-08-10T20:56:10.233998Z","title":"Deep anomaly detection with outlier exposure","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.233998Z"},"links":{"cited_paper":"/paper/1812.04606","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:29d404a32280585087df2235eb04a6d3e95376d86b7cf26b1b6d97c0c4fa209b","observation_id":"74dc36b2-a5aa-4f1d-8ad4-887d44df4a21","resolution":{"observed_at":"2026-08-10T20:56:10.233998Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.02037","last_updated":"2022-02-01T21:32:15Z","snapshot_observed_at":"2026-08-16T17:51:46.489013Z","submitted_at":"2021-10-05T13:36:55Z","title":"Autoregressive Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.02037","snapshot_observed_at":"2026-08-10T20:56:10.239667Z","title":"Autoregressive diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.239667Z"},"links":{"cited_paper":"/paper/2110.02037","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:c5d49851a323148f0f5e8a559472b8e9d6da1497644d4f60bb65ff4171c351b2","observation_id":"14157d43-c0d6-4a74-bf1c-e1bcf539d06b","resolution":{"observed_at":"2026-08-10T20:56:10.239667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10196","last_updated":"2018-02-26T15:33:34Z","snapshot_observed_at":"2026-08-18T02:27:14.215000Z","submitted_at":"2017-10-27T15:28:35Z","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10196","snapshot_observed_at":"2026-08-10T20:56:10.244455Z","title":"Progressive growing of gans for improved quality, stability, and variation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.244455Z"},"links":{"cited_paper":"/paper/1710.10196","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:1f5df0d9f26b52e3e59e201354ebf1f2991802bb9c528231ec1a0331aeab2446","observation_id":"4e57d041-0cb8-405b-9bee-90746f120f6a","resolution":{"observed_at":"2026-08-10T20:56:10.244455Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-08-14T23:50:45.029465Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-10T20:56:10.254919Z","title":"Auto-encoding variational bayes","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.254919Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:816d0fdb6a62cd090ac25cb75933482b3ec4c395553fabc6a5a68f09c72b6b32","observation_id":"a4657e19-bf90-4aa1-9471-e979bcdcd20c","resolution":{"observed_at":"2026-08-10T20:56:10.254919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-16T02:30:42.660030Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-10T20:56:10.264308Z","title":"Flow matching for generative modeling","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.264308Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:8dbef8c808ba28a4e2c977b67924cc13410d316ffdfc1564f6488af14f27934b","observation_id":"6c11c711-26ae-4406-af2d-c6795ebc4851","resolution":{"observed_at":"2026-08-10T20:56:10.264308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01608","last_updated":"2018-12-04T15:47:44Z","snapshot_observed_at":"2026-08-14T17:48:42.776974Z","submitted_at":"2018-12-04T15:47:44Z","title":"Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01608","snapshot_observed_at":"2026-08-10T20:56:10.269331Z","title":"Generating high fidelity images with subscale pixel networks and multidimensional upscaling","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.269331Z"},"links":{"cited_paper":"/paper/1812.01608","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:5cf586bbecded0fc1c7798caefbb77c478c48b632a285b9524e17ec9651927cd","observation_id":"ae5a1486-5723-4da2-89f6-97199ef06d00","resolution":{"observed_at":"2026-08-10T20:56:10.269331Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.09136","last_updated":"2019-02-24T11:57:32Z","snapshot_observed_at":"2026-08-15T00:45:03.614274Z","submitted_at":"2018-10-22T08:32:02Z","title":"Do Deep Generative Models Know What They Don't Know?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.09136","snapshot_observed_at":"2026-08-10T20:56:10.273982Z","title":"Do deep generative models know what they don’t know? arXiv preprint arXiv:1810.09136,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.273982Z"},"links":{"cited_paper":"/paper/1810.09136","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:edddcf2e39261894d5ebb101eb5a6f523e95bde1d149875354f909cf7d12a9af","observation_id":"a2d211a8-b4d5-4733-b5ea-5bbc3f706c1b","resolution":{"observed_at":"2026-08-10T20:56:10.273982Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.02994","last_updated":"2019-10-16T13:43:36Z","snapshot_observed_at":"2026-08-17T08:07:17.069241Z","submitted_at":"2019-06-07T10:03:16Z","title":"Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.02994","snapshot_observed_at":"2026-08-10T20:56:10.279437Z","title":"Detecting out-of- distribution inputs to deep generative models using typicality","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.279437Z"},"links":{"cited_paper":"/paper/1906.02994","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:a942ec24ba0d71883b58edbaa7b19ca62e85e77ff049ded7f762ad5edc4c9977","observation_id":"2c536664-1631-4c6e-b0a4-e6457c12589c","resolution":{"observed_at":"2026-08-10T20:56:10.279437Z","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":"2026-08-10T20:56:10.986749Z","title":"Parallel multiscale autoregressive density estimation","venue":null,"work_id":"81993faa-067a-4ac0-82e4-1f0750bcc68c","year":2024},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.288519Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:b052c28061afdb1ed448a0b0da7b7f3b6b1f96eb151f79d359966d78c1106920","observation_id":"72fbd232-5801-4145-8db9-3b8485cd4e3d","resolution":{"observed_at":"2026-08-10T20:56:10.991393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.04729","last_updated":"2019-08-20T17:46:05Z","snapshot_observed_at":"2026-08-14T18:29:08.570250Z","submitted_at":"2018-09-13T01:15:49Z","title":"A Less Biased Evaluation of Out-of-distribution Sample Detectors","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.04729","snapshot_observed_at":"2026-08-10T20:56:10.297675Z","title":"outlier","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.297675Z"},"links":{"cited_paper":"/paper/1809.04729","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:49520f888c9ac997330e72fcbac55e8d5ad44cc2b4e74f00caa789555a115b4a","observation_id":"2b15eeec-c5b9-43cc-9ef8-fe1c0dee9444","resolution":{"observed_at":"2026-08-10T20:56:10.297675Z","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":"2026-08-10T20:56:10.971502Z","title":"Approximate earth mover’s distance in linear time","venue":null,"work_id":"df3be469-2101-4aa4-bff9-7e7b4ba804fa","year":2008},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.301893Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:6ef07fb23a68423d6f2c66f25595923ac7238f6d468f77e0766f80cd9bcb799b","observation_id":"8c827286-925c-41b4-9172-aae2dbeecd46","resolution":{"observed_at":"2026-08-10T20:56:10.976379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T20:56:10.957221Z","title":"Flif: Free lossless image format based on maniac compression","venue":null,"work_id":"e5c4f4b1-23f3-4369-8840-d9d693c50734","year":2016},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.306321Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:f67627a38abd9cdc6a47f1aa66a5cbd5fe43e70ab1fba9358a66c6d02455c213","observation_id":"d5bc830b-b858-49ae-a3a9-ed8bce7684ec","resolution":{"observed_at":"2026-08-10T20:56:10.961685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-10T20:56:10.310882Z","title":"Sliced score matching: A scalable approach to density and score estimation","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.310882Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:943a5d66dade4386cdefb13f686982abc6c236aa87908e9c3484118920a62f94","observation_id":"8a44b488-df70-4d64-b471-ba4d6cc93e20","resolution":{"observed_at":"2026-08-10T20:56:10.310882Z","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":"2026-08-10T20:56:10.942434Z","title":"Pixel recurrent neural networks","venue":null,"work_id":"47946d34-966e-4c2f-8b24-ca6358bd9881","year":2024},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.320153Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:6e84baaa11869eafb029b166fd4f065dbc4d1d2d5f1b1694250cfa4eadaaafeb","observation_id":"eb6c6b9d-1b38-4073-9718-36e90d263735","resolution":{"observed_at":"2026-08-10T20:56:10.947168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.00490","last_updated":"2022-12-07T13:29:20Z","snapshot_observed_at":"2026-08-19T15:28:44.366291Z","submitted_at":"2022-12-01T13:33:47Z","title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.00490","snapshot_observed_at":"2026-08-10T20:56:10.325004Z","title":"Zero-shot image restoration using denoising diffusion null-space model","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.325004Z"},"links":{"cited_paper":"/paper/2212.00490","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:1be299efea14f71030ed362ad3713d3db3a4134a1cf3c06cd91b9cc105f96ff8","observation_id":"3a0652bc-92bb-468e-ae4e-b367a0d3d2b8","resolution":{"observed_at":"2026-08-10T20:56:10.325004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.02622","last_updated":"2019-09-26T09:56:23Z","snapshot_observed_at":"2026-08-18T00:26:27.692472Z","submitted_at":"2019-09-05T20:26:44Z","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.02622","snapshot_observed_at":"2026-08-10T20:56:10.329626Z","title":"Moverscore: Text generation evaluating with contextualized embeddings and earth mover distance","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.329626Z"},"links":{"cited_paper":"/paper/1909.02622","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:07d38c6f10280661d3ddbb6db87b2cb7697622feadd96de7dd5227a31056bdf0","observation_id":"ea78fbdb-62ce-4e49-88fd-b928bdbd1936","resolution":{"observed_at":"2026-08-10T20:56:10.329626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.03935","last_updated":"2024-04-06T07:01:53Z","snapshot_observed_at":"2026-08-16T15:35:09.410052Z","submitted_at":"2023-05-06T05:21:24Z","title":"Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs","version":4},"cited_work":{"arxiv_id":"2305.03935","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.03935","snapshot_observed_at":"2026-08-10T20:56:10.397297Z","title":"Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs","venue":"cs.LG","work_id":"f4271e20-83fa-4d13-b13c-3f5620e6e36d","year":2023},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.333894Z"},"links":{"cited_paper":"/paper/2305.03935","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:4921dd135ec52a797af207875778cdd2b6c8121a280b4603d2088d65851dc95e","observation_id":"8de2fe94-4ae9-4b3a-bd67-5b26fc06b0b6","resolution":{"observed_at":"2026-08-10T20:56:10.404254Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T20:56:10.894966Z","title":null,"venue":null,"work_id":"23f0bc42-0148-42cd-b22c-d2b963936d82","year":2024},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.348351Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:77cbc8e5bf148d18fbb4b34f3831a11ffacb549b65ad300971f499a37fbf8709","observation_id":"1114dc03-8d04-41a4-a1e5-e458ff8ad4aa","resolution":{"observed_at":"2026-08-10T20:56:10.899455Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T20:56:10.862690Z","title":"This is why we get differing behaviors between the two hierarchical maps","venue":null,"work_id":"832e6dbe-7e24-48ff-9774-37f3be042da9","year":2024},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.357084Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:d2ecd9adda337e9d71e52b9ff8e9166d140255fca03c6187e3f4c0cd4f80fd97","observation_id":"0079fbdb-2474-4e0c-9f31-5fd7a305bdfe","resolution":{"observed_at":"2026-08-10T20:56:10.868718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T20:56:10.847148Z","title":"All model architecture and hyper- parameters are retained from W-PCDM and LP-PCDM, except for the choice of z(1),","venue":null,"work_id":"b902e497-d45b-430a-9d17-a2db34250259","year":2024},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.361807Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:b8390727fa6d835ec45afcb19574d9aa27e08679b8e7e999e4a059151936647c","observation_id":"27849bb2-1674-4136-9de9-576a838e63dc","resolution":{"observed_at":"2026-08-10T20:56:10.852089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.00396","last_updated":"2022-08-05T17:54:38Z","snapshot_observed_at":"2026-08-14T01:02:41.198730Z","submitted_at":"2021-10-31T03:32:18Z","title":"Efficiently Modeling Long Sequences with Structured State Spaces","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.00396","snapshot_observed_at":"2026-08-10T20:56:10.218875Z","title":"Efficiently modeling long sequences with structured state spaces","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":1995,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.218875Z"},"links":{"cited_paper":"/paper/2111.00396","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:6cef87e4355222e76d9ef3e24d1c21c2005f3ee38c1a1bb137a437a37dc53153","observation_id":"3edfc101-ffe2-497d-9fc6-3b038da89bc6","resolution":{"observed_at":"2026-08-10T20:56:10.218875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1701.05517","last_updated":"2017-01-19T17:29:06Z","snapshot_observed_at":"2026-08-15T06:38:10.590597Z","submitted_at":"2017-01-19T17:29:06Z","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.05517","snapshot_observed_at":"2026-08-10T20:56:10.293366Z","title":"Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.293366Z"},"links":{"cited_paper":"/paper/1701.05517","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:82d3e65bf5d4d30b026b89f7c0905a49eb61c84a0b51f8f77bd73f86b4dfce9d","observation_id":"65a6c68f-a227-450f-835d-21f24ad73ab0","resolution":{"observed_at":"2026-08-10T20:56:10.293366Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.04866","last_updated":"2019-01-15T14:45:47Z","snapshot_observed_at":"2026-08-17T19:47:31.813545Z","submitted_at":"2019-01-15T14:45:47Z","title":"Practical Lossless Compression with Latent Variables using Bits Back Coding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.04866","snapshot_observed_at":"2026-08-10T20:56:10.315535Z","title":"Practical lossless compression with latent variables using bits back coding","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2003,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.315535Z"},"links":{"cited_paper":"/paper/1901.04866","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:aacb9f8ff7431762b72098ad4419d5e4a2161a92103f5e4ae5217f65bba1ac7d","observation_id":"8818800f-e2bb-4652-b68a-667c68839efe","resolution":{"observed_at":"2026-08-10T20:56:10.315535Z","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":"2026-08-10T20:56:10.879293Z","title":"Lemma A.1 (From Theorem 2 in (Shirdhonkar & Jacobs, 2008))","venue":null,"work_id":"d9a7fc54-965d-405e-8547-aca1fe896783","year":2008},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.352810Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:68f3447cde1cb7a8a54cfcd5661957fa450c21d4800f8ae436fec059141380b5","observation_id":"de381e70-1ead-46c3-a714-06fb8852b62a","resolution":{"observed_at":"2026-08-10T20:56:10.884185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06359","last_updated":"2022-12-13T03:48:01Z","snapshot_observed_at":"2026-08-20T06:07:11.182135Z","submitted_at":"2022-12-13T03:48:01Z","title":"Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance","version":1},"cited_work":{"arxiv_id":"2212.06359","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.06359","snapshot_observed_at":"2026-08-10T20:56:10.592352Z","title":"Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance","venue":"cs.LG","work_id":"d01a4f1c-0e93-43f4-98e1-7604d8a0a6d3","year":2022},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.259555Z"},"links":{"cited_paper":"/paper/2212.06359","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:d85859273881fe271cd3ecd3a1c00a0c67f1c6bcdf31591b9ddce6950a345119","observation_id":"d63afaab-226d-4fe9-bcd0-f65334f36d6d","resolution":{"observed_at":"2026-08-10T20:56:10.597637Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.03499","last_updated":"2016-09-19T18:04:35Z","snapshot_observed_at":"2026-08-16T05:39:41.727705Z","submitted_at":"2016-09-12T17:29:40Z","title":"WaveNet: A Generative Model for Raw Audio","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.03499","snapshot_observed_at":"2026-08-10T20:56:10.284004Z","title":"Wavenet: A generative model for raw audio","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.284004Z"},"links":{"cited_paper":"/paper/1609.03499","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:1375f2e496b42dcec72757c51caf491222637a86526190790565b0f0f55ed606","observation_id":"21ae3f99-7ab1-486f-b819-b0095109a3c1","resolution":{"observed_at":"2026-08-10T20:56:10.284004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.08689","last_updated":"2020-06-30T03:25:59Z","snapshot_observed_at":"2026-08-14T20:02:13.664853Z","submitted_at":"2019-03-20T18:34:29Z","title":"Implicit Generation and Generalization in Energy-Based Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.08689","snapshot_observed_at":"2026-08-10T20:56:10.208757Z","title":"Implicit generation and generalization in energy-based models","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.208757Z"},"links":{"cited_paper":"/paper/1903.08689","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:d72f74629128f8f7157f9a3511c39727ebc7577fac6fefc9e0bb060fd2441ba4","observation_id":"47c6a456-7625-4d83-9269-5d5a43e0830c","resolution":{"observed_at":"2026-08-10T20:56:10.208757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.00364","last_updated":"2022-10-11T13:20:30Z","snapshot_observed_at":"2026-07-06T13:16:16.926712Z","submitted_at":"2022-06-01T10:03:24Z","title":"Elucidating the Design Space of Diffusion-Based Generative Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.00364","snapshot_observed_at":"2026-08-10T20:56:10.249960Z","title":"Elucidating the design space of diffusion- based generative models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.249960Z"},"links":{"cited_paper":"/paper/2206.00364","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:6d317dfa645a544a8f1d1904f3df4ad5f660cbc650cb1e2a9200ff497c4320f6","observation_id":"aacc5bb6-3ad2-4a38-aa4f-5f33948c746b","resolution":{"observed_at":"2026-08-10T20:56:10.249960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.11291","last_updated":"2023-04-03T08:50:44Z","snapshot_observed_at":"2026-08-19T13:01:57.147516Z","submitted_at":"2021-10-21T17:18:59Z","title":"Likelihood Training of Schr\\\"odinger Bridge using Forward-Backward SDEs Theory","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.11291","snapshot_observed_at":"2026-08-10T20:56:10.177332Z","title":"Likelihood training of schr\\\" odinger bridge using forward-backward sdes theory","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.177332Z"},"links":{"cited_paper":"/paper/2110.11291","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:f7fe79f3b57422f81afc308a6f7146e56b244362442d3225cf6ebec6b57cf6b1","observation_id":"813a0701-f176-41e5-8306-9def49578130","resolution":{"observed_at":"2026-08-10T20:56:10.177332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.01392","last_updated":"2019-05-23T23:48:06Z","snapshot_observed_at":"2026-08-16T01:12:24.218734Z","submitted_at":"2018-10-02T17:32:07Z","title":"WAIC, but Why? Generative Ensembles for Robust Anomaly Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.01392","snapshot_observed_at":"2026-08-10T20:56:10.193547Z","title":"Waic, but why? generative ensembles for robust anomaly detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.193547Z"},"links":{"cited_paper":"/paper/1810.01392","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:1afea8857121b358c30a68153970ca099513ac702b517b460542b1e5c7933288","observation_id":"60144a12-5a0f-4018-8c0a-5507123612b9","resolution":{"observed_at":"2026-08-10T20:56:10.193547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.10509","last_updated":"2019-04-23T19:29:47Z","snapshot_observed_at":"2026-08-16T10:03:03.268538Z","submitted_at":"2019-04-23T19:29:47Z","title":"Generating Long Sequences with Sparse Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.10509","snapshot_observed_at":"2026-08-10T20:56:10.188502Z","title":"Generating long sequences with sparse transformers","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.188502Z"},"links":{"cited_paper":"/paper/1904.10509","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:31ebc5d6450e886d8421ef67b4d367b78178f5a7c984efbc598796e7ba1c82c5","observation_id":"139a9d4b-ac1e-469e-a3bf-d80faa0d1cdc","resolution":{"observed_at":"2026-08-10T20:56:10.188502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.10650","last_updated":"2021-03-16T18:33:19Z","snapshot_observed_at":"2026-08-17T06:26:53.900350Z","submitted_at":"2020-11-20T21:35:31Z","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.10650","snapshot_observed_at":"2026-08-10T20:56:10.183265Z","title":"Very deep vaes generalize autoregressive models and can outperform them on images","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.183265Z"},"links":{"cited_paper":"/paper/2011.10650","citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:abb8082dd8e977b7ad36c84d2498ff7ebe36a540f809bddce3865eb6c8a2c8a4","observation_id":"0419342b-7edb-4769-b2aa-7262a9c80de9","resolution":{"observed_at":"2026-08-10T20:56:10.183265Z","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":"2026-08-10T20:56:11.001125Z","title":"Laplacian pyramid-like autoencoder","venue":null,"work_id":"f0582b33-e205-40fc-89c9-3718e32c148f","year":2022},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.228711Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:27a44898c86b3814a50f8690d5ecf44cba648ecd789138d77c3365bccf72a8dc","observation_id":"20c29356-3ef6-46c2-a6f6-d21a754e5ec5","resolution":{"observed_at":"2026-08-10T20:56:11.005837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-10T20:56:10.926540Z","title":"Let h be a hierarchi- cal volume-preserving map such that h(x) = (z(1), z(2),","venue":null,"work_id":"3786fda9-c00b-4d12-bb00-47b17c0e0e8d","year":2024},"citing_paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T20:56:10.338649Z"},"links":{"citing_paper":"/paper/2501.06999"},"observation_digest":"sha256:5d4cc57937b758f6b7e7bc8f7460fc4650d37f2548e19593d2c782d84a63b359","observation_id":"53eaad3e-9b80-4cb7-9cf8-49252b8c9435","resolution":{"observed_at":"2026-08-10T20:56:10.931723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.06999","last_updated":"2025-01-13T01:20:23Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T10:58:01.005176Z","submitted_at":"2025-01-13T01:20:23Z","title":"Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":3,"verified_fuzzy":10},"total_outbound_references":39},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2501.06999."}