{"as_of":"2026-08-15T12:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:05630ab6b946e322900ec47bed01951ca624b8b108b67d290fb57a8108d31cd4","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T15:11:14.334476Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T11:23:56.932223Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-14T11:23:57.302151Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"cited_work":{"arxiv_id":"1908.01686","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.01686","snapshot_observed_at":"2026-08-14T11:23:57.302151Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","venue":"cs.LG","work_id":"dd10faa5-72f9-4a12-a0e1-23e2ec023a21","year":2019},"citing_paper":{"arxiv_id":"1908.09257","last_updated":"2020-06-06T00:24:11Z","snapshot_observed_at":"2026-08-15T07:50:17.607913Z","submitted_at":"2019-08-25T06:14:08Z","title":"Normalizing Flows: An Introduction and Review of Current Methods","version":4},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-14T11:23:56.932223Z"},"links":{"cited_paper":"/paper/1908.01686","citing_paper":"/paper/1908.09257"},"observation_digest":"sha256:866549e0216d4090722f753bc9a0a13ff5154999b28b84e2a9fe74634456374d","observation_id":"fa55dfdd-7c39-483c-b797-caaafe12be40","resolution":{"observed_at":"2026-08-14T11:23:57.306433Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1908.01686/citation-record","integrity":"/paper/1908.01686/integrity","json":"/paper/1908.01686/citation-record.json","paper":"/paper/1908.01686"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1905.00505","last_updated":"2020-06-22T10:07:33Z","snapshot_observed_at":"2026-08-14T16:38:34.151864Z","submitted_at":"2019-05-01T21:26:48Z","title":"Semi-Conditional Normalizing Flows for Semi-Supervised Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.00505","snapshot_observed_at":"2026-08-14T15:11:14.194788Z","title":"Semi- conditional normalizing flows for semi-supervised learning","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.194788Z"},"links":{"cited_paper":"/paper/1905.00505","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:d1884a7d91b91e6a6dcbaf6e0aed1f8ee3c6dba66aa3ef0a38ea89b7684a70a9","observation_id":"553c7ec8-76f5-47a2-bf90-417f712e71fe","resolution":{"observed_at":"2026-08-14T15:11:14.194788Z","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":"2026-08-14T15:11:14.755017Z","title":"Datasets: We perform experiments on four benchmarked image datasets: CIFAR-10 (Krizhevsky, 2009), Imagenet (Russakovsky et al.,","venue":null,"work_id":"c7d780e5-4a70-4189-b13e-a48c60e1cf76","year":2009},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.322793Z"},"links":{"citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:e26b39fdc3295f74bde03234f0a7830527d6b3f9e17a66e6840e5ab7fe8d5873","observation_id":"ab26f721-b03b-4a78-8bb7-3593ad33e291","resolution":{"observed_at":"2026-08-14T15:11:14.760813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1308.0850","last_updated":"2014-06-05T16:04:02Z","snapshot_observed_at":"2026-08-15T00:07:53.077276Z","submitted_at":"2013-08-04T21:04:36Z","title":"Generating Sequences With Recurrent Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.0850","snapshot_observed_at":"2026-08-14T15:11:14.234864Z","title":"Generating sequences with recurrent neural networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.234864Z"},"links":{"cited_paper":"/paper/1308.0850","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:298363334c803df9b4d6bedd800c273e1d9156e09b013023fea1530b26934b9c","observation_id":"f840f1be-34e5-4dc1-9534-e251b0754a18","resolution":{"observed_at":"2026-08-14T15:11:14.234864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.11137","last_updated":"2019-05-20T08:56:28Z","snapshot_observed_at":"2026-08-14T17:23:18.007577Z","submitted_at":"2019-01-30T23:02:37Z","title":"Emerging Convolutions for Generative Normalizing Flows","version":3},"cited_work":{"arxiv_id":"1901.11137","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.11137","snapshot_observed_at":"2026-08-14T15:11:14.552952Z","title":"Emerging Convolutions for Generative Normalizing Flows","venue":"cs.LG","work_id":"f89d8941-678e-4a73-b159-a7a3c0eba94a","year":2019},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.247448Z"},"links":{"cited_paper":"/paper/1901.11137","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:fbdc259fc92c2570cc63f984c1a791e6823a982cd981df6e57dd966f32888c94","observation_id":"d67bee5f-350a-46b3-90a2-06b672d61bb2","resolution":{"observed_at":"2026-08-14T15:11:14.560757Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.04948","last_updated":"2019-03-29T11:08:46Z","snapshot_observed_at":"2026-08-14T17:44:45.577553Z","submitted_at":"2018-12-12T13:59:43Z","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.04948","snapshot_observed_at":"2026-08-14T15:11:14.253726Z","title":"A style-based generator architecture for generative adversarial networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.253726Z"},"links":{"cited_paper":"/paper/1812.04948","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:3887904c32aa1fbdeab9bf4021926ff2984663e3ae84198cfd786d326d7cf360","observation_id":"6cb7dd7d-a49e-4aea-8c02-11666e23415c","resolution":{"observed_at":"2026-08-14T15:11:14.253726Z","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":"2026-08-14T15:11:14.268408Z","title":"Auto-encoding variational bayes","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.268408Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:dafab456099bc82a0bc1c04bbfc2023e999f2b7cea298569db66129fc95e43e2","observation_id":"4ea0df73-d73c-4e54-a52a-75907e41b383","resolution":{"observed_at":"2026-08-14T15:11:14.268408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01583","last_updated":"2016-10-22T01:07:38Z","snapshot_observed_at":"2026-08-14T21:54:06.816374Z","submitted_at":"2016-06-05T23:42:19Z","title":"Semi-Supervised Learning with Generative Adversarial Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.01583","snapshot_observed_at":"2026-08-14T15:11:14.280522Z","title":"Semi-supervised learning with generative adversarial networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.280522Z"},"links":{"cited_paper":"/paper/1606.01583","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:820ce6d4c3d08e482d67ff7eae49696b48da57554ed6f54743dabb735350bb0f","observation_id":"5ca7c496-9e0d-4694-be19-17ab2332cad9","resolution":{"observed_at":"2026-08-14T15:11:14.280522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1601.06759","last_updated":"2016-08-19T14:10:16Z","snapshot_observed_at":"2026-08-14T22:13:10.910190Z","submitted_at":"2016-01-25T20:34:24Z","title":"Pixel Recurrent Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1601.06759","snapshot_observed_at":"2026-08-14T15:11:14.287115Z","title":"Conditional image generation with pixelcnn decoders","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.287115Z"},"links":{"cited_paper":"/paper/1601.06759","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:ba616a8b456b8dd4d59d04a3fc2d28dd09fb905d0bb13946301aff3bbdf64ed9","observation_id":"68dc640a-00a0-4c7f-bbec-11a4f63c0392","resolution":{"observed_at":"2026-08-14T15:11:14.287115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.0575","last_updated":"2015-01-30T01:23:59Z","snapshot_observed_at":"2026-08-14T23:21:09.382166Z","submitted_at":"2014-09-01T22:29:38Z","title":"ImageNet Large Scale Visual Recognition Challenge","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.0575","snapshot_observed_at":"2026-08-14T15:11:14.301928Z","title":"Tim Salimans, Andrej Karpathy, Xi Chen, and Diederik P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.301928Z"},"links":{"cited_paper":"/paper/1409.0575","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:1036a1dbf167ffb1d131144fa3b5890211610a3308014bfad81d4152ef9b6e49","observation_id":"480137c1-feec-459b-812d-ded07b798fa6","resolution":{"observed_at":"2026-08-14T15:11:14.301928Z","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":"2026-08-14T15:11:14.308857Z","title":"Benigno Uria, Iain Murray, and Hugo Larochelle","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.308857Z"},"links":{"cited_paper":"/paper/1701.05517","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:e502211940bae457616afb5228a42d4dbd1e92cabae05653526db6685ff1f638","observation_id":"dc731299-a34a-4b5c-afa5-655b90d0ab24","resolution":{"observed_at":"2026-08-14T15:11:14.308857Z","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":"2026-08-14T15:11:14.774510Z","title":null,"venue":null,"work_id":"e0eedc12-428e-4bda-b180-6dd5bbf9f264","year":2016},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.316421Z"},"links":{"citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:5257e7ffb154d9e40ccc88bf8a0c43fa815a6d6f05b18499da947a4f7d31682c","observation_id":"16d2a607-d35b-4533-8438-b6c758e47528","resolution":{"observed_at":"2026-08-14T15:11:14.779718Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T15:11:14.736505Z","title":"Pre-processing: For CelebA, we take a central crop of 148× 148 then resize it to 64×","venue":null,"work_id":"fbbece57-ed38-4bc3-ae78-2cca58e7192a","year":2015},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.328208Z"},"links":{"citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:b318974d12b1314516daa07e215df60ea922023951f15702b36c873474b1af7c","observation_id":"4fba8725-c56f-4dde-bf3e-a55ea8b83995","resolution":{"observed_at":"2026-08-14T15:11:14.742173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T15:11:14.719186Z","title":"The sample allocation for training and validation were done as per the official allocation for the datasets","venue":null,"work_id":"985501e8-081b-442a-8207-4474b3573fb2","year":2016},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.334476Z"},"links":{"citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:aa58f91144c9fa70cbe33dd6b7b656de3e133f683a1a67a3350b4a0003469012","observation_id":"ec6aa7d5-be2d-4764-bba8-2e380382c932","resolution":{"observed_at":"2026-08-14T15:11:14.724645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.09763","last_updated":"2017-12-28T05:54:44Z","snapshot_observed_at":"2026-08-14T19:59:42.157845Z","submitted_at":"2017-12-28T05:54:44Z","title":"PixelSNAIL: An Improved Autoregressive Generative Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.09763","snapshot_observed_at":"2026-08-14T15:11:14.202251Z","title":"doi: 10.1162/neco.1995.7.6.1129","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":1995,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.202251Z"},"links":{"cited_paper":"/paper/1712.09763","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:e30e657065394fe455ede8ada28daf8aad6c7faee5f088b7725af3d2a4f6288b","observation_id":"9aaf2dd9-5667-43c8-8fdc-47b92af25c0a","resolution":{"observed_at":"2026-08-14T15:11:14.202251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.01434","last_updated":"2020-02-12T16:55:25Z","snapshot_observed_at":"2026-08-14T17:07:37.204130Z","submitted_at":"2019-03-04T18:55:45Z","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.01434","snapshot_observed_at":"2026-08-14T15:11:14.274648Z","title":"Videoflow: A flow-based generative model for video","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.274648Z"},"links":{"cited_paper":"/paper/1903.01434","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:cb9bec2730f2aec9bb7c8961b5296f699bf01f30e3f4ebd574a9aa347dc5dfb1","observation_id":"1bc2c39e-e44f-429b-8073-af3f68908e6b","resolution":{"observed_at":"2026-08-14T15:11:14.274648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.00275","last_updated":"2019-05-15T23:16:06Z","snapshot_observed_at":"2026-08-14T17:22:28.284755Z","submitted_at":"2019-02-01T11:13:40Z","title":"Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.00275","snapshot_observed_at":"2026-08-14T15:11:14.241001Z","title":"Flow++: Improving flow- based generative models with variational dequantization and architecture design","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.241001Z"},"links":{"cited_paper":"/paper/1902.00275","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:972955f28453106e43d7270560c6bc241c21c53859fa67cf03446ab56b917bb7","observation_id":"ff64f107-2880-4a35-a187-03d8b0522954","resolution":{"observed_at":"2026-08-14T15:11:14.241001Z","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":"2026-08-14T15:11:14.209603Z","title":"Nice: Non-linear independent components estimation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.209603Z"},"links":{"cited_paper":"/paper/1410.8516","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:53765ff4d78ba77f7204d9724284892db9b3c85857e855feb439191c66081bad","observation_id":"d2a95501-3192-4bdc-a96b-d794a4ff05da","resolution":{"observed_at":"2026-08-14T15:11:14.209603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1605.08803","last_updated":"2017-02-27T23:21:10Z","snapshot_observed_at":"2026-08-10T10:35:06.780085Z","submitted_at":"2016-05-27T21:24:32Z","title":"Density estimation using Real NVP","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.08803","snapshot_observed_at":"2026-08-14T15:11:14.222751Z","title":"Conor Durkan, Artur Bekasov, Iain Murray, and George Papamakarios","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.222751Z"},"links":{"cited_paper":"/paper/1605.08803","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:6076aa311277ad606fa2ddeeafe6de056feb8103677453356d8e95395fc86217","observation_id":"b5e30d06-8175-4161-bf4c-12150b8ea048","resolution":{"observed_at":"2026-08-14T15:11:14.222751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","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":"2026-08-14T15:11:14.262682Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.262682Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:83479f63e73592da998089b495225f80d0aeecd244bc613307ad05b022d898d1","observation_id":"99a5a27b-aa6f-484f-b22c-9a9b1d5a1873","resolution":{"observed_at":"2026-08-14T15:11:14.262682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08710","last_updated":"2019-04-15T01:37:13Z","snapshot_observed_at":"2026-08-15T06:20:17.917294Z","submitted_at":"2019-02-23T00:55:16Z","title":"GANSynth: Adversarial Neural Audio Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08710","snapshot_observed_at":"2026-08-14T15:11:14.228608Z","title":"Gansynth: Adversarial neural audio synthesis","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows","version":3},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-14T15:11:14.228608Z"},"links":{"cited_paper":"/paper/1902.08710","citing_paper":"/paper/1908.01686"},"observation_digest":"sha256:a461356a071436f081a178a774b0225d367852136612c4001964bce96110ae08","observation_id":"df7eca7d-06a2-4e85-bac6-49d915584ebd","resolution":{"observed_at":"2026-08-14T15:11:14.228608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.01686","last_updated":"2022-01-27T07:39:34Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T06:39:08.754613Z","submitted_at":"2019-08-05T15:14:18Z","title":"Likelihood Contribution based Multi-scale Architecture for Generative Flows"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":1,"verified_fuzzy":3},"total_outbound_references":20},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:1908.01686."}