{"as_of":"2026-08-16T10:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f0cbddcf27af066cab6f4d0182627454cd08c4dc62297f9d01cdbe04b6b0e8d3","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T12:41:42.159757Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/1908.06694/citation-record","integrity":"/paper/1908.06694/integrity","json":"/paper/1908.06694/citation-record.json","paper":"/paper/1908.06694"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:41:42.930073Z","title":"Maskconnect: Con- nectivity learning by gradient descent","venue":null,"work_id":"cc7bc4e6-e904-4c4d-a03f-9cbfd9073a4a","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.912973Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:320eec68c6f7d74af8f7dfdfc65718535721020fb12753fe752ef3541de53b02","observation_id":"f21cf885-d3f0-403d-b0a5-1bb53772cae5","resolution":{"observed_at":"2026-08-14T12:41:42.933869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.917604Z","title":"Understanding dropout","venue":null,"work_id":"a79ea3e3-e128-4bde-9de7-72e96516fe8f","year":2013},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.917357Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:13a49c4dd5acaa254776ee6cbfc911d85a806e194e36323bdd1f0f9c3b4b1e6f","observation_id":"5c4e0866-00aa-4d20-b045-aae5d4631764","resolution":{"observed_at":"2026-08-14T12:41:42.922918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.906459Z","title":"Bagging predictors","venue":null,"work_id":"5f077741-087e-47bf-bd8a-b5b0c20819b9","year":1996},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.920886Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:ad5dbe52e4d71e68a8c982e37d2f76f4c4a82954dd418839805eaa35ab570031","observation_id":"0f42fe03-7721-4e4b-8d65-38c559422311","resolution":{"observed_at":"2026-08-14T12:41:42.910523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.894944Z","title":"Learning efficient object detection mod- els with knowledge distillation","venue":null,"work_id":"b78e8f98-6a28-4d70-abd3-6d89fcf3ee80","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.924792Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:8c4d64c179a91e11f309cabea9f34f9be2219c77e3396009f4d3521fc4c29eb0","observation_id":"8d8940b8-f2bc-476e-a4d4-f98381a39984","resolution":{"observed_at":"2026-08-14T12:41:42.898879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.882110Z","title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolu- tion, and fully connected crfs","venue":null,"work_id":"e836388d-99a3-486e-8cb7-689ab5d855ba","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.928530Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:6ce79a65902084322d5cf81c411f2a88917f90ec64818f5a387b4bcda1f99c8d","observation_id":"6742a9ad-ce18-4972-8d60-6ebbaee1b3ec","resolution":{"observed_at":"2026-08-14T12:41:42.886692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:41.932186Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.932186Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:d78396e8cd789b62186ff451ccdcaa5a996653e93c1bb3b13e0b66a0011370f3","observation_id":"c67998f6-19d8-40b2-b77b-273273213a30","resolution":{"observed_at":"2026-08-14T12:41:41.932186Z","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":"2026-08-14T12:41:42.862278Z","title":"Gradient descent provably optimizes over-parameterized neural networks","venue":null,"work_id":"e41cd722-349b-4744-9288-74ee2a1b3363","year":2019},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.936071Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:9fa130b8a8a81a4d60a9601599d4e02f89c3ac9a4edebc4a6ea998e29dcedd97","observation_id":"35fab3b7-7cf4-49eb-ab6b-1048cd41efd7","resolution":{"observed_at":"2026-08-14T12:41:42.866203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.851193Z","title":"Cou- pled ensembles of neural networks","venue":null,"work_id":"c96017d1-9d3e-475f-b885-aeb11bcaecc0","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.939353Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:7dfe82a4ed6b3746f3631ae1ac2eddd70adad9b88197057a8ffaaa74c4a8a808","observation_id":"db37e1b8-ca4c-49b9-afb5-0be43f0282e6","resolution":{"observed_at":"2026-08-14T12:41:42.855046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.840066Z","title":"The lottery ticket hy- pothesis: Training pruned neural networks","venue":null,"work_id":"3a4bb009-cca6-4569-a97f-e80e30243227","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.942771Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:fe14baa1c29e2b2a272cce19aea70317cd5c2066a37844e2c12f100b4bb9be1d","observation_id":"c7e6c752-e45d-4acd-863c-1b7f59337839","resolution":{"observed_at":"2026-08-14T12:41:42.844088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.829275Z","title":"Concrete dropout","venue":null,"work_id":"6d506326-9dbf-49e7-bee3-62ccd777f7bf","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.945962Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:0c681f9fd91ed82805f159358fc8cdfa01a9f1df16a1121221861486aacd1e8a","observation_id":"4dbfd8f1-1128-4990-a7f1-75e9315fe85c","resolution":{"observed_at":"2026-08-14T12:41:42.833172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.818488Z","title":"Struc- tured variational learning of bayesian neural networks with horseshoe priors","venue":null,"work_id":"d1570344-0983-4ffe-bb66-fe7099e4edd0","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.949261Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:6c3a115d5f784069d6a36cacc76b551616cb3b06419b8051841b31978bfa3eb2","observation_id":"c658a752-d0b6-44d1-8b22-b4e2475e34c0","resolution":{"observed_at":"2026-08-14T12:41:42.822483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.807189Z","title":"Branchout: Regularization for online ensemble tracking with convolu- tional neural networks","venue":null,"work_id":"ba501778-6238-4992-9b44-f9612a47cba6","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.952793Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:8479b4b0c862af04bf8a1404f50c9173578d2f74334422c115214531edb55eb9","observation_id":"aa4428ec-5526-413e-97d0-f654f060fd1b","resolution":{"observed_at":"2026-08-14T12:41:42.810872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.795637Z","title":"Identity mappings in deep residual networks","venue":null,"work_id":"d1470989-58c0-4592-aa8d-6de4137a4474","year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.956244Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:845aea472454a2a33919d4eaddf0a72b160fb39b905e81c24ddd64d5bca21fa4","observation_id":"307628fd-4079-4c3c-96b6-134ba450acb4","resolution":{"observed_at":"2026-08-14T12:41:42.799846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.781946Z","title":"AMC: AutoML for model compression and ac- celeration on mobile devices","venue":null,"work_id":"1f133c48-abde-4a4a-b5d6-0055684b47b4","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.959661Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:512bf5d42b3c801f55d240a72d01aa60b98e6848b0eefbd25ab14d00c16bc6fe","observation_id":"69c70629-a024-473b-9999-434a178b5892","resolution":{"observed_at":"2026-08-14T12:41:42.787848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.769904Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":"a496f6ce-da25-46d9-b37b-fb6dbda796be","year":2015},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.963008Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:3aa17444bfa9b933316d8ad7ab0c3c6aa6ff096471234714b207f6a85618a87e","observation_id":"0bec4dc0-9c6f-4581-a4f6-c32cb751ec14","resolution":{"observed_at":"2026-08-14T12:41:42.773553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-14T12:41:41.966976Z","title":"Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.966976Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:112f3e5aad8112d91ef77ffaa45eae2dc13e3d8204d4ee97a6a22174d32d86a8","observation_id":"04568d5d-c735-4faf-9c04-b44c22e007e3","resolution":{"observed_at":"2026-08-14T12:41:41.966976Z","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":"2026-08-14T12:41:42.758573Z","title":"Huang, D","venue":null,"work_id":"a84347de-1388-4b0f-abcb-483497113266","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.970872Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:c8b61ba37bf1851f6b79212f4e851788c2067b2be5b8616f42f394df8d2b6fc4","observation_id":"9515e91d-43fa-4aa6-8d73-b8500c37af7c","resolution":{"observed_at":"2026-08-14T12:41:42.762347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.747836Z","title":"Snapshot ensembles: Train 1, get m for free","venue":null,"work_id":"8756561b-e014-4349-9f41-8617491d2602","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.974396Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:15f562d84f11c221585d63b675db324434802349cb86e25d24c44fecbd503255","observation_id":"bf8b120d-71ea-4a1a-bb40-e20bb3e681a5","resolution":{"observed_at":"2026-08-14T12:41:42.751378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.737546Z","title":"Huang, S","venue":null,"work_id":"71e5e436-ea16-47e4-91e2-918144ff80a6","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.977837Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:94edee975df78cac31a106dc5fcf973f1138067109f3c9981b81711bced6c978","observation_id":"6b621a87-2684-4652-8f4d-ddf8ac4ee753","resolution":{"observed_at":"2026-08-14T12:41:42.741023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.727095Z","title":"Huang, Z","venue":null,"work_id":"b72eb9e4-3c83-4134-958c-b940c61bd29f","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.981451Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:d65df255eaaa1272437e5f7352d08ea61016d38783f3e1475511ba8103579786","observation_id":"827d9db4-da3f-42c3-88f3-e971071d4b6d","resolution":{"observed_at":"2026-08-14T12:41:42.730864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.716026Z","title":"Deep networks with stochastic depth","venue":null,"work_id":"960278b9-46fb-465e-9cdc-dbe018c97ca8","year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.984693Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:69f17de55cb06bd37490f2347dfa10fe235e37c735e09cad702709c7ca5f3476","observation_id":"0d91a194-f59f-4cc3-96e1-81c59ec28fe2","resolution":{"observed_at":"2026-08-14T12:41:42.719589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.705681Z","title":"Data-driven sparse struc- ture selection for deep neural networks","venue":null,"work_id":"51ffdb0f-a42e-418d-8233-7678e216f241","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.988492Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:92b496b86b4eda2f799e06f4686df780d941fabe4834c24be3aa2f2b2b1986a8","observation_id":"d43fcefb-882f-4250-83d9-d1475fbc1efd","resolution":{"observed_at":"2026-08-14T12:41:42.709369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.07360","last_updated":"2016-11-04T21:26:08Z","snapshot_observed_at":"2026-08-14T22:09:04.541956Z","submitted_at":"2016-02-24T00:09:45Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.07360","snapshot_observed_at":"2026-08-14T12:41:41.992276Z","title":"Squeezenet: Alexnet-level accuracy with 50x fewer pa- rameters and¡ 0.5 mb model size","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.992276Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:5117e1c520a16f259e7eef08dd9da9abe2e7e056b2f8b9e8dadd465ca0d61fc9","observation_id":"21d5c6f7-38ba-45b0-b694-3d48d0ff60ec","resolution":{"observed_at":"2026-08-14T12:41:41.992276Z","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":"2026-08-14T12:41:42.693974Z","title":"Uncertainty es- timates and multi-hypotheses networks for optical flow","venue":null,"work_id":"6cd5d8bb-1da8-4ee2-9ff0-e6489f79d489","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.996048Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:f6c3d00a413f7853135bba32e50ca50eda6c717a15759d8be9ae15f229d4aa48","observation_id":"ac2308f1-338b-457a-aebc-dc3d395e7a88","resolution":{"observed_at":"2026-08-14T12:41:42.698153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.682664Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":"06679ace-c45c-45d9-8a9b-e53c0b01a936","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:41.999819Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:0a4ce191a253a17eb58226dbd607a6ad2ef8ce3f266d2d0e725ffe8263fa4bcc","observation_id":"eb9fd258-2c50-461a-a0f4-db304e33f1a5","resolution":{"observed_at":"2026-08-14T12:41:42.686574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.671880Z","title":"Speeding up convolutional neural networks with low rank expansions","venue":null,"work_id":"3923d4fd-7bb0-48e3-947d-640eb12d8947","year":2014},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.005295Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:3e90a6fc5afc71bc014f81f93f064929c7d474afd68147b54265279c1b77c568","observation_id":"e86ed9b9-e1f4-4ff2-9b78-756d45ee6166","resolution":{"observed_at":"2026-08-14T12:41:42.675642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.011485Z","title":"Kingma and M","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.011485Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:c641e174f0fe4831f4b10f96e3e1bc6489ae90a9870ae154fd8f36e8371f45a8","observation_id":"0d99bc36-d9e6-4061-9b47-31aebeaa8f70","resolution":{"observed_at":"2026-08-14T12:41:42.011485Z","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":"2026-08-14T12:41:42.655468Z","title":"Vari- ational dropout and the local reparameterization trick","venue":null,"work_id":"995954d0-70ec-4367-9920-c90ee60d5fc6","year":2015},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.015800Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:fe167e9acd9dd19378bd2185398afa55c9b7bdfcab2ab69a62249c4062016bbd","observation_id":"b2d649d8-0751-4877-b6dd-549ef8ffff2d","resolution":{"observed_at":"2026-08-14T12:41:42.659202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.019491Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.019491Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:1516abc8dfe6b583425160bfec7395be91c15311f0bbc68cf50ac4c5077d3a59","observation_id":"45562407-880f-4534-a89d-5268c4e97f39","resolution":{"observed_at":"2026-08-14T12:41:42.019491Z","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":"2026-08-14T12:41:42.638167Z","title":"Neural network ensem- bles, cross validation, and active learning","venue":null,"work_id":"903b4f1b-db4a-41a1-ab8f-26b6a6e22938","year":1995},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.023309Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:a82387a7479bd6ad69c8e97844b60cd4d9762f4b5208db18b555c33a860e3ba9","observation_id":"5d1e88d1-8702-4795-a288-79d59c75066c","resolution":{"observed_at":"2026-08-14T12:41:42.642203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.627390Z","title":"Simple and scalable predictive uncertainty esti- mation using deep ensembles","venue":null,"work_id":"bd9caca8-e573-417b-96c2-73b00ec5501b","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.027146Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:a7b8d18611f85e0103d57976844a8fe517f6b0a70bf956f1c4cb3b41a18f3876","observation_id":"4bb4df56-6772-4e1e-a3fa-46d64407853b","resolution":{"observed_at":"2026-08-14T12:41:42.631348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.615408Z","title":"Fractalnet: Ultra-deep neural networks without residuals","venue":null,"work_id":"48f88463-07bf-4b9e-b2f5-1573f2791ea3","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.031270Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:16b5124837e1f44430fb396e816f588b582386323247fdfcfb99c8667f8280aa","observation_id":"f2bafe83-9d23-4859-b42a-4fbec232a077","resolution":{"observed_at":"2026-08-14T12:41:42.619680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.605423Z","title":"LeCun, J","venue":null,"work_id":"4819bd35-8120-43fb-a4c0-8df3a0a9bb4d","year":1990},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.035413Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:127b8efdb8b5a07fab5d743a39228de478a3d2d4aab3670bb7a9cbbd1a627f18","observation_id":"50b307f9-d4f5-41ac-94fb-0ae8e472961a","resolution":{"observed_at":"2026-08-14T12:41:42.608744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.06314","last_updated":"2015-11-19T19:19:58Z","snapshot_observed_at":"2026-08-14T22:22:10.975731Z","submitted_at":"2015-11-19T19:19:58Z","title":"Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.06314","snapshot_observed_at":"2026-08-14T12:41:42.040189Z","title":"Why m heads are bet- ter than one: Training a diverse ensemble of deep networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.040189Z"},"links":{"cited_paper":"/paper/1511.06314","citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:da8b4e592b51991d402b4ed9a7d47683102d88a3f40b6266478d53ab0b82d137","observation_id":"5494e171-051b-4b7a-94e3-a655945e01d8","resolution":{"observed_at":"2026-08-14T12:41:42.040189Z","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":"2026-08-14T12:41:42.595459Z","title":"Pruning filters for efficient convnets","venue":null,"work_id":"21474320-7fab-4b4c-92a9-9153aa1c0da0","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.044367Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:d9dd66804a9bda7c0c7f1653f80a483d8f40720d8d1876a96717a34c68442b39","observation_id":"9dce20c1-965e-4249-898a-1c85e2b2b1ad","resolution":{"observed_at":"2026-08-14T12:41:42.599239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.584628Z","title":"Fixed point quantization of deep convolutional networks","venue":null,"work_id":"2c98b687-8fb0-4f38-844d-d377a74dc260","year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.049356Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:feb2150f68ab6435424c08ad2adbd9a9d502da7b5bf48e7ea16446870351241d","observation_id":"77e76a5a-0730-452a-925b-a60091806726","resolution":{"observed_at":"2026-08-14T12:41:42.588477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.572747Z","title":"Darts: Differentiable architecture search","venue":null,"work_id":"682c20e1-fcc2-43be-9534-d0eb4751cc5c","year":2019},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.054213Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:2f664ef396ca2c71548a4aff5e09c9c9b3a3d03df38e1ffe79dcf16b763738e0","observation_id":"c8a79208-435a-4aab-a09e-70924e89fa60","resolution":{"observed_at":"2026-08-14T12:41:42.577311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.558446Z","title":"Learning efficient convolutional networks through network slimming","venue":null,"work_id":"17a4adb6-ba0d-4347-980a-3a88fbc5f1a3","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.058069Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:07e260c873392da3d54f3c3bb09816fe9a7c93e35e99fd69ca4dda4e0372c4d8","observation_id":"a86e9dff-c937-4bd8-bb88-4c7b7de97275","resolution":{"observed_at":"2026-08-14T12:41:42.562898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.544919Z","title":"Sgdr: Stochastic gradient descent with warm restarts","venue":null,"work_id":"c8889f0d-22da-4474-8823-37a2776ec867","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.062557Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:499b116ebcadd4d49a4ab8ec102594f47fe41a0d765d2ede12b5fdcf5f3b077c","observation_id":"c8031fb3-c7da-411f-85c2-7cc579f6750b","resolution":{"observed_at":"2026-08-14T12:41:42.548911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.532655Z","title":"Multiplicative normaliz- ing flows for variational bayesian neural networks","venue":null,"work_id":"e2ecd8e7-4813-408b-aed3-5c8abe8bf1bf","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.066791Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:82104b41fdc6c198a700346dec4d8267ee932d71380aa91100205552f7923b05","observation_id":"a38cd691-7558-4963-b149-beebf9c30b9d","resolution":{"observed_at":"2026-08-14T12:41:42.537181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.521420Z","title":"Learning sparse neural networks through l 0 regularization","venue":null,"work_id":"7bff4862-4899-459e-9dd6-a8475588fec3","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.071655Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:e361d9734c262fb440df9fde6cb981a79bab32eeb8bce3a7317b516fa028c32d","observation_id":"4b5db635-b2c1-4cb5-a8b8-90a6dfd49545","resolution":{"observed_at":"2026-08-14T12:41:42.525370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.507962Z","title":"The concrete distribution: A continuous relaxation of discrete random variables","venue":null,"work_id":"2d6aac38-5b8b-478c-b921-25d7299612e6","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.076893Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:222e253aab4a2020c9fbdc4dda9c18f275552bb514a174db69aa80d484562536","observation_id":"c1b5c7e4-1506-4e0d-9c91-71575f240c74","resolution":{"observed_at":"2026-08-14T12:41:42.514246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.494604Z","title":"Domain-adaptive deep net- work compression","venue":null,"work_id":"32c4e02f-a7aa-4c30-8779-8146f6657ac5","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.081122Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:5510fd6f07d3ddbca9f7c3734d0388a95d25bd7988ed3db79793fc5b546252c9","observation_id":"dcd8f3cf-3dfe-4a46-8b6e-671573e186a8","resolution":{"observed_at":"2026-08-14T12:41:42.498876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.479793Z","title":"Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation","venue":null,"work_id":"634cbb22-d27f-42ac-97c7-a65fe24f4643","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.085855Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:fe9f9c3ff7b0fac1c3498a885569881b6432b4a89988a8a96081a66db10c0154","observation_id":"d63702cf-f3ef-4fe1-87a0-a4d4354abb5c","resolution":{"observed_at":"2026-08-14T12:41:42.484684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.466957Z","title":"Espnetv2: A light-weight, power ef- ficient, and general purpose convolutional neural network","venue":null,"work_id":"4babe060-5488-4743-a201-cd6ac3efb120","year":2019},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.089937Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:62262a297d5bb6c25e78ef55b92a5c7958173feb3d17c5434e0843abbf2f8889","observation_id":"edd10a95-82a8-493d-8408-e5896b331c46","resolution":{"observed_at":"2026-08-14T12:41:42.471190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.455614Z","title":"Optimal en- semble averaging of neural networks","venue":null,"work_id":"00dea82a-35c2-4d18-98a4-45d851bb957e","year":1997},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.094336Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:fc5035de6488aaede9817ad505f6693180f6b592478f1880a58f6d998f2c67e2","observation_id":"df5d8509-9316-45dd-895f-623ea00b6eeb","resolution":{"observed_at":"2026-08-14T12:41:42.459568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.442475Z","title":"Structured bayesian pruning via log-normal multiplicative noise","venue":null,"work_id":"d155709f-2d71-4f59-bd03-f821e48f0296","year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.098399Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:b363d5f11e53c3c6538335638ce4fff3737038489a0566f05717023a4faf3804","observation_id":"881501ff-730d-4dd9-86dd-4e0cf4a6110f","resolution":{"observed_at":"2026-08-14T12:41:42.447088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.430627Z","title":"Rezende, S","venue":null,"work_id":"8eaace9f-c512-4383-99bd-f524678d648c","year":2014},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.102630Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:cce366de4519d0f40fcd53617e9736fff3d24e91990eaea759fd8040a0553409","observation_id":"5db5e81a-55c7-4701-884d-d7490c2a5d63","resolution":{"observed_at":"2026-08-14T12:41:42.434546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.416933Z","title":"The boosting approach to machine learn- ing: An overview","venue":null,"work_id":"3166a6ee-98c8-407c-9142-4609bb27869d","year":2003},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.106415Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:fc8e47944b9d36522cc4e4220f7ce08a7bab51f367602da9737a4983b0b0e72e","observation_id":"89084203-7db4-47d0-aa75-871358f6f972","resolution":{"observed_at":"2026-08-14T12:41:42.422350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.403588Z","title":"Swapout: Learning an ensemble of deep architectures","venue":null,"work_id":"ae4c7eb0-b5e2-462a-b603-227af7b42f1d","year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.110303Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:93073095136f1e6a62ac0aebfca29b4d1b2d75d871e394daa1dec059107f46af","observation_id":"ad9400c5-303d-450d-b963-15d4dca9b2ab","resolution":{"observed_at":"2026-08-14T12:41:42.407631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.390385Z","title":"Data-free parameter pruning for deep neural networks","venue":null,"work_id":"8f5e4393-45a5-436a-ac91-d953c03c344f","year":2015},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.113632Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:a8a6e7dbda1b824b10e0773050f25f39195f3a0d73ec8d7516ab38f2d3041efe","observation_id":"90bb225a-37cf-4440-b191-38ad096619c0","resolution":{"observed_at":"2026-08-14T12:41:42.394410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.374747Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":"46745d3f-37b3-412c-a2b3-21024cf13fa4","year":2014},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.117310Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:f3ce9a2c147e3d74dad2c8e4308e0f9c1b25cb17d38b965d84931cc80816f632","observation_id":"efccfa97-eb61-4687-99a6-4eb464de0e21","resolution":{"observed_at":"2026-08-14T12:41:42.381808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.120739Z","title":"Rethinking the inception ar- chitecture for computer vision","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.120739Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:2b78ef3f17b38f5b5f522d18d819fdee465b14585486054820c221f587783407","observation_id":"1b0dd2da-986f-449e-95f0-e6b415e3583a","resolution":{"observed_at":"2026-08-14T12:41:42.120739Z","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":"2026-08-14T12:41:42.351163Z","title":"Convolutional neural networks with low-rank regularization","venue":null,"work_id":"9ffaf7bf-8463-40f3-a91b-6824f6064a71","year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.124644Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:a22906d9a046c7cb2d1c665295a0bedb05fb034726a51b8bd0595ac5f0e877e3","observation_id":"4776f73d-74f7-4acc-98ca-e3776dfd1566","resolution":{"observed_at":"2026-08-14T12:41:42.355637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.336656Z","title":"Resid- ual networks behave like ensembles of relatively shallow net- works","venue":null,"work_id":"c79d5cae-1265-4e18-842b-3ecec59cc319","year":2016},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.128566Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:3a2e03385f3a76927d43cda311952b9f22ecd637946ce564d8844bcf71a61375","observation_id":"ac534109-22bc-4f52-868f-62e2e495f52a","resolution":{"observed_at":"2026-08-14T12:41:42.341394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.324647Z","title":"Learning time/memory- efficient deep architectures with budgeted super networks","venue":null,"work_id":"ba9eea0f-f1ee-41c8-b0d8-c69bbbcb0815","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.132249Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:874ff2844607e8a1339454a86f804c3bc08a1a8673db51f4176fefa0aed8e0ee","observation_id":"0748f865-6910-4544-a183-0f64d33066b7","resolution":{"observed_at":"2026-08-14T12:41:42.328801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.312989Z","title":"Slimmable neural networks","venue":null,"work_id":"9aee4d17-65e6-4138-9b7b-8b60f61383ce","year":2019},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.135888Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:486d974a3da2932ac5fb653f51f8db833bfef574655b767b4c3c5ec1ef267483","observation_id":"2c48c0d7-a972-4568-8072-c19f1e5dd4d0","resolution":{"observed_at":"2026-08-14T12:41:42.316795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.300904Z","title":"Shufflenet: An extremely efficient convolutional neural net- work for mobile devices","venue":null,"work_id":"889cd71d-8358-4520-b9c1-eb3da2b194f6","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.139459Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:d544bfac8716ceada2cca0b6f984d41d91e503fa1d54bd26bbe05b5c9d18fa5e","observation_id":"e61d5170-b442-4818-8888-5e05db97cfc6","resolution":{"observed_at":"2026-08-14T12:41:42.305476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.143031Z","title":"Pyramid scene parsing network","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.143031Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:3966353a633d1b5c6edfd8cef0db3336df8d23b40baf3e466c26f3c70d4f7497","observation_id":"5c9cb884-bbb3-4712-acd7-1229767256ec","resolution":{"observed_at":"2026-08-14T12:41:42.143031Z","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":"2026-08-14T12:41:42.281334Z","title":"Re- training: A simple way to improve the ensemble accuracy of deep neural networks for image classification","venue":null,"work_id":"9659b366-908c-4b53-8578-f2293789d293","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.147481Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:54b182103d6cb517a6574a70462304db419d4e796de898c91a33bf893dda87a4","observation_id":"80531f32-f6c3-454a-8703-051f9480f027","resolution":{"observed_at":"2026-08-14T12:41:42.285673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.268169Z","title":"Ensembling neu- ral networks: many could be better than all","venue":null,"work_id":"c10bbf1f-bec6-4001-b896-82d6ab426453","year":2002},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.151839Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:e4346fa3e538f48efb18355f96ad309892e81d2b7e2c5d74bfcb0fefb0578952","observation_id":"6df25eff-950a-4a00-86d1-26098b8dbd63","resolution":{"observed_at":"2026-08-14T12:41:42.272404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.253829Z","title":"Binary ensemble neural network: More bits per network or more networks per bit? CVPR, 2019","venue":null,"work_id":"a8cce2c2-b8c5-4c74-845a-d23b29f3ee7e","year":2019},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.155652Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:3b7db70f014d99f2fba03c3acef9fdf09ca36c616c226ec7867176a5c4f2328a","observation_id":"a9906c45-3e9a-498e-bf07-d5bf100e89ae","resolution":{"observed_at":"2026-08-14T12:41:42.258809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T12:41:42.240377Z","title":"Training with expectations","venue":null,"work_id":"39a13f80-8a99-4566-b3db-3a72ca7033f7","year":2018},"citing_paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-14T12:41:42.159757Z"},"links":{"citing_paper":"/paper/1908.06694"},"observation_digest":"sha256:c14b54ae177f1c5ff57c9336782c1ba69cedaf23dcfbad44040c036693eb6443","observation_id":"a672844f-68bd-4eb9-b8c5-a2c970bb5810","resolution":{"observed_at":"2026-08-14T12:41:42.245188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.06694","last_updated":"2019-08-19T11:10:50Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T15:19:38.295881Z","submitted_at":"2019-08-19T11:10:50Z","title":"Adaptative Inference Cost With Convolutional Neural Mixture Models"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":55},"total_outbound_references":63},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:1908.06694."}