{"as_of":"2026-08-14T23:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:64b5c5fe9b636cf95f68b931d312424a7d29be06b782407d007bc92c298c42da","coverage":[{"denominator":181,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T12:19:53.789282Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.08926/citation-record","integrity":"/paper/1908.08926/integrity","json":"/paper/1908.08926/citation-record.json","paper":"/paper/1908.08926"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.167220Z","title":"The Vapnik-Chervonenkis dimension: Information versus com- plexity in learning","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.167220Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:dbff6b76530ac2fedbdfb7a2336e4969012841bd4fba4d97cd07bba60f06241b","observation_id":"2ec01566-f5d1-42c4-a2f4-8b3ccc48bf66","resolution":{"observed_at":"2026-08-14T12:19:53.167220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.178704Z","title":"Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.178704Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:8ef067e86afdbccd9bbaff0fcc39730954655876823002c652ea92de192b42e4","observation_id":"2711d48e-0bb0-4dfb-9df3-f4d2a226a710","resolution":{"observed_at":"2026-08-14T12:19:53.178704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01561","last_updated":"2016-06-05T21:04:46Z","snapshot_observed_at":"2026-08-14T21:54:07.365863Z","submitted_at":"2016-06-05T21:04:46Z","title":"Shallow Networks for High-Accuracy Road Object-Detection","version":1},"cited_work":{"arxiv_id":"1606.01561","doi":null,"metadata_source":"pith","pith_arxiv_id":"1606.01561","snapshot_observed_at":"2026-08-14T12:19:56.226426Z","title":"Shallow Networks for High-Accuracy Road Object-Detection","venue":"cs.CV","work_id":"5ba3f3b9-636c-419f-988b-d64a4220468c","year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.185793Z"},"links":{"cited_paper":"/paper/1606.01561","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:3044c9cd853f9b22953a33b90174a13b9ad1c3c696eee20b7d1e84371be60d33","observation_id":"dfdac729-99f2-4243-b36c-d24625ab6d94","resolution":{"observed_at":"2026-08-14T12:19:56.234494Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.02641","last_updated":"2018-05-07T17:52:42Z","snapshot_observed_at":"2026-08-14T19:17:57.386021Z","submitted_at":"2018-05-07T17:52:42Z","title":"Label Refinery: Improving ImageNet Classification through Label Progression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.02641","snapshot_observed_at":"2026-08-14T12:19:53.193184Z","title":"Label Refinery: Improving ImageNet Classification through Label Progression","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.193184Z"},"links":{"cited_paper":"/paper/1805.02641","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:7ce34c28456260a2377dc6c843083edd99e7f3ff3c424ddf425690013cc5cd01","observation_id":"604d3f5b-ede4-4ab7-9f78-49dc714c6e78","resolution":{"observed_at":"2026-08-14T12:19:53.193184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1308.3432","last_updated":"2013-08-15T15:19:34Z","snapshot_observed_at":"2026-08-14T04:51:04.817737Z","submitted_at":"2013-08-15T15:19:34Z","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.3432","snapshot_observed_at":"2026-08-14T12:19:53.199309Z","title":"Estimating or propagating gradients through stochastic neurons for conditional computation","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.199309Z"},"links":{"cited_paper":"/paper/1308.3432","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:99a78a3a08876a88956562ba5efdc89cc21493c2f83fccb1649ea302ac2fc510","observation_id":"69a3cff5-9b51-4da0-8792-ecef25b0932c","resolution":{"observed_at":"2026-08-14T12:19:53.199309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.04570","last_updated":"2018-09-12T17:24:49Z","snapshot_observed_at":"2026-08-14T18:29:19.091622Z","submitted_at":"2018-09-12T17:24:49Z","title":"FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.04570","snapshot_observed_at":"2026-08-14T12:19:53.206295Z","title":"FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.206295Z"},"links":{"cited_paper":"/paper/1809.04570","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:d688d90155dc64ba4efe00519b56bb25a8c63a2263ef893b854f7c7818e85fd1","observation_id":"6112699b-341a-4a69-a3fe-4a2c344b5141","resolution":{"observed_at":"2026-08-14T12:19:53.206295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.215434Z","title":"Unsupervised pixel-level domain adaptation with gen- erative adversarial networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.215434Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:ed61a5ace6c7ce18b64d312978d9714c445b1ff75c439a010993540279f8b13e","observation_id":"edd9de93-8c1c-47aa-9794-8313452339c5","resolution":{"observed_at":"2026-08-14T12:19:53.215434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.220990Z","title":"A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.220990Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:0028014dac46c2ea31e273be2fb7f9109826ac809991943fcda667f57c519432","observation_id":"b72991b5-d75c-4924-9368-eb8062ef3ea6","resolution":{"observed_at":"2026-08-14T12:19:53.220990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.226714Z","title":"Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.226714Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:bebf058709b4e5328eef9dec6bc9ebbfb8d4bbe1e2d45f9974c9c2129ef54e3b","observation_id":"5de02892-1a12-4bfd-bfdd-331a281bec2c","resolution":{"observed_at":"2026-08-14T12:19:53.226714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.232147Z","title":"Annotating object instances with a polygon-rnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.232147Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:0a0d8d76b1ed5f789065595d1390a5e7637603bc5fc272430a78c2eb1704d72e","observation_id":"c3839e3b-a5dc-4747-9b23-73a950ed4a51","resolution":{"observed_at":"2026-08-14T12:19:53.232147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.00915","last_updated":"2017-05-12T03:25:47Z","snapshot_observed_at":"2026-08-14T21:54:25.974440Z","submitted_at":"2016-06-02T21:52:21Z","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.00915","snapshot_observed_at":"2026-08-14T12:19:53.238084Z","title":"Deeplab: Semantic image segmentation with deep con- volutional nets, atrous convolution, and fully connected crfs","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.238084Z"},"links":{"cited_paper":"/paper/1606.00915","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:edecb5faa001ec4bc56470aaaa12d3cd2a6d2efc7585548552998b0030034270","observation_id":"fd014703-6adf-452d-b1a4-a5027f03553a","resolution":{"observed_at":"2026-08-14T12:19:53.238084Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.05285","last_updated":"2019-03-13T01:44:39Z","snapshot_observed_at":"2026-08-14T17:03:09.680507Z","submitted_at":"2019-03-13T01:44:39Z","title":"All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification","version":1},"cited_work":{"arxiv_id":"1903.05285","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.05285","snapshot_observed_at":"2026-08-14T12:19:56.112621Z","title":"All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification","venue":"cs.CV","work_id":"e743ac47-b8fe-4be0-9506-1c813379fcaa","year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.243505Z"},"links":{"cited_paper":"/paper/1903.05285","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:a4b5d9f99db2fa479391e33bbc37ce5809635b1e50c3cfe0d6acf2e9ac1d5df3","observation_id":"c2ac8184-7c16-4556-af0f-9b905b02855f","resolution":{"observed_at":"2026-08-14T12:19:56.118577Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07759","last_updated":"2017-06-22T03:23:51Z","snapshot_observed_at":"2026-08-14T22:40:09.494597Z","submitted_at":"2016-11-23T12:08:38Z","title":"Multi-View 3D Object Detection Network for Autonomous Driving","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07759","snapshot_observed_at":"2026-08-14T12:19:53.249949Z","title":"Multi-view 3d object detection network for autonomous driving","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.249949Z"},"links":{"cited_paper":"/paper/1611.07759","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:900fa5ba0ac5f3434f7c51fa051dde9bcce6d842f723bd4b5aadce916375f812","observation_id":"751a8dd8-1c7f-4a85-bbd8-96d49e2f81fa","resolution":{"observed_at":"2026-08-14T12:19:53.249949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10979","last_updated":"2019-12-30T14:04:15Z","snapshot_observed_at":"2026-08-14T16:56:30.972603Z","submitted_at":"2019-03-26T16:08:30Z","title":"DetNAS: Backbone Search for Object Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10979","snapshot_observed_at":"2026-08-14T12:19:53.255327Z","title":"Detnas: Neural architecture search on object detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.255327Z"},"links":{"cited_paper":"/paper/1903.10979","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:8a7e79fc8d92e46e3e3a674060f05d62e100a7b707ae2fcf6a0665a3a2e5953d","observation_id":"cef7af58-330c-4e7a-8e0a-2d4b483eaf1f","resolution":{"observed_at":"2026-08-14T12:19:53.255327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1410.0759","last_updated":"2014-12-18T01:13:16Z","snapshot_observed_at":"2026-08-14T23:17:07.466378Z","submitted_at":"2014-10-03T06:16:43Z","title":"cuDNN: Efficient Primitives for Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1410.0759","snapshot_observed_at":"2026-08-14T12:19:53.261036Z","title":"cuDNN: Efficient Primitives for Deep Learning","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.261036Z"},"links":{"cited_paper":"/paper/1410.0759","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:25bc413ac5a0ec9688cb143e8b367fd5776a9ea43678f49834ee58ae9a8d5559","observation_id":"c6557833-1db6-4921-85ee-9275cb216349","resolution":{"observed_at":"2026-08-14T12:19:53.261036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06085","last_updated":"2018-07-17T07:33:19Z","snapshot_observed_at":"2026-08-14T19:14:52.069991Z","submitted_at":"2018-05-16T01:19:43Z","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06085","snapshot_observed_at":"2026-08-14T12:19:53.266794Z","title":"PACT: Parameterized Clipping Activation for Quantized Neu- ral Networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.266794Z"},"links":{"cited_paper":"/paper/1805.06085","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:ced75fafc0929ad4880e0b448ab8596173e0d771c0b4e5c05e92212b1d93a90d","observation_id":"d51e9ec8-f881-4df0-b22e-08e2c21ca1f3","resolution":{"observed_at":"2026-08-14T12:19:53.266794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02357","last_updated":"2017-04-04T18:40:27Z","snapshot_observed_at":"2026-08-14T21:36:12.359558Z","submitted_at":"2016-10-07T17:51:51Z","title":"Xception: Deep Learning with Depthwise Separable Convolutions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02357","snapshot_observed_at":"2026-08-14T12:19:53.273230Z","title":"Xception: Deep Learning with Depthwise Separable Convolutions","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.273230Z"},"links":{"cited_paper":"/paper/1610.02357","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:ba6af4a0c8ab4ef8ee76fe19196b2b3e73c70757a9457676e3071ab64a4b370c","observation_id":"179e128a-3d4b-44aa-85f8-1ca68d9d5f49","resolution":{"observed_at":"2026-08-14T12:19:53.273230Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.05721","last_updated":"2019-06-12T17:47:21Z","snapshot_observed_at":"2026-08-14T16:16:38.585767Z","submitted_at":"2019-06-12T17:47:21Z","title":"Visual Wake Words Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.05721","snapshot_observed_at":"2026-08-14T12:19:53.279989Z","title":"Visual Wake Words Dataset","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.279989Z"},"links":{"cited_paper":"/paper/1906.05721","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:567a6dcad2fdbbf8a53533fc7c441f5e840b3be0948e782119f281a7aab5b6e0","observation_id":"fd9bc8c2-2140-4176-8fb9-6e956c4da554","resolution":{"observed_at":"2026-08-14T12:19:53.279989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.05374","last_updated":"2017-03-30T15:42:12Z","snapshot_observed_at":"2026-08-14T21:16:00.098867Z","submitted_at":"2017-02-17T15:07:40Z","title":"Domain Adaptation for Visual Applications: A Comprehensive Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.05374","snapshot_observed_at":"2026-08-14T12:19:53.286424Z","title":"Domain adaptation for visual applications: A comprehensive sur- vey","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.286424Z"},"links":{"cited_paper":"/paper/1702.05374","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:b5aba5419a2a5a17c622364139e180680896ebd995331e222ddb391701f3a3c8","observation_id":"9d4e72c8-0a56-4bf1-8815-eebec2c0ccb8","resolution":{"observed_at":"2026-08-14T12:19:53.286424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.292338Z","title":"Histograms of Oriented Gradients for Human Detec- tion","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.292338Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:281c818a4c7f9ef53bbd48a7c284d381df278e910983f90f1091e3539d8c67a2","observation_id":"6d0d0ac1-d69e-49d9-aeda-d405680392e0","resolution":{"observed_at":"2026-08-14T12:19:53.292338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.298606Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.298606Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:62be468fc964fefd17c365d27351fc816a834d9746a1fbbead7b0143e8e4b58b","observation_id":"49b7c034-8b23-4410-82c5-aad3bc04d7df","resolution":{"observed_at":"2026-08-14T12:19:53.298606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.03696","last_updated":"2019-04-29T06:49:08Z","snapshot_observed_at":"2026-08-14T16:40:12.673015Z","submitted_at":"2019-04-29T06:49:08Z","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.03696","snapshot_observed_at":"2026-08-14T12:19:53.305424Z","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.305424Z"},"links":{"cited_paper":"/paper/1905.03696","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:278eab833b2592983cae6a70a7d89b128e9576001002e36d748f4bc2b0618178","observation_id":"ae365b72-0a84-46af-82ae-9dbff7f0cef2","resolution":{"observed_at":"2026-08-14T12:19:53.305424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.316287Z","title":"CARLA: An Open Urban Driving Simulator","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.316287Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:eb9c76e7e776560277a1726d7b1e23d4ceb6b6e5c50ab60dbac3f578dec567f9","observation_id":"e6c41bd7-4231-48df-a5ae-c7c4aaa3a957","resolution":{"observed_at":"2026-08-14T12:19:53.316287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.321867Z","title":"On the segmentation of 3D LIDAR point clouds","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.321867Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:2a656c7c7e2b551dc3f10a72a251253ed66e01d3aa89864927ad0a46278a4de5","observation_id":"d2b5175f-651d-4552-b971-6409688894c6","resolution":{"observed_at":"2026-08-14T12:19:53.321867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.328957Z","title":"On the segmentation of 3D LIDAR point clouds","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.328957Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:dc861ac01809b4ecc7bdc36876f35bf1d637dc601722f78c87c41da46e25c8c7","observation_id":"a02d5742-959e-4fdd-8c22-041389df4f7a","resolution":{"observed_at":"2026-08-14T12:19:53.328957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.335090Z","title":"Dutta, A","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.335090Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:034abe46b2898fa5b0eafabffcff8385af395479668b0c5e3aaba2c1bdec527a","observation_id":"b7aae3d9-33bd-4227-b61f-b1ec55a97485","resolution":{"observed_at":"2026-08-14T12:19:53.335090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.340136Z","title":"A Density-based Algorithm for Discovering Clusters a Density- based Algorithm for Discovering Clusters in Large Spatial Databases with Noise","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.340136Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:7ced9e2cfe7ed2fac8c7fcb4e9ab61822defb9471b724671d1a12071c7ff13cc","observation_id":"4341ebc9-4916-4182-befc-01e136015b3c","resolution":{"observed_at":"2026-08-14T12:19:53.340136Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.352065Z","title":"The Pascal Visual Object Classes (VOC) Challenge","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.352065Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:9e00e7fa001e47612f1e470dc1b50f5eaf55ccea98951a538fd9155be997b73d","observation_id":"03f52c2c-c976-4f05-85d8-0a1e43a21038","resolution":{"observed_at":"2026-08-14T12:19:53.352065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.357070Z","title":"Object detection with discriminatively trained part- based models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.357070Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:bd241fea083638ed5e7aefc6ef938b6a8d01a7ba3db6c707cd1d229e2e04c418","observation_id":"d473c221-aa9b-4957-807e-718c068bc35e","resolution":{"observed_at":"2026-08-14T12:19:53.357070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.362127Z","title":"Scenic: a language for scenario specification and scene gen- eration","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.362127Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:66d0ca41b3accab4925dc4a006137e751c156873e01b1512c332fe54fd0ec11c","observation_id":"d5b164e2-0b40-4c45-8d2e-eb80e6579a29","resolution":{"observed_at":"2026-08-14T12:19:53.362127Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.368189Z","title":"Domain-adversarial training of neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.368189Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:58b3f76660a96650c841069af45720537d1a0b6f9a7d47e6df7ffc364e0af3b5","observation_id":"bcc3e234-33e7-4efd-ad4e-09364b93dfe9","resolution":{"observed_at":"2026-08-14T12:19:53.368189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1508.06576","last_updated":"2015-09-02T08:24:59Z","snapshot_observed_at":"2026-08-14T22:35:07.015195Z","submitted_at":"2015-08-26T17:14:42Z","title":"A Neural Algorithm of Artistic Style","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1508.06576","snapshot_observed_at":"2026-08-14T12:19:53.372718Z","title":"A Neural Algorithm of Artistic Style","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.372718Z"},"links":{"cited_paper":"/paper/1508.06576","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:415366a23a6866dfa3dd5cb745e38e3d6f44c94276b11d4ab530964ff64f642d","observation_id":"f3741753-ef8a-46e7-b730-f18ec452579d","resolution":{"observed_at":"2026-08-14T12:19:53.372718Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.378135Z","title":"Are we ready for autonomous driving? the kitti vision benchmark suite","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.378135Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:49a67640eae1a1e5486358fc2cf2cfa3f1e9899422907386570e922021f1b2e5","observation_id":"28dc2a53-05c5-43ca-a1be-7f7f2d9c24fd","resolution":{"observed_at":"2026-08-14T12:19:53.378135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.383835Z","title":"Are we ready for autonomous driving? the kitti vision benchmark suite","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.383835Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:2ae6e9ba07fbd3df843f667ab115a3563aeb8ea8bc2211db6a195d91f5884add","observation_id":"e29c0250-b225-4c9e-90f3-c7dfdd4cfdeb","resolution":{"observed_at":"2026-08-14T12:19:53.383835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.389847Z","title":"Deep reconstruction-classification networks for unsuper- vised domain adaptation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.389847Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:aa044eb4f391a71187e1bc7b209dd6b498d0dcd0190edf75c917c4edb3968744","observation_id":"feb316e7-fad1-4729-93f7-b295e32170d5","resolution":{"observed_at":"2026-08-14T12:19:53.389847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.394727Z","title":"Domain generalization for object recognition with multi- task autoencoders","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.394727Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:14762400539a4bce403c4e26f0869f702767962d13f2db42530c003d760cf0f5","observation_id":"79fbc93a-be03-4486-a9bd-f66ab04b0555","resolution":{"observed_at":"2026-08-14T12:19:53.394727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.10615","last_updated":"2018-08-27T18:38:51Z","snapshot_observed_at":"2026-08-14T19:33:06.165481Z","submitted_at":"2018-03-23T16:40:30Z","title":"SqueezeNext: Hardware-Aware Neural Network Design","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.10615","snapshot_observed_at":"2026-08-14T12:19:53.399145Z","title":"SqueezeNext: Hardware-Aware Neural Network Design","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.399145Z"},"links":{"cited_paper":"/paper/1803.10615","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:c727520e5538f0f10751b17a780bdd4582ed97f23ca72b90c8a8a59b8521b452","observation_id":"cadc9ca1-3c55-4ca5-bfd4-b215e182d21f","resolution":{"observed_at":"2026-08-14T12:19:53.399145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.403936Z","title":"Fast R-CNN","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.403936Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:d267f83495b645713b1a5c43dc76d74d5b5f71e748dc8dd20e0e3a0c4209ddaa","observation_id":"c8cf4cae-15ec-4b38-ace6-e15536204729","resolution":{"observed_at":"2026-08-14T12:19:53.403936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.408649Z","title":"Deformable Part Models are Convolutional Neural Networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.408649Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:4cb5b3555e4f01ddff884a0f67666f80046087b7e6fc240dff2a5286628f640a","observation_id":"49011878-abce-4509-b061-55935cd5204c","resolution":{"observed_at":"2026-08-14T12:19:53.408649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.413888Z","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.413888Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:fef4b651fd1a3f631032e138aa669f74b34804492570a3a3e3e075224d912ef4","observation_id":"2b80f77a-2092-442f-9e71-52a145b82811","resolution":{"observed_at":"2026-08-14T12:19:53.413888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.418650Z","title":"Supplementary Material: Rich feature hierarchies for accurate object detection and semantic segmentation","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.418650Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:6cb94cf012d7b13c1438612605ff5af808185ee735e37255f66247136f5be8cf","observation_id":"b6956c08-3538-4ba1-a461-64516ecac71f","resolution":{"observed_at":"2026-08-14T12:19:53.418650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.425414Z","title":"Software-Hardware Codesign for Efficient Neural Network Ac- celeration","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.425414Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:7095a8ec512039ce2ed27b3bcfcb95afe07d8ff7ac969a3367c8705a076d932b","observation_id":"a487f029-b190-4ca6-8e72-7351091ed32a","resolution":{"observed_at":"2026-08-14T12:19:53.425414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.431950Z","title":"Ms-celeb-1m: Challenge of recognizing one million celebrities in the real world","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.431950Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:eb7f7288a87c1aa3e9b2be1f53b46ae85d4d702e985b7f4455f0c6bbc6188460","observation_id":"f956af2d-2d4e-4a01-a31b-9848fa13cc7c","resolution":{"observed_at":"2026-08-14T12:19:53.431950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.00420","last_updated":"2020-07-08T10:55:28Z","snapshot_observed_at":"2026-08-14T16:54:06.408888Z","submitted_at":"2019-03-31T14:34:43Z","title":"Single Path One-Shot Neural Architecture Search with Uniform Sampling","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.00420","snapshot_observed_at":"2026-08-14T12:19:53.437827Z","title":"Single path one-shot neural architecture search with uniform sam- pling","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.437827Z"},"links":{"cited_paper":"/paper/1904.00420","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:e8ce2c9a17d1cd4abbf19902092f406d0a2bee283cd08b3726f79c0cbbf53ace","observation_id":"3e5a560c-1d32-4f67-91d7-abb5efb40731","resolution":{"observed_at":"2026-08-14T12:19:53.437827Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.443903Z","title":"The unreasonable effectiveness of data","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.443903Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:8be5f9956f2510cf8a180f51a0b31a2d621fda621c0a6316640f7da3c98530d8","observation_id":"56933147-b87c-487c-8ea7-8c7d88c916a2","resolution":{"observed_at":"2026-08-14T12:19:53.443903Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.451290Z","title":"Deep Compression: Compressing DNNs with Pruning, Trained Quantization and Huffman Coding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.451290Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:5d0d3b00ad4d896448bd1d37776874f2f6d6e8fd1d39a7c9398eb3cc9ed1c1bf","observation_id":"e874090a-36f6-4753-8d3d-29db09332d27","resolution":{"observed_at":"2026-08-14T12:19:53.451290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-14T12:19:53.458539Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.458539Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:a99537cc142297c8e1b43f3e6ff951c7f535036ff45eb8028fd4951d1e8457e2","observation_id":"197d12ff-dc88-4194-9b80-895993347ea1","resolution":{"observed_at":"2026-08-14T12:19:53.458539Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05567","last_updated":"2018-06-29T19:16:39Z","snapshot_observed_at":"2026-08-14T19:36:00.860774Z","submitted_at":"2018-03-15T01:30:58Z","title":"Achieving Human Parity on Automatic Chinese to English News Translation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05567","snapshot_observed_at":"2026-08-14T12:19:53.463873Z","title":"Achieving human parity on automatic chinese to english news translation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.463873Z"},"links":{"cited_paper":"/paper/1803.05567","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:ddc772363d5212166af62914b6fc0393899f2934b837b3ef98d392066caa7b25","observation_id":"36396b45-d17a-402b-9ed8-d682298078f5","resolution":{"observed_at":"2026-08-14T12:19:53.463873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-14T12:19:53.468969Z","title":"Deep Residual Learning for Image Recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.468969Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:f533037718fb3881f52ce06987fe161064b0262ed20b4f7f01371ebbbbb5950b","observation_id":"af56d365-1384-438e-8345-ff44724bf29b","resolution":{"observed_at":"2026-08-14T12:19:53.468969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.475038Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.475038Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:19055d4be07ddc17f2685e78ccf64f66142845140a742b6c6efabe7e339b9b4e","observation_id":"71cda0b5-7f68-4dd7-bb50-8566dce0d84c","resolution":{"observed_at":"2026-08-14T12:19:53.475038Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.480147Z","title":"Identity mappings in deep residual networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.480147Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:cdf6589b6859b902e04194c55cf4246b19a8f3ed16863c6b3640175655d480ec","observation_id":"e8787b2d-3823-4a1d-aea1-609df6288973","resolution":{"observed_at":"2026-08-14T12:19:53.480147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.484941Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.484941Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:55b3efcc54ce453435b240b2ca8c0bf5fd955f0271acae715e41146cd07246e8","observation_id":"f85c0c5e-51c0-4125-8b73-f4c89b9e686e","resolution":{"observed_at":"2026-08-14T12:19:53.484941Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.489759Z","title":"Addressnet: Shift-based primitives for efficient convolutional neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.489759Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:6f1c2cb59c961f2ad717992e8243441192ea382f3833058fc5e3b063d7d9d336","observation_id":"869450c0-1917-4c25-a439-df51a21c274b","resolution":{"observed_at":"2026-08-14T12:19:53.489759Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.494547Z","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.494547Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:3be38fc7276b1f8e313d64ab8456ef66e24df22108104c1e282e54ab7734b076","observation_id":"de81de27-6881-4180-b522-6f5b6492c093","resolution":{"observed_at":"2026-08-14T12:19:53.494547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.499752Z","title":"LIDAR-based 3D object perception","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.499752Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:dcb02f1ad66506ef93c31457ca4c88974144f8dc33b3ed188b7712b22fdadf96","observation_id":"60e528f8-c534-477c-9b30-a5940d824db0","resolution":{"observed_at":"2026-08-14T12:19:53.499752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.504754Z","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.504754Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:d58852b2c84850c15cdc84d19c5d7efd233d95a39f16264897f70d25462c821b","observation_id":"6be9eea1-96af-4da5-b3e9-bc1cf0e3601b","resolution":{"observed_at":"2026-08-14T12:19:53.504754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-14T12:19:53.516223Z","title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.516223Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:925aeef4ff3f88e73f623feb3e50b9b3009b3b6301ee77ce83e7caf6f315e6cc","observation_id":"c53cac01-349d-49b1-82b1-fc038ff28885","resolution":{"observed_at":"2026-08-14T12:19:53.516223Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.02244","last_updated":"2019-11-20T17:26:40Z","snapshot_observed_at":"2026-08-14T16:36:30.006489Z","submitted_at":"2019-05-06T19:38:31Z","title":"Searching for MobileNetV3","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.02244","snapshot_observed_at":"2026-08-14T12:19:53.521579Z","title":"Searching for mobilenetv3","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.521579Z"},"links":{"cited_paper":"/paper/1905.02244","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:25107def3cd79b07492ab28a0a439592f0dcb71a22fe2a154e088060e621f118","observation_id":"611672a4-baa9-43a5-b5dc-2a6af153f9c1","resolution":{"observed_at":"2026-08-14T12:19:53.521579Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.534338Z","title":"Squeeze-and-excitation networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.534338Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:44fc4feb3aec464ee5fa2b3d2d28c254d1e4c635567c2bd0dd9520f2a99732c0","observation_id":"0a7b0bdb-94bb-42de-bea5-e00597206775","resolution":{"observed_at":"2026-08-14T12:19:53.534338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.539688Z","title":"Densely Connected Convolutional Networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.539688Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:e7e0326d0a7b49bbff4a5b42b3b90375f46329a7174c1debc6e2ced3e6d34a15","observation_id":"87db7b75-88b3-4d4d-933a-0f76acce4d36","resolution":{"observed_at":"2026-08-14T12:19:53.539688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.544490Z","title":"Rethinking the inception architecture for computer vision","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.544490Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:aca0d20439e4730bcd6bd8fa2d3cf3a01b987ccdb298713d3e2a26f2c1ebc98b","observation_id":"5e6225bd-009f-48de-be2b-610a760b0090","resolution":{"observed_at":"2026-08-14T12:19:53.544490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.550345Z","title":"The apolloscape dataset for autonomous driving","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.550345Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:dbedae751fd02fb817fd87e879db6088a1371031754606796024e9881a70d8ab","observation_id":"7f3d99e3-b8fe-4eec-94ae-4487644ce94d","resolution":{"observed_at":"2026-08-14T12:19:53.550345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1404.1869","last_updated":"2014-04-07T18:08:56Z","snapshot_observed_at":"2026-08-14T23:38:22.478078Z","submitted_at":"2014-04-07T18:08:56Z","title":"DenseNet: Implementing Efficient ConvNet Descriptor Pyramids","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1404.1869","snapshot_observed_at":"2026-08-14T12:19:53.555866Z","title":"DenseNet: Implementing Efficient ConvNet Descriptor Pyra- mids","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.555866Z"},"links":{"cited_paper":"/paper/1404.1869","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:c7a4094f9f5afa25718eb9d4a1eb7dc60ef1c500cb6906d696e72a125b2521e7","observation_id":"948bc508-43f5-40b8-90f6-364c4d08aaff","resolution":{"observed_at":"2026-08-14T12:19:53.555866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-14T12:19:53.566440Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer param- eters and ¡0.5MB model size","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.566440Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:70f5668564195c2579f7a46611e4333d74e610d59017eb44b8fea8cfeb5cc932","observation_id":"ec95d0c1-feff-4cb6-9c0b-559a27ccfc31","resolution":{"observed_at":"2026-08-14T12:19:53.566440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.571543Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.571543Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:1d6df7229d6924176afe83a313715bbdd8d7b860810ab9614683ecb2383126d8","observation_id":"518bfc4b-f1b6-497a-ad54-d5bd35134f9e","resolution":{"observed_at":"2026-08-14T12:19:53.571543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01144","last_updated":"2017-08-05T22:45:19Z","snapshot_observed_at":"2026-08-01T18:34:23.156273Z","submitted_at":"2016-11-03T19:48:08Z","title":"Categorical Reparameterization with Gumbel-Softmax","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01144","snapshot_observed_at":"2026-08-14T12:19:53.576669Z","title":"Categorical reparameterization with gumbel- softmax","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.576669Z"},"links":{"cited_paper":"/paper/1611.01144","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:552932cd8217f744885a71acc010bf49c63069a99b19c0b4a61a6383d6a18781","observation_id":"add08769-768e-4c9a-9dde-878b670bca6a","resolution":{"observed_at":"2026-08-14T12:19:53.576669Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1408.5093","last_updated":"2014-06-20T23:00:32Z","snapshot_observed_at":"2026-08-14T23:29:34.870683Z","submitted_at":"2014-06-20T23:00:32Z","title":"Caffe: Convolutional Architecture for Fast Feature Embedding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1408.5093","snapshot_observed_at":"2026-08-14T12:19:53.581656Z","title":"Caffe: Convolutional Architecture for Fast Feature Embedding","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.581656Z"},"links":{"cited_paper":"/paper/1408.5093","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:fa8464134ed5f44a5974bf01541e601d07746b19a9de70e38bad1e3ba87fc519","observation_id":"7ba52d64-782a-4b9c-9644-2159f65e8f5c","resolution":{"observed_at":"2026-08-14T12:19:53.581656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.586287Z","title":"Accelerating low bit-width convolutional neural networks with em- bedded FPGA","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.586287Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:b92da26b5e5a646daec0377ceff2f3d2d1e6543a89c330c0da026caa8557005a","observation_id":"41cde180-6434-441f-bb4c-75699c579f73","resolution":{"observed_at":"2026-08-14T12:19:53.586287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1603.08155","last_updated":"2016-03-27T01:04:27Z","snapshot_observed_at":"2026-08-14T22:04:21.333248Z","submitted_at":"2016-03-27T01:04:27Z","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.08155","snapshot_observed_at":"2026-08-14T12:19:53.591332Z","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.591332Z"},"links":{"cited_paper":"/paper/1603.08155","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:a688e765e92e49babcea8efd724255bd9fb8ba328c0c1506676b25c269ebc4e0","observation_id":"50715c44-eb90-4abf-af38-9664ec17ceed","resolution":{"observed_at":"2026-08-14T12:19:53.591332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.01983","last_updated":"2017-02-25T13:20:49Z","snapshot_observed_at":"2026-08-14T21:36:22.415763Z","submitted_at":"2016-10-06T18:26:43Z","title":"Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.01983","snapshot_observed_at":"2026-08-14T12:19:53.596401Z","title":"Driving in the Matrix: Can Virtual Worlds Re- place Human-Generated Annotations for Real World Tasks?","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.596401Z"},"links":{"cited_paper":"/paper/1610.01983","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:3a927e61e6ab148b8d3022945ce9915ec1a8b05c5c047fb222bc6c8608f05fe9","observation_id":"e9824cd3-55c1-4512-88e1-6fab87875955","resolution":{"observed_at":"2026-08-14T12:19:53.596401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.602134Z","title":"Driving in the matrix: Can virtual worlds replace human-generated annotations for real world tasks?","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.602134Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:0b09c673c6f4c34e7101db4faec49eaac5ebe32705440cba64b0fdf2140148bb","observation_id":"6b07934d-41bb-46c3-a267-7869b6c6668e","resolution":{"observed_at":"2026-08-14T12:19:53.602134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06049","last_updated":"2017-07-01T17:02:44Z","snapshot_observed_at":"2026-08-14T21:43:19.890729Z","submitted_at":"2016-08-22T04:32:21Z","title":"Local Binary Convolutional Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06049","snapshot_observed_at":"2026-08-14T12:19:53.606975Z","title":"Local Binary Convo- lutional Neural Networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.606975Z"},"links":{"cited_paper":"/paper/1608.06049","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:305a24522161672a30fd997d8a0b9912a9af947d1ddd5ee3d9b84a1133b6e876","observation_id":"9b1ff8c6-6f8e-45ea-84b3-b9f48d8b4268","resolution":{"observed_at":"2026-08-14T12:19:53.606975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.05779","last_updated":"2018-11-23T02:18:04Z","snapshot_observed_at":"2026-08-14T18:40:05.529453Z","submitted_at":"2018-08-17T07:28:17Z","title":"Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.05779","snapshot_observed_at":"2026-08-14T12:19:53.611892Z","title":"Joint Training of Low-Precision Neural Network with Quantization Interval Parameters","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.611892Z"},"links":{"cited_paper":"/paper/1808.05779","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:4f29473b1063368d4c35cecedf3e08adaf8ebab6c094e7b6bc68f7b63596e52b","observation_id":"8d4a21af-f7f7-49cc-8961-b5b9ca6a6223","resolution":{"observed_at":"2026-08-14T12:19:53.611892Z","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":"2026-08-14T12:19:53.616787Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.616787Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:89e77f695d6a818d5d3d1f278308a4ed12fa69754138b1a2d1a585b11c3b0454","observation_id":"b85881c2-0895-4820-b4f5-3a9d63340106","resolution":{"observed_at":"2026-08-14T12:19:53.616787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.621277Z","title":"Free supervision from video games","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.621277Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:3434586fd1bfaae548bcea08c2389e07fb481be40b052ddf27466451a8bc2910","observation_id":"862dd1f3-f6f7-4873-94ae-4857ce5a4be2","resolution":{"observed_at":"2026-08-14T12:19:53.621277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.625762Z","title":"Efficient inference in fully connected crfs with gaussian edge potentials","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.625762Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:7aae22d4f4b84335b56392c55b4731822e25ddc21903d9c46c49cd4638cc29f8","observation_id":"1e1131b0-c1f1-4a60-a815-f5673577e129","resolution":{"observed_at":"2026-08-14T12:19:53.625762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.632080Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.632080Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:6c58dd9ad046de4a7ba7b3ee19ec62c4606bc7d0f5853b79045bd0a857a41697","observation_id":"232a1255-efff-4487-ae38-81bbf3e2d003","resolution":{"observed_at":"2026-08-14T12:19:53.632080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.637204Z","title":"ImageNet Classification with Deep Convolutional Neural Networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.637204Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:dc026dce56d97b9f47812c6ca601539d1e106a36cdd6cc5eb6ae4eedb587cba5","observation_id":"b45b4d12-de28-4531-959c-25006dcbb4ba","resolution":{"observed_at":"2026-08-14T12:19:53.637204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.642831Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.642831Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:77e755399948637d51e4fd522b437236a39ee16ac2b0a98dadb56e08483da2ef","observation_id":"10b897b6-a939-490f-9397-301cbf6eb469","resolution":{"observed_at":"2026-08-14T12:19:53.642831Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.650101Z","title":"Maestro: A Memory-on-Logic Architecture for Coordinated Parallel Use of Many Systolic Arrays","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.650101Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:c486a57506c6c548624ad4860c94b4f6e760f0b50e5413855aaea865cf0ee673","observation_id":"0667944b-87ec-4236-ac27-c5817e81fa5b","resolution":{"observed_at":"2026-08-14T12:19:53.650101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.655359Z","title":"Research methods in human-computer interaction","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.655359Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:9b30c15126d8a9e982bfb28936db245ef66b7e4185e6b124d366a43fda17207e","observation_id":"458fae54-bdb7-4c9b-a774-a9e0225ec4f7","resolution":{"observed_at":"2026-08-14T12:19:53.655359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.09870","last_updated":"2017-09-13T03:21:48Z","snapshot_observed_at":"2026-08-14T20:45:48.947592Z","submitted_at":"2017-07-24T04:50:50Z","title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM","version":2},"cited_work":{"arxiv_id":"1707.09870","doi":null,"metadata_source":"pith","pith_arxiv_id":"1707.09870","snapshot_observed_at":"2026-08-14T12:19:55.316810Z","title":"Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM","venue":"cs.CV","work_id":"af913174-0a99-4df9-afd9-3c0c49bd96bf","year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.660599Z"},"links":{"cited_paper":"/paper/1707.09870","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:8c7ee850ad40fbb625f87b511ba0f573971ccbc16770f93f1f682f5886f47ada","observation_id":"95e64fd7-1bda-4a2d-b620-9e31f071811e","resolution":{"observed_at":"2026-08-14T12:19:55.324435Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.07916","last_updated":"2016-08-29T05:57:36Z","snapshot_observed_at":"2026-08-14T21:42:26.871054Z","submitted_at":"2016-08-29T05:57:36Z","title":"Vehicle Detection from 3D Lidar Using Fully Convolutional Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.07916","snapshot_observed_at":"2026-08-14T12:19:53.666240Z","title":"Vehicle detection from 3d lidar using fully convolutional network","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.666240Z"},"links":{"cited_paper":"/paper/1608.07916","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:251edc5ec72eee718a693934277b2959f4bb2a6bb87985e5cd4f601fdb8b7dde","observation_id":"5bd5b1f6-16ac-45c3-8d0b-2ce30f5250af","resolution":{"observed_at":"2026-08-14T12:19:53.666240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.671154Z","title":"Adaptive Batch Normalization for practical domain adaptation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.671154Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:bb1eb8b7a7b1eac928bf66464d5fb64d2591d2da53ab52e2ebedc2b95a5b7906","observation_id":"2917963e-4648-4b3c-a24e-6844920888ab","resolution":{"observed_at":"2026-08-14T12:19:53.671154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.11013","last_updated":"2018-07-29T06:58:38Z","snapshot_observed_at":"2026-08-14T18:46:43.696596Z","submitted_at":"2018-07-29T06:58:38Z","title":"Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.11013","snapshot_observed_at":"2026-08-14T12:19:53.677197Z","title":"Tiny-dsod: Lightweight object detection for resource-restricted usages","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.677197Z"},"links":{"cited_paper":"/paper/1807.11013","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:83e5c5506ee409b5eb03b191790c6e7bceb91357e08c798e12dc3e856899e577","observation_id":"0d1e2cac-9565-4188-972d-d917e62a8751","resolution":{"observed_at":"2026-08-14T12:19:53.677197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.688853Z","title":"FP-BNN: Binarized neural network on FPGA","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.688853Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:f1c847f9ec5b3364f77fbde5e1b013343ed5e744ca64272979a5625f4d3c4f75","observation_id":"ea02eb2b-24ea-44d5-a70f-bdb15c37770d","resolution":{"observed_at":"2026-08-14T12:19:53.688853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.08383","last_updated":"2019-08-22T16:31:16Z","snapshot_observed_at":"2026-08-14T17:56:04.039749Z","submitted_at":"2018-11-20T17:39:26Z","title":"TSM: Temporal Shift Module for Efficient Video Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.08383","snapshot_observed_at":"2026-08-14T12:19:53.694910Z","title":"Temporal shift module for efficient video un- derstanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.694910Z"},"links":{"cited_paper":"/paper/1811.08383","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:0c55f98c8ed431c91b38cb384261f8501990357cf42ef5fb989ffd1574219209","observation_id":"7a6b8673-7b60-433b-996f-40bc427bd64c","resolution":{"observed_at":"2026-08-14T12:19:53.694910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.701829Z","title":"Focal loss for dense object detection","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.701829Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:5dbc7cf482c693b7d19329d8a3cfa9c24017c1ce9a13224a49fbc14c69fd1d80","observation_id":"cb110077-be60-4f87-b9fc-326559bffcce","resolution":{"observed_at":"2026-08-14T12:19:53.701829Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1405.0312","last_updated":"2015-02-21T01:48:49Z","snapshot_observed_at":"2026-07-06T03:42:37.507458Z","submitted_at":"2014-05-01T21:43:32Z","title":"Microsoft COCO: Common Objects in Context","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1405.0312","snapshot_observed_at":"2026-08-14T12:19:53.707865Z","title":"Microsoft COCO: Common Objects in Context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.707865Z"},"links":{"cited_paper":"/paper/1405.0312","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:b29f46b8754309d65840935aa664fb923755f7726573057615dd206b03390d95","observation_id":"adbf9402-281a-47b9-8375-28b22d6c4407","resolution":{"observed_at":"2026-08-14T12:19:53.707865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.00559","last_updated":"2018-07-26T19:51:26Z","snapshot_observed_at":"2026-08-14T20:07:44.068933Z","submitted_at":"2017-12-02T06:23:16Z","title":"Progressive Neural Architecture Search","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.00559","snapshot_observed_at":"2026-08-14T12:19:53.721030Z","title":"Progressive neural architecture search","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.721030Z"},"links":{"cited_paper":"/paper/1712.00559","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:1ca03e8f4496abbcd42af09ce36c92eea0b04ea5a434efea2987b282268c1111","observation_id":"b611cfb5-8452-4258-9f05-9c3e9835586d","resolution":{"observed_at":"2026-08-14T12:19:53.721030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.09055","last_updated":"2019-04-23T06:29:32Z","snapshot_observed_at":"2026-08-14T19:00:06.514996Z","submitted_at":"2018-06-24T00:06:13Z","title":"DARTS: Differentiable Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.09055","snapshot_observed_at":"2026-08-14T12:19:53.727731Z","title":"Darts: Differentiable architecture search","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.727731Z"},"links":{"cited_paper":"/paper/1806.09055","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:e8d4a8fdb2953eb7cfff8b51df8b24e8719ea609056671f7429e793b088c3a60","observation_id":"1bc00182-e4f2-4565-bd0c-e91e64da5ebb","resolution":{"observed_at":"2026-08-14T12:19:53.727731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.734064Z","title":"Coupled generative adversarial networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.734064Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:eace3d44e0af3bcbccf13744f5091e8668bcb5a98c4ad166f7b935660eb75171","observation_id":"688992c3-8f30-4fe5-af6e-c2bc26876f3d","resolution":{"observed_at":"2026-08-14T12:19:53.734064Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.741982Z","title":"Ssd: Single shot multibox detector","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.741982Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:25643242294ca17ac4bcfc0b9a5ebe8c2a0f24fc54e6fc84279ab5110f857d84","observation_id":"8646009a-4b4a-41cd-b549-0b1ee5106c5d","resolution":{"observed_at":"2026-08-14T12:19:53.741982Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10258","last_updated":"2019-08-14T03:41:11Z","snapshot_observed_at":"2026-08-14T16:57:18.424628Z","submitted_at":"2019-03-25T12:05:27Z","title":"MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.10258","snapshot_observed_at":"2026-08-14T12:19:53.748263Z","title":"MetaPruning: Meta Learning for Automatic Neural Network Chan- nel Pruning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.748263Z"},"links":{"cited_paper":"/paper/1903.10258","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:95fd8a1bb276b494415f7d4cb44c309997058907e2c4b486183935f666e7206a","observation_id":"9d35c388-f72b-4f4a-a71d-f832f2b56a6d","resolution":{"observed_at":"2026-08-14T12:19:53.748263Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.753905Z","title":"Fully Convolutional Networks for Semantic Segmentation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.753905Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:fa25371647a0ecc7370dd55f1dd85519aacee21cc56191a82641bb4f9bc0d371","observation_id":"06c4b7cb-555e-4bdf-87b9-1219ad9058bb","resolution":{"observed_at":"2026-08-14T12:19:53.753905Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.766341Z","title":"Learning transferable features with deep adaptation net- works","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.766341Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:358ba49a26c36d8243e3b6b1c93a7c6a49f20f66edfe7ed63bac07b84b11107e","observation_id":"cb0c2b90-04a8-4f0e-b733-44496e412542","resolution":{"observed_at":"2026-08-14T12:19:53.766341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.11164","last_updated":"2018-07-30T04:18:25Z","snapshot_observed_at":"2026-08-14T18:46:34.880368Z","submitted_at":"2018-07-30T04:18:25Z","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.11164","snapshot_observed_at":"2026-08-14T12:19:53.772804Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.772804Z"},"links":{"cited_paper":"/paper/1807.11164","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:32d557e401d3bb057aa1148a062887f1162c87304ecac7cf62993ceb2e859e7d","observation_id":"b22a9383-bee0-4baf-8463-67b09d4452c9","resolution":{"observed_at":"2026-08-14T12:19:53.772804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.00712","last_updated":"2017-03-05T16:59:44Z","snapshot_observed_at":"2026-08-14T21:32:15.920360Z","submitted_at":"2016-11-02T18:25:40Z","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.00712","snapshot_observed_at":"2026-08-14T12:19:53.778296Z","title":"The concrete distribution: A continuous relaxation of discrete random variables","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.778296Z"},"links":{"cited_paper":"/paper/1611.00712","citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:2010e00400bab09b8574656f9aa9884a8004adf846f6d44f528c0cf8439c83a8","observation_id":"b6cebff1-c011-49d4-82dd-e5d4dc448534","resolution":{"observed_at":"2026-08-14T12:19:53.778296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.784158Z","title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.784158Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:a8f5986356a7eec88aa7618df1430a21fb9d27ac529ce70fff038715be32d212","observation_id":"2367b1b8-4224-4def-b431-07b8bade5d47","resolution":{"observed_at":"2026-08-14T12:19:53.784158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:19:53.789282Z","title":"3d convolutional neural networks for land- ing zone detection from lidar","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks","version":1},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-08-14T12:19:53.789282Z"},"links":{"citing_paper":"/paper/1908.08926"},"observation_digest":"sha256:7f05c3d5018db2d7a58631495caba1dd328b0cdd77c33a76c36f9305ab4776c5","observation_id":"9657d810-31b2-4cb0-a563-a18cf7329c0d","resolution":{"observed_at":"2026-08-14T12:19:53.789282Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.08926","last_updated":"2019-08-20T23:26:04Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T19:51:52.899670Z","submitted_at":"2019-08-20T23:26:04Z","title":"Efficient Deep Neural Networks"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":97,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":181},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 100 of 181 outbound references and 0 inbound Pith citation observations for arXiv:1908.08926."}