{"as_of":"2026-08-22T09:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0f8b47ef27019ccb0f18746bc879789438236b02db1c0820bcaf6d8b5b19edd9","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T12:53:41.647801Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/1908.06294/citation-record","integrity":"/paper/1908.06294/integrity","json":"/paper/1908.06294/citation-record.json","paper":"/paper/1908.06294"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:43.391086Z","title":"Do deep nets really need to be deep? In NIPS, 2014","venue":null,"work_id":"6189a8bd-bae1-4f69-a250-f2ffaf60335c","year":2014},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:40.976628Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:a4dd92531f8770ae622aabdcb8f8970f5f6122fb717ff2073002da923011078e","observation_id":"3ebaf5b4-66b1-48a3-a918-c4b577cf4189","resolution":{"observed_at":"2026-08-14T12:53:43.398553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:43.354318Z","title":"Adaptive neural networks for fast test-time pre- diction","venue":null,"work_id":"f929a187-f925-4c06-86d5-48f38e6946ee","year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:40.984088Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:98186529ff9e64319fc0686bf6a07be707f1a0706394cdd022754e44853db0d0","observation_id":"93a7c40d-40dc-4da5-85ad-8ee7fa1accb3","resolution":{"observed_at":"2026-08-14T12:53:43.368592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:43.318717Z","title":"Model compression","venue":null,"work_id":"9eba9118-014e-4e44-990d-d2d2239ea6c7","year":2006},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:40.989806Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:e07a0ae3d31cb57369f23af09b4d0138f1a02d0701f81acf5b307bdff3a48211","observation_id":"f8220771-07b0-4f9a-ab75-3b148884050a","resolution":{"observed_at":"2026-08-14T12:53:43.330982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:43.257903Z","title":"Compressing convolutional neural networks in the frequency domain","venue":null,"work_id":"deb98d95-31bb-4d8a-9e15-0299402ae915","year":2016},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:40.995466Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:87e1076a38afa60406108dcdbbd572058ae8feead5b848b81d7f0c31d4deb003","observation_id":"3b040894-cf4a-4c0d-a8e3-a3799a95d248","resolution":{"observed_at":"2026-08-14T12:53:43.285776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:41.004020Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.004020Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:f80f886cc6fbe33bb63231c453fc0eb55cf9dcb977b90a25c593a2a4a1ab3903","observation_id":"5bac5870-0a83-4938-a102-20ca171717ef","resolution":{"observed_at":"2026-08-14T12:53:41.004020Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.02297","last_updated":"2017-07-02T17:49:27Z","snapshot_observed_at":"2026-08-14T21:26:39.814915Z","submitted_at":"2016-12-07T15:37:57Z","title":"Spatially Adaptive Computation Time for Residual Networks","version":2},"cited_work":{"arxiv_id":"1612.02297","doi":null,"metadata_source":"pith","pith_arxiv_id":"1612.02297","snapshot_observed_at":"2026-08-14T12:53:41.897577Z","title":"Spatially Adaptive Computation Time for Residual Networks","venue":"cs.CV","work_id":"999c80ad-3e26-49f7-8289-f84b0437af1f","year":2016},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.010611Z"},"links":{"cited_paper":"/paper/1612.02297","citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:5233f5a18272dcad09ad43111bb555caa2f507afb95847cf8b75b1ec6a6cfd2c","observation_id":"a5555e5a-b270-4f8d-909a-a01e21274f2a","resolution":{"observed_at":"2026-08-14T12:53:41.943354Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1603.08983","last_updated":"2017-02-21T16:21:21Z","snapshot_observed_at":"2026-08-19T09:41:48.169666Z","submitted_at":"2016-03-29T22:09:00Z","title":"Adaptive Computation Time for Recurrent Neural Networks","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.08983","snapshot_observed_at":"2026-08-14T12:53:41.054373Z","title":"Adaptive computation time for recurrent neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.054373Z"},"links":{"cited_paper":"/paper/1603.08983","citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:55f546bb2c126db7ad1970dd892dcb3b99bf8e398d503b3b9f502c35296d481b","observation_id":"9f90ead9-828d-4abb-96c4-bfcc7d988073","resolution":{"observed_at":"2026-08-14T12:53:41.054373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:43.172908Z","title":"Deep com- pression: Compressing deep neural networks with pruning, trained quantization and huffman coding","venue":null,"work_id":"70c72470-161b-47cd-bb8d-9b190ce8bbc4","year":2016},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.091967Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:b0ee19d72fe4cc3d9d541ae114560701c887cfe6c99a0c5115eef655eecad466","observation_id":"03fe346f-f790-48d0-afab-b88aaaaf63de","resolution":{"observed_at":"2026-08-14T12:53:43.204936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:41.108528Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.108528Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:ade41c347b071b8c55f92d67e410beebf339357dbf6d858af5c805cc17e69f8a","observation_id":"353d0884-d216-4d25-9338-e95686283062","resolution":{"observed_at":"2026-08-14T12:53:41.108528Z","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":"2026-08-14T12:53:41.114480Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.114480Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:f96b1fa1ee128f98ed3dc1711f21729f0864068416bcc456a959919dc4602b09","observation_id":"903599e9-4fe9-4216-bd1f-3dad6b36e4e8","resolution":{"observed_at":"2026-08-14T12:53:41.114480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:43.103278Z","title":"Amc: Automl for model compression and accel- eration on mobile devices","venue":null,"work_id":"dcd128bc-34e5-4e8c-8830-821b64805eed","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.120743Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:d44e22919ebb2044a2d5f68d9d6814b941eb701e12249862041a9a291063b997","observation_id":"3c081ad8-234c-43be-a81a-b2f817ef2aab","resolution":{"observed_at":"2026-08-14T12:53:43.112808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:43.078856Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":"0444ea92-90d6-43a3-a796-1d3e2cff5861","year":2014},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.128394Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:afcb9a2b5f03d779ec5543db438a6c400e6e40e6363f28e5b0a61f8a852501ee","observation_id":"c009b934-9af4-4a99-9034-10078b91b8ba","resolution":{"observed_at":"2026-08-14T12:53:43.086200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-08-20T09:32:02.065929Z","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":"2026-08-14T12:53:41.137650Z","title":"Mobilenets: Efficient convolu- tional neural networks for mobile vision applications","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.137650Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:f54cc3caf2f39a10030be2ebb41a82f9a98709ea839eb00f4cd658d03f89afb7","observation_id":"b489a409-044e-449e-8dcd-2a4c5f12da17","resolution":{"observed_at":"2026-08-14T12:53:41.137650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:43.035974Z","title":"Multi-scale dense networks for resource efficient image classification","venue":null,"work_id":"73994c76-19d5-4763-baac-1be031098f47","year":null},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.143804Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:d07f6c406479d79f66295c4c3ff15c24b95e45055557d7b45dc8c831e05324d1","observation_id":"08164da0-81c5-4e7d-a119-04d72faed422","resolution":{"observed_at":"2026-08-14T12:53:43.059765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.931573Z","title":"Condensenet: An efficient densenet using learned group convolutions","venue":null,"work_id":"9b46512e-446c-4a0c-9432-9b2e816760a4","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.152462Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:3b75456f9a3bd0ada975b52057f75629412b93de23d25a458e4cc297f71f2e9a","observation_id":"38a7dd92-c9e3-41d8-ba4e-da812d02a490","resolution":{"observed_at":"2026-08-14T12:53:42.983021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.908021Z","title":"Densely connected convolutional networks","venue":null,"work_id":"ff953063-ff19-4853-94ae-11316587193f","year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.223301Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:fbbd5733982f329be02505ab2f837c6049e74826fcde9bee6da4ebb94ed4d853","observation_id":"da864756-af89-4c69-a2c7-8916161bb287","resolution":{"observed_at":"2026-08-14T12:53:42.914323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.876807Z","title":"Binarized neural networks","venue":null,"work_id":"b3192723-902b-40bb-9fe1-3d9dd56f61b0","year":2016},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.247977Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:497667cad40882f8c4d618f71460b5cc53aecd3039199f711dbff90765071e39","observation_id":"0fce080a-f4cf-4084-835e-fc42150635a1","resolution":{"observed_at":"2026-08-14T12:53:42.885610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.811013Z","title":"Incorporating side information by adaptive convolution","venue":null,"work_id":"861f9124-2186-4b6e-a9ec-8217b6b41c78","year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.254462Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:99104dc47705d09f8df7cc13900c14f2796de0a065d87878d85d6c529b4e1512","observation_id":"6c111a02-f664-43dc-81c0-c26e314cd23f","resolution":{"observed_at":"2026-08-14T12:53:42.837038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.01556","last_updated":"2018-12-18T22:46:32Z","snapshot_observed_at":"2026-08-14T19:19:00.954742Z","submitted_at":"2018-05-03T22:05:57Z","title":"Pixel-wise Attentional Gating for Parsimonious Pixel Labeling","version":2},"cited_work":{"arxiv_id":"1805.01556","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.01556","snapshot_observed_at":"2026-08-14T12:53:41.802338Z","title":"Pixel-wise Attentional Gating for Parsimonious Pixel Labeling","venue":"cs.CV","work_id":"621ece70-b6a5-4de3-87f2-3bd5b44d9a23","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.260696Z"},"links":{"cited_paper":"/paper/1805.01556","citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:08f0729906684392c57bd7505d91001b92a2d9ab30009dddd01fba6263fed940","observation_id":"0ae44b59-a9b6-4b7f-9b5a-ffd7710c5852","resolution":{"observed_at":"2026-08-14T12:53:41.811260Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.748491Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"e25767fb-643b-4200-a66f-ad3363030995","year":2009},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.269246Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:9e8b033bb963ff05f4c882cfd41d67e370590ed843f78f1afcb64975c5f422a2","observation_id":"fe08199f-1c47-4258-9fb2-a898e16da2af","resolution":{"observed_at":"2026-08-14T12:53:42.773485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:41.319327Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.319327Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:94f717ce8244d8a219f055222724463604b952dbfefc7716e6d086787f4e9eda","observation_id":"1c814ee9-61f1-4480-bf41-f4d5b8e46367","resolution":{"observed_at":"2026-08-14T12:53:41.319327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.04606","last_updated":"2018-09-08T22:27:55Z","snapshot_observed_at":"2026-08-14T19:04:40.754703Z","submitted_at":"2018-06-12T15:28:53Z","title":"Knowledge Distillation by On-the-Fly Native Ensemble","version":2},"cited_work":{"arxiv_id":"1806.04606","doi":null,"metadata_source":"pith","pith_arxiv_id":"1806.04606","snapshot_observed_at":"2026-08-14T12:53:41.719403Z","title":"Knowledge Distillation by On-the-Fly Native Ensemble","venue":"cs.CV","work_id":"de265c34-806c-454d-b5d3-dc3493ebe4e9","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.350996Z"},"links":{"cited_paper":"/paper/1806.04606","citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:5ef6739187f3ab8289bf6332e215577bcdef4925471979dffec6d6128176d670","observation_id":"84bf2383-f8be-484c-91f5-9751de1dd2d4","resolution":{"observed_at":"2026-08-14T12:53:41.777049Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.669418Z","title":"Pruning filters for efficient convnets","venue":null,"work_id":"f0b0ec51-bc4c-4b22-991f-a09aa4e378b2","year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.363828Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:a6bd3256441597f011469b0239c170c1ed2f2c45fa0b17102e20ab385a0abe8f","observation_id":"342717c4-9d10-408d-9158-c8c9afadf2cd","resolution":{"observed_at":"2026-08-14T12:53:42.680622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.636857Z","title":"Dynamic computational time for visual attention","venue":null,"work_id":"c05ab27f-a749-4eea-8baa-bcfa27c0b7ad","year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.370911Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:bb4cb2e08098e26f59a7ee771ddf925f0f7048d8acba1ce8575376904d485e4a","observation_id":"9ad95a24-718a-48ff-acf4-2dc33470eb8f","resolution":{"observed_at":"2026-08-14T12:53:42.645401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.610832Z","title":"Runtime neural pruning","venue":null,"work_id":"074a3499-c24a-4b88-a604-4da46073213b","year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.378437Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:9816b2a3f375ecc60f79ba99483c5b1d173bdc69b9cc5130f9bd82428775daef","observation_id":"04b33ced-ec33-4a47-b3ee-51802dc20396","resolution":{"observed_at":"2026-08-14T12:53:42.618726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.589345Z","title":"Learning efficient convolutional networks through network slimming","venue":null,"work_id":"51bc49c0-07fd-4112-b552-5d39537cf6e1","year":null},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.385484Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:92e4a491ca7c90d27c93f66d6e40e89c984eb7679f673a06204a74762ba4a4ce","observation_id":"7caacf33-2205-4dcc-9165-f321ec88a742","resolution":{"observed_at":"2026-08-14T12:53:42.594515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:41.393305Z","title":"Fully convolutional networks for semantic segmentation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.393305Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:d2e122be1f639ffd7fac7dbf44143c948f7300ffca2d6a45bb6aa22f7301c7e7","observation_id":"53f2dd69-7ee9-4091-ab12-f069032f9d9b","resolution":{"observed_at":"2026-08-14T12:53:41.393305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.555239Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architec- ture design","venue":null,"work_id":"afaf1dfb-1612-4550-94a8-903ebaa06f8e","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.399204Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:850867fd2e83e056add38c2a4ea39c9ffe0950ab68e1d4d033c7c3ef577c67c7","observation_id":"af60b9dd-3c99-4f25-9186-847aca52ae76","resolution":{"observed_at":"2026-08-14T12:53:42.561352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.535198Z","title":"Recurrent segmentation for variable com- putational budgets","venue":null,"work_id":"da8d95ef-0583-48d1-9c8c-2ff5256588a6","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.405308Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:83adbc205ce4320e7fc35ce18711c88c659803827e91cfa38c0941ff34213b11","observation_id":"19267e72-d2e4-44ca-960c-0a5871b06132","resolution":{"observed_at":"2026-08-14T12:53:42.542294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.515727Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"4c84fb51-c7e7-4edb-940f-eb55596cbf96","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.415681Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:6159743103b81cd26c03f85d526f6f8828a121f2df4ff7e4eb92bc9a93afa560","observation_id":"67de7665-4520-4c2c-bd75-df248b874159","resolution":{"observed_at":"2026-08-14T12:53:42.522236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.457369Z","title":"Collaborative learning for deep neural networks","venue":null,"work_id":"eba63a03-97fb-42a7-9793-8f85dcb2faba","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.452475Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:3ee2d52dcfbd0676ab3a780c6dc8312796cfdf6c1798089a10395d1a23f99e92","observation_id":"73f85639-6560-4adf-833e-490506752ad2","resolution":{"observed_at":"2026-08-14T12:53:42.491964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.404823Z","title":"Going deeper with convolutions","venue":null,"work_id":"4c73651f-8263-466c-93cc-7fa873e42053","year":2015},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.505310Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:fa6e88b5a57c29662b82101dedc8d9037264115f398ad92a889563a49536d1d0","observation_id":"145272ec-f072-4383-a8f8-1ce81b682f77","resolution":{"observed_at":"2026-08-14T12:53:42.431047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.342954Z","title":"Branchynet: Fast inference via early exiting from deep neu- ral networks","venue":null,"work_id":"e613ff89-0e30-4441-b18d-1a8d21ec18b0","year":2016},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.535494Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:6ae51fd36194554de1a32e40a9b0e630f7d8d5efae8dcb7325cb56b0d7f86781","observation_id":"4d83a3ab-9844-4e06-8f8e-9f2b2d663481","resolution":{"observed_at":"2026-08-14T12:53:42.370506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.290286Z","title":"Hydranets: Specialized dynamic archi- tectures for efficient inference","venue":null,"work_id":"0c5c1c5c-866f-4576-a337-03f3a0816d89","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.542657Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:fec791892a7fb8424dd545753f09244f9150051850bf75d2a2a60a0bfb543c60","observation_id":"e6499a1e-1315-4dca-b188-cb8b56b37b8d","resolution":{"observed_at":"2026-08-14T12:53:42.297858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.268558Z","title":"Convolutional networks with adaptive inference graphs","venue":null,"work_id":"4bcef2ba-9791-4331-aaaa-02f57d73a3b9","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.548583Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:c9291fcf8bf675853dfa8c0eb6d50673538f5f4130ffbcde4a6dec8b9c0e237a","observation_id":"70c9c47a-3361-4a55-88c7-0c8ddcafa915","resolution":{"observed_at":"2026-08-14T12:53:42.274437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.242820Z","title":"Skipnet: Learning dynamic routing in convolutional networks","venue":null,"work_id":"3b68489a-4ac5-46c9-ad6e-02a49651e795","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.561605Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:558b4ac916fc97ec5c02b208e926cc1d5bce1799624979f81136ad4cdd4c007a","observation_id":"6eed9890-6961-4429-8f0d-861374c7774b","resolution":{"observed_at":"2026-08-14T12:53:42.249702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.108034Z","title":"Blockdrop: Dynamic inference paths in residual networks","venue":null,"work_id":"8b72c7ff-1d42-4ccc-9eca-d3bb7c8dd3dd","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.584630Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:4ba50070f5462fcc1153b3e0e3cade3b30dcfa5e0e1a8d20c5cfd5161ccd3cde","observation_id":"3d0877cf-1bb9-4e68-82ec-f401e8c250b9","resolution":{"observed_at":"2026-08-14T12:53:42.172484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.052028Z","title":"Depth-adaptive com- putational policies for efficient visual tracking","venue":null,"work_id":"fa47e2ab-b3bf-4977-880a-e691bbcbbec7","year":2017},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.628483Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:a1402c080574bc9fb7a23691027cd5ea5a848dc2fc4fab316aa195ef50d99a5c","observation_id":"f88a89a8-f157-4021-a00d-ee48fd5650dd","resolution":{"observed_at":"2026-08-14T12:53:42.064396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:42.022800Z","title":"Shufflenet: An extremely efficient convolutional neural net- work for mobile devices","venue":null,"work_id":"3e73e767-d04f-4413-b176-bae243230fbf","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.637571Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:ee4c2855640126ede6f5f66a9c6fb4a1a4d54b5e03ae024e782f3566b42fa62f","observation_id":"0b441bd1-7fe2-4d7a-b1b2-ca242b9e63a8","resolution":{"observed_at":"2026-08-14T12:53:42.031007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:53:41.994757Z","title":"Learning transferable architectures for scalable image recognition","venue":null,"work_id":"f72ff75f-d2ab-4b74-8e54-187ea1f5156e","year":2018},"citing_paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T12:53:41.647801Z"},"links":{"citing_paper":"/paper/1908.06294"},"observation_digest":"sha256:e8e2e34b8e1ead2ed839c0f644823850ef52528e590c1ca260dafd2bb50adb8d","observation_id":"826f3fae-d06a-4573-a22e-2254b0bf6094","resolution":{"observed_at":"2026-08-14T12:53:42.000988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.06294","last_updated":"2019-08-17T10:53:53Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T12:30:47.329050Z","submitted_at":"2019-08-17T10:53:53Z","title":"Improved Techniques for Training Adaptive Deep Networks"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":3,"verified_fuzzy":30},"total_outbound_references":40},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:1908.06294."}