{"as_of":"2026-08-16T07:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7f3fd2dfbfe0027eab92bb4f80f40fd5522f0648ef39122e6ce35eb7502d964f","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:01:23.120783Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.03930/citation-record","integrity":"/paper/1908.03930/integrity","json":"/paper/1908.03930/citation-record.json","paper":"/paper/1908.03930"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:24.539705Z","title":"Tensorflow: A system for large-scale machine learning","venue":null,"work_id":"995345b2-7b48-4d0a-a0b0-aa4c461ae075","year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.815209Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:bff6ee80b303a7b23b8bf67a14c94564be0f2397f6588fcadf144bb4b94ce953","observation_id":"cd759f33-eb18-4491-a97c-f9cd6b39c2e1","resolution":{"observed_at":"2026-08-14T14:01:24.548380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.02830","last_updated":"2016-03-17T14:54:25Z","snapshot_observed_at":"2026-08-15T07:00:41.403404Z","submitted_at":"2016-02-09T01:01:59Z","title":"Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.02830","snapshot_observed_at":"2026-08-14T14:01:22.822832Z","title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.822832Z"},"links":{"cited_paper":"/paper/1602.02830","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:152ea842a810bbb15e735b6fa04e009fd92cfffbf1aec748d7e706effc658ad4","observation_id":"f04e3bde-2da1-418a-896d-a9b414e8b735","resolution":{"observed_at":"2026-08-14T14:01:22.822832Z","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":"2026-08-14T14:01:22.831820Z","title":"Imagenet: A large-scale hierarchical im- age database","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.831820Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:0d0c348d38e3e1fb648a85da29ff97900e98c73a746c365b2acd964dd7d63f12","observation_id":"e1045917-f894-49e5-9a59-dfa944895ca5","resolution":{"observed_at":"2026-08-14T14:01:22.831820Z","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":"2026-08-14T14:01:24.447778Z","title":"Exploiting linear structure within con- volutional networks for efficient evaluation","venue":null,"work_id":"02c65125-d314-41f9-bfe3-7f44341118a1","year":null},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.857077Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:2025f3dcc8d79c08ba0c2582cac4fb27a29072ae582df5e2b75792982252ffed","observation_id":"ec38426b-cc8b-4444-8794-66e1289d7c9b","resolution":{"observed_at":"2026-08-14T14:01:24.457876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:24.398331Z","title":"Centripetal sgd for pruning very deep convolutional networks with complicated structure","venue":null,"work_id":"71c8bdfe-a825-40fc-8b2c-ba2fc6215730","year":2019},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.863686Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:0bf38c10a4dcd62244eee165dcca8dec4fa2c56cf31de01a6f458d3e7d5aef07","observation_id":"495df0de-e0f9-41c6-8e36-c1a9dbce1755","resolution":{"observed_at":"2026-08-14T14:01:24.412412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:24.353377Z","title":"Approximated oracle filter pruning for destructive cnn width optimization","venue":null,"work_id":"e130fa6b-3fab-41c5-99f2-018d8bb276ec","year":2019},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.874250Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:8bdf77d94c7722a620117de24b87b1d96505de6d6f029f1227e632c90feeca8f","observation_id":"f082ea4c-a092-4259-9985-6497bb911512","resolution":{"observed_at":"2026-08-14T14:01:24.363713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:24.316013Z","title":"Auto-balanced filter pruning for efficient convolu- tional neural networks","venue":null,"work_id":"7313cfa5-8987-469d-90d7-d285bae05eae","year":2018},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.882227Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:2ad1240cbd8a558eaef3683e6729a81b3822b5a0f5e43264cfa64f955e34399d","observation_id":"b4715e49-a1d0-475f-a05c-70ab6bd91707","resolution":{"observed_at":"2026-08-14T14:01:24.331161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:24.235599Z","title":"Tensorflow-alexnet","venue":null,"work_id":"bb5491e5-7d19-4eb6-92da-d275d163ebe4","year":2017},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.889956Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:b35dd016a326b81a82e0b433309582aaeeca2fd81c8ec5123d2c18e07d310b1c","observation_id":"c51fb5b8-9ab3-4b96-adee-8078a35cbb44","resolution":{"observed_at":"2026-08-14T14:01:24.247317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:24.197376Z","title":"Dynamic net- work surgery for efficient dnns","venue":null,"work_id":"99268f57-61ad-43ee-9b4f-356fc04f6f39","year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.896935Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:4ba646ac0d103f411f2277afae8430fc4095e62c8a902ba606d144a95c2f8f49","observation_id":"6dd6d7d2-68f3-4caa-a3b9-e629e227d1a4","resolution":{"observed_at":"2026-08-14T14:01:24.206424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:24.166900Z","title":"Deep learning with limited numerical precision","venue":null,"work_id":"91c23232-f6c9-4f2c-a022-0f0be162db47","year":2015},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.902958Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:086ed64fee715aed0ae187d6d3cfb7565aba3b47686d529de6cac1004e86c555","observation_id":"7bf52b62-66ad-413b-9e78-8f4c4de720dc","resolution":{"observed_at":"2026-08-14T14:01:24.174926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-14T14:01:22.908101Z","title":"Deep com- pression: Compressing deep neural networks with pruning, trained quantization and huffman coding","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.908101Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:90e96b9b737e59e87b9b0c1a76028733df7b65eb486d22f1cfe64e42b0ce75fc","observation_id":"36b0b197-0880-4638-b34d-6e9aea7059f6","resolution":{"observed_at":"2026-08-14T14:01:22.908101Z","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":"2026-08-14T14:01:24.126913Z","title":"Learning both weights and connections for efficient neural network","venue":null,"work_id":"5ae1031b-c3d7-49d6-b675-5ca9aa115c4f","year":2015},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.917494Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:075f7b3fe9233f77d441f54808519546ccfb640243d19ceeb87807484ed5a82c","observation_id":"e61d30d1-c03e-4fe2-a1ba-ebb8f034fd91","resolution":{"observed_at":"2026-08-14T14:01:24.135267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:22.925539Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.925539Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:27ed0216d061b68574c3dee038bcbaa7ca24de9f17c80b741a8ee59296ab193b","observation_id":"65bda889-9683-4b89-a7d6-4fa7c747f81e","resolution":{"observed_at":"2026-08-14T14:01:22.925539Z","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":"2026-08-14T14:01:24.052811Z","title":"Squeeze-and-excitation net- works","venue":null,"work_id":"991914a9-f9e0-454c-9ae5-95cd7446efb1","year":2018},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.931888Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:bb44b864354f55803def44f3cfb345a65193e87eb418bf9aa7a8c878e46f6e78","observation_id":"7ef02f97-0145-4ee9-bcfa-da52311d65a5","resolution":{"observed_at":"2026-08-14T14:01:24.062599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:24.016765Z","title":"Densely connected convolutional networks","venue":null,"work_id":"b0593a04-c572-48fe-a5e7-bad16f1b4199","year":2017},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.938145Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:e5571f4f9ca6d9e7243b2358205dfe7a851d7b46120d00ad97d6a4912145fe61","observation_id":"3b454507-ae8b-45b7-ad47-2a28ebd5f5e2","resolution":{"observed_at":"2026-08-14T14:01:24.028246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:23.986583Z","title":"Batch normalization: Accelerating deep network training by reducing internal co- variate shift","venue":null,"work_id":"5434cb77-f60d-4874-96c4-303608d9a7fe","year":2015},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.945475Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:3cf6da50276a9481e9878730e4a958989b49f707c3b5e0003bd1c8b8e0980105","observation_id":"5a60ba0b-8d1d-4a56-a75d-c426cd398d0b","resolution":{"observed_at":"2026-08-14T14:01:23.993072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1405.3866","last_updated":"2014-05-15T14:41:06Z","snapshot_observed_at":"2026-08-14T23:33:55.484836Z","submitted_at":"2014-05-15T14:41:06Z","title":"Speeding up Convolutional Neural Networks with Low Rank Expansions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1405.3866","snapshot_observed_at":"2026-08-14T14:01:22.953295Z","title":"Speeding up convolutional neural networks with low rank expansions","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.953295Z"},"links":{"cited_paper":"/paper/1405.3866","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:a522b00716c68a767393ef23c51f5445dcbd7c1b12c1fb7224d0a34531a759b9","observation_id":"2c189d54-661c-4469-a989-f4428944f245","resolution":{"observed_at":"2026-08-14T14:01:22.953295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.5474","last_updated":"2015-11-20T05:50:23Z","snapshot_observed_at":"2026-08-14T23:07:09.679037Z","submitted_at":"2014-12-17T16:48:54Z","title":"Flattened Convolutional Neural Networks for Feedforward Acceleration","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.5474","snapshot_observed_at":"2026-08-14T14:01:22.960666Z","title":"Flattened convolutional neural networks for feedforward ac- celeration","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.960666Z"},"links":{"cited_paper":"/paper/1412.5474","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:de80b11a6f5de2af30b71defc778455ff2e26e2d1eeb1049156ce1f3c4d03534","observation_id":"16ab1b47-a6d1-4288-8b74-cbcacc9592cd","resolution":{"observed_at":"2026-08-14T14:01:22.960666Z","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":"2026-08-14T14:01:23.941528Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"db368d17-0d7b-4c08-9022-6ee5a1b77494","year":2009},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.974664Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:bf45d134478fe65bb567298fc472f2bc0578dde5d04663df62848f4948c9f9e5","observation_id":"89f260df-8910-450d-9fd8-b9a234b5bd2a","resolution":{"observed_at":"2026-08-14T14:01:23.951999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:23.911931Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":"3882873b-e4ba-402f-8e5b-45752f3f2932","year":2012},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.984782Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:c76216cc0de6cc2b400f42976760f12ec1554751e76c83798031841268ee4371","observation_id":"f198192a-40c8-4aed-ae3f-e5a2b11ebfff","resolution":{"observed_at":"2026-08-14T14:01:23.918909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.08710","last_updated":"2017-03-10T17:57:56Z","snapshot_observed_at":"2026-08-14T21:42:03.106939Z","submitted_at":"2016-08-31T02:29:59Z","title":"Pruning Filters for Efficient ConvNets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.08710","snapshot_observed_at":"2026-08-14T14:01:22.994872Z","title":"Pruning filters for efficient convnets","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.994872Z"},"links":{"cited_paper":"/paper/1608.08710","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:7411c3aa9bced7109656288e222b01d90b2c8042bea19bac2b2855c9f3fcf88e","observation_id":"df94be3c-8d44-445c-98f2-8b7499976a89","resolution":{"observed_at":"2026-08-14T14:01:22.994872Z","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":"2026-08-14T14:01:23.881731Z","title":"Learning efficient convolutional networks through network slimming","venue":null,"work_id":"d2f71e03-677a-4e3e-a3cc-191ff884d744","year":2017},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.004533Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:29d75301eb4d34ba45c693b0117695cf816b99952dfb85d452fc659af0141f58","observation_id":"500d01f1-ed7f-4b04-8a08-9f6b57374458","resolution":{"observed_at":"2026-08-14T14:01:23.894921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.06323","last_updated":"2019-12-28T06:11:57Z","snapshot_observed_at":"2026-08-14T18:27:20.680358Z","submitted_at":"2018-09-17T16:52:46Z","title":"Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.06323","snapshot_observed_at":"2026-08-14T14:01:23.012055Z","title":"Efficient dense modules of asymmetric con- volution for real-time semantic segmentation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.012055Z"},"links":{"cited_paper":"/paper/1809.06323","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:92857a16737c6f05e994984ce7458e6d553504135d2edf58183127c3a2ab8f70","observation_id":"b1abd261-eb76-4d40-89dd-43a118466c31","resolution":{"observed_at":"2026-08-14T14:01:23.012055Z","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":"2026-08-14T14:01:23.842126Z","title":"Thinet: A filter level pruning method for deep neural network compression","venue":null,"work_id":"97a3c1d3-fdd4-4fd9-a36e-7a3e9eba5b36","year":2017},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.022300Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:0f4553c49cbd3e0fbc35fdb75de4a150982d73ba3ace26c3a5e12a3727c547fb","observation_id":"340266b1-92ea-4d77-82f1-b4361e092fc5","resolution":{"observed_at":"2026-08-14T14:01:23.850671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.02147","last_updated":"2016-06-07T14:09:27Z","snapshot_observed_at":"2026-08-14T21:53:50.690297Z","submitted_at":"2016-06-07T14:09:27Z","title":"ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.02147","snapshot_observed_at":"2026-08-14T14:01:23.029781Z","title":"Enet: A deep neural network architec- ture for real-time semantic segmentation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.029781Z"},"links":{"cited_paper":"/paper/1606.02147","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:0234b94ae852da7991f7b190985390ea3f0d44d2d3426388749404d5904dbf70","observation_id":"1f012256-615b-4b3e-b364-95a3ba01f320","resolution":{"observed_at":"2026-08-14T14:01:23.029781Z","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":"2026-08-14T14:01:23.039078Z","title":"Automatic differentiation in pytorch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.039078Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:74835a5bc133de22dab213825ba4b7e4f0806862908bc26abff78f621b7bd181","observation_id":"325bcfb3-7a44-4a61-921e-cce742b9107c","resolution":{"observed_at":"2026-08-14T14:01:23.039078Z","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":"2026-08-14T14:01:23.778992Z","title":"Xnor-net: Imagenet classification using bi- nary convolutional neural networks","venue":null,"work_id":"9c6f84a5-2f7e-4b63-8c6e-b3b8a092aa14","year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.049832Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:e0198c0c98f1ee7aa8ba0021479d48678a9ca41957514aa610aedb12f6854c8d","observation_id":"c678a225-4861-4b85-b2fa-cc816e352358","resolution":{"observed_at":"2026-08-14T14:01:23.790934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T23:20:42.336514Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-14T14:01:23.057392Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.057392Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:fb41496f13c6d3f7510f7c139592d36d548145bfe3a62d91d5482ee8c42c6426","observation_id":"4959bf40-f931-400f-908d-bcc6e79106c0","resolution":{"observed_at":"2026-08-14T14:01:23.057392Z","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":"2026-08-14T14:01:23.747085Z","title":"Prac- tical bayesian optimization of machine learning algorithms","venue":null,"work_id":"2c5e3711-46b3-4b5f-87f5-764a4210a817","year":2012},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.065842Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:76e729eb60c1244440fe99e3ff26db5555a2a556a43a947558880d934b5b9af7","observation_id":"9eda9dd2-de69-4603-b12c-fb23744e9279","resolution":{"observed_at":"2026-08-14T14:01:23.755490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:23.718231Z","title":"Design of kernels in convolutional neural networks for image classifi- cation","venue":null,"work_id":"bd1c7189-8f73-430b-955a-966c46e58b72","year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.072216Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:034e73e5453c8b8c7acabfa4db61c4dfab3632621faa6ac8085e80fe5e1368b1","observation_id":"766bae7f-96f7-45c8-964d-e8207991d9d3","resolution":{"observed_at":"2026-08-14T14:01:23.725930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:23.668473Z","title":"Inception-v4, inception-resnet and the impact of residual connections on learning","venue":null,"work_id":"5164d7f5-2a85-4aea-8fd6-77ec6d9fe9e5","year":2017},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.079395Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:af43f27c3611da6e5a0a481ac63bc0692600f01b5c4a7172b2eb9402a0e3753f","observation_id":"db647bd8-1b42-4a14-9a69-3e9f18994aa8","resolution":{"observed_at":"2026-08-14T14:01:23.679661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:23.634770Z","title":"Going deeper with convolutions","venue":null,"work_id":"a71ebe71-c143-4d88-9cb7-887e4ceb7dd5","year":2015},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.088416Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:fadff1b524361b2b324cfb71fe2c639c3ac398f25ca13f8689ddafdb0621d6dc","observation_id":"5c3478f2-646c-4efd-b06b-b258b86a195a","resolution":{"observed_at":"2026-08-14T14:01:23.642740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:23.598354Z","title":"Rethinking the inception archi- tecture for computer vision","venue":null,"work_id":"1c036ab6-5d03-4804-af84-f6578d78a481","year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.095283Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:ff4728babd12824c52b9f674de44faddc832f838cd9166051585c1ce48d61d28","observation_id":"0d08653f-8a83-4d87-83d0-078e9dcce039","resolution":{"observed_at":"2026-08-14T14:01:23.611112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:01:23.566583Z","title":"Be- yond filters: Compact feature map for portable deep model","venue":null,"work_id":"98515953-0ea4-4b7a-a136-e9957ea28758","year":2017},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.102212Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:bec80252f41531032589cf87f1f8e934685b24a1aafdc0cea62187c1ed14ac41","observation_id":"439311ea-44bd-407d-a962-aa6eeadf5b35","resolution":{"observed_at":"2026-08-14T14:01:23.577120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07146","last_updated":"2017-06-14T06:06:48Z","snapshot_observed_at":"2026-08-13T10:21:59.687060Z","submitted_at":"2016-05-23T19:27:13Z","title":"Wide Residual Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07146","snapshot_observed_at":"2026-08-14T14:01:23.111401Z","title":"Wide residual net- works","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.111401Z"},"links":{"cited_paper":"/paper/1605.07146","citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:1131ce9cc1fbd429313540e244aa6e285eba80c968ef1527bbb4c49262c218b0","observation_id":"7a526f94-3829-4a6a-89cf-a2a7bccd552e","resolution":{"observed_at":"2026-08-14T14:01:23.111401Z","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":"2026-08-14T14:01:23.120783Z","title":"Learning transferable architectures for scalable image recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:23.120783Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:789c0db41f25de0f6e655c8d3661d661d9168f9dc88272569e7c923f99dcd353","observation_id":"c8fe6f3e-711b-4ff1-9279-e6dfe4376264","resolution":{"observed_at":"2026-08-14T14:01:23.120783Z","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":"2026-08-14T14:01:24.480961Z","title":"IEEE Conference on , pages 248–255","venue":null,"work_id":"be2496e6-7e08-4bdf-8b3a-13e13fd5d186","year":2009},"citing_paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","version":3},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-14T14:01:22.841349Z"},"links":{"citing_paper":"/paper/1908.03930"},"observation_digest":"sha256:180e664457a3a6a9580fa1d53077c1ca7761f7e1d1c6cf2b707c1159bc1b851b","observation_id":"a376a432-91fb-41a9-b821-609c07e9e816","resolution":{"observed_at":"2026-08-14T14:01:24.492149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.03930","last_updated":"2019-08-31T12:50:35Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T13:55:18.375694Z","submitted_at":"2019-08-11T16:06:58Z","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":24},"total_outbound_references":37},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:1908.03930."}