{"as_of":"2026-08-12T17:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3e3085f7f5670f1a3ae89d0be2dd2df901ccc5abb754f7397e90972192a25824","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T06:05:51.524610Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2412.16886/citation-record","integrity":"/paper/2412.16886/integrity","json":"/paper/2412.16886/citation-record.json","paper":"/paper/2412.16886"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1611.02167","last_updated":"2017-03-22T20:08:30Z","snapshot_observed_at":"2026-07-31T08:09:30.794006Z","submitted_at":"2016-11-07T16:49:43Z","title":"Designing Neural Network Architectures using Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.02167","snapshot_observed_at":"2026-08-11T06:05:51.242213Z","title":"Designingneuralnetworkarchitecturesusingreinforcementlearning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.242213Z"},"links":{"cited_paper":"/paper/1611.02167","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:9644bb32d89ac1abbf96b8de2950c2e33e7e497dda9d301c175fa7614d370cd4","observation_id":"86672c99-16e4-465d-b7fe-59f769b62ed9","resolution":{"observed_at":"2026-08-11T06:05:51.242213Z","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":"2026-08-11T06:05:53.339029Z","title":"Neural optimizer search with reinforcement learning, in: Precup, D., Teh, Y.W","venue":null,"work_id":"01c91984-64f8-41f1-aea0-ef2e531ee7f5","year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.248296Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:e002e51c364deced48d1334d48411e4573f455a3a37f0d00d3ff71543cec4adb","observation_id":"6efe2a87-326f-412d-a995-3a4818218f4b","resolution":{"observed_at":"2026-08-11T06:05:53.343861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.253954Z","title":"Modelcompression,in:Proceedingsofthe12thACMSIGKDDInternationalConference on Knowledge Discovery and Data Mining, Association for Computing Machinery, New York, NY, USA","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.253954Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:1c84ff4cac92468b029bc8960dd9d761b007d79dd53b9c26496950fae709c651","observation_id":"50c79908-3a4f-409a-b9ba-b5cf52dc16a3","resolution":{"observed_at":"2026-08-11T06:05:51.253954Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00332","last_updated":"2019-02-23T01:36:47Z","snapshot_observed_at":"2026-08-10T08:54:59.663457Z","submitted_at":"2018-12-02T05:29:53Z","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00332","snapshot_observed_at":"2026-08-11T06:05:51.259356Z","title":"Proxylessnas: Direct neural architecture search on target task and hardware","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.259356Z"},"links":{"cited_paper":"/paper/1812.00332","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:570890d63cd70cc716321171780d0e260954ec5e7ed8ddd0feacf973d4830d2f","observation_id":"dfa5b0a4-66fe-4b02-bb0a-474e95647e3c","resolution":{"observed_at":"2026-08-11T06:05:51.259356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.06088","last_updated":"2024-07-31T13:05:56Z","snapshot_observed_at":"2026-08-12T02:56:23.891576Z","submitted_at":"2022-11-11T09:44:23Z","title":"RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.06088","snapshot_observed_at":"2026-08-11T06:05:51.264586Z","title":"Repghost: A hardware-efficient ghost module via re-parameterization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.264586Z"},"links":{"cited_paper":"/paper/2211.06088","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:be168fc664e5a2dd8afadd50158387a6b0695d6c1b4da21febf56a65b0aba683","observation_id":"66e9f351-0e0d-4a1a-b0a8-048fdeef8e5b","resolution":{"observed_at":"2026-08-11T06:05:51.264586Z","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":"2026-08-11T06:05:51.275478Z","title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.275478Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:4f914e56d8ca9771928040eb5bbf569d70f3f1a1e1b1a368a3a4d699f9cf1088","observation_id":"97ca0009-2c41-42bb-9b0a-10f97eacb037","resolution":{"observed_at":"2026-08-11T06:05:51.275478Z","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":"2026-08-11T06:05:53.324214Z","title":"Darkrank: Accelerating deep metric learning via cross sample similarities transfer","venue":null,"work_id":"b91323d1-aa4e-49b9-a8c6-1c695e24eff8","year":null},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.280243Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:ec9e77c85b1411615a01a22f65df683ce3fb51bcfa12971bacf2667067fd6f2a","observation_id":"d03e9307-d33b-480d-82f8-0926170882da","resolution":{"observed_at":"2026-08-11T06:05:53.329184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.308785Z","title":"Sobolev training for neural networks, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, USA","venue":null,"work_id":"17c3037c-d24b-4741-8aa5-be87b1762d8c","year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.285034Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:8533522a3869ec1c9ea30da57bccabc188fb8f41c4b6f74be2d862d784630e96","observation_id":"97c48ffa-ccdb-435e-812c-a64c51042782","resolution":{"observed_at":"2026-08-11T06:05:53.313951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.294148Z","title":null,"venue":null,"work_id":"cd01f74f-b7c0-4ced-8563-d4a0a7ff0d4f","year":2014},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.289988Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:0608727ed3ddf5b26f506322cec9c72dbebfacf0ebd8fc0e6e584f67081c151e","observation_id":"a3da0983-6fb3-46a2-9e06-44d050a1b532","resolution":{"observed_at":"2026-08-11T06:05:53.298726Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.294983Z","title":"Repvgg:Makingvgg-styleconvnetsgreatagain,in:2021IEEE/CVFConference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.294983Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:70115419fc19a545100f1da41c21c26be2878df2a72566208547a31769271624","observation_id":"b0c62a52-cd22-4dfb-82fb-90e3a9b5cfaa","resolution":{"observed_at":"2026-08-11T06:05:51.294983Z","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":"2026-08-11T06:05:51.299321Z","title":"Ghostnet: More features from cheap operations, in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.299321Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:e86a5351a1b7d110b4567f50bff2d98c01c7d3550515a7901102919ef135445a","observation_id":"1e85db94-06dd-4bfa-8f9b-541cd97298b8","resolution":{"observed_at":"2026-08-11T06:05:51.299321Z","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":"2026-08-11T06:05:53.279000Z","title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding, in: International Conference on Learning Representations","venue":null,"work_id":"e83cb5c6-d3ed-434e-a510-f69afa01d9fc","year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.304088Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:b175074eb99d56389fd1922116fece10f0f061bb644d0d9b94b0705dead7b6ab","observation_id":"c8acbaf5-2f2d-4168-a76b-b650f0cb6902","resolution":{"observed_at":"2026-08-11T06:05:53.284211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.308726Z","title":"Deep residual learning for image recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.308726Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:5e235f3da45631efb1c2b8212826ed6df52e54d29577e0f8c0d739448c6fbea7","observation_id":"8dbf7d35-ade5-4570-9285-411b2585797e","resolution":{"observed_at":"2026-08-11T06:05:51.308726Z","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":"2026-08-11T06:05:51.313451Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.313451Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:afd52e7964f1d4104746d0c1c0c22ca6da45561b90e3bce02e5c0934b331257f","observation_id":"2d65270b-d4de-4d6e-8237-f5276e554084","resolution":{"observed_at":"2026-08-11T06:05:51.313451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-11T06:05:51.318063Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.318063Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:fd7b5f6596747a24454bb9a200fb329ceda4779dfb0c3d06bbd3b93d6a2153d1","observation_id":"d2f6098b-9a44-47e0-a2c6-cb046ca6cd1c","resolution":{"observed_at":"2026-08-11T06:05:51.318063Z","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":"2026-08-11T06:05:51.322800Z","title":"Searchingformobilenetv3,in:2019IEEE/CVFInternationalConferenceonComputerVision(ICCV),pp.1314–1324","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.322800Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:b6f6b0760b77d58bc053b1df742a012f63f20fc02202a8c035ea0bf1ef930a5b","observation_id":"bce2f9c7-e8b2-4197-acac-9a2e635ebeaf","resolution":{"observed_at":"2026-08-11T06:05:51.322800Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-11T06:05:51.327206Z","title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.327206Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:13927c4385dd96769321ae5d904294f77e795a2d72ad9f1131e233603b039389","observation_id":"eb11ef69-2689-42b8-b4f7-a4a579e441d7","resolution":{"observed_at":"2026-08-11T06:05:51.327206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.11394","last_updated":"2018-05-29T12:37:46Z","snapshot_observed_at":"2026-07-06T06:41:46.380029Z","submitted_at":"2018-05-29T12:37:46Z","title":"A novel channel pruning method for deep neural network compression","version":1},"cited_work":{"arxiv_id":"1805.11394","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.11394","snapshot_observed_at":"2026-08-11T06:05:52.549637Z","title":"A novel channel pruning method for deep neural network compression","venue":"cs.CV","work_id":"7a76ca40-bc58-4592-b9ec-299b27fa96da","year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.332066Z"},"links":{"cited_paper":"/paper/1805.11394","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:475afc4736ab51d36605e50566327a259933404db31c5f285709f914119f7998","observation_id":"c1b50194-6d16-48ca-930f-c6102b8f3c84","resolution":{"observed_at":"2026-08-11T06:05:52.554752Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.337069Z","title":"Densely connected convolutional networks, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.337069Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:3c880bb72d73a95027b34f7ababd61bcacdfe922c63c8b77f1332bf6eeb08ca5","observation_id":"c56d6a00-316f-4cd4-9eb2-51d691c4a179","resolution":{"observed_at":"2026-08-11T06:05:51.337069Z","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":"2026-08-11T06:05:53.263999Z","title":"Binarized neural networks, in: Proceedings of the 30th International Conference on Neural Information Processing Systems, Curran Associates Inc., Red Hook, NY, USA","venue":null,"work_id":"fced8a94-a3ac-4866-8dbb-dc72f1c9af63","year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.341645Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:d8ccb06a0582aaf3960c255652b0e3c57ca5323c589ccf4ffc4e42ae84c1a287","observation_id":"a6dff74d-f862-47d6-b4b3-3c78a9749058","resolution":{"observed_at":"2026-08-11T06:05:53.268977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.07360","last_updated":"2016-11-04T21:26:08Z","snapshot_observed_at":"2026-07-06T04:47:10.710916Z","submitted_at":"2016-02-24T00:09:45Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.07360","snapshot_observed_at":"2026-08-11T06:05:51.346190Z","title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <1mb model size","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.346190Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:afca061ec5e375cfb2955383fe9f1cd8827d1e342401c83c36e07757d05dfaf9","observation_id":"91a6f801-850c-4f27-8a02-9f51eb56ec53","resolution":{"observed_at":"2026-08-11T06:05:51.346190Z","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":"2026-08-11T06:05:53.248731Z","title":"Compression of deep convolutional neural networks for fast and low power mobile applications, in: International Conference on Learning Representations","venue":null,"work_id":"4ec29554-15cb-4fcc-899c-45ffc091f06b","year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.350905Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:0519fe8ea1e1bf8dc3b441ba1a13ef4c1754ccfc94905c32e38315a64c0daff4","observation_id":"af6e31f9-adbb-4475-bbb9-e9d0d4e672ea","resolution":{"observed_at":"2026-08-11T06:05:53.253741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.234253Z","title":null,"venue":null,"work_id":"3a5175ed-6317-4e47-9052-d28618d2386c","year":2012},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.355355Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:3a119eea846666a7d9b4baf45b3040d49bfa495111214c8acff9da9764b642f6","observation_id":"6ebca077-5112-4dc1-ae32-73a96fe73140","resolution":{"observed_at":"2026-08-11T06:05:53.238777Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.219356Z","title":"Speeding-up convolutional neural networks using fine-tuned cp- decomposition, in: International Conference on Learning Representations","venue":null,"work_id":"6fd76e43-90c0-4305-b3ef-d19d5e4c3875","year":2015},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.359722Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:dedf4dabb0e41a6d071a184baed04ba99bd6e34fcf41f8b3e2e52673f64652dc","observation_id":"f3fb009a-fc94-44e7-a75e-15b7d5ecd708","resolution":{"observed_at":"2026-08-11T06:05:53.224337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.364149Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.364149Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:ef1669d50f38d9fdcf61f27e4ad004b984dca4d7a7831a949566be7775eb1c0d","observation_id":"82d4b488-cbd7-44b4-bd9f-32e8e2a025b9","resolution":{"observed_at":"2026-08-11T06:05:51.364149Z","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":"2026-08-11T06:05:53.204870Z","title":"Optimal brain damage, in: Touretzky, D","venue":null,"work_id":"ef1ab9ad-acd7-422f-a064-23cf6acb7c91","year":1989},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.369237Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:cf10ade76876598d1e9a714a07fa1dddf3d95ede8e05617b33eed42403214112","observation_id":"aa86dc12-bc26-4b53-87c5-d8c3af732b31","resolution":{"observed_at":"2026-08-11T06:05:53.209628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.189876Z","title":"Memory-efficient patch-based inference for tiny deep learning, in: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W","venue":null,"work_id":"050c6352-a26f-4f8b-96a8-7b8540da5ae6","year":2021},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.374501Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:457719240023d524d86138477ed0c3d9a92a66e187d1c462d6e4fa3710bb53dd","observation_id":"c62dbfd2-9fca-4123-a090-8c05ba5498f0","resolution":{"observed_at":"2026-08-11T06:05:53.194570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.176333Z","title":null,"venue":null,"work_id":"7cbe8b2f-fd12-48d7-b3fc-e693ffdb4b71","year":2020},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.379124Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:10ffeb53e0703ff6f8fdfc2a59cfd5f2f83bc649c4e2df46a1bac832cb362b89","observation_id":"b9bef59e-29ef-445c-8920-6e05108bec51","resolution":{"observed_at":"2026-08-11T06:05:53.180808Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.383727Z","title":"Ternary weight networks, in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.383727Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:dca23cea824c0232fb8ffc66d83974d0e2c56dca1dd22f09f57cad39f59c50ab","observation_id":"c4fc8df3-ad06-4b04-bcbf-ba7928d801fb","resolution":{"observed_at":"2026-08-11T06:05:51.383727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00436","last_updated":"2018-02-22T22:31:30Z","snapshot_observed_at":"2026-08-10T11:54:25.127506Z","submitted_at":"2017-11-01T16:46:27Z","title":"Hierarchical Representations for Efficient Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.00436","snapshot_observed_at":"2026-08-11T06:05:51.388587Z","title":"Hierarchicalrepresentationsforefficientarchitecturesearch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.388587Z"},"links":{"cited_paper":"/paper/1711.00436","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:8c58f3b9ec225345bf83776e62ca45403a8b7f36e699f486ba636c67483c3ffe","observation_id":"af6f9fb7-e607-4e63-a47e-332702a3833f","resolution":{"observed_at":"2026-08-11T06:05:51.388587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.09055","last_updated":"2019-04-23T06:29:32Z","snapshot_observed_at":"2026-08-09T13:23:20.015254Z","submitted_at":"2018-06-24T00:06:13Z","title":"DARTS: Differentiable Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.09055","snapshot_observed_at":"2026-08-11T06:05:51.393596Z","title":"DARTS:differentiablearchitecturesearch","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.393596Z"},"links":{"cited_paper":"/paper/1806.09055","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:9742f2f44df32772323d549c63071ae4e4a0269fc31d2076f3e06bfd04140d85","observation_id":"1d2201f7-c9c4-4ff3-90e9-beebce82f78a","resolution":{"observed_at":"2026-08-11T06:05:51.393596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.05791","last_updated":"2017-06-19T05:29:29Z","snapshot_observed_at":"2026-07-06T05:47:20.889388Z","submitted_at":"2017-06-19T05:29:29Z","title":"An Entropy-based Pruning Method for CNN Compression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05791","snapshot_observed_at":"2026-08-11T06:05:51.398814Z","title":"An entropy-based pruning method for cnn compression","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.398814Z"},"links":{"cited_paper":"/paper/1706.05791","citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:b05e238f0242be2a87f4de2f616877a531323ffe7bd474a4d88a69e998fea344","observation_id":"96711e17-98de-415a-90eb-596308e2054a","resolution":{"observed_at":"2026-08-11T06:05:51.398814Z","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":"2026-08-11T06:05:53.162509Z","title":"Extremenetworkcompressionviafiltergroupapproximation,in:Ferrari,V.,Hebert, M., Sminchisescu, C., Weiss, Y","venue":null,"work_id":"6e4e991a-fd99-4325-8094-a49796aa9b1d","year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.403619Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:c2e8c6235ba03c103cac2337ef5d843d857481bcf0c28d7992a5c05e6fd98a1b","observation_id":"445e8af0-f325-4b26-8f11-313aef7af1b7","resolution":{"observed_at":"2026-08-11T06:05:53.167384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/cvpr.2017.189","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T06:05:51.621326Z","title":"Largekernelmatters—improvesemanticsegmentationbyglobalconvolutionalnetwork, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":"131387f3-056a-4930-9708-d00e0310cae1","year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.408619Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:48ee794d1c103a0a9be73d93f0751fd762eebd8cb8bf3cb80d32227b08bf4008","observation_id":"c237ccfc-6785-4c20-a9f8-80c181df82d7","resolution":{"observed_at":"2026-08-11T06:05:51.626592Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.147971Z","title":"Xnor-net: Imagenet classification using binary convolutional neural networks, in: Leibe, B., Matas, J., Sebe, N., Welling, M","venue":null,"work_id":"99d3ba58-e628-4d92-86ea-19550dfcd63c","year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.413420Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:5ef77a2b88fabd29c782d8d72de05030f64d04451486b6b283ed250cdb2a16c5","observation_id":"d1dc08fa-4f73-476d-8084-6f696c6f2eef","resolution":{"observed_at":"2026-08-11T06:05:53.152639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.133894Z","title":"AutoML-zero: Evolving machine learning algorithms from scratch, in: III, H.D., Singh, A","venue":null,"work_id":"6e9d47b4-11d5-4c4f-870b-ba28a056fe4d","year":2020},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.418060Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:473474af9d4137b3767f94434bb0eb072f786a273535b1515e1346526d3e933f","observation_id":"c8fa9304-e78d-416a-a858-9485889f40b9","resolution":{"observed_at":"2026-08-11T06:05:53.138612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.422568Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks, in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.422568Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:fdaa8fb8d81e776ae68dfaa929d036ebef5e08358435f6dea151a35f55517f8e","observation_id":"c236b6eb-7da4-42e1-8d99-7cfe212d4a3f","resolution":{"observed_at":"2026-08-11T06:05:51.422568Z","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":"2026-08-11T06:05:51.427106Z","title":"Efficient acceleration of deep learning inference on resource-constrained edge devices: A review","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.427106Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:6862577fdcb11ec4868d444650aae07fb8e5ecb4213770e1e013dddaeadc4777","observation_id":"b070fee7-a958-457c-9984-4e749571d3df","resolution":{"observed_at":"2026-08-11T06:05:51.427106Z","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":"2026-08-11T06:05:53.119357Z","title":"Very deep convolutional networks for large-scale image recognition, in: International Conference on Learning Representations, p","venue":null,"work_id":"e849957c-ff61-4de6-b216-5ef8d534e323","year":2015},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.431517Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:4060964c6056837278902b900561be86e25a764704a82ebb77fb3db2a9b22c40","observation_id":"9fcc2a6f-475b-445f-ba2c-657d7587c351","resolution":{"observed_at":"2026-08-11T06:05:53.124107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.103807Z","title":"Addersr: Towards energy efficient image super-resolution, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":"08f47ffe-7261-42aa-b791-2122591e4ba2","year":2021},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.435979Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:718e37b3396da2fb858807f4d2a3d9aceba6767449e04656f6309d1764c0e6fe","observation_id":"5e4cd3a8-242b-49f7-8917-3d129decce94","resolution":{"observed_at":"2026-08-11T06:05:53.109033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.087588Z","title":"Inception-v4, inception-resnet and the impact of residual connections on learning, in: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI Press","venue":null,"work_id":"5e977d10-fddd-4305-bbda-4ac8134c19ec","year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.440489Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:d96f1f3b3341f97e91b2426050db8ce0bc30d66a4af100ccab4b44c03b754276","observation_id":"abc9b612-c468-44fc-8895-1c77d6456e16","resolution":{"observed_at":"2026-08-11T06:05:53.093223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.445477Z","title":"Going deeper with convolutions,in:2015IEEEConferenceonComputerVisionandPatternRecognition(CVPR),pp.1–9","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.445477Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:500842ed82f6ef46f8c180eed62fa8b704c0adf6249abc478267fc0eb2a81f9f","observation_id":"2051e245-88fd-4f6a-9aca-79fb186627cd","resolution":{"observed_at":"2026-08-11T06:05:51.445477Z","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":"2026-08-11T06:05:53.071011Z","title":null,"venue":null,"work_id":"84b0b965-2e82-44ec-81bc-ab06af86b2a9","year":2013},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.450691Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:cb4b016455798e574553640e71ab7cc30f3abad9c4d8550ef2e940343985315d","observation_id":"c0cf4f36-dca9-4e54-aeb4-8605ca1378d1","resolution":{"observed_at":"2026-08-11T06:05:53.075614Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.455810Z","title":"Rethinking the inception architecture for computer vision, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.455810Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:a4d92700d51056688b8b78d928e121ba66a93dba97a115324219ee90a08b45cd","observation_id":"8761299e-cc05-4523-bbb7-9f9df3a37730","resolution":{"observed_at":"2026-08-11T06:05:51.455810Z","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":"2026-08-11T06:05:53.056302Z","title":null,"venue":null,"work_id":"6ae89f2a-1b50-478d-93f1-4e920bea7c07","year":2019},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.460672Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:010cb5a93f899deb8a757280c247aa83ce63185e2ccab107cf8bc5406f3d2b6a","observation_id":"97e0c8cd-50de-4dbe-b396-31216e17afaf","resolution":{"observed_at":"2026-08-11T06:05:53.060873Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/83.892448","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T06:05:51.594718Z","title":"Image classification for content-based indexing","venue":null,"work_id":"83a7c13d-9965-4bee-a8d6-9798b9e2fde9","year":2001},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.465621Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:5095553c43508b3ee0fefdf178b72bd4a47ab191db3e9ca0319eeabd0017a9d4","observation_id":"8e869c5d-0eb9-4fbd-96df-21a1e2e336b9","resolution":{"observed_at":"2026-08-11T06:05:51.600620Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"4284.29672","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T06:05:52.183005Z","title":"Acceleratingconvolutionalneuralnetworksformobileapplications,in:Proceedingsofthe24thACMInternational Conferenceon Multimedia,AssociationforComputingMachinery, NewYork,NY,USA","venue":null,"work_id":"f6024dc2-23fe-4d42-8b67-54b275eb7ef3","year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.470557Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:58315ff47f970aaae3ea8057da8c3c9e1ca6891c4767f5dcd97dcf70e54f9ffe","observation_id":"6018837e-289b-47c5-bf0b-6f0510dd8175","resolution":{"observed_at":"2026-08-11T06:05:52.191002Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.040518Z","title":null,"venue":null,"work_id":"6aaedb8e-6ba5-41a1-a852-bf8eaa6c27dc","year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.475204Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:b72d774d169e3ab195242c75a87e64ed0b40159dd4a342473e48dc1efbca12f1","observation_id":"78bf07ba-be94-45bb-a071-b0d47b6f98dd","resolution":{"observed_at":"2026-08-11T06:05:53.045665Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.480316Z","title":"Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search, in: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.480316Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:90af7945f341860ac06760a6c48ceb8edac3393a519932f9d6686dad4f6eef2b","observation_id":"9071bd7a-dd0e-4910-9dda-a3d11773ed28","resolution":{"observed_at":"2026-08-11T06:05:51.480316Z","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":"2026-08-11T06:05:53.025452Z","title":null,"venue":null,"work_id":"620a2fad-6dc8-4dd3-a0fa-6ea7cb5e804d","year":2020},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.485187Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:367ce1ce54f69907eb04c55bf4865cebfba429a45698f84ae08625b6c4a4b9ea","observation_id":"3e314c9e-7ab1-45c3-9ee7-2c6de9b1b636","resolution":{"observed_at":"2026-08-11T06:05:53.030244Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.489780Z","title":"Designing energy-efficient convolutional neural networks using energy-aware pruning, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.489780Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:d13f6b82598d891e3628876d6b913e740862ced6cef4ffe1e666d43c9fd28b2e","observation_id":"689bcf6e-04f7-44f5-a7bf-49425d7273f9","resolution":{"observed_at":"2026-08-11T06:05:51.489780Z","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":"2026-08-11T06:05:51.494829Z","title":"A gift from knowledge distillation: Fast optimization, network minimization and transfer learning, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.494829Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:810427d223e1bbd41f2b7bb2707a6fd0f1bc66faac6521fb041caa83a07b9e74","observation_id":"8abf9eda-ff9d-4a9f-9f77-928eb3600c7b","resolution":{"observed_at":"2026-08-11T06:05:51.494829Z","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":"2026-08-11T06:05:51.499882Z","title":"Accelerating very deep convolutional networks for classification and detection","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.499882Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:c87077d3a7d20e861130ebf269a02432f102cced98778f98d30756d91370068a","observation_id":"da57ccc3-d30b-421a-949c-7781753d8a1d","resolution":{"observed_at":"2026-08-11T06:05:51.499882Z","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":"2026-08-11T06:05:51.504547Z","title":"Efficientandaccurateapproximationsofnonlinearconvolutionalnetworks,in:2015IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.504547Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:07828dd2825c902990ffc674fa5f37c9f7bb6eb3c06c2c5b72c970086535cda2","observation_id":"e964a3ee-d939-4b2d-811a-fe819e4eab9a","resolution":{"observed_at":"2026-08-11T06:05:51.504547Z","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":"2026-08-11T06:05:51.509399Z","title":"Object detection with deep learning: A review","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.509399Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:77eaed0f4b3a167fc51ea067caee524f55baad04d99b6ae8b406197710957e6c","observation_id":"affa915c-2453-46a2-91d9-f33a9c1f4a2a","resolution":{"observed_at":"2026-08-11T06:05:51.509399Z","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":"10.1609/aaai.v32i1.11601","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T06:05:51.556407Z","title":"ProceedingsoftheAAAIConferenceonArtificialIntelligence32","venue":null,"work_id":"7efd86a6-a2fd-44ee-977b-7649eb4dc6ef","year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.514344Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:b2c10e12933d3d857285d8486ab1ac8fae3285c8da9bf27d4e754ea2da9bcb19","observation_id":"cb966a84-5d78-4489-bd0b-2374d86444e1","resolution":{"observed_at":"2026-08-11T06:05:51.562443Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:53.010316Z","title":null,"venue":null,"work_id":"24316828-21c9-423e-b072-6a29cdcff5d4","year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.519289Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:218143ad289adad1343f237ae8a6d5e492417cfde41fc7ec9bee5ba0479dcdb9","observation_id":"e5ca3e5c-4821-4eac-abe4-7e64994599d5","resolution":{"observed_at":"2026-08-11T06:05:53.015108Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T06:05:51.524610Z","title":"Learning transferable architectures for scalable image recognition, in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T06:05:51.524610Z"},"links":{"citing_paper":"/paper/2412.16886"},"observation_digest":"sha256:3df641cd3d31e16a55ec4d76ab018a00fda0ba77d325981cf508238760175169","observation_id":"9c89d77e-a0c3-4a50-ae95-650cfecbff27","resolution":{"observed_at":"2026-08-11T06:05:51.524610Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.16886","last_updated":"2024-12-22T06:47:01Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T05:58:42.900359Z","submitted_at":"2024-12-22T06:47:01Z","title":"Lightweight Design and Optimization methods for DCNNs: Progress and Futures"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":37,"verified_exact":4,"verified_fuzzy":15},"total_outbound_references":58},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:2412.16886."}