{"as_of":"2026-08-15T05:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b49afe80aed16c4c4899432968a79ae9e2942cbcd7ae63127c76125ba5cdd03b","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T05:36:32.050169Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1909.00948/citation-record","integrity":"/paper/1909.00948/integrity","json":"/paper/1909.00948/citation-record.json","paper":"/paper/1909.00948"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.554598Z","title":"Fused-layer CNN accelerators","venue":null,"work_id":"45deaabc-c6c0-4f31-9547-026dfdc6dcff","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.885064Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:036b24ec49f4e30046d6139ba2b42ffaee90e8d595999f856a237ca7cd2b8a90","observation_id":"18430ca8-20b5-4180-8924-26ae70c66c96","resolution":{"observed_at":"2026-08-14T05:36:32.558677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.542966Z","title":"SegNet: A Deep Convolutional Encoder-Decoder Architec- ture for Image Segmentation","venue":null,"work_id":"d91376c2-3c6f-4786-831a-3e262357bf68","year":2017},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.892321Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:dee12e43592de22f41b6ff5171b7287d966696794f2563db2885d480857f1f4d","observation_id":"e9f1df31-9c3a-4d54-a55b-4c91f483bb4a","resolution":{"observed_at":"2026-08-14T05:36:32.546946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.530720Z","title":"Brostow, Julien Fauqueur, and Roberto Cipolla","venue":null,"work_id":"e6202090-22be-4bc8-9cc5-555697b63f2c","year":2009},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.897995Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:0233b9a2a4a5bc75791a9cf8a4a3b8475c8d6b459f8d25f92bfe576381f3459f","observation_id":"8c1e378b-6c25-4640-8f79-0c09b65911d3","resolution":{"observed_at":"2026-08-14T05:36:32.534952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.518090Z","title":"Goodman, and Alain K ¨agi","venue":null,"work_id":"fa43ae24-34c2-452a-a39c-add18f65ad9a","year":1996},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.902844Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:834ca806e00f2793fdd57003d93360c9ad3bd1744df6fce1879a705a0ae2ee8a","observation_id":"3631064a-2007-421b-b6b7-aeeb87aa0ec7","resolution":{"observed_at":"2026-08-14T05:36:32.522882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.506429Z","title":"A dynamically configurable coproces- sor for convolutional neural networks","venue":null,"work_id":"89c2f215-c335-4a87-8f6e-3add99079197","year":2010},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.908171Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:805ae72bdbb6f3013ea809848c2b693e5c718f1701b5585b0446eecce26a2d16","observation_id":"fcbfed46-2c18-42e5-9619-32e0eb4eb748","resolution":{"observed_at":"2026-08-14T05:36:32.510547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.493094Z","title":"Diannao: A small-footprint high-throughput accelerator for ubiquitous machine-learning","venue":null,"work_id":"58886f41-01b5-4fa7-9052-f5feac6eb5ec","year":2014},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.912774Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:8f89e83e669ea41b5a119a8259a090819c4a7cf1ae6c2056c165b3d48d1e3dc1","observation_id":"fb75555b-8713-4b12-9bf5-7722c8fae42e","resolution":{"observed_at":"2026-08-14T05:36:32.497907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.481202Z","title":"Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Con- volutional Neural Networks","venue":null,"work_id":"03afc2b4-0f75-432e-9be0-2d9e46210ffc","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.917530Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:7b27e724996b7df4434a9e27d7f1bdf7cb1e7128ef301909af087b0c6d0a9a3b","observation_id":"ada6a1be-9437-492c-a6c1-48d9852fb46b","resolution":{"observed_at":"2026-08-14T05:36:32.485473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.02830","last_updated":"2016-03-17T14:54:25Z","snapshot_observed_at":"2026-08-15T03:12:56.840603Z","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":"2026-08-14T05:36:31.921622Z","title":"Binarized neural networks: Training Neural Networks with Weights and Activations Constrained to +1 or−1","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.921622Z"},"links":{"cited_paper":"/paper/1602.02830","citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:cbcbb729b27f99d2d3430aad0ee03bf097aca7b03db291942deebb81d45e2a30","observation_id":"e2292ced-ed1a-48f3-879f-4e8f5d4a0147","resolution":{"observed_at":"2026-08-14T05:36:31.921622Z","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":"2026-08-14T05:36:32.468875Z","title":"ImageNet: A large-scale hierarchical im- age database","venue":null,"work_id":"c8e32729-d655-44bb-9d77-26273edd8ec0","year":2009},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.926347Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:f6a82874956322f96fca8510beb038d4c5d5bffdfdb8c5df0c9626ced3e3372f","observation_id":"14927a6c-5788-4421-b671-8b3e7bb4bce2","resolution":{"observed_at":"2026-08-14T05:36:32.473195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.04117","last_updated":"2016-09-22T20:14:09Z","snapshot_observed_at":"2026-08-14T21:44:15.221134Z","submitted_at":"2016-08-14T17:10:30Z","title":"The Importance of Skip Connections in Biomedical Image Segmentation","version":2},"cited_work":{"arxiv_id":"1608.04117","doi":null,"metadata_source":"pith","pith_arxiv_id":"1608.04117","snapshot_observed_at":"2026-08-14T05:36:32.162661Z","title":"The Importance of Skip Connections in Biomedical Image Segmentation","venue":"cs.CV","work_id":"fe67930c-78bc-4058-bf8e-b26b647dbd7d","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.931583Z"},"links":{"cited_paper":"/paper/1608.04117","citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:10edf20b72e7d1b0a4193f39884b911d397de610970333b935b350e9eaaa6e70","observation_id":"a6cc8fc6-3a7e-4b29-a793-4d24f028ce73","resolution":{"observed_at":"2026-08-14T05:36:32.168070Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.456383Z","title":"NullHop: A Flexible Convolutional Neural Network Accelerator Based on Sparse Representa- tions of Feature Maps","venue":null,"work_id":"b8392cce-2451-4162-9b94-4c970327e15a","year":2018},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.936134Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:a073b3b2704b168751cd80023485a63c90144945e4aa82c07cb97a7bbdbc01d5","observation_id":"2d297dff-41e8-4ee8-8a9a-55bc0dce66fd","resolution":{"observed_at":"2026-08-14T05:36:32.460771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.443966Z","title":null,"venue":null,"work_id":"97614253-000b-4d52-8634-845da6a1adf2","year":2010},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.940357Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:296162265b7fdb5ca5122c83740c45c389aefd2d412bcc3e509f6109350d9186","observation_id":"c0432169-c6bd-4c07-94d9-b03d20c29c22","resolution":{"observed_at":"2026-08-14T05:36:32.448337Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.430710Z","title":"NeuFlow: A runtime reconfigurable dataflow processor for vision","venue":null,"work_id":"6db4d5fe-083b-4581-b703-a5cf68f27cc6","year":2011},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.944446Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:8470f3d0908b5799d27292e8d8a4f83d1cc1662446df389bdae85649e9257f11","observation_id":"9b65c352-f5a2-4e12-9011-773c2c4ddd8d","resolution":{"observed_at":"2026-08-14T05:36:32.435606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.416919Z","title":"Hardware-oriented approximation of convolutional neural networks","venue":null,"work_id":"b8e3c6b7-f9f3-42d3-84ae-1926277e2b91","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.948349Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:aad63dd37278cf85e691b119e7c50d69e791159602773848e4f071b4835ddb25","observation_id":"9be0998e-429a-408f-a819-4c5796a94312","resolution":{"observed_at":"2026-08-14T05:36:32.422219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.404466Z","title":null,"venue":null,"work_id":"275bd1c4-9874-45ea-9ba6-583e7a52c365","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.952257Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:cd5d38ab9a0678554ae78f3cc3b137fe6819ce1f0d625ffb0a51207776da17ea","observation_id":"2f241371-b9e2-4830-8885-5f699c16e034","resolution":{"observed_at":"2026-08-14T05:36:32.408542Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.390771Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"de1ad4ba-9a36-4158-8bfa-d0c4d823ffcf","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.956244Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:27b3bc2206b671d6ca2e4f14515955732579759c383e824ae0f563f043438625","observation_id":"2402c6ae-c0e7-4ae8-a5ae-f5c24c94c78e","resolution":{"observed_at":"2026-08-14T05:36:32.394836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.00002","last_updated":"2017-10-30T22:01:08Z","snapshot_observed_at":"2026-08-14T20:18:40.999442Z","submitted_at":"2017-10-30T22:01:08Z","title":"Log-DenseNet: How to Sparsify a DenseNet","version":1},"cited_work":{"arxiv_id":"1711.00002","doi":null,"metadata_source":"pith","pith_arxiv_id":"1711.00002","snapshot_observed_at":"2026-08-14T05:36:32.142860Z","title":"Log-DenseNet: How to Sparsify a DenseNet","venue":"cs.CV","work_id":"3ba4865b-5e44-497b-947a-5bd49420a20d","year":2017},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.960805Z"},"links":{"cited_paper":"/paper/1711.00002","citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:0f58dc03cb9bfbee8b12d844bd08dfaa5f80643bcf9affaabd0bcae856ec2ad7","observation_id":"0ad6b67e-0fe5-461f-b983-92cf6f73cbe1","resolution":{"observed_at":"2026-08-14T05:36:32.148300Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.377155Z","title":"Weinberger","venue":null,"work_id":"264962cd-dbbc-4f7f-b26a-f1cd0e4a7de9","year":2017},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.965239Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:274d9e1cf9a8a5481d14f2413f4e48d98f32c4b5436b4517826211f854435eb5","observation_id":"5a274779-6d26-4292-bac9-86ba37f6dd75","resolution":{"observed_at":"2026-08-14T05:36:32.382236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.362558Z","title":"Deep networks with stochastic depth","venue":null,"work_id":"e1d5166f-f43a-46ef-a44c-a209bed613c2","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.969049Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:3dca72cdea1eea495fa2cad358367537bb39ccc5e62cf6b22719b964c0c84225","observation_id":"78253d6b-17e6-4c91-926f-d385ac86881d","resolution":{"observed_at":"2026-08-14T05:36:32.367765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1602.07360","last_updated":"2016-11-04T21:26:08Z","snapshot_observed_at":"2026-08-14T22:09:04.541956Z","submitted_at":"2016-02-24T00:09:45Z","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.07360","snapshot_observed_at":"2026-08-14T05:36:31.974189Z","title":"Iandola, Song Han, Matthew W","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.974189Z"},"links":{"cited_paper":"/paper/1602.07360","citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:20d08fda8df8a1774d7168ab7fb38892fef74dbdd11bcc4b3cbc93594e6d2d59","observation_id":"16ba2b0a-91b9-41db-acfc-9003c282f28c","resolution":{"observed_at":"2026-08-14T05:36:31.974189Z","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":"2026-08-14T05:36:32.349637Z","title":"The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Seg- mentation","venue":null,"work_id":"521ecb93-7b97-434f-a2f1-16dbfd7b2783","year":2017},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.979360Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:6e6b4172ca818da05134d9458930ec0de3c24d598fadf9bbc4a2d6cd7999f0d7","observation_id":"ddf3ac50-a9a2-4023-838d-8cde43a9f25b","resolution":{"observed_at":"2026-08-14T05:36:32.353833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.337470Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"2ff2762d-f375-469d-ba2d-68ab09603ed8","year":2009},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.983500Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:df27cdc3e780ea73af2b434de83fe01434a03a66a0377e81b7f235aed7304ffa","observation_id":"1a07ce1a-1957-4a8c-9639-2ce9988320c2","resolution":{"observed_at":"2026-08-14T05:36:32.341701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.324042Z","title":null,"venue":null,"work_id":"45fc75b1-6d02-4803-af77-ae713f416849","year":2012},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.988326Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:7ab72ad6f532ef93d8b5e38b41aac51d63abf12973f4bb4824a2c2ba7f2bbb18","observation_id":"51b73c2c-f62a-4058-891e-adc1bff73ff4","resolution":{"observed_at":"2026-08-14T05:36:32.329369Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.311453Z","title":"FractalNet: Ultra-deep neural networks without residuals","venue":null,"work_id":"66a9513d-7071-4a79-86b7-471d2a6557ef","year":2017},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.993018Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:f114f084a497cc02f4f6b67059d0a3f646c281e97e95d7f8a6927c3e3c3ef680","observation_id":"5ba46521-93df-4b48-9967-abdae7e07e72","resolution":{"observed_at":"2026-08-14T05:36:32.315828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.298577Z","title":"Optimizing Memory Efficiency for Deep Convolutional Neural Networks on GPUs","venue":null,"work_id":"9083ebd3-c583-48ec-a2f6-c086a21a3225","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:31.997186Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:44b5aac65df63d5e97401fd1b5679c3185cdc989069b0859c1f60d622151d289","observation_id":"24da818c-4844-45cf-bef8-71205b31babc","resolution":{"observed_at":"2026-08-14T05:36:32.302824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.286261Z","title":"Lawrence Zitnick, and Piotr Doll ´ar","venue":null,"work_id":"eb910898-12af-475f-952d-14441ef7c3ae","year":2014},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.001184Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:a7735789eae6128468834521b17b0a58268508078e767598343abf45cb4e0678","observation_id":"bfbb06fd-49e7-4b2f-a9d4-c28b43371b28","resolution":{"observed_at":"2026-08-14T05:36:32.290489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.274178Z","title":"Fully convolutional networks for semantic segmentation","venue":null,"work_id":"56c9c72c-86e4-48e0-873d-78db987c2938","year":2015},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.005349Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:28223966d20a06368db6236a20fd9ccbff830df28a44667a93f72f77d5865e64","observation_id":"78d9f84d-a93c-4ec9-8fd0-2f169195758a","resolution":{"observed_at":"2026-08-14T05:36:32.278343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1603.01025","last_updated":"2016-03-17T03:32:30Z","snapshot_observed_at":"2026-08-14T22:07:42.783045Z","submitted_at":"2016-03-03T08:51:52Z","title":"Convolutional Neural Networks using Logarithmic Data Representation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.01025","snapshot_observed_at":"2026-08-14T05:36:32.010938Z","title":"Lee, and Boris Murmann","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.010938Z"},"links":{"cited_paper":"/paper/1603.01025","citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:89ef28e67e2ee321dccbcc86ccebf926966d2a0fc4ea0820831169d28290993e","observation_id":"b1c737d2-dbb7-4156-b4a7-cf9bb0572cb6","resolution":{"observed_at":"2026-08-14T05:36:32.010938Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1603.05279","last_updated":"2016-08-02T20:59:14Z","snapshot_observed_at":"2026-08-14T22:05:42.494685Z","submitted_at":"2016-03-16T20:56:21Z","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.05279","snapshot_observed_at":"2026-08-14T05:36:32.015533Z","title":"XNOR-net: Imagenet classification us- ing binary convolutional neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.015533Z"},"links":{"cited_paper":"/paper/1603.05279","citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:3defc93dac86dffd0f482450110d50a07a8f46dd8b82472bcec7139bf2b7913f","observation_id":"9fadaeb6-5885-4802-8a57-96d4d2e760ca","resolution":{"observed_at":"2026-08-14T05:36:32.015533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.02883","last_updated":"2019-02-02T04:01:45Z","snapshot_observed_at":"2026-08-14T18:13:33.714744Z","submitted_at":"2018-10-16T22:33:46Z","title":"SCALE-Sim: Systolic CNN Accelerator Simulator","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.02883","snapshot_observed_at":"2026-08-14T05:36:32.020182Z","title":"SCALE-Sim: Systolic CNN Accelerator Simulator","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.020182Z"},"links":{"cited_paper":"/paper/1811.02883","citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:626555e7276014cf35585ab14057c006c260d7d42e994c56de52407d43c10318","observation_id":"6203af4a-fa03-474a-8abf-0a27b97479d7","resolution":{"observed_at":"2026-08-14T05:36:32.020182Z","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":"2026-08-14T05:36:32.260467Z","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","venue":null,"work_id":"42f47882-b71e-4f79-8af8-6eabbfe87a48","year":2018},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.024634Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:2df52627e8203a3676502f468cbaad235545680faa98ac604eb6fc206a7b2bc7","observation_id":"3fc2a457-2e41-45c2-96a4-f5d952b998b1","resolution":{"observed_at":"2026-08-14T05:36:32.265130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.246903Z","title":"Very deep con- volutional networks for large-scale image recognition","venue":null,"work_id":"9c36ad2e-e043-4537-95b1-b4c5aeccafee","year":2014},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.028710Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:1cb56afec32ee5eea5a55afff006ba3c73f14a6a7454cefdbbcfe6dd08b61951","observation_id":"56226113-fb32-49aa-9519-289c8b8eae52","resolution":{"observed_at":"2026-08-14T05:36:32.251467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.233069Z","title":"Training very deep networks","venue":null,"work_id":"7cef482e-5d96-4e81-babd-10d4267ff34e","year":2015},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.033659Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:9d9e70abde3baf0cf34813a976cf06adba2f87bda36c3564e3e8afe7d2db77c0","observation_id":"418d41f0-1184-4e5c-8735-ebe3fb9ca1f6","resolution":{"observed_at":"2026-08-14T05:36:32.237706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.218255Z","title":"Rethinking the in- ception architecture for computer vision","venue":null,"work_id":"22231052-5ab5-4c54-8bf6-61f65c6a9a81","year":2016},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.041182Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:9beda0c7a4ae25c4e40d7b6e87a37910ceb524aeed85526e82a33e215738fc07","observation_id":"7357c732-ea4d-4123-981e-e9f81a28f047","resolution":{"observed_at":"2026-08-14T05:36:32.223677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.205338Z","title":null,"venue":null,"work_id":"97ed4919-ada8-4cf4-89af-489fd9dc7c2c","year":2018},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.045625Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:0c7672965583bf9cebb313fc74ab18304f945e5d62bc11c2c96f0a77621ff81d","observation_id":"0f2c6e6b-7984-4164-adad-bc938414792f","resolution":{"observed_at":"2026-08-14T05:36:32.210011Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:36:32.192067Z","title":"Sparsely Aggregated Convolu- tional Networks","venue":null,"work_id":"a288aaa8-2d42-479b-92a8-8a184d5994cb","year":2018},"citing_paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T05:36:32.050169Z"},"links":{"citing_paper":"/paper/1909.00948"},"observation_digest":"sha256:9a1b75aec185dac5143c376489baae43b0c01198fce91c349ae8d05ac74607f0","observation_id":"06abaf03-c76d-4163-9d5f-42c6f3544a8f","resolution":{"observed_at":"2026-08-14T05:36:32.196876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1909.00948","last_updated":"2019-09-03T04:34:18Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T01:32:24.097610Z","submitted_at":"2019-09-03T04:34:18Z","title":"HarDNet: A Low Memory Traffic Network"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":2,"verified_fuzzy":25},"total_outbound_references":36},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:1909.00948."}