{"as_of":"2026-08-17T18:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:655df4b8c4bffcf5ec0b27b08ab1bd712edf707e1dacb85f9e38a8b880db46ad","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T06:04:07.099376Z","state":"measured"},{"denominator":26,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":26,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/1909.00182/citation-record","integrity":"/paper/1909.00182/integrity","json":"/paper/1909.00182/citation-record.json","paper":"/paper/1909.00182"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-08-15T04:53:45.483331Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-14T06:04:06.976026Z","title":"Layer normalization","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:06.976026Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:65753dc440ff6cfba3ce4d6bc6bc21806f42a7c4e59a744538ea3a66e3b2c651","observation_id":"19bd6213-53ac-4e42-83a1-1aabcbddbed8","resolution":{"observed_at":"2026-08-14T06:04:06.976026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06085","last_updated":"2018-07-17T07:33:19Z","snapshot_observed_at":"2026-08-17T06:12:39.940205Z","submitted_at":"2018-05-16T01:19:43Z","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06085","snapshot_observed_at":"2026-08-14T06:04:06.982430Z","title":"Pact: Parameterized clipping activa- tion for quantized neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:06.982430Z"},"links":{"cited_paper":"/paper/1805.06085","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:0ba493be909b522b333318633e744e927d372a10ee87734a65a34ed010f9c183","observation_id":"f91df1e1-76ca-446a-84d2-b2a594e53831","resolution":{"observed_at":"2026-08-14T06:04:06.982430Z","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":"2026-08-14T06:04:06.988171Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:06.988171Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:f88429d8ae65296699ba0a6eebe93f86737fc2130490d44e295537b9764b4dbe","observation_id":"0759882d-89fb-458a-ac88-0abcced25bbb","resolution":{"observed_at":"2026-08-14T06:04:06.988171Z","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":"2026-08-14T06:04:06.993267Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:06.993267Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:65e149cf381db4cc2ac1e4cc9f001e927e1b7604dee13f0b85bf6a0f7e3be5b9","observation_id":"f4e3ab89-a548-4c48-81d2-bdd47b4a961f","resolution":{"observed_at":"2026-08-14T06:04:06.993267Z","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":"2026-08-14T06:04:06.998324Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:06.998324Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:5b4e9651618a534233ff0889d5425b26cb7631ca17c1ba6664fd4cf6791f08f8","observation_id":"95b149b5-b3c6-475f-835b-dd3bd5bd421f","resolution":{"observed_at":"2026-08-14T06:04:06.998324Z","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":"2026-08-14T06:04:07.459610Z","title":"Bag of tricks for image classification with convolutional neural networks","venue":null,"work_id":"c9747e0e-cac6-46d7-827a-d78152b7d80c","year":2019},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.003247Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:31dceb1c376ab66ee94620eed8fe608fcf9c835fe0063defa7eb7c37f7492770","observation_id":"a514a96a-d886-4203-a941-3c681b3b0a61","resolution":{"observed_at":"2026-08-14T06:04:07.464499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","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":"2026-08-14T06:04:07.008563Z","title":"Distill- ing the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.008563Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:d1822b4b8e7912c7621323d5fca681621b455711a4972d73cf1bf05e463041a0","observation_id":"ad262c59-a695-4fa4-8ebc-26044433f0dc","resolution":{"observed_at":"2026-08-14T06:04:07.008563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-14T06:04:07.014411Z","title":"Mobilenets: Efficient convolu- tional neural networks for mobile vision applications","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.014411Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:ff5fbc72787ebf5f1476cc2852108ede4a3e15a9778aad6f3c34fab1de85e7e4","observation_id":"7b5fe11c-7e39-40e1-ae8c-4281ab3355d6","resolution":{"observed_at":"2026-08-14T06:04:07.014411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-08-12T21:01:12.961874Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-14T06:04:07.019638Z","title":"Batch normalization: Accelerating deep network training by reducing internal co- variate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.019638Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:294358c6c4e770044174222b4509db4af432ebf2f1bb3f0e8ba3bda4a3029638","observation_id":"00d3980e-5265-4df6-939c-21d3b8939571","resolution":{"observed_at":"2026-08-14T06:04:07.019638Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10196","last_updated":"2018-02-26T15:33:34Z","snapshot_observed_at":"2026-08-15T04:29:56.166616Z","submitted_at":"2017-10-27T15:28:35Z","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10196","snapshot_observed_at":"2026-08-14T06:04:07.024575Z","title":"Progressive growing of gans for improved quality, stability, and variation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.024575Z"},"links":{"cited_paper":"/paper/1710.10196","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:bd84024843cb458deae3d4dece84c727c077d94926dbe4ab249f2276be2c642e","observation_id":"4c0580cd-82d2-48fc-84b4-59b2329da2c9","resolution":{"observed_at":"2026-08-14T06:04:07.024575Z","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":"2026-08-14T06:04:07.444048Z","title":"The cifar-10 dataset","venue":null,"work_id":"2737309f-fb9a-49bd-a44d-5935dffcad13","year":2014},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.030157Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:6ee485d40da60ae411278cc057a73b57dc598b6030a98ddd89d49e17a29938c7","observation_id":"695633da-d319-4f93-a8ef-544fd20171ce","resolution":{"observed_at":"2026-08-14T06:04:07.448838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-14T06:04:07.035180Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.035180Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:be2cc3b03ddb4ef2889a76be45f7b913200d61ccf911a0b5ea3ea33f1c289795","observation_id":"68508288-1f1a-4f9b-b7df-41c48ca3fec1","resolution":{"observed_at":"2026-08-14T06:04:07.035180Z","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":"2026-08-14T06:04:07.419371Z","title":"Repr: Improved training of convolutional filters","venue":null,"work_id":"5e206093-9590-4bb7-834a-ee96bbe4cc44","year":2019},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.039907Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:598b2437526b2d39032330a90b091a3e976e14b19ce0edff7509e8245d9b92a2","observation_id":"476dab1a-864c-47ce-8be1-5a2b2366dac4","resolution":{"observed_at":"2026-08-14T06:04:07.424376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-14T06:04:07.044597Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.044597Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:3a495d30f5ead73b8dbd4f364ebbbbcfa3bab8856bf8f1d3f23c4716e61212d9","observation_id":"05774e08-44b4-4213-ba64-162287a7237f","resolution":{"observed_at":"2026-08-14T06:04:07.044597Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T23:20:42.336514Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-14T06:04:07.049394Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.049394Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:fb415440d50fa5db06506994f907c69ef83fd014bbe1a34143fc2047343c507f","observation_id":"74cf26cb-c1ca-44c2-b05f-135edae5908d","resolution":{"observed_at":"2026-08-14T06:04:07.049394Z","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":"2026-08-14T06:04:07.393187Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":"ff847790-42bb-49a6-9f52-fb66677a6a8b","year":1929},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.054085Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:05000be6a5e8eb9b89859227c50ff1af0b5ca6cb338edf7b746133c166b76760","observation_id":"e1462646-85a2-4041-b834-2c766582911b","resolution":{"observed_at":"2026-08-14T06:04:07.398477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-14T06:04:07.058389Z","title":"Going deeper with convolutions","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.058389Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:c27eb5f7504f578df753c9a26306cf9a4ce6742b7cb99c3639ebc2af9db01367","observation_id":"c8ee5865-1060-4c4e-8551-b7e44666c75f","resolution":{"observed_at":"2026-08-14T06:04:07.058389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11946","last_updated":"2020-09-11T05:08:01Z","snapshot_observed_at":"2026-08-10T19:44:30.311627Z","submitted_at":"2019-05-28T17:05:32Z","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11946","snapshot_observed_at":"2026-08-14T06:04:07.062302Z","title":"Efficientnet: Rethinking model scaling for convolutional neural networks","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.062302Z"},"links":{"cited_paper":"/paper/1905.11946","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:151cbece4c5dcfaa2cde86caf0abb9575ddd1e6e247478bc244e12fa204a7029","observation_id":"6d3ecf28-c3c6-4bef-9e73-082e4e2d80fd","resolution":{"observed_at":"2026-08-14T06:04:07.062302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.06423","last_updated":"2022-01-20T11:02:01Z","snapshot_observed_at":"2026-08-14T16:15:19.784756Z","submitted_at":"2019-06-14T22:27:30Z","title":"Fixing the train-test resolution discrepancy","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.06423","snapshot_observed_at":"2026-08-14T06:04:07.066947Z","title":"Fixing the train-test resolution discrepancy","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.066947Z"},"links":{"cited_paper":"/paper/1906.06423","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:2dd1683e029bdffb197dde3a4187ae41c72d45d3f9fc6b290b0d665cdbff5779","observation_id":"f2d05cd5-8d55-48a1-9ef2-4e2a004314f8","resolution":{"observed_at":"2026-08-14T06:04:07.066947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.08022","last_updated":"2017-11-06T14:21:43Z","snapshot_observed_at":"2026-08-15T14:21:42.814056Z","submitted_at":"2016-07-27T10:23:00Z","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.08022","snapshot_observed_at":"2026-08-14T06:04:07.071224Z","title":"In- stance normalization: The missing ingredient for fast styliza- tion","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.071224Z"},"links":{"cited_paper":"/paper/1607.08022","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:1c927fb1b7156460dbdbe8af51ff1d0fa493aeda6a24f1924dc9a5e13dee46ea","observation_id":"711bb18b-ceb9-47e1-8d94-1911eb6e316f","resolution":{"observed_at":"2026-08-14T06:04:07.071224Z","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":"2026-08-14T06:04:07.366074Z","title":"Regularization of neural networks using drop- connect","venue":null,"work_id":"23ffd5ca-0399-431a-8a6c-6e112a8a3429","year":2013},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.075564Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:f342d6e449ddb4d2e3525cd28678ff8aea15601cc1578df381ff460ce8efa31f","observation_id":"1e2d9bf2-3ecc-448b-9787-f33509194f8b","resolution":{"observed_at":"2026-08-14T06:04:07.371128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-14T06:04:07.350484Z","title":"Towards dropout training for convolutional neural networks","venue":null,"work_id":"bcb356e7-9184-42b2-9f2a-9732f4cd488e","year":2015},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.079836Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:9afdcd5b3374a89ecf3c0efd78cd3a8cda4cb41953fe6003c189952f7632098b","observation_id":"f0607f61-7c88-41de-ba4b-c41c9fd53eb4","resolution":{"observed_at":"2026-08-14T06:04:07.355672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-14T06:04:07.334072Z","title":"Group normalization","venue":null,"work_id":"e8538932-2df7-4dd4-b2a2-6b78425ca372","year":2018},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.084612Z"},"links":{"citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:e297b6ac6d7257ed8064ef4b2a3d47d7a6205988b66ea545500ec88ccfe64217","observation_id":"7d3903df-b687-4f75-ba85-5dcf44e406d5","resolution":{"observed_at":"2026-08-14T06:04:07.339750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.01187","last_updated":"2018-12-05T22:17:01Z","snapshot_observed_at":"2026-08-14T17:49:04.928598Z","submitted_at":"2018-12-04T03:07:35Z","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.01187","snapshot_observed_at":"2026-08-14T06:04:07.089487Z","title":"Bag of tricks for image classifica- tion with convolutional neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.089487Z"},"links":{"cited_paper":"/paper/1812.01187","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:4541428c16815480d23eec015128b4c6cd982514ceebc354bfffa45a67992480","observation_id":"68f05454-3c53-4063-a32c-32d69eada630","resolution":{"observed_at":"2026-08-14T06:04:07.089487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-14T06:04:07.094451Z","title":"mixup: Beyond empirical risk minimiza- tion","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.094451Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:a45b057897a94329eeb77cb2484aee46e27708dbdd8983323dba06f6555a9e16","observation_id":"424b3ff5-9bd5-40e6-8f88-b0b2aaa968fe","resolution":{"observed_at":"2026-08-14T06:04:07.094451Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.09321","last_updated":"2019-03-12T00:31:18Z","snapshot_observed_at":"2026-08-14T17:25:25.486314Z","submitted_at":"2019-01-27T05:30:11Z","title":"Fixup Initialization: Residual Learning Without Normalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.09321","snapshot_observed_at":"2026-08-14T06:04:07.099376Z","title":"Fixup ini- tialization: Residual learning without normalization","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T06:04:07.099376Z"},"links":{"cited_paper":"/paper/1901.09321","citing_paper":"/paper/1909.00182"},"observation_digest":"sha256:159a22c184035de538013c495721bdab99f46e0778c177a606de3f24357ce904","observation_id":"1defcd17-782b-408c-ac12-b9370c8904fe","resolution":{"observed_at":"2026-08-14T06:04:07.099376Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1909.00182","last_updated":"2020-09-07T15:09:01Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T10:14:57.111844Z","submitted_at":"2019-08-31T10:01:37Z","title":"Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":0,"verified_fuzzy":7},"total_outbound_references":26},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:1909.00182."}