{"as_of":"2026-08-15T10:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d8d7208821a8f59acab83c551b61ea7c1246f59d4a9f61796b10aee387f99a30","coverage":[{"denominator":76,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":76,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T11:42:05.840537Z","state":"measured"},{"denominator":76,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":76,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.08520/citation-record","integrity":"/paper/1908.08520/integrity","json":"/paper/1908.08520/citation-record.json","paper":"/paper/1908.08520"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:42:05.402456Z","title":"Im- agenet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.402456Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:90174192c640453f1f4a51c1afde680fc5e057a941838036a1211bc4739a7433","observation_id":"25ab7421-bded-45b6-a42f-ecd696440e88","resolution":{"observed_at":"2026-08-14T11:42:05.402456Z","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":"2026-08-14T11:42:07.517147Z","title":"Openimages: A public dataset for large-scale multi-label and multi-class image classification","venue":null,"work_id":"a93a1b91-39ce-4b01-9594-3e6bcabf66fc","year":2016},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.407968Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:25f57f74314c113545b5b4b920c3cc910a35a76a9eb46b57590d53c84d813749","observation_id":"6db7a6d8-c71b-4e3e-a80f-002b70393b85","resolution":{"observed_at":"2026-08-14T11:42:07.524701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.493794Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":"6be99d03-164b-4232-acd6-732028e595d3","year":2014},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.413595Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:2722eb9e6d83f0fe3ebd4d80c44f2be26dde6003750722ee3408f0cb757b1af7","observation_id":"8f4804c5-b148-4f02-8213-e92a081c3e6a","resolution":{"observed_at":"2026-08-14T11:42:07.499725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.468530Z","title":"Regu- larization of neural networks using dropconnect,","venue":null,"work_id":"dae7b979-346e-4c7d-966c-b27d40fb2b24","year":2013},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.420575Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:9970ec72f7b0605195918a30e7cbe9179a411bc68a281928e12bd18a1f9b2841","observation_id":"b0ca15cc-df91-4f2a-9838-7c6277ef5eac","resolution":{"observed_at":"2026-08-14T11:42:07.477499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.434345Z","title":"Deep networks with stochastic depth,","venue":null,"work_id":"79a26103-9863-4956-8eb8-9335dafbf3a8","year":2016},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.428170Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:c7f7c25708a6bac288defb4a925b8d14d13d46c6eea8cd99e88077981452b206","observation_id":"5ae50b3a-a203-417d-a9a5-fb82d5a9f978","resolution":{"observed_at":"2026-08-14T11:42:07.448390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.404395Z","title":"Swapout: Learning an ensemble of deep architectures,","venue":null,"work_id":"88df4b30-bc60-4e22-a42d-64029047d1d4","year":2016},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.434150Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:3628ffbf7a2a705e034f8312bf832f888fefa0fa66ea118ecb31501774ed8765","observation_id":"d90b0c87-5fe1-4310-8a87-a10fbd6bb3fe","resolution":{"observed_at":"2026-08-14T11:42:07.415705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:05.441446Z","title":"Visualizing data using t-sne,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.441446Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:9c28224a14788abbabd09d9ca5b2b0f037674dfbca039afa71f5f761164d02df","observation_id":"29710ac7-675e-40f4-bc32-16329d61b7ba","resolution":{"observed_at":"2026-08-14T11:42:05.441446Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07485","last_updated":"2017-05-23T13:36:46Z","snapshot_observed_at":"2026-08-14T20:59:15.484135Z","submitted_at":"2017-05-21T18:51:27Z","title":"Shake-Shake regularization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07485","snapshot_observed_at":"2026-08-14T11:42:05.447949Z","title":"Shake-shake regularization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.447949Z"},"links":{"cited_paper":"/paper/1705.07485","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:c01b52058268b81b501ffe4ffc2d6dbed9bcd39cea8cf1f95da5e870b4e2b8a5","observation_id":"17fea7c3-71b1-477a-b70d-28efa5968c90","resolution":{"observed_at":"2026-08-14T11:42:05.447949Z","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":"2026-08-14T11:42:07.360241Z","title":"Meal: Multi-model ensemble via adversarial learning,","venue":null,"work_id":"0c8c4a5c-c4f9-4be3-b331-ffbb179a69bd","year":2019},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.454202Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:e0dc9be73270c8c2e7fab0fb4235efaae4a6d3b1f7059b4d0d5c0a4c4c556826","observation_id":"319ee813-7564-468e-b47d-e1307ce36f8a","resolution":{"observed_at":"2026-08-14T11:42:07.371312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.337281Z","title":"Snapshot ensembles: Train 1, get m for free,","venue":null,"work_id":"330f1a8a-2875-4cad-8b55-d7b7a62b7166","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.459319Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:f9b0c936a82af54f876e2e99d813b36d3b268161a15b2cf0bc0a8e7c51fc64ab","observation_id":"e812c425-e196-41cc-975b-7ee56f495865","resolution":{"observed_at":"2026-08-14T11:42:07.344339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.316344Z","title":"Neural network ensembles,","venue":null,"work_id":"4b61533d-e48b-4447-a6d4-9dd3d05cd51a","year":1990},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.464762Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:62be04f494c02bb2da3ddddb4102f46494c02cc1b10c9be8bbce85e94a58c893","observation_id":"6ea0a760-9cbd-4be8-8741-d5c14d865344","resolution":{"observed_at":"2026-08-14T11:42:07.322829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.288983Z","title":"When networks disagree: En- semble methods for hybrid neural networks,","venue":null,"work_id":"2e06b718-1c6f-4e80-86cb-858bcc648d45","year":1995},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.469740Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:9a155930d72af1c7c68f84bca0fdb61463c435e4506ce868c5a89129fd673a3d","observation_id":"6cdae2a4-5bff-46b4-bbc6-cc399aceafe7","resolution":{"observed_at":"2026-08-14T11:42:07.298032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.265206Z","title":"Neural network ensembles, cross validation, and active learning,","venue":null,"work_id":"1e612854-8446-43f2-ab7f-af1fcf5ff7b1","year":1995},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.479698Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:7590335a41b7e244073dcd3e3a3a3ec36ef385db446df80660ea21dce744daac","observation_id":"3a2da5ff-619c-4842-a21c-8bff7ae9c5fc","resolution":{"observed_at":"2026-08-14T11:42:07.275129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.244828Z","title":"Ensemble methods in machine learning,","venue":null,"work_id":"62f84a6d-1dee-442c-a66f-1cb78d6fdf6d","year":2000},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.486237Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:a4fb22af8a98be11a738f6402888aff48a4a0d466a60300230bf289837179e70","observation_id":"4e4f725b-8fde-4dbf-b0ba-9b73787f7199","resolution":{"observed_at":"2026-08-14T11:42:07.251735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.220026Z","title":"Simple and scalable predictive uncertainty estimation using deep ensembles,","venue":null,"work_id":"b69909bc-4ad9-44fc-a5f8-704099b274f5","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.491891Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:3794767077cdfaaa5312ac316ccb5f56cdf615bbb996122105a05069e7190732","observation_id":"386b7b20-4006-4223-b64a-2570dbf9770b","resolution":{"observed_at":"2026-08-14T11:42:07.227058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.197071Z","title":"Knowledge distillation by on-the-fly native ensemble,","venue":null,"work_id":"3d2efd55-d8b5-4dfc-80a4-1327638412b9","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.496815Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:36c678a4897a7116e0580b913146894dab7bef538fb1590fb84dfc4a64873254","observation_id":"053427cb-135c-4a5f-9952-ac8367cc7962","resolution":{"observed_at":"2026-08-14T11:42:07.205239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.173323Z","title":"Diverse ensemble evolution: Curriculum data-model marriage,","venue":null,"work_id":"33e47b44-e305-4679-8802-6b3508020fb8","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.502276Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:b7aef1c58321f3c7447bc1a666b9a3b457fab1acd6388ff5b7e52f4139789d9c","observation_id":"128f71b3-fee0-436a-b0e6-2d7af9127ccb","resolution":{"observed_at":"2026-08-14T11:42:07.180837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-14T22:57:08.956233Z","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":"2026-08-14T11:42:05.507206Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.507206Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:3ebf46720fd86a23739d4c7650e0b89fd91f2f143d73984e0720f802fa95a3b8","observation_id":"3cc22b1d-40c7-4384-9831-0d0b34d6061b","resolution":{"observed_at":"2026-08-14T11:42:05.507206Z","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":"2026-08-14T11:42:07.140460Z","title":"Semi-supervised knowledge transfer for deep learning from private training data,","venue":null,"work_id":"1484c34c-f067-4ebf-bc89-bd04c446063f","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.513225Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:8fb3f9ca5bb0d3b196731c108536a5eede40c9a0c96d3bc5871845738bb2910b","observation_id":"49011a91-b2cd-4c30-a936-1c607307585d","resolution":{"observed_at":"2026-08-14T11:42:07.149180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.113789Z","title":"Learning from noisy labels with distillation,","venue":null,"work_id":"e21cc7a7-4277-4665-972e-4cda37a608ce","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.531547Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:0f0e135096ce56c9f1c93c7bda1606deb00bdb0c56f7b0ed684da4cc17528677","observation_id":"1c7aba55-2b46-4840-bb70-21a1047a6e9d","resolution":{"observed_at":"2026-08-14T11:42:07.122142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.087885Z","title":"A gift from knowledge distillation: Fast optimization, network minimization and transfer learning,","venue":null,"work_id":"e8390784-744b-456f-bffe-f179db4856a2","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.537311Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:5eebe979982657ece0e5eb1ef61a9dd6fcb80c4a5bf8dac905139824b06445a0","observation_id":"60f8b062-03ed-49c3-a56f-43ffd624cdfa","resolution":{"observed_at":"2026-08-14T11:42:07.095009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.060357Z","title":"Generative adversarial nets,","venue":null,"work_id":"bea12099-16c1-4a93-831c-a8e82964d180","year":2014},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.542848Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:e8394f15f2f9266ad47d5864fd1bd4d33be8bfe0f333a706843eeece3ca408e2","observation_id":"6bea4c14-0adb-4a18-aed5-6ecdb9ca6931","resolution":{"observed_at":"2026-08-14T11:42:07.066127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.035377Z","title":"Label refinery: Improving imagenet classification through label progression,","venue":null,"work_id":"ff77cf60-44a4-4ac5-86cd-24b35121a85e","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.547852Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:ef609448eaa467525cfeb913c0e1f6f4d586131bc30614299f0dee2905432be7","observation_id":"ea6e9b6f-13b6-4ace-a714-2fed3319b129","resolution":{"observed_at":"2026-08-14T11:42:07.043851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:07.014983Z","title":"Wasserstein generative adversarial networks,","venue":null,"work_id":"a7b6ebf2-f460-40da-9f2b-8cd02a1394c9","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.552765Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:16a279c497654f302e0809d99665cb93d99cd2d150e56053be8eb0c49a028694","observation_id":"d81bb5c0-171d-4d0e-b51f-91374c6d50b5","resolution":{"observed_at":"2026-08-14T11:42:07.021678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.992567Z","title":"Improved training of wasserstein gans,","venue":null,"work_id":"5eb0f829-98f2-4a57-9afc-61cc4b3f82f2","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.558067Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:bd7ae7a8155c0a1899b3716a55a3e874a8100867a17de5ba6d20e45bb8311be0","observation_id":"e3af3db3-75af-45f1-bb46-564ce4e1973c","resolution":{"observed_at":"2026-08-14T11:42:06.999517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07215","last_updated":"2017-12-10T15:24:13Z","snapshot_observed_at":"2026-08-14T20:59:26.167385Z","submitted_at":"2017-05-19T22:41:56Z","title":"On Convergence and Stability of GANs","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07215","snapshot_observed_at":"2026-08-14T11:42:05.563547Z","title":"On convergence and stability of gans,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.563547Z"},"links":{"cited_paper":"/paper/1705.07215","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:b64877764411fe44f13a3ef77e29193ac30d49882d5c58c6634a8c3a23f16702","observation_id":"291e09c3-bcae-48ef-abd1-7c41f7876e50","resolution":{"observed_at":"2026-08-14T11:42:05.563547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.08446","last_updated":"2018-02-20T22:10:33Z","snapshot_observed_at":"2026-08-14T20:21:06.862364Z","submitted_at":"2017-10-23T18:30:56Z","title":"Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.08446","snapshot_observed_at":"2026-08-14T11:42:05.569147Z","title":"Many paths to equilibrium: Gans do not need to decrease a divergence at every step,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.569147Z"},"links":{"cited_paper":"/paper/1710.08446","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:2d72c9c7a01c51231130577cbc310d249e08a7a88be5543d1000a45691a08917","observation_id":"8c7f01b0-bce0-486f-875c-e146608cdc0c","resolution":{"observed_at":"2026-08-14T11:42:05.569147Z","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":"2026-08-14T11:42:06.972052Z","title":"Least squares generative adversarial networks,","venue":null,"work_id":"1bd2b742-7640-44b3-bb8e-fe4fa787b3fc","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.574257Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:4bff6458f8ed8ce0dc05af35f3a1a3036f8a991f8739b99f7f82e329b5ff0681","observation_id":"2a8dcc34-025e-4aba-831d-f117e8fb30f5","resolution":{"observed_at":"2026-08-14T11:42:06.977909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.948151Z","title":"Image-to-image translation with conditional adversarial networks,","venue":null,"work_id":"90b1a28d-bfe9-49fc-928f-0a0352452e63","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.579235Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:be19b2ac3e369b4b0093326baf0ee428ab44db85f7540730341527fb51afb757","observation_id":"5600b450-5af9-4c42-b5cb-1655a48d19bc","resolution":{"observed_at":"2026-08-14T11:42:06.954220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.927191Z","title":"Unpaired image-to- image translation using cycle-consistent adversarial networks,","venue":null,"work_id":"7d8810f2-f644-4c56-a0ce-12fa41d1778b","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.583983Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:b425e705b8980330c22cf01e642b3c665723c9dadd5e39049db7b3120042245b","observation_id":"58ae4e6f-9df6-4e6b-9de2-5e36d7ec24ed","resolution":{"observed_at":"2026-08-14T11:42:06.934125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.902826Z","title":"Toward multimodal image-to-image translation,","venue":null,"work_id":"c730e437-4356-4453-a71b-d72cd3a2cba5","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.588975Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:c600082b102c173a04f245ad1126b07e36ec72e21653c39eec48d4e6442d3b27","observation_id":"b25e86db-6ebf-4265-b098-2b885a6169ad","resolution":{"observed_at":"2026-08-14T11:42:06.911136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.879643Z","title":"Unsupervised image-to-image translation networks,","venue":null,"work_id":"d06bf4d8-4879-4b7c-a3a3-df258e52ec4f","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.593896Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:714c1cbe76fae724d337b9671e62b13cc861966276e261f5cfbaae3fdb408b9b","observation_id":"04c93e3d-8f06-4d3a-bd26-5330b6f416e6","resolution":{"observed_at":"2026-08-14T11:42:06.885463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.860184Z","title":"Multimodal unsupervised image-to-image translation,","venue":null,"work_id":"f3a8b63f-d52a-4e7a-9709-238d95c4be46","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.599027Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:af9f4a9fda8e5d05aad8573cf98bd88600d6a2d1c0c17f5a55ace2a9b20a5d16","observation_id":"4eb86805-3bdc-4338-849e-4491612d4091","resolution":{"observed_at":"2026-08-14T11:42:06.865879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.837254Z","title":"Towards instance-level image-to-image translation,","venue":null,"work_id":"7f6ab8ad-b260-446b-9394-b8da44de457b","year":2019},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.603889Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:19191329f5cd5119a60548fa322a619b9280ee6826e24a3966cd6a962f97327b","observation_id":"22c5ad0a-ea6a-4639-90e5-0c7c15b3ec88","resolution":{"observed_at":"2026-08-14T11:42:06.844585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.817534Z","title":"Image generation from scene graphs,","venue":null,"work_id":"ad34d73f-f668-42b1-bf9b-8e524b7ac444","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.609379Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:b843833e8ab05c84341a51f6e318faadb0d8a7071e89cca5daae6ff1e26e8692","observation_id":"468deefd-4efd-4940-8cab-ee0d587c686a","resolution":{"observed_at":"2026-08-14T11:42:06.823335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.796206Z","title":"Finding tiny faces in the wild with generative adversarial network,","venue":null,"work_id":"43120440-bf2a-40db-bf33-dc0a4872ef33","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.614235Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:acc7d229c9ac0434d2949594e039e740a0021471d5f84b0065f02ba11d7e3ad2","observation_id":"d3742cef-a19e-4ccc-8b59-7bfefa1883d1","resolution":{"observed_at":"2026-08-14T11:42:06.802280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.775339Z","title":"Net2net: Accelerating learning via knowledge transfer,","venue":null,"work_id":"78b1323d-02f7-4ea1-99af-fc58f789d52c","year":2016},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.619597Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:21f7d323bb21017233a2118e9de8eba8a250a614f4704723f02610caa3a2d39d","observation_id":"1746177a-cb80-46aa-a51f-05c15eda525e","resolution":{"observed_at":"2026-08-14T11:42:06.781758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1709.00513","last_updated":"2018-04-16T18:42:13Z","snapshot_observed_at":"2026-08-14T20:36:47.953556Z","submitted_at":"2017-09-02T01:03:08Z","title":"Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1709.00513","snapshot_observed_at":"2026-08-14T11:42:05.625157Z","title":"Training shallow and thin net- works for acceleration via knowledge distillation with conditional adversarial networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.625157Z"},"links":{"cited_paper":"/paper/1709.00513","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:f1fb73d06715f74a821efe2a07d9abf42326b3e8ec02ffe43b2c4d0e1327a460","observation_id":"34300875-1ae7-442f-8aa2-fefd7ee2bffe","resolution":{"observed_at":"2026-08-14T11:42:05.625157Z","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":"2026-08-14T11:42:06.751038Z","title":"Mean teachers are better role mod- els: Weight-averaged consistency targets improve semi-supervised deep learning results,","venue":null,"work_id":"7ec01f3e-b9ef-45fb-b5dd-269fe55d0ca8","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.630387Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:252d791ab67549c8e1dd783703c496a2ec2c8ef0a25ab1abaf46d451bb51e71d","observation_id":"b4726ad2-eb23-4f19-bbc8-78c72ae7cd8b","resolution":{"observed_at":"2026-08-14T11:42:06.759036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.719784Z","title":"Large scale distributed neural network training through online distillation,","venue":null,"work_id":"24ec7348-397c-45b5-965f-011510315d63","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.635036Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:b2a660359e3a9bcaf655b745c6e7b4b159e42c5c34e2da99e6e8faea6a7eded5","observation_id":"09d04c5d-00de-4c09-bc04-e4de2186dca9","resolution":{"observed_at":"2026-08-14T11:42:06.726798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.700137Z","title":"Darkrank: Accelerating deep metric learning via cross sample similarities transfer,","venue":null,"work_id":"3a946db5-4b73-455b-ab4b-a31c4b4d944d","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.640620Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:7c4e8bac268acf05633f84e31d666f0a0e0055c22cf0afa6526586781db57f64","observation_id":"5bec2de2-a7d4-44a1-a518-8d0bcf571422","resolution":{"observed_at":"2026-08-14T11:42:06.706081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.681310Z","title":"Relational knowledge distillation,","venue":null,"work_id":"162e6511-e999-405a-852d-b7fa0b776050","year":2019},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.646103Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:6b78a8bbc5eb3ddc011c817ef6785fff8dffe7b0f49ab1dda464d27ed01fcfa6","observation_id":"6d6e9483-581f-427e-a0cf-38cb7352593c","resolution":{"observed_at":"2026-08-14T11:42:06.687177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.03233","last_updated":"2018-12-14T15:29:53Z","snapshot_observed_at":"2026-08-14T18:02:26.082907Z","submitted_at":"2018-11-08T02:47:56Z","title":"Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.03233","snapshot_observed_at":"2026-08-14T11:42:05.651715Z","title":"Knowledge transfer via distillation of activation boundaries formed by hidden neurons,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.651715Z"},"links":{"cited_paper":"/paper/1811.03233","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:4dbbf627f8d486a6e2e25139c94ccb3242d15f1c00248580afd1dee620d89726","observation_id":"7cf23720-26bb-4ef3-aa59-10c35d785931","resolution":{"observed_at":"2026-08-14T11:42:05.651715Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.04770","last_updated":"2018-06-29T10:46:28Z","snapshot_observed_at":"2026-08-14T19:16:03.451808Z","submitted_at":"2018-05-12T19:48:50Z","title":"Born Again Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.04770","snapshot_observed_at":"2026-08-14T11:42:05.657793Z","title":"Born again neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.657793Z"},"links":{"cited_paper":"/paper/1805.04770","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:ff5595fbc295122595f8abcac4536af1f099e943f585b139ac22790da1b7b4ce","observation_id":"52546b84-cce6-4842-a41f-75dadb43269f","resolution":{"observed_at":"2026-08-14T11:42:05.657793Z","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":"2026-08-14T11:42:06.662142Z","title":"Revisiting knowledge transfer for training object class detectors,","venue":null,"work_id":"ede7b1b4-a1e2-4878-9144-96c2fdf01172","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.662764Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:35084a3a79d8cb85e4e9b908ddd7d2b3a2a269dc4fa911e11ad4db86ebec8e25","observation_id":"2e246503-d4aa-4286-8cc8-0e535e61e405","resolution":{"observed_at":"2026-08-14T11:42:06.668667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.639092Z","title":"Moonshine: Distilling with cheap convolutions,","venue":null,"work_id":"fc917d13-23f4-4b6f-a74b-f2dd7d3bb9f3","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.668212Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:20a4518f3b96f8b8f773499616de5d53f81928006b2ce14e3b5c4c1762c6fca4","observation_id":"2297e50a-3c92-47a7-8592-f9c16b39cdd3","resolution":{"observed_at":"2026-08-14T11:42:06.647204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.618088Z","title":"Snapshot distillation: Teacher-student optimization in one generation,","venue":null,"work_id":"dee8d83e-f084-4eb5-adb5-f95605a1b156","year":2019},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.674406Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:533a6b7c38172b5c41be5aee1addaab8e63365dbea87fd6206a70e9a74e110b8","observation_id":"cc29057b-03ae-4182-86f5-7e225d565c7c","resolution":{"observed_at":"2026-08-14T11:42:06.624301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.598552Z","title":"Learning to learn from noisy labeled data,","venue":null,"work_id":"f081d949-73d4-428d-b424-34d99d055792","year":2019},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.679442Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:bacc571418e0a31b740d12e67b03709375889960e542392e5e233cca4ff7857d","observation_id":"a884225b-5520-4bed-9209-560bfe442de6","resolution":{"observed_at":"2026-08-14T11:42:06.604565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.580388Z","title":"Toward robustness against label noise in training deep discriminative neural networks,","venue":null,"work_id":"7266f772-29fe-473d-91f3-9e2d68cdc0c6","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.684733Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:da19fc0f04bc9adb887da51f216d17cdcc221f15d7f9adc0558421c2a366c876","observation_id":"4e963bbf-ec9f-432c-9ffc-db31cdc4e22d","resolution":{"observed_at":"2026-08-14T11:42:06.586552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.560460Z","title":"Learning from massive noisy labeled data for image classification,","venue":null,"work_id":"326999b6-a2ee-4370-9fab-a0918f5055e1","year":2015},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.689418Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:690a03ea045b675d1ba0f5bcebce2e38e78557998542ffb30dcdb416d99068ab","observation_id":"7b8cdec6-92c0-408e-8b6f-20f84c0b74f1","resolution":{"observed_at":"2026-08-14T11:42:06.566727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05055","last_updated":"2018-08-13T21:27:39Z","snapshot_observed_at":"2026-08-14T20:03:50.399672Z","submitted_at":"2017-12-14T00:02:37Z","title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05055","snapshot_observed_at":"2026-08-14T11:42:05.695303Z","title":"Mentornet: Learning data-driven curriculum for very deep neural networks on corrupted labels,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.695303Z"},"links":{"cited_paper":"/paper/1712.05055","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:8d4daf2001e7c23a71f78af3fdb5b75cbd5aba27de2dc2dd166afed0364ce644","observation_id":"f9c880d4-18f8-488e-9feb-1fefcffb63e4","resolution":{"observed_at":"2026-08-14T11:42:05.695303Z","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":"2026-08-14T11:42:06.541460Z","title":"Training deep neural-networks using a noise adaptation layer,","venue":null,"work_id":"d8443fe6-c110-4efe-b363-a08e7f092d77","year":2016},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.700310Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:2858864af61cebe4b22ccf96bc36f13ef8f1143b7894da0eb8bcf9863fec7d27","observation_id":"c1446cf6-4e5e-434d-a00a-f7b1e7c86cb4","resolution":{"observed_at":"2026-08-14T11:42:06.547064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.518402Z","title":"Learning from noisy large-scale datasets with minimal supervision,","venue":null,"work_id":"a508e219-c057-4004-9f3d-8426524702fd","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.705771Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:4cf7f227ebf52a23b5f723abf434fc713a7ba7499865b83d2f3653b3220ced15","observation_id":"5af1930c-17f7-4b74-8703-0698087df9cd","resolution":{"observed_at":"2026-08-14T11:42:06.525114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.2080","last_updated":"2015-04-10T16:44:00Z","snapshot_observed_at":"2026-08-14T23:31:07.371995Z","submitted_at":"2014-06-09T05:45:12Z","title":"Training Convolutional Networks with Noisy Labels","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.2080","snapshot_observed_at":"2026-08-14T11:42:05.710584Z","title":"Training convolutional networks with noisy labels,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.710584Z"},"links":{"cited_paper":"/paper/1406.2080","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:98a260aa197943ff76ed709052b99fdbe77c185cbd0752b68498fb76c7bf130c","observation_id":"bc8ad90a-6b66-4c08-b02d-8c709edc8d5f","resolution":{"observed_at":"2026-08-14T11:42:05.710584Z","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":"2026-08-14T11:42:06.498328Z","title":"Making deep neural networks robust to label noise: A loss correc- tion approach,","venue":null,"work_id":"5d443b77-970e-4a39-b082-2608987e4f0a","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.715850Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:a4f88ef8aba5793aa4d464404d9ba0fd245632e78deb0b8a0c70f5ac452b1133","observation_id":"4acad293-1d19-4045-a393-6f4af633b6e7","resolution":{"observed_at":"2026-08-14T11:42:06.505130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.09050","last_updated":"2019-05-05T15:21:40Z","snapshot_observed_at":"2026-08-15T06:56:38.039192Z","submitted_at":"2018-03-24T03:41:59Z","title":"Learning to Reweight Examples for Robust Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.09050","snapshot_observed_at":"2026-08-14T11:42:05.721401Z","title":"Learning to reweight examples for robust deep learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.721401Z"},"links":{"cited_paper":"/paper/1803.09050","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:2a31f6555e3998cf88d967f29eda9594474bc5a060a90b71ce8a1defcbc09292","observation_id":"3802cc0b-4f26-4b64-9f12-d3ae5f1ad21b","resolution":{"observed_at":"2026-08-14T11:42:05.721401Z","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":"2026-08-14T11:42:06.478176Z","title":"Cleannet: Transfer learning for scalable image classifier training with label noise,","venue":null,"work_id":"8477987b-7670-413d-979d-313f96124c22","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.729877Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:1423d17e736a8605c1f1e84bfe3cf19261e19bcea72b4cbba8b2131335ec7683","observation_id":"57136043-42fc-4c71-adf8-301c95850fcd","resolution":{"observed_at":"2026-08-14T11:42:06.484530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.458777Z","title":"Classification with noisy labels by importance reweighting,","venue":null,"work_id":"588ecacd-b02d-433b-9128-7c4ed4a74c00","year":2015},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.735295Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:3cbf4c6ce2e2be90e99e4cc48c8a258d6d40c6f7b44b911d4d72eee62a90632f","observation_id":"0db50957-2826-45dd-b6fc-fa6b76cf9b59","resolution":{"observed_at":"2026-08-14T11:42:06.464813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:05.740592Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.740592Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:79bd35811017aba86ee95bf7559f1da7edc2044f3cbd2de1ff8a95670001a3d0","observation_id":"d6615b52-6033-48ea-b030-c7d6d22de6af","resolution":{"observed_at":"2026-08-14T11:42:05.740592Z","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":"2026-08-14T11:42:06.424541Z","title":"Reading digits in natural images with unsupervised feature learning,","venue":null,"work_id":"8233cc08-048a-4d11-90a2-1ab102a258d6","year":2011},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.746342Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:f8d8169e32f6d357f8c1ee1fd2d56c1d99c3f7883e1a68fb6e2c6d97815db1df","observation_id":"03fb3cde-fb6a-4d4a-81fb-cf966b2691ab","resolution":{"observed_at":"2026-08-14T11:42:06.431028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:05.751412Z","title":"Very deep convolutional net- works for large-scale image recognition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.751412Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:a503379239163f916dec355dc14d6ae71c2f2cc0b87cb39aa522e3da69ac0a3b","observation_id":"5a1fec6e-dbeb-4b7b-80ad-241eeabaa1bb","resolution":{"observed_at":"2026-08-14T11:42:05.751412Z","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":"2026-08-14T11:42:05.757159Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.757159Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:3dc2a5cfc555441f03772fbe3a6bf8d2aa71a84c82f7766e075f233d0641c395","observation_id":"3168f1f6-1991-4f8d-a8f6-28a7ae69c77c","resolution":{"observed_at":"2026-08-14T11:42:05.757159Z","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":"2026-08-14T11:42:05.762566Z","title":"Densely connected convolutional networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.762566Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:45e6e09612ac57cb2878f37403b5e03d8f8377bf924434eb4413cf71b37026ea","observation_id":"07eeae1f-bd32-41d7-be8e-cf2d6fd8fc7b","resolution":{"observed_at":"2026-08-14T11:42:05.762566Z","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":"2026-08-14T11:42:05.768062Z","title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.768062Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:50cf2b5acf222925a80a77eca06a7b1c55545d8d9743281eda5aec39430e6de7","observation_id":"fecf5f7b-4acb-475e-be7d-43b619db0a4e","resolution":{"observed_at":"2026-08-14T11:42:05.768062Z","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":"2026-08-14T11:42:05.773707Z","title":"Automatic differ- entiation in pytorch,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.773707Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:854a41dda6019bb07af473949df45a4a66663ca061a806cbe5aebdd97a2e0ebe","observation_id":"b1864cf7-8e99-452f-8501-70249f5f0e93","resolution":{"observed_at":"2026-08-14T11:42:05.773707Z","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":"2026-08-14T11:42:06.339813Z","title":"Deeply-supervised nets","venue":null,"work_id":"871ba1c1-852c-4d25-93bf-58e89a4afed6","year":2015},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.779426Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:62aaa8186380fe99bb9cd87983bcfdc18dd46a6af949563be929749d24932683","observation_id":"4f36b49f-72b3-445e-a9d9-f9ff5be6e1e5","resolution":{"observed_at":"2026-08-14T11:42:06.347179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.318279Z","title":"Fitnets: Hints for thin deep nets,","venue":null,"work_id":"7193352d-bd79-42bf-a28c-a683cf824e96","year":2015},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.785627Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:aef015c54b04ecc9e1f8af756460295cff9439154065c5b2130e91ef04457808","observation_id":"24e14ad7-fa1d-41e5-a6e4-1661245d044a","resolution":{"observed_at":"2026-08-14T11:42:06.324562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07648","last_updated":"2017-05-26T18:53:56Z","snapshot_observed_at":"2026-08-14T21:55:53.547322Z","submitted_at":"2016-05-24T20:28:53Z","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.07648","snapshot_observed_at":"2026-08-14T11:42:05.790945Z","title":"Fractalnet: Ultra-deep neural networks without residuals,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.790945Z"},"links":{"cited_paper":"/paper/1605.07648","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:00f5cfdd942500c0ff6f4985456ae51b5faab5f44e53fb04e698d38de7b92e68","observation_id":"154605b1-5d6f-4f24-8f7b-fb26433f9ab3","resolution":{"observed_at":"2026-08-14T11:42:05.790945Z","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":"2026-08-14T11:42:06.295414Z","title":"Learning efficient convolutional networks through network slimming,","venue":null,"work_id":"63aaba73-14e0-4de9-8cd8-eceb37a75b91","year":2017},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.796434Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:a5ceeed0acbf436d015685cd1eadadc637bd0c766d7f3ff9598150dbb805a2a8","observation_id":"e0530f8f-18fc-4436-8378-1377cd1a2443","resolution":{"observed_at":"2026-08-14T11:42:06.301406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.277655Z","title":"Maxout networks,","venue":null,"work_id":"22f3f04f-9a2c-4b5f-9276-2ea0f9bdc7d8","year":2013},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.803090Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:cd484bf7768ddd53b39d18933715ef9ff47af6b6e7a592181b094caf642d6cdb","observation_id":"a45a7ea4-de44-4d71-a5d6-4182bd45b721","resolution":{"observed_at":"2026-08-14T11:42:06.282847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.259683Z","title":"Imagenet classifi- cation with deep convolutional neural networks,","venue":null,"work_id":"c509b2e2-b248-4b55-a800-324c96bdc31e","year":2012},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.808985Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:c3c26c64e91f5f05e5bbd0d89f6a9a28dacde3e82438cfd56675e3251cf9ed92","observation_id":"62deac91-5a8e-4dac-9135-a75c05f21e67","resolution":{"observed_at":"2026-08-14T11:42:06.265473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-14T11:42:05.814363Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.814363Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:51423edb6ff65c6267632378b9ce874d5c0edea66b6d89f108b968e25bbdc51f","observation_id":"2180c811-aeb9-42bf-830e-9e57771a641d","resolution":{"observed_at":"2026-08-14T11:42:05.814363Z","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":"2026-08-14T11:42:06.241322Z","title":"Going deeper with convolutions,","venue":null,"work_id":"0c7e328e-e1c6-4d07-874f-b3c36836bf64","year":2015},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.819818Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:75768c54aa38386ebf36d894823e3a70d144036e7ce348b1e3d1d8ae2e1c009a","observation_id":"40a80775-9c8f-4b65-a5d0-33c96575d03a","resolution":{"observed_at":"2026-08-14T11:42:06.247114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-14T11:42:06.219628Z","title":"mixup: Beyond empirical risk minimization,","venue":null,"work_id":"b40af1bb-86e0-4089-9447-c4091f0f1b15","year":2018},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.825061Z"},"links":{"citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:74835fc6f601d79b26d0125bb2f74b79b5be6475f8715fb652e599a8bad3a5e9","observation_id":"98f35d09-94ef-44cf-8e00-b9a10d0f3c36","resolution":{"observed_at":"2026-08-14T11:42:06.227596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.04899","last_updated":"2019-08-07T07:15:29Z","snapshot_observed_at":"2026-08-14T16:33:23.205222Z","submitted_at":"2019-05-13T08:10:22Z","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.04899","snapshot_observed_at":"2026-08-14T11:42:05.833857Z","title":"Cutmix: Regularization strategy to train strong classifiers with localizable features,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.833857Z"},"links":{"cited_paper":"/paper/1905.04899","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:905e926cc707204ee13f3d073725ba798c48f95d7df90502f09a248a6b29dafa","observation_id":"0b0f64a8-ede5-48e1-8e5f-fd5b445f9220","resolution":{"observed_at":"2026-08-14T11:42:05.833857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-08-14T11:42:05.840537Z","title":"Sgdr: Stochastic gradient descent with warm restarts,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-14T11:42:05.840537Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/1908.08520"},"observation_digest":"sha256:2a94f816a1ccc314e21909f9df1479744909ed2d2b45952d2a77183737121607","observation_id":"e4fc13b8-a58d-4271-9e32-278cd15bd0ea","resolution":{"observed_at":"2026-08-14T11:42:05.840537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.08520","last_updated":"2019-08-22T17:51:16Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T07:49:25.764791Z","submitted_at":"2019-08-22T17:51:16Z","title":"Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement"},"reference_resolution":{"displayed":76,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":0,"verified_fuzzy":54},"total_outbound_references":76},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 76 of 76 outbound references and 0 inbound Pith citation observations for arXiv:1908.08520."}