{"as_of":"2026-08-15T01:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:34a4c5eae7ba6cb6ef9927df2b6e1a57f4486e1cd3460dd19a2f90e82589dbbf","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T11:04:11.290295Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.09822/citation-record","integrity":"/paper/1908.09822/integrity","json":"/paper/1908.09822/citation-record.json","paper":"/paper/1908.09822"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:12.132387Z","title":"Semi-supervised logistic regression","venue":null,"work_id":"73de5582-097d-47a1-9bba-cfe4bf73170b","year":2002},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:10.997127Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:30b0ff3ab9bff0402e95eaedadc6ca8d7c82c80ec8b81f0c5b41f1b5e164f701","observation_id":"3f3ed13e-da30-4afb-86b4-cf55197f30a6","resolution":{"observed_at":"2026-08-14T11:04:12.136778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.02641","last_updated":"2018-05-07T17:52:42Z","snapshot_observed_at":"2026-08-14T19:17:57.386021Z","submitted_at":"2018-05-07T17:52:42Z","title":"Label Refinery: Improving ImageNet Classification through Label Progression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.02641","snapshot_observed_at":"2026-08-14T11:04:11.001014Z","title":"Label refinery: Improv- ing imagenet classification through label progression","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.001014Z"},"links":{"cited_paper":"/paper/1805.02641","citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:82623696b2c2dcca25e4beb60bd0126e94778845dac0685af488758715cf4659","observation_id":"a5e9224e-92ca-41df-85ff-b9c8bc77a514","resolution":{"observed_at":"2026-08-14T11:04:11.001014Z","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":"2026-08-14T11:04:12.119559Z","title":"Convex optimiza- tion","venue":null,"work_id":"abddc833-d67b-40fb-8fd2-d26e7ce36fd5","year":2004},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.005193Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:5d14ee874edb2c746fe478622dd22824ef1c07ed41f200e26763b9473b4232b6","observation_id":"dc0b7430-2a7b-442a-a760-6a1987403efe","resolution":{"observed_at":"2026-08-14T11:04:12.124013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:12.106445Z","title":"Open set domain adaptation for image and action recognition","venue":null,"work_id":"3aeded0d-b738-46df-bec1-6e7e831baac8","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.010408Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:2da777afa802e1ab242fd0fe38da1a02c9c5334fa0cee91cdf6cafcab8e0a00f","observation_id":"6e628762-a2f1-4511-bf97-72b3d657d909","resolution":{"observed_at":"2026-08-14T11:04:12.110890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:12.093590Z","title":"Progressive feature alignment for unsupervised do- main adaptation","venue":null,"work_id":"d20d950d-b5f1-4880-84c8-5b60c4e7e115","year":2019},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.014679Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:954046be5199fc16ce5460bf5cbb99dd7cc661b8e68c3617f6e21cd971c6bf1c","observation_id":"31fd320d-a299-4f53-85f7-243c672794d1","resolution":{"observed_at":"2026-08-14T11:04:12.097949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:12.079815Z","title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolu- tion, and fully connected crfs","venue":null,"work_id":"5632748e-c8ea-42e9-8b4e-d23fe8705ef6","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.019077Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:4110baf04f115ab0684127d07fc21ae6b8dce916b4aced414cb3fa9256d4ef84","observation_id":"f95c11bc-6691-4836-9246-13b5075a64e0","resolution":{"observed_at":"2026-08-14T11:04:12.084068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1512.01274","last_updated":"2015-12-03T22:49:21Z","snapshot_observed_at":"2026-08-14T22:20:04.562155Z","submitted_at":"2015-12-03T22:49:21Z","title":"MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.01274","snapshot_observed_at":"2026-08-14T11:04:11.023724Z","title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems.arXiv preprint arXiv:1512.01274, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.023724Z"},"links":{"cited_paper":"/paper/1512.01274","citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:fafc09251c31fc17d98078e890b8fb7300715dfb915a38e4af227019f2f2da85","observation_id":"5a0dfc3a-93f8-4694-a683-d3f27a340de2","resolution":{"observed_at":"2026-08-14T11:04:11.023724Z","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":"2026-08-14T11:04:12.067336Z","title":"Learning semantic segmentation from synthetic data: A ge- ometrically guided input-output adaptation approach","venue":null,"work_id":"b0efadce-0265-4424-af70-3486c834291b","year":2019},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.028146Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:68791b13b00b637073f565592137d42d3875e9095f85f8def89af3619691c372","observation_id":"c009742b-f022-4b4b-ac52-735e2fc29e01","resolution":{"observed_at":"2026-08-14T11:04:12.071403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:12.055574Z","title":"Domain adaptive faster r-cnn for object de- tection in the wild","venue":null,"work_id":"c7cfca7c-764d-4705-867a-8cbdc17dc0e8","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.032751Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:4d7b814adc255b48914428bb04b9ac04ecf8ee6cb283471c1cb6162eb8c23698","observation_id":"2b9d297c-3f67-4ca4-81a7-16df7ff6e23f","resolution":{"observed_at":"2026-08-14T11:04:12.059665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:12.041220Z","title":"No more discrimi- nation: Cross city adaptation of road scene segmenters","venue":null,"work_id":"a9ab2694-c1cc-4751-8f4a-f25e9557e4b8","year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.036883Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:fbfe43a51d2ee28979ff37e32548a8fe511b35fc39769a5d03baa7eb2f63bd05","observation_id":"60bbc543-509e-4ac6-b499-5d5f05dac84a","resolution":{"observed_at":"2026-08-14T11:04:12.047252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.041535Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.041535Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:e507ead9096f21bea618a2dcd79009c6c8a1a9c1436c19d27241ea9df03b24ef","observation_id":"57002139-f85a-4102-860b-b7b105003ccf","resolution":{"observed_at":"2026-08-14T11:04:11.041535Z","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":"2026-08-14T11:04:11.046707Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.046707Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:7b64bb4bc0e13c597220ac875427bda45a84ef10d18f46974ffea9e628dc261e","observation_id":"4f183bee-54b4-44df-a8f2-e2fd05c2e8c7","resolution":{"observed_at":"2026-08-14T11:04:11.046707Z","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":"2026-08-14T11:04:12.008754Z","title":"Domain styliza- tion: A fast covariance matching framework towards domain adaptation","venue":null,"work_id":"37dbb01e-d742-4558-8932-8e8c366a7cf2","year":2020},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.050782Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:4c267415a287e8c79d443c56b17593f6170ae1edf2d5fd8322895f1110436071","observation_id":"271726d1-54a3-4534-984b-bbfc630cad1b","resolution":{"observed_at":"2026-08-14T11:04:12.013558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.995608Z","title":"Self-ensembling for visual domain adaptation","venue":null,"work_id":"eb46c519-4b36-4b82-8d9d-5a3ac937e3e4","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.055620Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:290b77310a8f6a85d9bb5a9e5cb84bc8bace05e1088b7cff1c0dff92dd587e33","observation_id":"f28706b6-3294-4f37-8ca5-a6cbd6e5603f","resolution":{"observed_at":"2026-08-14T11:04:11.999777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.060970Z","title":"Unsupervised domain adaptation by backpropagation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.060970Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:f38d14ab68e4e9e1f1349fe24b0eb5e5c6e8e4f19df87be07f3a2ed5b0d29bde","observation_id":"454f14b2-db38-49cc-a197-787c3e61eedd","resolution":{"observed_at":"2026-08-14T11:04:11.060970Z","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":"2026-08-14T11:04:11.974517Z","title":"Domain-adversarial train- ing of neural networks","venue":null,"work_id":"9a0e3264-6003-434e-9f04-b3b5b301c89a","year":2016},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.065556Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:6665dfc123e70976101156c85477e069abcb4bcdc32bbea8fb7bba75cda499e3","observation_id":"586d5b01-0b6e-4a82-8a3b-8241ab143471","resolution":{"observed_at":"2026-08-14T11:04:11.978680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.960337Z","title":"DLOW: Domain flow for adaptation and generalization","venue":null,"work_id":"00089d35-58f5-4795-a1c0-789b9d6f56bd","year":null},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.069656Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:1358cda7748077271929197c72c47080c160281073f9928e6a7a30aef56eb02a","observation_id":"088a3787-26f3-4b5c-ae8b-34aa1ee7cdfa","resolution":{"observed_at":"2026-08-14T11:04:11.964420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.947529Z","title":"Deep Learning","venue":null,"work_id":"0c628355-8682-4def-bf67-bbf17a2982d0","year":2016},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.074085Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:92d84c237834392c82338b95057608b2a5e66ff505e973bca7b0a2f71f9b743c","observation_id":"5f036fba-f33b-49e6-a8cb-3de227dc2da6","resolution":{"observed_at":"2026-08-14T11:04:11.951669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.934925Z","title":"Semi-supervised learning by entropy minimization","venue":null,"work_id":"42e668cd-a1ec-478c-9a3e-de01ee950e67","year":2005},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.078236Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:ca851171c5ff5462f5324f8cc0f44da4b2a0734b6652f3ea039d6b4cda29b626","observation_id":"1203092f-b2c5-4310-9880-f416c0747ce3","resolution":{"observed_at":"2026-08-14T11:04:11.939394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.921457Z","title":"Weinberger","venue":null,"work_id":"3207a710-f5c0-4e83-ae43-66b74bc7ca65","year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.082948Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:5e14e282db2d1614cf93b0e28bf35bafc52622c47776b3dc25fde03747376985","observation_id":"bc770475-790b-4bcf-b85a-497bf49f34ab","resolution":{"observed_at":"2026-08-14T11:04:11.926351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.908191Z","title":"Unsupervised domain adaptation via calibrat- ing uncertainties","venue":null,"work_id":"e382322d-5abf-4f96-8606-42c18ab08452","year":2019},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.088013Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:8ff1dabc254bfff2f6e79277a46600cb4474a0cd37a1629b6ef02f8023ddddfd","observation_id":"56e72a30-c88d-445e-8a47-eba0234de78d","resolution":{"observed_at":"2026-08-14T11:04:11.912487Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.093226Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.093226Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:61a3388a95c1fcc7ec389b00e9ed3ac6d1b18689db03c870c6b65b1555df9e2b","observation_id":"3fa91c94-c728-463c-9a34-66262ce32f59","resolution":{"observed_at":"2026-08-14T11:04:11.093226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-14T22:57:08.956233Z","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":"2026-08-14T11:04:11.096839Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.096839Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:4a44294079c099f6699436b4c71ef70d26f207413822da347f0200f57297c447","observation_id":"0257e4d1-bcdc-47fe-94bb-aa092fc084b0","resolution":{"observed_at":"2026-08-14T11:04:11.096839Z","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":"2026-08-14T11:04:11.889554Z","title":"Cycada: Cycle-consistent adversarial domain adapta- tion","venue":null,"work_id":"6ded9177-f092-47b8-9f46-c5d818a06559","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.101621Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:c68395fe1c7240cef329ee3d47b865cf6a321b1801c36722acbc0ed05638883b","observation_id":"d6e1c5e4-e970-4b62-a41d-60ce41d80179","resolution":{"observed_at":"2026-08-14T11:04:11.893231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.105613Z","title":"Cross-domain weakly-supervised object de- tection through progressive domain adaptation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.105613Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:3c994b8ba9e7fc988b831ed55a6cd6d86e809c7a1cd14eae275eae9e877aea99","observation_id":"19e30cb8-3e47-42d0-97e0-57d0792883d4","resolution":{"observed_at":"2026-08-14T11:04:11.105613Z","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":"2026-08-14T11:04:11.869235Z","title":"Unsupervised visual domain adaptation: A deep max-margin Gaussian process approach","venue":null,"work_id":"17016d5f-408a-40e9-8b92-fff72735dfb2","year":null},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.110197Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:32abd2c7b31d9d3abcc2d5c04937138fac15afe1a0c20a15098e81b077484dbb","observation_id":"5f44928c-53d0-4aa2-a5fd-740ac5a8f3d2","resolution":{"observed_at":"2026-08-14T11:04:11.873319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.856819Z","title":"Temporal ensembling for semi- supervised learning","venue":null,"work_id":"2b24e2d8-d9d8-4e1e-ac9c-2127b5be7116","year":2016},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.115750Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:645df75eda5ce86a615efda9d43496a629f9a96b88289ea7e0a2e41ea42c6ba0","observation_id":"5dd90c2d-9008-4f54-af04-7807347e8027","resolution":{"observed_at":"2026-08-14T11:04:11.860579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.843855Z","title":"Sliced wasserstein discrepancy for unsu- pervised domain adaptation","venue":null,"work_id":"57860d65-9b0a-43d5-bad2-889520bbb836","year":2019},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.120103Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:0d184a1f98e3ea05c07de37300cda1fdccfb621a01f5a5989479091d120aba51","observation_id":"b6638d44-f591-47ac-a44f-872b434a640f","resolution":{"observed_at":"2026-08-14T11:04:11.848636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.829774Z","title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","venue":null,"work_id":"30d0dde1-9469-402a-8f62-c666036d78a8","year":2013},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.124553Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:1675822334b8cbc2379acaf665d8cedf64944ffd08dec0bb224eb5214a89c636","observation_id":"8a392608-e325-4c00-a32b-5719154cefa8","resolution":{"observed_at":"2026-08-14T11:04:11.834520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.128558Z","title":"Microsoft COCO: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.128558Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:a2063b159d9eb57ccad4e1a978f23ca410055fdd51df7720a28482770573f719","observation_id":"fdf1d454-9348-4e4d-b8a4-021bd43a561d","resolution":{"observed_at":"2026-08-14T11:04:11.128558Z","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":"2026-08-14T11:04:11.808943Z","title":"Feature-level franken- stein: Eliminating variations for discriminative recognition","venue":null,"work_id":"79db209c-bc62-49f5-a3e4-604cb819fb21","year":2019},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.132796Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:59ec023e8bf712172f366fdd88f9d6848a61bf8cb88d07fbf080fa4ba43d42e9","observation_id":"3e8da626-537f-4982-85ab-901191ef1b21","resolution":{"observed_at":"2026-08-14T11:04:11.813451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.796936Z","title":null,"venue":null,"work_id":"ac97e358-d4bf-4e04-ae97-446da1559c90","year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.137425Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:74a99fdc894c8ba974bcb2ebecd045f0335e909a934ad15c94e0f5aa6aabe845","observation_id":"e8328cc0-a287-4452-8551-125048a22a5b","resolution":{"observed_at":"2026-08-14T11:04:11.800693Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.784922Z","title":"Learning transferable features with deep adaptation networks","venue":null,"work_id":"046c9ebc-be59-4e22-9756-61bcbd9e93b9","year":2015},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.141496Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:7eddf83670cb41080a0482133c6e6dabd137e18ec512c7dd58f6bcb2cef99973","observation_id":"606bc4f8-6040-47ac-80b5-6dfc5696aad1","resolution":{"observed_at":"2026-08-14T11:04:11.788991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.773373Z","title":"Conditional adversarial domain adapta- tion","venue":null,"work_id":"bd96adc1-c247-45d0-90d9-4094c1a58690","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.147290Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:4f7f4712140408f6f213bd137eaaddbe92beff17f5127f451b97298a84703ce9","observation_id":"a7088f9e-7b0b-42da-b8f3-827cdd13ee4d","resolution":{"observed_at":"2026-08-14T11:04:11.777497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.759560Z","title":"Unsupervised domain adaptation with residual trans- fer networks","venue":null,"work_id":"16758bed-357a-4f2a-b59f-6e284b514ed0","year":2016},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.152265Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:86bf4b9018fc28a396a280ac487f83a1c2d43fbdfd4dafb5faebaf5cd1db2739","observation_id":"24ae4aa1-a5f3-40a9-8116-ad7f9ab8e0bd","resolution":{"observed_at":"2026-08-14T11:04:11.763959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.746039Z","title":"Deep transfer learning with joint adaptation net- works","venue":null,"work_id":"3b4912d9-e012-4d05-84af-3e35551d2a02","year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.158685Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:35880844443c12f7a76d6901cdf7706611e3b1581967c14c9a48348a8baabbc2","observation_id":"5bcb0a72-7705-48f2-9503-de84a923ffb7","resolution":{"observed_at":"2026-08-14T11:04:11.750459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.732568Z","title":"Smooth neighbors on teacher graphs for semi-supervised learning","venue":null,"work_id":"fec46c9a-1151-402b-ab77-d30bd5718c5c","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.163106Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:4bb64820eaab709eee379b412fac15c7623a731e7299f919d803b5ecf71be8c5","observation_id":"28662ff9-6b7a-4038-bf8e-9c1a7834fb21","resolution":{"observed_at":"2026-08-14T11:04:11.736939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.719413Z","title":"Image to image translation for domain adaptation","venue":null,"work_id":"28c848de-1e06-4b69-a41d-fe019cea6b7e","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.167523Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:11939ee030034853de6992dbe70b386bb446258b2300d5e64957557ea97668c4","observation_id":"a0a9f460-43fe-483b-a4ad-646e42a0788b","resolution":{"observed_at":"2026-08-14T11:04:11.724082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.706471Z","title":"Learning with noisy labels","venue":null,"work_id":"93b83dfb-3485-4d46-9a71-0efec4efc7e5","year":2013},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.172432Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:9e2ec1073bc93277ce2c51357e1ce0939b4401beea8a6887ab91c6f30ffd4475","observation_id":"280a6131-4070-4839-9ff0-fc2759a8ccce","resolution":{"observed_at":"2026-08-14T11:04:11.710533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.693121Z","title":"Open set domain adaptation","venue":null,"work_id":"41742772-414d-4042-80e2-48ecad3ede38","year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.175810Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:f91a5ce6a757261933a975a080b9c0d4e725b57fb3b76b6352d9dc10718bed60","observation_id":"c3a806e7-87db-4bc1-8cfe-cf8349e0167e","resolution":{"observed_at":"2026-08-14T11:04:11.697146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.179640Z","title":"Automatic differentiation in pytorch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.179640Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:a8b561d8eb863c92356742c4b4d4ae8079b8d01cc89dbbd8306b827b862fcbea","observation_id":"d55e6686-c313-4b15-a0b8-8d626df87791","resolution":{"observed_at":"2026-08-14T11:04:11.179640Z","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":"2026-08-14T11:04:11.674126Z","title":"Visda: A synthetic-to-real benchmark for visual do- main adaptation","venue":null,"work_id":"203526d3-14b8-4ac6-b79e-ce5dd309b54b","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.182927Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:afab05d3d8a85afca8c3c6ef4fa997c56db933c0d549ef2de5ef13ecc28acfd1","observation_id":"ddb0178b-2d03-45f5-a20c-1acb191b98c0","resolution":{"observed_at":"2026-08-14T11:04:11.677604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.662863Z","title":"Regularizing neural networks by penalizing confident output distributions","venue":null,"work_id":"50e00735-8677-42ec-8f53-a41ffd446755","year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.186204Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:4488cfca3aee51978a4bf6fb2f3ea48f01d4ae723d395ee75da0a7a5395ddc6a","observation_id":"a34f951a-48c8-4dec-ab1c-7e72af75f60d","resolution":{"observed_at":"2026-08-14T11:04:11.666881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.652253Z","title":"Unsupervised domain adaptation with similarity learning","venue":null,"work_id":"4a6f4220-13e1-487e-a963-a854e8a17faa","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.189742Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:b2cf8a75dc38eab3171c6e460f1e7be63e9650cdace2717e56fb6ab0eee82f22","observation_id":"50bd8bfa-64f6-41c8-97d4-2fbb080b8659","resolution":{"observed_at":"2026-08-14T11:04:11.656072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.640212Z","title":"Train- ing deep neural networks on noisy labels with bootstrapping","venue":null,"work_id":"a8eb77a0-c41d-4b20-bfcc-52d74cab3d12","year":2015},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.193557Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:693823c3d762ae47d5c0560bccb327e0ea569e6180ad83b9704bf368422de4c7","observation_id":"4b227bbe-0c3e-48c1-a118-80c0f074fa61","resolution":{"observed_at":"2026-08-14T11:04:11.645259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.627786Z","title":"Playing for data: Ground truth from computer games","venue":null,"work_id":"a983845d-d623-4603-91d5-cd4e13b4dc4d","year":2016},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.197698Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:ed6b056c79c74b649d67e7285171f7fe342a9e632f4f0133335e981bf9c0b449","observation_id":"362bfe26-a16a-4ce2-8751-442d97a4d7ef","resolution":{"observed_at":"2026-08-14T11:04:11.632725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.616110Z","title":"The SYNTHIA dataset: A large collection of synthetic images for semantic segmen- tation of urban scenes","venue":null,"work_id":"7203fc43-eb9b-4fbd-aa92-01fa9744ed60","year":2016},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.201372Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:62f53c11ee58957c544b7b0715ecb354069f4944e5ab80b8f38076a9d56c6f07","observation_id":"48793531-5a3e-4206-b071-5a9a0ecfae31","resolution":{"observed_at":"2026-08-14T11:04:11.620155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.603828Z","title":"Adapting visual category models to new domains","venue":null,"work_id":"8b67fb89-1cd9-43f3-9bb9-54da4b1ad2c9","year":null},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.205085Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:b214d4bd20698319e193d1b1c0817ac34f4fcbeb4508ab9b220ab1b85c175ddb","observation_id":"979905bf-47e0-4e16-bfab-6ee28ad7c0c7","resolution":{"observed_at":"2026-08-14T11:04:11.608148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.592234Z","title":"Asymmetric tri-training for unsupervised domain adaptation","venue":null,"work_id":"ea6458dc-c312-4b01-a2f2-4cc32a831a9c","year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.209765Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:8bbac5d82e092db781134c42ad87df5eefa8f975eb56051c1e60acc426cc8f72","observation_id":"65bc478e-7e8b-4ea8-a01a-3d469b768a99","resolution":{"observed_at":"2026-08-14T11:04:11.595908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.581978Z","title":"Adversarial dropout regularization","venue":null,"work_id":"94cc87ec-d059-4570-8528-2ea86b5c5968","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.213688Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:a6253ce066243e96bc7161bedfedc40914e7900f744c730782b6469d28d9e10c","observation_id":"2983b5f8-9a1b-4594-bdd2-ddbc7b65f3d3","resolution":{"observed_at":"2026-08-14T11:04:11.585218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.569028Z","title":"Maximum classifier discrepancy for unsuper- vised domain adaptation","venue":null,"work_id":"be83f02e-a958-4042-8bfb-266d56ce3178","year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.217439Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:93d2254428f7a44c104d62e4558bb6f73feb0931791fd04e611d622ea1c0613a","observation_id":"0963cecc-8fdf-42c0-b3c9-f3b2530e9300","resolution":{"observed_at":"2026-08-14T11:04:11.573448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.556245Z","title":"Open set domain adaptation by backpropa- gation","venue":null,"work_id":"aed06d58-f2ed-4ce4-80aa-6b3ea960760b","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.221627Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:1cffcf8574823bf083c946e335dedde0839d1ac1a4b696612ecb4d5c188f3bb0","observation_id":"1f7edc46-6ae0-49c2-a15f-caa12805a3ee","resolution":{"observed_at":"2026-08-14T11:04:11.560623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.543618Z","title":"Generate to adapt: Aligning domains using generative adversarial networks","venue":null,"work_id":"441b4a09-2ed1-4d01-8d77-5e2945315cce","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.225742Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:720a87428ea0fccf01868b9e0e5558a7eea71233907a6e7f15438394b56c5f74","observation_id":"c596d32b-cda0-4ef3-8d8e-582bf7d1c5ce","resolution":{"observed_at":"2026-08-14T11:04:11.548028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.530116Z","title":"A dirt-t approach to unsupervised domain adaptation","venue":null,"work_id":"0b888f60-52e8-4209-97fc-55ed28216d85","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.229551Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:e18cff7d3e9965566490b2e38c719f09a26a9357b8f07a76f6233c420269e129","observation_id":"d638c38b-ff61-4a8d-b241-9bfd102f2911","resolution":{"observed_at":"2026-08-14T11:04:11.534723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-14T11:04:11.233330Z","title":"Training convolutional networks with noisy labels","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.233330Z"},"links":{"cited_paper":"/paper/1406.2080","citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:957acadc1fe104e387e6d8b15308f2b5c376bcd861a25c5537a40ff7b2626a1f","observation_id":"453ad21f-af74-4bf3-a111-1ad9eae1a921","resolution":{"observed_at":"2026-08-14T11:04:11.233330Z","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":"2026-08-14T11:04:11.517233Z","title":"Deep coral: Correlation alignment for deep domain adaptation","venue":null,"work_id":"57f5842b-e6a5-425e-971b-b60e1b96bd74","year":2016},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.237706Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:e7f90b9519e38400b38185c7c14ab4d62370f73aff911c83522ef7975ae5947a","observation_id":"7df3e681-d4b4-44b0-9ab7-1e1fafa2e007","resolution":{"observed_at":"2026-08-14T11:04:11.521778Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.503975Z","title":"Rethinking the inception ar- chitecture for computer vision","venue":null,"work_id":"91375ea9-fc98-4f42-a705-2d119b723334","year":2016},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.244114Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:166666100a34c26878961b642f23758f026b48e16f8c6e444f21811079a14d84","observation_id":"ca87a5fe-7e51-403d-97ba-9132311b61f4","resolution":{"observed_at":"2026-08-14T11:04:11.509054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.248071Z","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.248071Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:2fb7af75b6adc7fea15ef2c4c7f0672a6c4f386a2fc49eeb792b1e34f639f693","observation_id":"c577e7cb-9424-4853-8823-c381b9aea630","resolution":{"observed_at":"2026-08-14T11:04:11.248071Z","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":"2026-08-14T11:04:11.485531Z","title":"Self-labeled techniques for semi-supervised learning: taxon- omy, software and empirical study.Knowledge and Informa- tion Systems, 2015","venue":null,"work_id":"afc8303e-eaf7-4cb0-95af-65594856cc82","year":2015},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.252090Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:0fa966fef5e98b3ba529de3b6d77dd302fd90b32879d6c2d6d71e925a780fc2f","observation_id":"f0e4230a-26a8-457d-8ded-d258d572678f","resolution":{"observed_at":"2026-08-14T11:04:11.489873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.473024Z","title":"Learning to adapt structured output space for semantic seg- mentation","venue":null,"work_id":"9441f329-a8f2-4566-85ef-91442e92873c","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.256891Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:0d174e07ea107231b1487942dc4809e6b11fd748f8e61c179fcaede636055dc9","observation_id":"0104c046-74e0-4cf5-ae49-16f21abf149b","resolution":{"observed_at":"2026-08-14T11:04:11.477375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.460817Z","title":"Adversarial discriminative domain adaptation","venue":null,"work_id":"f9d839f2-37ec-49fd-aff3-0d9ad699e158","year":null},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.260862Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:82852a7984e0252e462ffb9ef5cdd7e10a85000854d1034cfc6ca947dd77aed0","observation_id":"ba503377-a96e-4ea8-918d-55d48286384d","resolution":{"observed_at":"2026-08-14T11:04:11.465122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.3474","last_updated":"2014-12-10T21:20:54Z","snapshot_observed_at":"2026-08-14T23:08:06.157493Z","submitted_at":"2014-12-10T21:20:54Z","title":"Deep Domain Confusion: Maximizing for Domain Invariance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.3474","snapshot_observed_at":"2026-08-14T11:04:11.265452Z","title":"Deep domain confusion: Maximizing for domain invariance","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.265452Z"},"links":{"cited_paper":"/paper/1412.3474","citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:0ef1c5cd222b47692f835a90c6de1730d44358b075c350988c7ac6dd1469da77","observation_id":"83dc3c85-dd44-4266-9f23-ea6da6945559","resolution":{"observed_at":"2026-08-14T11:04:11.265452Z","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":"2026-08-14T11:04:11.447701Z","title":"Advent: Adversarial entropy mini- mization for domain adaptation in semantic segmentation","venue":null,"work_id":"03599ec8-6943-4345-b883-b1a38531d21d","year":2019},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.269259Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:4d6b11bfb4a5197d24a9dff6d85082d438721bb1960c53a7b5adf96905406d1b","observation_id":"3ecdcfbd-b706-4005-ae22-82031b5e02ae","resolution":{"observed_at":"2026-08-14T11:04:11.452386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.434219Z","title":"Dcan: Dual channel-wise alignment networks for un- supervised scene adaptation","venue":null,"work_id":"4d92d8e0-b9b2-4a7e-83a8-0234ee14fd85","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.272705Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:ae5c12cfbf83b622356ed2cc2b2334482522d6fe621555f99ea25837a23cc0f1","observation_id":"0c35211e-d54a-426d-82ea-03d087d5983d","resolution":{"observed_at":"2026-08-14T11:04:11.438868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.421293Z","title":"Unsupervised word sense disambiguation rivaling supervised methods","venue":null,"work_id":"3c0744dc-2623-4260-9567-dafdb1d5d533","year":1995},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.276519Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:65af960fb1a3e5235f361d7879d1ff9a576ba1cf37e44f36823162a0a6d6e758","observation_id":"eb683b32-be86-4c8c-8caa-4e98a04e550b","resolution":{"observed_at":"2026-08-14T11:04:11.425684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.408400Z","title":null,"venue":null,"work_id":"02086eb9-b8ba-4cbc-a20e-10cb042df1c7","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.280401Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:ce06ff95465c927e8d887a0210ac0dfc460dbd84a5d294a7156fa7458f72da62","observation_id":"e9893a43-518d-4c2f-9f75-19721525dc1a","resolution":{"observed_at":"2026-08-14T11:04:11.412556Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.394824Z","title":"Fully convolutional adaptation networks for semantic segmentation","venue":null,"work_id":"eb88ebfe-3393-407c-bda1-8d575ccf9c19","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.285542Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:2e08c9095ec79c411e5ca4c8b3723d5603cd729a7fa1705e12ef3abe936b7c34","observation_id":"53e3d760-017e-43aa-a269-990d3480fe0a","resolution":{"observed_at":"2026-08-14T11:04:11.399925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:04:11.380696Z","title":"expectation","venue":null,"work_id":"7cd5ddee-42ec-4c7d-8913-d3aeba1e0913","year":2018},"citing_paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-14T11:04:11.290295Z"},"links":{"citing_paper":"/paper/1908.09822"},"observation_digest":"sha256:577482e51e484fab26c3f0e02f5187d57c9ebda50a9c7bb75d8facb9711dc6ec","observation_id":"cecec1d1-c92f-42a4-90f3-49b6cbddb6bf","resolution":{"observed_at":"2026-08-14T11:04:11.386705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.09822","last_updated":"2020-07-15T10:57:38Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T20:20:45.473573Z","submitted_at":"2019-08-26T17:56:13Z","title":"Confidence Regularized Self-Training"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":0,"verified_fuzzy":53},"total_outbound_references":68},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 0 inbound Pith citation observations for arXiv:1908.09822."}