{"as_of":"2026-08-19T07:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:90c78bfb3da6c7a4cadc0617f4ebcbfe7b316dbdae8432c2dcd9c6d06d00d785","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T05:06:30.971642Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1909.02180/citation-record","integrity":"/paper/1909.02180/integrity","json":"/paper/1909.02180/citation-record.json","paper":"/paper/1909.02180"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.515557Z","title":"Ardehaly and Aron Culotta","venue":null,"work_id":"7362a6cc-8ac4-4e9d-b592-17542b93c886","year":2017},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.832683Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:376113bf6270a71282d6e09d54973648e3a3170264498577465d0d5296dbadd9","observation_id":"5fbda7f7-17c9-41a1-a13f-49b03b09fc0b","resolution":{"observed_at":"2026-08-14T05:06:31.520057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.501871Z","title":"Towards principled methods for training generative adver- sarial networks","venue":null,"work_id":"e68525b9-a120-4126-8bab-e360f6171554","year":2016},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.837999Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:f0398a3a8a6108fb55f3c85409ec0bfd13a151d5b30f147ca00eec7e8b54be8f","observation_id":"e01283b4-ec54-4c9d-ac38-33dbcb060087","resolution":{"observed_at":"2026-08-14T05:06:31.506459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T05:06:30.842361Z","title":"Wasserstein generative adversarial networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.842361Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:75a16642a212abf4e23315b6d481122b1ae75088c0b86de0d5cef4084b868ee4","observation_id":"a8bc6da6-ed41-44ec-892a-4cbf0694ef2d","resolution":{"observed_at":"2026-08-14T05:06:30.842361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.01261","last_updated":"2018-10-17T17:51:36Z","snapshot_observed_at":"2026-08-17T23:08:02.689731Z","submitted_at":"2018-06-04T17:58:18Z","title":"Relational inductive biases, deep learning, and graph networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.01261","snapshot_observed_at":"2026-08-14T05:06:30.846879Z","title":"Relational inductive biases, deep learning, and graph networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.846879Z"},"links":{"cited_paper":"/paper/1806.01261","citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:2adf73f20aeb64780ff3fd02a12b77ff26bfa58114ec2f092e473940de4f3ba2","observation_id":"547daeb3-f619-4b15-853e-7a1a7960a183","resolution":{"observed_at":"2026-08-14T05:06:30.846879Z","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":"2026-08-14T05:06:30.851908Z","title":"Representation learning: A review and new perspectives","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.851908Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:a951eb5bba226e336b543ac0179c68e0fd4907fade3ec754b1e95335ce5a4c21","observation_id":"377f1246-0bf2-4c08-95ff-aff76420088e","resolution":{"observed_at":"2026-08-14T05:06:30.851908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.471456Z","title":"Pattern Recognition and Machine Learning","venue":null,"work_id":"f3e969a9-b015-4598-aad6-014af5e8a33c","year":2006},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.856228Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:8f3e3730e8eeb3cb816d7ddaacdea99c597de07fa64493dc368c0bfb5af15e91","observation_id":"02c474a8-1857-4ee4-a4ba-2cff77f0f000","resolution":{"observed_at":"2026-08-14T05:06:31.475913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T05:06:30.861148Z","title":"Convex optimization","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.861148Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:abbd64ca0349d0d16fde8147e744b5e18356a84eb25e593b8dd40eb18ce7de2b","observation_id":"af1342e6-6ef0-438a-bc4d-6404cb7f410f","resolution":{"observed_at":"2026-08-14T05:06:30.861148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.449299Z","title":"Good semi-supervised learning that requires a bad gan","venue":null,"work_id":"eae7095b-79e6-4408-9b04-b3d83c3070c6","year":2017},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.865245Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:f07d2a91ec3e9b53f79cafecc3a47fb7edc0841da7500c000a4758a65f9000f8","observation_id":"49106635-7395-4035-80de-bd876d18ff8b","resolution":{"observed_at":"2026-08-14T05:06:31.453702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.435950Z","title":"Dietterich, Richard H","venue":null,"work_id":"2d69074e-c864-45e0-b96a-aae12287c73e","year":1997},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.869345Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:1439dd6acb656b1d64b6ac7efc429fa6e3302c5d8aa447426856d89fabd145cf","observation_id":"e16f5c7f-ecb5-4124-8562-7afa3525250c","resolution":{"observed_at":"2026-08-14T05:06:31.440240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.12909","last_updated":"2019-06-26T12:20:13Z","snapshot_observed_at":"2026-08-14T16:23:53.960361Z","submitted_at":"2019-05-30T08:26:47Z","title":"Deep multi-class learning from label proportions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.12909","snapshot_observed_at":"2026-08-14T05:06:30.873377Z","title":"Deep multi-class learning from label proportions","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.873377Z"},"links":{"cited_paper":"/paper/1905.12909","citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:720d7d0108085296431fca97edd516fff7247e3117855316e9743660c181fdd7","observation_id":"00e8b16a-91fd-4e10-bf75-c13cfe7b6740","resolution":{"observed_at":"2026-08-14T05:06:30.873377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.422107Z","title":"Generative adversarial nets","venue":null,"work_id":"f8a2110e-9c87-4cc1-bdbd-5c0792d47fb6","year":2014},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.877831Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:ed767aadc08a6532bef5fca815cb21aa576080ebbfb3090e60fefa65e62e5f7d","observation_id":"a550f698-b7cf-43fa-ae05-db9e711d1ab2","resolution":{"observed_at":"2026-08-14T05:06:31.426848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T05:06:30.881983Z","title":"Semi-supervised learning by entropy minimization","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.881983Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:ee42584a97c16bd6f6265ad4c3de1142980d24c051d147978249454eecd1e01d","observation_id":"3eca4d6d-09b1-434e-853c-55aa943a3bdd","resolution":{"observed_at":"2026-08-14T05:06:30.881983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.396822Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"d2afdb01-4d8c-4c2c-996f-1fa696f65f65","year":2016},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.886257Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:1832b5e25635c0b69cb790133cb0fb76fca89b1370ba218475220043beedd75f","observation_id":"0654713a-bbac-4ea5-9528-253ccb25158f","resolution":{"observed_at":"2026-08-14T05:06:31.401866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.306579Z","title":"Deep neural networks for acoustic modeling in speech recognition","venue":null,"work_id":"39d69d25-ca7a-48ed-88cc-ad051ffdb5d0","year":2012},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.890302Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:72b91d0848a5be4a9671ba67de80872afce2f2f4e65182c742322980c333f2f6","observation_id":"426f85e2-848e-4933-85a7-ff3808de5a1f","resolution":{"observed_at":"2026-08-14T05:06:31.344163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.291648Z","title":"Perceptual losses for real-time style transfer and super-resolution","venue":null,"work_id":"12076797-f70b-4cca-8517-bc08abe23fcf","year":2016},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.894448Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:711d24c60720bf0ff2e4cba385b27f4ff4678c50aa8adbf0edd13ae32f1decc3","observation_id":"0beae9a7-bde8-43f1-9ddf-f0176e75c6bc","resolution":{"observed_at":"2026-08-14T05:06:31.296900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-08-14T23:50:45.029465Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-14T05:06:30.898472Z","title":"Kingma and Max Welling","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.898472Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:bc5304028639a9af6e1435feb3ecd63a09ec7b5e002a41cba1cfe3472e84c76b","observation_id":"fbfc5853-fcf2-4fff-8b6a-f7d993826c90","resolution":{"observed_at":"2026-08-14T05:06:30.898472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.277355Z","title":"Semi-supervised learning with deep generative models","venue":null,"work_id":"24bade22-a9bd-4bd3-82fe-fde76a764612","year":2014},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.902747Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:1d8c12bfbaa0533cda63ecfe7bf189b97c899de3d30ae837760e336baa1c08bd","observation_id":"1692ceeb-5ad9-430a-90fd-ea4317b44909","resolution":{"observed_at":"2026-08-14T05:06:31.282158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.4400","last_updated":"2014-03-04T05:15:42Z","snapshot_observed_at":"2026-08-14T23:51:30.531758Z","submitted_at":"2013-12-16T15:34:13Z","title":"Network In Network","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.4400","snapshot_observed_at":"2026-08-14T05:06:30.906884Z","title":"Network in network.arXiv preprint arXiv:1312.4400, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.906884Z"},"links":{"cited_paper":"/paper/1312.4400","citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:50c53172f6ff70204f04d902eff96d37342a98302b4df9dd3c477032fe1850ef","observation_id":"68b2ba45-61a7-4a85-a093-c34891f5a0e4","resolution":{"observed_at":"2026-08-14T05:06:30.906884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.263093Z","title":"A framework for multiple-instance learning","venue":null,"work_id":"e212eb38-e668-426e-9275-8139452e38ea","year":1998},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.911136Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:6eb11a69b2f74321dded4d2be5e71d37fe746609621ce88f3782c7ff6a603f0d","observation_id":"29a66af3-6956-4135-bf95-f8943504867f","resolution":{"observed_at":"2026-08-14T05:06:31.267575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-14T05:06:30.915018Z","title":"The expectation-maximization algorithm","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.915018Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:2b19d739e5a97a2a569078233a4fb9d32312adc3b6f05d06906f8d46ef5acf11","observation_id":"9a30bdd6-25e6-4529-8434-0a7a0cb5b2d6","resolution":{"observed_at":"2026-08-14T05:06:30.915018Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.239760Z","title":"(Almost) no label no cry","venue":null,"work_id":"7c2485d7-da71-4283-b3d8-9a0c874df7f0","year":2014},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.919178Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:0fa1c8c0017b70ef2af28ce818b648f648f1dfc4150a5195d485736320639e6f","observation_id":"8e6984f3-7f98-4703-9ef3-90bc795bbbec","resolution":{"observed_at":"2026-08-14T05:06:31.244791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.225853Z","title":"Learning with label proportions via NPSVM","venue":null,"work_id":"48a55d48-2d6f-4218-821a-309d811d3480","year":2017},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.923137Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:e43e42bf0f63f6ea69a4c9142449c5e396d5921658a7e629edeeb2b519f029da","observation_id":"32f6d559-de8b-4160-bced-a6d338aecaaa","resolution":{"observed_at":"2026-08-14T05:06:31.230381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.212076Z","title":"Smola, Tiberio S","venue":null,"work_id":"d6acdb7b-c0af-4aa9-8728-363522db663d","year":2009},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.927210Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:60d96d04ad02db801c690336921adfe0b349050d51510f3548be40a09697e26c","observation_id":"f54200e2-6066-4149-ae51-904498635b97","resolution":{"observed_at":"2026-08-14T05:06:31.216255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.06434","last_updated":"2016-01-07T23:09:39Z","snapshot_observed_at":"2026-08-12T18:43:14.431633Z","submitted_at":"2015-11-19T22:50:32Z","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.06434","snapshot_observed_at":"2026-08-14T05:06:30.931047Z","title":"Unsupervised representation learning with deep convolutional generative adversarial networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.931047Z"},"links":{"cited_paper":"/paper/1511.06434","citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:67ecd5b65441d3b66b226d49178b26315b3b84b1054d7cb1d75fc7e6e74623f2","observation_id":"8ac30876-09b9-4e62-b31f-db67775e57c0","resolution":{"observed_at":"2026-08-14T05:06:30.931047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.197748Z","title":"Semi- supervised learning with ladder networks","venue":null,"work_id":"a518422b-a37e-44c1-a1c7-835a417b5385","year":2015},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.935334Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:d3bf3cb46163b30bc09f15fb53f1585cb9b45687da5b9fc7ee0de6da94d1cbd9","observation_id":"3ff3d659-efb0-4255-b33c-cf2eae662636","resolution":{"observed_at":"2026-08-14T05:06:31.202476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.184578Z","title":"You only look once: Unified, real-time object detection","venue":null,"work_id":"14ad4495-d0a3-43a0-8738-1c5143bc882a","year":2016},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.939474Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:a7fa50e15581391eed03820527e33aefd23235bc6f0f974ea7e3ee32a20dd053","observation_id":"b30db5dc-955d-45b5-8c00-c590d9129c8b","resolution":{"observed_at":"2026-08-14T05:06:31.189005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.170647Z","title":"SVM classifier estimation from group probabilities","venue":null,"work_id":"c34dcfbe-ce91-48b7-a810-0f463a2bfc23","year":2010},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.943550Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:da48c0c5996df22dba1398519a5858a19899d8db0ab432f57ecb851360880a73","observation_id":"2bf9b29e-f8d1-4755-b26c-5a97abd703a0","resolution":{"observed_at":"2026-08-14T05:06:31.175176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.155259Z","title":"Improved techniques for training GANs","venue":null,"work_id":"881315f3-e1de-4b81-b189-90d99fcd2275","year":2016},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.947499Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:22c8be567ea708a73bc1a454ba183c766731caa4b64ed86e30fa3a8d36a5280d","observation_id":"ad8d3291-b6c7-4835-ab57-2936450c6f16","resolution":{"observed_at":"2026-08-14T05:06:31.160414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.06390","last_updated":"2016-04-30T21:23:46Z","snapshot_observed_at":"2026-08-14T22:22:08.693507Z","submitted_at":"2015-11-19T21:26:58Z","title":"Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.06390","snapshot_observed_at":"2026-08-14T05:06:30.951585Z","title":"Springenberg","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.951585Z"},"links":{"cited_paper":"/paper/1511.06390","citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:a099c883c18d9dbfd4fe40f8c2164dbbf87081fd467044662191f539a83b5f30","observation_id":"26dc623b-1c93-4c6f-afd7-62e303eae335","resolution":{"observed_at":"2026-08-14T05:06:30.951585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.139710Z","title":"Rethinking the inception architecture for computer vision","venue":null,"work_id":"2db9d0e4-3105-4a99-84fc-8c6f38937617","year":2016},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.955829Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:47afb2aa49af6cc33dd0b3b2eb4f2d3e4cceedb0b57ac689c8caa39a79828b51","observation_id":"d423ce61-ea37-4758-9d83-a7ad2fc20368","resolution":{"observed_at":"2026-08-14T05:06:31.144528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.125678Z","title":"Multi-class learning from class proportions","venue":null,"work_id":"dc993179-fa58-4774-82e6-8812eddf09fa","year":2013},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.959630Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:627f1ae646171cce77c1a9ae15c7e501108b0ab6f9672e4d581621f1102d38ea","observation_id":"63fb1662-744f-4a72-926f-e469e960275e","resolution":{"observed_at":"2026-08-14T05:06:31.130360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.111520Z","title":"Adversarial perturbations of deep neural networks","venue":null,"work_id":"36be461a-b6bf-47ff-a93c-79a7eb45122a","year":2016},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.963642Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:7634f9ec4d9a396f5a8773017a302380fc9da609ca08788e74ae0f5912e13ec9","observation_id":"42907df0-57ee-4c53-a4a5-f52e6ade73cb","resolution":{"observed_at":"2026-08-14T05:06:31.116334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.098018Z","title":"Yu, Liangliang Cao, Michele Merler, et al","venue":null,"work_id":"e03fddfb-0cc8-4f32-ae6c-7b2e803bb0f4","year":2014},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.967602Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:a42bc82d2b955849d0724f3d7e83fe4f96ed2edc692f6d5e677e0f29707c6cbe","observation_id":"70c9efc7-349a-431d-8118-d533727f3dff","resolution":{"observed_at":"2026-08-14T05:06:31.102337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T05:06:31.081552Z","title":"Yu, Dong Liu, Sanjiv Kumar, et al.∝-SVM for learning with label proportions","venue":null,"work_id":"3dc3bea9-b6f4-46c6-b614-64cb916eac8b","year":2013},"citing_paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T05:06:30.971642Z"},"links":{"citing_paper":"/paper/1909.02180"},"observation_digest":"sha256:598cbff1f4f9c4a2f6a37d029c288405b6c43db077bca565afd43287ca9b67cd","observation_id":"b669598f-307e-4226-ae22-89a2c1ec425c","resolution":{"observed_at":"2026-08-14T05:06:31.087410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1909.02180","last_updated":"2019-12-02T09:01:27Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-19T02:45:36.979222Z","submitted_at":"2019-09-05T01:55:35Z","title":"Learning from Label Proportions with Generative Adversarial Networks"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":23},"total_outbound_references":34},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:1909.02180."}