{"as_of":"2026-08-06T05:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:da490ce18d84ecae071acfdedff050699126823af3f784e99523e44bd5d3fd12","coverage":[{"denominator":16,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-24T16:21:56.723289Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T05:38:12.882914Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":34,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"cited_work":{"arxiv_id":"1907.11065","doi":"10.48550/arxiv.1907.11065","metadata_source":"arxiv_reference","pith_arxiv_id":"1907.11065","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, and Ming Zhou","venue":"arXiv (Cornell University)","work_id":"ebbfdba2-e8b5-4f0b-a4d3-b6e0eb9c4156","year":1907},"citing_paper":{"arxiv_id":"2604.17465","last_updated":"2026-04-30T22:17:02Z","snapshot_observed_at":"2026-08-02T19:54:22.380858Z","submitted_at":"2026-04-19T14:30:13Z","title":"Language models recognize dropout and Gaussian noise applied to their activations","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T05:38:12.882914Z"},"links":{"cited_paper":"/paper/1907.11065","citing_paper":"/paper/2604.17465"},"observation_digest":"sha256:fff2f5cd918822a0fa920cae3fec7e85879d7a0bd664403dec89ff18ffdba6ed","observation_id":"47a04ff2-2b44-42cb-99dc-edf3e28a25f5","resolution":{"observed_at":"2026-07-04T23:49:42.666573Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"cited_work":{"arxiv_id":"1907.11065","doi":"10.48550/arxiv.1907.11065","metadata_source":"arxiv_reference","pith_arxiv_id":"1907.11065","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, and Ming Zhou","venue":"arXiv (Cornell University)","work_id":"ebbfdba2-e8b5-4f0b-a4d3-b6e0eb9c4156","year":1907},"citing_paper":{"arxiv_id":"2604.20505","last_updated":"2026-04-22T12:45:51Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-04-22T12:45:51Z","title":"Explicit Dropout: Deterministic Regularization for Transformer Architectures","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T00:54:55.790878Z"},"links":{"cited_paper":"/paper/1907.11065","citing_paper":"/paper/2604.20505"},"observation_digest":"sha256:a72905e80dbc13deed73e0397c33059773aa8585ecbaa6a63ece6b0878589005","observation_id":"7aab1a54-bdef-4a3d-b301-ed8851fad4e4","resolution":{"observed_at":"2026-07-04T23:49:42.666573Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1907.11065/citation-record","integrity":"/paper/1907.11065/integrity","json":"/paper/1907.11065/citation-record.json","paper":"/paper/1907.11065"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":"1607.06450","doi":"10.1007/978-3-319-32025-0","metadata_source":"pith","pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Layer Normalization","venue":"stat.ML","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","year":2016},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:ecbf5814c4763d9b60d7ffb1c03a9770bc042a8a3e791e00849fa43e18eb362a","observation_id":"455e1d63-0152-4ba9-b2ff-e52b0495b38d","resolution":{"observed_at":"2026-05-24T16:24:40.604044Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1508.05326","last_updated":"2015-08-21T16:17:01Z","snapshot_observed_at":"2026-08-05T22:08:24.004344Z","submitted_at":"2015-08-21T16:17:01Z","title":"A large annotated corpus for learning natural language inference","version":1},"cited_work":{"arxiv_id":"1508.05326","doi":"10.48550/arxiv.1508.05326","metadata_source":"pith","pith_arxiv_id":"1508.05326","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A large annotated corpus for learning natural language inference","venue":"cs.CL","work_id":"c7bde334-463e-4827-a444-d90b456da346","year":2015},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1508.05326","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:c067143a346415725ea48ea8fea39dbe618830a741c0348970ee394beb6169ef","observation_id":"cfee279b-89c1-47f5-8daa-2e7b356b3ba9","resolution":{"observed_at":"2026-05-24T16:24:40.597594Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1603.06021","last_updated":"2016-07-29T18:36:15Z","snapshot_observed_at":"2026-07-06T04:50:00.997524Z","submitted_at":"2016-03-19T00:22:20Z","title":"A Fast Unified Model for Parsing and Sentence Understanding","version":3},"cited_work":{"arxiv_id":"1603.06021","doi":null,"metadata_source":"pith","pith_arxiv_id":"1603.06021","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A Fast Unified Model for Parsing and Sentence Understanding","venue":"cs.CL","work_id":"06c40967-de5a-42e0-abed-423eb4843cc7","year":2016},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1603.06021","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:cfda26c04734bccb11eb921259b81424fe9e30f08c9853d73682a4eee10b50c6","observation_id":"3aa9fcc1-20d4-4ec8-a5a2-3fd871e56814","resolution":{"observed_at":"2026-05-24T16:24:40.665328Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.04552","last_updated":"2017-11-29T14:51:40Z","snapshot_observed_at":"2026-07-06T05:55:22.966528Z","submitted_at":"2017-08-15T15:21:53Z","title":"Improved Regularization of Convolutional Neural Networks with Cutout","version":2},"cited_work":{"arxiv_id":"1708.04552","doi":null,"metadata_source":"pith","pith_arxiv_id":"1708.04552","snapshot_observed_at":"2026-07-11T01:47:48.046664Z","title":"Improved Regularization of Convolutional Neural Networks with Cutout","venue":"cs.CV","work_id":"a3bf8477-f913-4f6a-8e36-125767300d1f","year":2017},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1708.04552","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:df773effe31555e2a465fe2a596bfc2e31d7a81c78a3c53cc1bfd4d066c1a542","observation_id":"03b9a047-c677-4f9c-8ab0-1fc840b3ab11","resolution":{"observed_at":"2026-05-24T16:24:40.629341Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07485","last_updated":"2017-05-23T13:36:46Z","snapshot_observed_at":"2026-08-05T23:22:37.942108Z","submitted_at":"2017-05-21T18:51:27Z","title":"Shake-Shake regularization","version":2},"cited_work":{"arxiv_id":"1705.07485","doi":null,"metadata_source":"pith","pith_arxiv_id":"1705.07485","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shake-Shake regularization","venue":"cs.LG","work_id":"570f158d-121f-418a-b837-3649ded827f1","year":2017},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1705.07485","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:4f948da314151466dda70a4422347bb53537edd24fd0dd5bb0da7b525798cfdd","observation_id":"2b98b9c5-37c2-4eff-8e92-3f8d6f04dbf2","resolution":{"observed_at":"2026-05-24T16:24:40.660558Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01305","last_updated":"2017-09-22T20:43:09Z","snapshot_observed_at":"2026-07-06T04:58:46.681389Z","submitted_at":"2016-06-03T23:31:47Z","title":"Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations","version":4},"cited_work":{"arxiv_id":"1606.01305","doi":null,"metadata_source":"pith","pith_arxiv_id":"1606.01305","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations","venue":"cs.NE","work_id":"2793bb63-dda8-4bb5-8fdf-0c503acd761c","year":2016},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1606.01305","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:4dc8a60c50b0691be18d102433a74df1a47f42ecbc29f280dc1a643397bc64dc","observation_id":"99add77e-1a44-4f6b-b734-005b95635f94","resolution":{"observed_at":"2026-05-24T16:24:40.654846Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1605.07648","last_updated":"2017-05-26T18:53:56Z","snapshot_observed_at":"2026-07-06T04:57:27.652360Z","submitted_at":"2016-05-24T20:28:53Z","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","version":4},"cited_work":{"arxiv_id":"1605.07648","doi":null,"metadata_source":"pith","pith_arxiv_id":"1605.07648","snapshot_observed_at":"2026-07-10T20:17:33.749623Z","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","venue":"cs.CV","work_id":"ecf74c2e-7eed-4017-8f0b-f90686110609","year":2016},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1605.07648","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:91e62b5062f8942d72a1d7ed24302a1876b61986a18c7acfb71ea3a89bdb7bc4","observation_id":"be3f2a85-1d4d-4009-a534-38daabf7007a","resolution":{"observed_at":"2026-05-24T16:24:40.619522Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.10183","last_updated":"2018-10-24T04:08:27Z","snapshot_observed_at":"2026-07-06T07:10:12.570041Z","submitted_at":"2018-10-24T04:08:27Z","title":"Multi-Head Attention with Disagreement Regularization","version":1},"cited_work":{"arxiv_id":"1810.10183","doi":null,"metadata_source":"pith","pith_arxiv_id":"1810.10183","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multi-Head Attention with Disagreement Regularization","venue":"cs.CL","work_id":"27cc5a25-192f-4d64-aeb9-7b95bb263996","year":2018},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1810.10183","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:205f2d93cfc03eea8bdfeb9b97d98662b175dd715d6242dcbe962bbd14abf6fe","observation_id":"029888f5-3fce-4f4a-ac9e-a12fe88822bd","resolution":{"observed_at":"2026-05-24T16:24:40.650077Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.03130","last_updated":"2017-03-09T04:42:30Z","snapshot_observed_at":"2026-08-01T16:29:44.580051Z","submitted_at":"2017-03-09T04:42:30Z","title":"A Structured Self-attentive Sentence Embedding","version":1},"cited_work":{"arxiv_id":"1703.03130","doi":null,"metadata_source":"pith","pith_arxiv_id":"1703.03130","snapshot_observed_at":"2026-07-01T08:35:34.322025Z","title":"A Structured Self-attentive Sentence Embedding","venue":"cs.CL","work_id":"b3754c6d-a97f-431c-9e57-e5da516ff977","year":2017},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1703.03130","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:10aa062ddc75a96ee04f72354bdc62b0746f73c3920dadba37ea7e30068f6625","observation_id":"76e96180-c9bd-4dfe-a0ab-bc64bed8da73","resolution":{"observed_at":"2026-05-24T16:24:40.639360Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.00187","last_updated":"2018-09-04T23:19:27Z","snapshot_observed_at":"2026-07-06T06:42:25.746932Z","submitted_at":"2018-06-01T04:33:16Z","title":"Scaling Neural Machine Translation","version":3},"cited_work":{"arxiv_id":"1806.00187","doi":null,"metadata_source":"pith","pith_arxiv_id":"1806.00187","snapshot_observed_at":"2026-07-01T23:06:20.196502Z","title":"Scaling Neural Machine Translation","venue":"cs.CL","work_id":"6caa5078-a814-42e2-973c-29bda2b1b1ca","year":2018},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1806.00187","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:757c1fcf9490ddbe9de989c9d057215b2767624de0a2f7a5eb09f033c2093a91","observation_id":"765f4032-333a-454f-832f-9fa8a1cff8cc","resolution":{"observed_at":"2026-05-24T16:24:40.614014Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1603.05118","last_updated":"2016-08-05T09:59:25Z","snapshot_observed_at":"2026-07-06T04:49:41.776701Z","submitted_at":"2016-03-16T14:33:47Z","title":"Recurrent Dropout without Memory Loss","version":2},"cited_work":{"arxiv_id":"1603.05118","doi":null,"metadata_source":"pith","pith_arxiv_id":"1603.05118","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Recurrent Dropout without Memory Loss","venue":"cs.CL","work_id":"c11b4d74-a243-48e7-9a26-c3580bc91187","year":2016},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1603.05118","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:3c53008b37fd45d8094fb47895c481693cd24e3c9d4d8640f0054cd5c38526e6","observation_id":"bf86cfd3-6cc2-4959-b976-e580facc9aa4","resolution":{"observed_at":"2026-05-24T16:24:40.608947Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1508.07909","last_updated":"2016-06-10T14:45:08Z","snapshot_observed_at":"2026-07-06T04:28:16.222296Z","submitted_at":"2015-08-31T16:37:31Z","title":"Neural Machine Translation of Rare Words with Subword Units","version":5},"cited_work":{"arxiv_id":"1508.07909","doi":"10.48550/arxiv.1508.07909","metadata_source":"pith","pith_arxiv_id":"1508.07909","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Neural Machine Translation of Rare Words with Subword Units","venue":"cs.CL","work_id":"b540b77d-96cd-4550-9c11-d02686beb7b1","year":2015},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1508.07909","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:8e001f3ad8a5a70094ce9c0729048e647756d804adb00fb5c77683a12979f1d4","observation_id":"717f01bd-1150-44bc-b59f-4b45acca9ea4","resolution":{"observed_at":"2026-05-24T16:24:40.624403Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":"a8616a03-91af-4e77-b25a-c786e9d697ad","year":1929},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:fd029f0a3e0b4e0d2e278a617986e42f33ed57a1c0e9270677e0cb812fc421d9","observation_id":"a946d029-c64d-49ad-8e59-0df37f61023c","resolution":{"observed_at":"2026-05-24T16:24:41.723911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Document modeling with gated recurrent neural network for sentiment classification","venue":null,"work_id":"fa982356-e066-4530-af41-d0078cd366b4","year":2015},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:f89ff7c99e2ac084ace9825f3bedd9f8c3501cb0bc5b069783bcbd3b9829c018","observation_id":"2bf2915d-f25e-4ba3-8513-2b03f9650ac6","resolution":{"observed_at":"2026-05-24T16:24:41.720276Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.02375","last_updated":"2020-01-06T07:14:51Z","snapshot_observed_at":"2026-07-06T06:22:10.478346Z","submitted_at":"2018-02-07T10:23:54Z","title":"ShakeDrop Regularization for Deep Residual Learning","version":3},"cited_work":{"arxiv_id":"1802.02375","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1802.02375","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shakedrop regularization for deep residual learning","venue":null,"work_id":"5b3f1e06-f528-4bd5-9ce7-0461e75650eb","year":2021},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1802.02375","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:03ad7d96e6b9abafc7142b3d06a28d3ba942a91cd117fcffc034d382aeff0802","observation_id":"fb610ff7-6f68-4d04-b92f-089923217bb5","resolution":{"observed_at":"2026-05-24T16:24:40.644605Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1603.06270","last_updated":"2016-08-09T15:07:39Z","snapshot_observed_at":"2026-07-06T04:50:06.866392Z","submitted_at":"2016-03-20T21:15:56Z","title":"Multi-Task Cross-Lingual Sequence Tagging from Scratch","version":2},"cited_work":{"arxiv_id":"1603.06270","doi":null,"metadata_source":"pith","pith_arxiv_id":"1603.06270","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Multi-Task Cross-Lingual Sequence Tagging from Scratch","venue":"cs.CL","work_id":"3f9fe304-03bc-4980-a6a5-3f05f0fb8c04","year":2016},"citing_paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-24T16:21:56.723289Z"},"links":{"cited_paper":"/paper/1603.06270","citing_paper":"/paper/1907.11065"},"observation_digest":"sha256:662a435fa0e5878a14635fcecb007afcbea9eec530b35f2bf1687140a010d42c","observation_id":"1612a02a-b768-4bb1-a41c-904e4749f701","resolution":{"observed_at":"2026-05-24T16:24:40.633858Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1907.11065","last_updated":"2019-07-26T01:49:33Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T08:10:10.910194Z","submitted_at":"2019-07-25T14:03:06Z","title":"DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks"},"reference_resolution":{"displayed":16,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":0,"verified_exact":13,"verified_fuzzy":2},"total_outbound_references":16},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 2 inbound Pith citation observations for arXiv:1907.11065."}