{"as_of":"2026-08-22T08:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2190ac276ff33e4080c47d66d37aeaa10474caca42f64f09d1e95b7e426f5680","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:24:40.258828Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:24:40.161149Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-14T14:24:40.304973Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"cited_work":{"arxiv_id":"1908.05227","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.05227","snapshot_observed_at":"2026-08-14T14:24:40.304973Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","venue":"eess.AS","work_id":"72c24f55-966c-452f-a390-b2086766e6b8","year":2019},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.161149Z"},"links":{"cited_paper":"/paper/1908.05227","citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:862389642c969cbbb3eb9ccced4521ee240566c6a5fd4ea1f81684bc8e03124d","observation_id":"34a42d0d-0071-4a02-a4ef-de9c9d7c3056","resolution":{"observed_at":"2026-08-14T14:24:40.310655Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1908.05227/citation-record","integrity":"/paper/1908.05227/integrity","json":"/paper/1908.05227/citation-record.json","paper":"/paper/1908.05227"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"cited_work":{"arxiv_id":"1908.05227","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.05227","snapshot_observed_at":"2026-08-14T14:24:40.304973Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","venue":"eess.AS","work_id":"72c24f55-966c-452f-a390-b2086766e6b8","year":2019},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.161149Z"},"links":{"cited_paper":"/paper/1908.05227","citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:862389642c969cbbb3eb9ccced4521ee240566c6a5fd4ea1f81684bc8e03124d","observation_id":"34a42d0d-0071-4a02-a4ef-de9c9d7c3056","resolution":{"observed_at":"2026-08-14T14:24:40.310655Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.550241Z","title":"An alternative technique, re- ferred to as end-to-end, aims to learn the mapping from acoustic features to text directly without the need of intermediate steps","venue":null,"work_id":"2cf61ca0-f8c9-4881-ade5-3f51ac32b4a6","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.165646Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:db15aa0e5a39d8a58167122a6821b2d634be19c297ad560d10b4239f95c78def","observation_id":"a4506887-9fb2-4cd9-871b-d4f0f316e616","resolution":{"observed_at":"2026-08-14T14:24:40.553837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.540813Z","title":null,"venue":null,"work_id":"a47998d7-f113-4df8-81eb-218952d30681","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.169153Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:646895c88ddb8da1cd5e87b276750a4ef2207848d79e36b258d0a2c17c7dbbb4","observation_id":"3e92d11f-df6f-43f3-b879-e2e9e364a21a","resolution":{"observed_at":"2026-08-14T14:24:40.544633Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.532151Z","title":null,"venue":null,"work_id":"db79107a-d92c-47bd-963a-fb5ced3ca4a1","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.173274Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:86801c3719eb6a1ea61d3d30f5b23c25921ca035a7d0097e022e0c1e14a03856","observation_id":"28c24970-2e7b-4e2a-8203-7f20f69c3e99","resolution":{"observed_at":"2026-08-14T14:24:40.535007Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.522960Z","title":null,"venue":null,"work_id":"632a1727-1bc5-4dbc-8e1e-ebadd141df4b","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.177384Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:051c6a35a8a8b4536683b37cc035054e746fca42007813297f5e9e39da4b6726","observation_id":"b06f6b36-e7f2-4c9d-af6b-bcbc71826420","resolution":{"observed_at":"2026-08-14T14:24:40.526272Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.513366Z","title":null,"venue":null,"work_id":"fab901c5-d58b-4ae1-8636-1f6a90604594","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.180973Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:acb2d17d03bb5d5fd94a1938c1a856a67f07db546fb45b0667ecd1d02a6a5c4f","observation_id":"79db2310-abdb-4a6a-9eb9-4105e64f1503","resolution":{"observed_at":"2026-08-14T14:24:40.517178Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.503868Z","title":"Experiments are performed on TEDLIUM and Table 1: Training, adaptation and test data for different dataset","venue":null,"work_id":"ca9e0dc6-6d85-42cf-9d37-5b8a84f40eee","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.184240Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:40c63c41839e1c0cf11a8c3ff83b12b2b42d2774f775634f398ea851ffd5e227","observation_id":"c0b1ba35-b3f5-46d7-8c48-eaa000fdb241","resolution":{"observed_at":"2026-08-14T14:24:40.507297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.494627Z","title":"The following ASR systems will be analyzed: • LF-MMI: This ASR refers to the traditional chain model using LF-MMI optimization criteria","venue":null,"work_id":"a6151f70-7350-444f-b101-7c7fc4309054","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.187945Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:6b8d2fc9f971cb2c0b18463eb42f258709fdc2feccd8d8dd1911731912985e8d","observation_id":"696375cb-c385-45ea-b724-c0bce53a37a3","resolution":{"observed_at":"2026-08-14T14:24:40.498102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.484851Z","title":"For exploiting unlabelled data, the base- line system employs a single best hypothesized text-transcript","venue":null,"work_id":"2ba45561-9f18-4d27-8875-8882a7ca0646","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.191357Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:3c0f86b3b4b6137482be5aee51355bd81b80ea3408fdd18f3d428e6dfb3c49df","observation_id":"7a1c058e-7600-40d1-921c-8295e851eed9","resolution":{"observed_at":"2026-08-14T14:24:40.488226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.475003Z","title":"SM2 - Extracting semantic meaning from spoken material","venue":null,"work_id":"4631d920-1e1b-4da7-9da0-3731ca36c358","year":null},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.194361Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:f2c7e1f82933f74175f83fbc70fd19d562d86429f5fc5f85be8756f907bb7058","observation_id":"72480f16-53bb-49f2-8d30-22eb6499258a","resolution":{"observed_at":"2026-08-14T14:24:40.478477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.465800Z","title":"Deep neural networks for acoustic modeling in speech recognition,","venue":null,"work_id":"ab416808-f324-42ee-8c55-2ef87ce7b6ee","year":2012},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.197451Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:1fe1447880ae20244a4c5017428663b1d0c617dc590b8e473adce6979d88b79d","observation_id":"05176ac8-633e-43e0-8716-040c8606e2a0","resolution":{"observed_at":"2026-08-14T14:24:40.469206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.455973Z","title":"New types of deep neural network learning for speech recognition and related applications: An overview,","venue":null,"work_id":"d251f7b6-7f2b-47a4-b003-7a2cd390e457","year":2013},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.200709Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:6fcd0a9fea704dda30f2c8f2244cc22028fc465caa427e34e8c137dfb49c29f7","observation_id":"d98ed778-3ed6-4203-ba36-2915df1427fb","resolution":{"observed_at":"2026-08-14T14:24:40.459617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.446511Z","title":"Purely sequence-trained neu- ral networks for asr based on lattice-free mmi","venue":null,"work_id":"8d6f926e-91d5-48fd-9692-329ba2f1f711","year":2016},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.204466Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:03867f126aff1aefc3d5ed6fd378389dd98a0917f38e94ceef3e7ec2185d3a26","observation_id":"72f2f636-0075-45f8-b6a6-f138cf5ce715","resolution":{"observed_at":"2026-08-14T14:24:40.449879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.435337Z","title":"Exploiting foreign resources for dnn-based asr,","venue":null,"work_id":"556cba54-0e4d-4d6c-9a98-a981cb3e82a6","year":2015},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.207697Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:e23e0654c51e2e5637f78f10f502747816f7b0bdb2c0918f0b40da128e8fc4c1","observation_id":"97140727-021b-46da-ac93-23b8ca1f4a79","resolution":{"observed_at":"2026-08-14T14:24:40.439520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.210964Z","title":"Joint ctc-attention based end-to-end speech recognition using multi-task learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.210964Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:bb72cf20b8164c3a93144a9fae5fbc8b44b0a19e2d332897b08293f8ae8c665f","observation_id":"b9135fd7-2632-4381-ade0-1416871ef5ef","resolution":{"observed_at":"2026-08-14T14:24:40.210964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.00015","last_updated":"2018-03-30T18:09:39Z","snapshot_observed_at":"2026-08-14T19:30:36.364778Z","submitted_at":"2018-03-30T18:09:39Z","title":"ESPnet: End-to-End Speech Processing Toolkit","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.00015","snapshot_observed_at":"2026-08-14T14:24:40.214331Z","title":"Espnet: End-to-end speech processing toolkit,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.214331Z"},"links":{"cited_paper":"/paper/1804.00015","citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:372b9bd323e6f1471ea030d8ee8ad5b30627b2495852068cfce6a52950219773","observation_id":"f64c8e50-6967-4ad8-97fc-5c3b8531561c","resolution":{"observed_at":"2026-08-14T14:24:40.214331Z","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":"2026-08-14T14:24:40.418813Z","title":"Eesen: End-to-end speech recognition using deep rnn models and wfst-based decoding,","venue":null,"work_id":"64114df7-0b7a-470f-865a-7173277c9323","year":2015},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.217708Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:0f79bedf269f7505e293b83f9171467cd8ad973329e88b398870ee7a961d2ac4","observation_id":"326409c8-81aa-4311-b3c3-9a5761498984","resolution":{"observed_at":"2026-08-14T14:24:40.422675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.408503Z","title":"Semi- supervised training of acoustic models using lattice-free mmi,","venue":null,"work_id":"79f9b2de-e28d-4c89-8346-2b1d2ed8725a","year":2018},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.220724Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:f2d907897e5d7d66621e5b8b533b4edb9b1f9c3dbc6998d957db4e18cfe07d85","observation_id":"4227d23d-e083-4bf9-ba59-10b03810e01f","resolution":{"observed_at":"2026-08-14T14:24:40.411964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.399380Z","title":"Semi-supervised end-to-end speech recognition,","venue":null,"work_id":"91c844c3-fab9-4367-8df4-9ea99a924ff1","year":2018},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.223886Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:01deadbc600c8221c8defb49d3fe1dd1e2bde5bfe877a72586e39b91b2d3fad6","observation_id":"fcc3294a-d0ed-4bad-a3ba-bd5ef7b8e881","resolution":{"observed_at":"2026-08-14T14:24:40.402798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.389726Z","title":"Pseudo-label: The simple and efficient semi- supervised learning method for deep neural networks,","venue":null,"work_id":"591488c3-1803-4642-ae84-f28054efa692","year":2013},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.226892Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:ea3864abb44134060dddff3dda20b0ef26c0ef87eb1fc1d0dd1cb908277c17c8","observation_id":"e1d2d826-9adc-4e1b-b11c-66b86888f455","resolution":{"observed_at":"2026-08-14T14:24:40.393446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.09724","last_updated":"2017-05-26T21:10:15Z","snapshot_observed_at":"2026-08-18T00:56:09.495841Z","submitted_at":"2017-05-26T21:10:15Z","title":"Semi-Supervised Model Training for Unbounded Conversational Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.09724","snapshot_observed_at":"2026-08-14T14:24:40.230291Z","title":"Semi-supervised model training for unbounded conversational speech recognition,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.230291Z"},"links":{"cited_paper":"/paper/1705.09724","citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:06faa9002a69c875ea866cd6a1781c99aec0382cd6fc3f29c1cffe5fb7ed8160","observation_id":"6a8ba271-431e-49ba-b8be-14cace826ece","resolution":{"observed_at":"2026-08-14T14:24:40.230291Z","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":"2026-08-14T14:24:40.379847Z","title":"Learning with pseudo- ensembles,","venue":null,"work_id":"997ad451-7a34-434d-8022-c9aa12aab11d","year":2014},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.233937Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:7e040351360dc098de334a7ccf68df3589385c86ed7eb417cd87b35ea7854573","observation_id":"cd04d784-46dd-4645-9ac1-fc2aebed5815","resolution":{"observed_at":"2026-08-14T14:24:40.383504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.237685Z","title":"Dropout: A simple way to prevent neural networks from overfitting,","venue":null,"work_id":null,"year":1929},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.237685Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:780b94054bd4f9a78c9f98cbd8f538f7e6dc2d6dce8810719405633a963c2df6","observation_id":"ac9bc6e5-b49c-4514-891b-984c83ffbc35","resolution":{"observed_at":"2026-08-14T14:24:40.237685Z","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":"2026-08-14T14:24:40.362304Z","title":"Analyzing uncer- tainties in speech recognition using dropout,","venue":null,"work_id":"f3fd9fd0-d465-4daf-a0a2-60834721f832","year":2019},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.241700Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:57b62dbad9835f936038d099039aafe7e0ca0db7ffb40f7a1e634a4ce85d9189","observation_id":"03a6b331-57cb-47b0-ad1d-ff16b6ee7336","resolution":{"observed_at":"2026-08-14T14:24:40.366359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.352407Z","title":"Dropout as a bayesian approxima- tion: Representing model uncertainty in deep learning,","venue":null,"work_id":"08f0dc72-00aa-424c-abca-8dd45363956b","year":2016},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.244807Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:83b21b4b5c578e46de88f1760c0350aa37d6e9b9db7613c03b803ce6056a43fc","observation_id":"cc754603-bb6b-4f66-886a-7089eacf2467","resolution":{"observed_at":"2026-08-14T14:24:40.356089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.342963Z","title":"End-to-end speech recogni- tion with word-based rnn language models,","venue":null,"work_id":"8beffac2-ea58-44de-b79e-4db25899527d","year":2018},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.248087Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:18eeed9d80f6687689edb455ae207ee7f84b0c9a599b1d1949b6f636d73613e6","observation_id":"54f4e272-9b97-45af-8f5a-91c022bd188b","resolution":{"observed_at":"2026-08-14T14:24:40.346212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.333016Z","title":"Lib- rispeech: an asr corpus based on public domain audio books,","venue":null,"work_id":"dff81847-2a2d-499a-adf1-e27b69892699","year":2015},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.251318Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:7865e7f54b3ce32bc2c10a9b2cf560c391eed60898a5637f3dd22ebb4d355dfe","observation_id":"fa139695-5ee4-429f-b444-e7c5613dcc25","resolution":{"observed_at":"2026-08-14T14:24:40.336161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.323262Z","title":"Ted-lium: an automatic speech recognition dedicated corpus","venue":null,"work_id":"4403ff81-76c0-4765-88f2-07129051f2ad","year":2012},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.254641Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:9e7c994e848cca0278d861a965c2a483b4f85398704640f8102abf4d12b143bd","observation_id":"0c3ce407-e2ba-484d-a0ad-69227bee21ca","resolution":{"observed_at":"2026-08-14T14:24:40.326669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-14T14:24:40.258828Z","title":"The kaldi speech recognition toolkit,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:24:40.258828Z"},"links":{"citing_paper":"/paper/1908.05227"},"observation_digest":"sha256:9da9bf4c97312d388626fc344495f0e9a9b6e530140a50acc0d62c0b5bea2d18","observation_id":"27d639b6-e898-4444-b7a7-4ab78e3a77c7","resolution":{"observed_at":"2026-08-14T14:24:40.258828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.05227","last_updated":"2019-08-08T19:21:49Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-19T17:38:07.336241Z","submitted_at":"2019-08-08T19:21:49Z","title":"Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":19},"total_outbound_references":29},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 1 inbound Pith citation observation for arXiv:1908.05227."}