{"as_of":"2026-08-16T13:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:12e503aad704cd7959a6aa929c80cb620245dad1a2e3725231a0e05159dd3d18","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":"2026-08-14T11:29:49.860590Z","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":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.08898/citation-record","integrity":"/paper/1908.08898/integrity","json":"/paper/1908.08898/citation-record.json","paper":"/paper/1908.08898"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.279441Z","title":null,"venue":null,"work_id":"0f57f13a-85c0-480a-9446-ce86df1d9955","year":null},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.744131Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:4d01802f141087e03401dccc5d59fb6c2674c56d22a01c67d87e13249d2f8a40","observation_id":"6bff5f19-d84d-4457-a982-686dd424dcd3","resolution":{"observed_at":"2026-08-14T11:29:50.283333Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.266322Z","title":"Background: Bitwise Neural Networks Binarization has been explored as a method of network compression","venue":null,"work_id":"4e7d6e3d-c60e-45b9-bee3-32743c89e8df","year":null},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.748469Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:201f21f2f1676b10eda63f70b3bf77f665ac7278e7b948ce53e91878edf76b6a","observation_id":"143c669b-1d04-4c91-bc1d-3eb93b941cb2","resolution":{"observed_at":"2026-08-14T11:29:50.270548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.252503Z","title":"Experimental Setups For the experiment, we randomly subsample 12 speakers for tr ain- ing and 4 speakers for testing from the TIMIT corpus","venue":null,"work_id":"c6c4a7c5-7508-4d15-ace1-05fe59cbb4ed","year":2000},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.752008Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:c99aa45b5a01e7886b2f092e55adf679efc6acd5fc98663ba75778147ddfce31","observation_id":"a0323365-8e5b-4f31-87c6-335bd4e451cc","resolution":{"observed_at":"2026-08-14T11:29:50.257137Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.239970Z","title":"The training is done in two roun ds, first in a weight compressed network and then in an incrementa lly bitwise version with the same topology","venue":null,"work_id":"603cb4db-102d-4f76-8b1f-abf1d7d54cb3","year":null},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.755623Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:40fe3259b83c7a02e0fc255ea3d73149e3935662e535e4008723f7ea154c8dbf","observation_id":"ed4827d7-1b7a-455c-b717-e68348239600","resolution":{"observed_at":"2026-08-14T11:29:50.244092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.227800Z","title":"An experimental st udy on speech enhancement based on deep neural networks,","venue":null,"work_id":"dd46a737-df87-4e1c-8800-401bdf62c449","year":2014},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.759106Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:8fbed5514aea5d40b9a0af3d54fbc8fbdf0303214942c438decef0f5a77c29ec","observation_id":"0445699f-35ca-48d2-ba9d-134552882711","resolution":{"observed_at":"2026-08-14T11:29:50.231923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.215224Z","title":"Joint optimization of masks and deep recurrent neural net- works for monaural source separation,","venue":null,"work_id":"820b8ffb-1d45-401e-9f92-145d80d6f684","year":2015},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.762219Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:4926d8e8eba5519967be1a89ec7f1a28374f79694d1b48b51a17748cc8722532","observation_id":"00f5a2f4-2ed9-4b86-9d0a-4fb61aed26e9","resolution":{"observed_at":"2026-08-14T11:29:50.219686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.203103Z","title":"Multichannel au- dio source separation with deep neural networks.,","venue":null,"work_id":"11e211dc-388f-44e4-98c4-2fae216c14e7","year":2016},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.765216Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:2fec80f580972ba229caa8a3f1029851c4d49042d050f6e46773dab55bd01511","observation_id":"9165163a-be31-40fc-8aaa-55e4e846849a","resolution":{"observed_at":"2026-08-14T11:29:50.207055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:49.768888Z","title":"Towards scaling up classification- based speech separation,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.768888Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:4dcda874ee9b0f494f2cfb295c2eb2947848de104b781bd196e21a5bda5cf3a0","observation_id":"aa2fad1e-c384-4ca6-9940-25947ffd1573","resolution":{"observed_at":"2026-08-14T11:29:49.768888Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.184067Z","title":"Deep NMF for speech separation,","venue":null,"work_id":"241e0771-4a14-44c8-b31a-1f9d82addad3","year":2015},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.772462Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:7aae083fce410162b16f52f894f9acecf471a88d3393bbab1a71fac6bfb8d788","observation_id":"639f66da-9b8e-495e-b6e4-edae473347f4","resolution":{"observed_at":"2026-08-14T11:29:50.187536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:49.776166Z","title":"Deep neural net- works for single channel source separation,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.776166Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:9497ed5f88b5a92ca5e1f4be7966473e648f872b60a15c77a943e044c7feddce","observation_id":"2a36adad-f6cf-415b-9c50-22410a52e185","resolution":{"observed_at":"2026-08-14T11:29:49.776166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.163888Z","title":"Phase-sensitive and recognition-boosted speech separat ion using deep recurrent neural networks,","venue":null,"work_id":"9a25f4e0-b0a4-4219-8164-f3e385e7cca5","year":2015},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.779654Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:cfde9230f931ea1512a201d8d45ec8d5629892f5a828571f0f1f3c70e3d26840","observation_id":"8f6d5ae0-b715-475a-9ce2-3dd5586d5002","resolution":{"observed_at":"2026-08-14T11:29:50.167627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.151393Z","title":"Speech enhancement with LSTM recurrent neural networks and its application to noise - robust ASR,","venue":null,"work_id":"356f7ee0-4b25-441c-a1b3-11628f7bbb9b","year":2015},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.784196Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:5fbc81148bb4ea11eef7ba88176a3e23ef618dbe4f49ae1cf924c67cd4418f82","observation_id":"9984ef04-5b9b-47f2-b610-c5192d20ffb9","resolution":{"observed_at":"2026-08-14T11:29:50.155682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.139210Z","title":"Discriminatively trained recurrent neural networks for s ingle- channel speech separation,","venue":null,"work_id":"4b3ceaf7-f213-4b77-930d-cdc1899d7af3","year":2014},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.787822Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:8ad1c791366b00b8cb439c143835471fe293bd93b44a1313584fd7fb4632e70e","observation_id":"e63f312d-5f30-4e2d-abda-543a42f5d5cc","resolution":{"observed_at":"2026-08-14T11:29:50.143651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1607.02173","last_updated":"2016-07-07T21:06:48Z","snapshot_observed_at":"2026-08-14T21:49:19.478287Z","submitted_at":"2016-07-07T21:06:48Z","title":"Single-Channel Multi-Speaker Separation using Deep Clustering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.02173","snapshot_observed_at":"2026-08-14T11:29:49.791290Z","title":"Single-channel multi-speaker separation using deep clus ter- ing,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.791290Z"},"links":{"cited_paper":"/paper/1607.02173","citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:e009ea30fdc9fb71dbe65da39cf512dbd693c30568f46c6a9dda686875eabe3f","observation_id":"6a6f2fb8-71eb-4d09-8eda-7e405218bd4d","resolution":{"observed_at":"2026-08-14T11:29:49.791290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.127240Z","title":"Spe ech enhancement and recognition using multi-task learning of l ong short-term memory recurrent neural networks,","venue":null,"work_id":"ff8e31cb-b32e-47e5-86a7-2d65105c1924","year":2015},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.795225Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:4bdcd6981f581219565f749d4dd6f3c02144503c08691fc640fa640a255c28ea","observation_id":"84922573-4942-4ce0-bcc6-e8a26582dbb4","resolution":{"observed_at":"2026-08-14T11:29:50.131444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.115308Z","title":"Learning long-t erm dependencies with gradient descent is difficult,","venue":null,"work_id":"aed4a694-484e-403d-b93f-316873c2a896","year":1994},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.798633Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:3661485f0312309e0c64a0c13b0f965caeceae8acedb9bf141439cb2acae2987","observation_id":"10d7a8e9-b414-4ce2-a23d-c26a278597a6","resolution":{"observed_at":"2026-08-14T11:29:50.119378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.103923Z","title":"An efficient gradient-based al- gorithm for on-line training of recurrent network trajecto ries,","venue":null,"work_id":"64ef7937-34b6-41fa-b075-5ac21dff3cc3","year":1990},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.801741Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:b2c9b1e22359eb7627e50375bc6d42f11a6cc9e9865b44566d549863fdccfd7c","observation_id":"1c9df97e-c8fd-4268-857b-ce501ef5aa4e","resolution":{"observed_at":"2026-08-14T11:29:50.107927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.092437Z","title":"Sutskever, Training recurrent neural networks , University of Toronto Toronto, Ontario, Canada, 2013","venue":null,"work_id":"9797104d-01c2-4b35-8b83-a87c4f810e89","year":2013},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.804522Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:622c11e1ca3d7f9684e07efe29a9d512a45269265319e1e9a929d89af8fd21e0","observation_id":"bd73657f-60c7-422a-a276-db004b9d11ab","resolution":{"observed_at":"2026-08-14T11:29:50.096192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.1078","last_updated":"2014-09-03T00:25:02Z","snapshot_observed_at":"2026-08-15T13:36:27.756066Z","submitted_at":"2014-06-03T17:47:08Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.1078","snapshot_observed_at":"2026-08-14T11:29:49.807485Z","title":"Learning phrase representations using RNN encoder-decoder for statistica l ma- chine translation,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.807485Z"},"links":{"cited_paper":"/paper/1406.1078","citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:38a27726a367fd5cf25af745e2997d99c8913058596d62d52f84820378b33b5f","observation_id":"32413502-d906-4e71-a8a9-d078e0a9ec53","resolution":{"observed_at":"2026-08-14T11:29:49.807485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.080585Z","title":"Bitwise neural networks for ef fi- cient single-channel source separation,","venue":null,"work_id":"bc600219-6b69-4024-b9f3-a7157c99d553","year":2018},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.810798Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:cb0dd1c0757e8fc92ba711f3d11096970e8a7d7dd6d3c1e580a0f42e72c8b3ad","observation_id":"87dd2193-fd60-4634-bc9d-47b3c5e96f8f","resolution":{"observed_at":"2026-08-14T11:29:50.084591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.069743Z","title":"BinaryCon- nect: Training deep neural networks with binary weights dur - ing propagations,","venue":null,"work_id":"e95e117a-9264-4ade-9af1-732c91befa7e","year":2015},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.813981Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:75e261832a15ac11f053c648a6eeb2afa2239b08a264616ccd5cffb513ad412b","observation_id":"c160e1ea-bdee-4ef6-95e7-1e1fdfcf511f","resolution":{"observed_at":"2026-08-14T11:29:50.073123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06902","last_updated":"2017-02-26T14:01:40Z","snapshot_observed_at":"2026-08-14T21:42:56.354467Z","submitted_at":"2016-08-24T17:15:29Z","title":"Recurrent Neural Networks With Limited Numerical Precision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06902","snapshot_observed_at":"2026-08-14T11:29:49.816913Z","title":"Recurrent neural networks with limited nu- merical precision,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.816913Z"},"links":{"cited_paper":"/paper/1608.06902","citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:339696c41a5e861c8b2e3b115e6713faab1ba4bfc0df773e9f01e429faafe709","observation_id":"e1cd9de2-3fc4-4dab-a729-2f299781980a","resolution":{"observed_at":"2026-08-14T11:29:49.816913Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.058996Z","title":"Binarized neural networks,","venue":null,"work_id":"223a7a72-1b3e-487a-b096-dbad29e387ba","year":2016},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.820290Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:e49fcac9a15f2645e406dccce32e26e0155f926c967ee77721681c5adea29d6c","observation_id":"b2bfcd85-3ae7-4e2e-aa9f-195e9e74a28c","resolution":{"observed_at":"2026-08-14T11:29:50.062085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.045728Z","title":"Xn or- net: Imagenet classification using binary convolutional ne u- ral networks,","venue":null,"work_id":"8ac68f04-544a-474f-bc4b-73517efb55de","year":2016},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.823872Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:b7dd0a4b5608fa2c9ea6b86fffd9e5bea80df1896c81662ec02466ace3a226a9","observation_id":"a4d34216-04da-4aaf-9cc2-643688669a96","resolution":{"observed_at":"2026-08-14T11:29:50.049868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.033257Z","title":"Analysis of high-performance floating-point arithmetic on fpgas,","venue":null,"work_id":"66438161-d62f-4f57-8866-06f46a632f3a","year":2004},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.827943Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:d9228ff3dcbf474703c452621f5a3f4a51ccecb46eb46204b8ca8fa9f1ce31f8","observation_id":"5c34511b-a156-4cf5-927e-5cc79231e52d","resolution":{"observed_at":"2026-08-14T11:29:50.038136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.020463Z","title":"Embedded floating-point units in fpgas,","venue":null,"work_id":"14092498-8de2-47d8-9cb8-65701b5c8f68","year":2006},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.831590Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:be6861af8d209f37735f198294f8bff9fd62c21d52b309655af23897188e6582","observation_id":"ef261f76-cd3e-49b0-a962-3920ca8a2faf","resolution":{"observed_at":"2026-08-14T11:29:50.025164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:50.007141Z","title":"Fixed-point feedforward deep neu ral network design using weights+ 1, 0, and- 1,","venue":null,"work_id":"2913e57e-aaa2-407c-bc3e-0335baff1baa","year":2014},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.835584Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:d060433159815baa5d763308efebd42208c3372004b9db143b126e41a761e58f","observation_id":"d83bad29-3458-4dce-84e3-ac1907fcdd59","resolution":{"observed_at":"2026-08-14T11:29:50.011825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.7024","last_updated":"2015-09-23T01:00:44Z","snapshot_observed_at":"2026-08-14T23:06:28.503239Z","submitted_at":"2014-12-22T15:22:45Z","title":"Training deep neural networks with low precision multiplications","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.7024","snapshot_observed_at":"2026-08-14T11:29:49.839382Z","title":"Training de ep neural networks with low precision multiplications,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.839382Z"},"links":{"cited_paper":"/paper/1412.7024","citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:de8d692d3ba0a67baf4b544821cfb92e798efd20c3d92db33da3f264f24148f1","observation_id":"cee85240-acf9-4ab7-85ae-02656e19cb38","resolution":{"observed_at":"2026-08-14T11:29:49.839382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.01064","last_updated":"2017-02-23T06:52:28Z","snapshot_observed_at":"2026-08-14T21:27:15.285323Z","submitted_at":"2016-12-04T05:00:22Z","title":"Trained Ternary Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.01064","snapshot_observed_at":"2026-08-14T11:29:49.843151Z","title":"Trained ternary quantization,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.843151Z"},"links":{"cited_paper":"/paper/1612.01064","citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:86c99557faa30dc6ab630d4745dedadb173ad4aaa5509030365edb2886ab8505","observation_id":"f48b7940-80dd-414d-87f9-a0f91bd41a89","resolution":{"observed_at":"2026-08-14T11:29:49.843151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:49.991248Z","title":"Bitwise neural networks,","venue":null,"work_id":"6f03e1ce-799e-4c4c-8a1f-9a6f9266096c","year":2015},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.847056Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:48203cc2b6ddcd0553e330ca7f3aaac839477484cf50ef207e170dcad7bd9320","observation_id":"12596f09-3325-44fe-90ff-efc1961b9ba3","resolution":{"observed_at":"2026-08-14T11:29:49.994552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:49.978880Z","title":"Least squares quantization in PCM,","venue":null,"work_id":"b6f852fe-0211-4ba8-8e2b-cac46b69a8f0","year":1982},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.850565Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:267c09fe648fa6f979ae835b6ead4970b49cf1923bfcd1e3322e6a135629f32b","observation_id":"019688fd-4c00-427b-9b4c-2db55a2d9dd0","resolution":{"observed_at":"2026-08-14T11:29:49.982791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:49.966521Z","title":"Online PLCA for real-time semi-supervised source separation,","venue":null,"work_id":"73c9556f-6119-4e93-8820-7de41bda67de","year":2012},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.853692Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:e1f984b8b16eef7734fb896769e7e3745f5db3364a7739cb0a83381857db5e8a","observation_id":"da452e2f-43b1-475b-b365-f1952b094598","resolution":{"observed_at":"2026-08-14T11:29:49.969911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:49.956243Z","title":"Performanc e mea- surement in blind audio source separation,","venue":null,"work_id":"b653181d-a0a5-40bb-8faa-c75c3f20c44d","year":2006},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.857147Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:8bd36584209f5ed9a7fda2ccd61dd20c0a5f5cdbd3e1cf93f7ba15eda2f4e418","observation_id":"ea9c3f42-ed2e-4c4a-8cb5-1e0ad664e296","resolution":{"observed_at":"2026-08-14T11:29:49.959496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T11:29:49.941660Z","title":"A short-time objective intelligibility measure for time-fr equency weighted noisy speech,","venue":null,"work_id":"d59bfbff-d148-4096-8320-1518385f734f","year":2010},"citing_paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T11:29:49.860590Z"},"links":{"citing_paper":"/paper/1908.08898"},"observation_digest":"sha256:88958a5c017a166db8599d6986c3a94768cfaf017d1c28bfcc1a7c73455534b5","observation_id":"9dafc297-33a0-4525-8049-424d0d8aade2","resolution":{"observed_at":"2026-08-14T11:29:49.948012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.08898","last_updated":"2019-08-23T16:38:02Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-14T11:24:08.769325Z","submitted_at":"2019-08-23T16:38:02Z","title":"Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":25},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:1908.08898."}