{"as_of":"2026-08-14T08:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:42c7921d2fc41cd2b2ca8dbffeddd1a97e1614bfdf2e298b9d06dd4a673da8fe","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":"2026-08-12T16:47:26.023182Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+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":"2026-08-12T16:47:25.902060Z","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":"2026-08-12T16:47:26.160280Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"cited_work":{"arxiv_id":"2411.14489","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.14489","snapshot_observed_at":"2026-08-12T16:47:26.160280Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","venue":"cs.CL","work_id":"cd2c4841-6449-45c1-b9c2-ac349d19ada6","year":2024},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.902060Z"},"links":{"cited_paper":"/paper/2411.14489","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:df9a6ee97a922e6b79ca46cd358719f1033d290e88bca3ae2164f3394cb62acd","observation_id":"5374ae97-75af-47ac-9644-2c5eecd9220a","resolution":{"observed_at":"2026-08-12T16:47:26.164550Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.14489/citation-record","integrity":"/paper/2411.14489/integrity","json":"/paper/2411.14489/citation-record.json","paper":"/paper/2411.14489"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.414144Z","title":null,"venue":null,"work_id":"c464111c-d8d4-4549-847a-9716a38801a3","year":null},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.897566Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:994b0dd0c20f220a525ab56eeee0e3b17ae91c69679562bacca47fdd3413428c","observation_id":"e3568320-910f-43a4-bf06-b473f4b010af","resolution":{"observed_at":"2026-08-12T16:47:26.418061Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.402023Z","title":"Without loss of generality, we use GRU to illustrate the definition of GhostRNN","venue":null,"work_id":"0bdd7b03-d7c3-4612-a4eb-341bb81beac4","year":null},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.906495Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:2e927c40e4c711774ebf77b29788c3e4a948a3d9c7ef4e84510f92d09051654f","observation_id":"94679594-71d8-4573-adf8-85260f7e2eba","resolution":{"observed_at":"2026-08-12T16:47:26.405867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.390749Z","title":null,"venue":null,"work_id":"d1597f20-8189-41db-9198-bb23ecc17568","year":null},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.910806Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:6d770270056ddcb49d63e21b135d13c8a32e15af0ca5a2963b981d8a37cd0e5c","observation_id":"5f9e2e86-a684-492f-8d9e-87743a5b4042","resolution":{"observed_at":"2026-08-12T16:47:26.394295Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.367675Z","title":null,"venue":null,"work_id":"0836882c-4d07-4076-b7fe-6b444b7ce88f","year":null},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.919197Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:c1cdb85243361d8a0326ad97ce566dcb65c460725836d25b55b74ef8232b0bd3","observation_id":"e4b5ec7e-4738-44dd-a443-51ca857308a6","resolution":{"observed_at":"2026-08-12T16:47:26.371068Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.378429Z","title":"• GRU-TasNet","venue":null,"work_id":"7c681feb-967e-4d8f-b2bb-d5f967cd5d2c","year":null},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.915157Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:bcbebd28db5c1cd549ff466d02d6097f3f396a999059fe65b4d494eec81019ec","observation_id":"363878b9-a5e7-4303-920e-da0cd473cf93","resolution":{"observed_at":"2026-08-12T16:47:26.382275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:25.947634Z","title":"Dual-path rnn: efficient long sequence modeling for time-domain single-channel speech sepa- ration,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.947634Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:109ca387cfd0d147972ade176d0bd92e357db70d960b94a8e534ee8dd2669569","observation_id":"2b8225d9-a6e8-4415-aa01-54e22c97feed","resolution":{"observed_at":"2026-08-12T16:47:25.947634Z","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":"2026-08-12T16:47:26.356554Z","title":"2022D01D43)","venue":null,"work_id":"9db57e78-6a9e-4ab7-82b3-b01e6ba698eb","year":null},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.923108Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:abe28ae75589634364fba869d8ec6b27706102f60021775a328e42045eee2f4a","observation_id":"988edbb8-8b94-4afb-974f-42a62a44c403","resolution":{"observed_at":"2026-08-12T16:47:26.360545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:25.926924Z","title":"Long short-term memory,","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.926924Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:eb125c7d2401c5608ee9800968e1b8d84c27ef1d038779481e2c4fe881ad244b","observation_id":"a6c04cf5-8fec-4507-a5a0-49e8a34c8bef","resolution":{"observed_at":"2026-08-12T16:47:25.926924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.3555","last_updated":"2014-12-11T06:46:53Z","snapshot_observed_at":"2026-08-13T10:35:27.214652Z","submitted_at":"2014-12-11T06:46:53Z","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.3555","snapshot_observed_at":"2026-08-12T16:47:25.931065Z","title":"Empirical evalu- ation of gated recurrent neural networks on sequence modeling,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.931065Z"},"links":{"cited_paper":"/paper/1412.3555","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:c9c2534b025265d844ca430c753fbb313fd2ef12d15a447b4e4d5c29b8dbe80e","observation_id":"3589998f-ccce-4c3f-81c7-969cf5214c27","resolution":{"observed_at":"2026-08-12T16:47:25.931065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.07128","last_updated":"2018-02-14T19:24:55Z","snapshot_observed_at":"2026-07-06T06:10:16.792443Z","submitted_at":"2017-11-20T03:19:03Z","title":"Hello Edge: Keyword Spotting on Microcontrollers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.07128","snapshot_observed_at":"2026-08-12T16:47:25.935118Z","title":"Hello edge: Keyword spotting on microcontrollers,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.935118Z"},"links":{"cited_paper":"/paper/1711.07128","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:7f78d7e91dde14a7e5333b67ea44b8ac8158829438420dfe6b0fc798601cd8d9","observation_id":"402039aa-da20-4d56-b821-93727f00fd4d","resolution":{"observed_at":"2026-08-12T16:47:25.935118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.06720","last_updated":"2020-07-29T01:53:16Z","snapshot_observed_at":"2026-08-12T05:50:15.907244Z","submitted_at":"2020-05-14T05:05:22Z","title":"Streaming keyword spotting on mobile devices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.06720","snapshot_observed_at":"2026-08-12T16:47:25.938967Z","title":"Streaming keyword spotting on mobile devices,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.938967Z"},"links":{"cited_paper":"/paper/2005.06720","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:f0d7ccea889d4252dfe78ded129708cfb3fdf149bda7e748ec9a93093016169b","observation_id":"6a70889e-6b8d-4898-8371-8a4f93ecfb1f","resolution":{"observed_at":"2026-08-12T16:47:25.938967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.00264","last_updated":"2020-09-23T03:16:28Z","snapshot_observed_at":"2026-08-14T07:21:56.171937Z","submitted_at":"2020-08-01T13:42:29Z","title":"DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.00264","snapshot_observed_at":"2026-08-12T16:47:25.942936Z","title":"Dccrn: Deep complex convolution re- current network for phase-aware speech enhancement,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.942936Z"},"links":{"cited_paper":"/paper/2008.00264","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:8849b44d41801b4927a4d57f898be4fe6b769ec33d6a2a2745ddc51218d54a9a","observation_id":"f1ac0804-7ed9-407f-95e7-35c4cadf0e5b","resolution":{"observed_at":"2026-08-12T16:47:25.942936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"cited_work":{"arxiv_id":"2411.14489","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.14489","snapshot_observed_at":"2026-08-12T16:47:26.160280Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","venue":"cs.CL","work_id":"cd2c4841-6449-45c1-b9c2-ac349d19ada6","year":2024},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.902060Z"},"links":{"cited_paper":"/paper/2411.14489","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:df9a6ee97a922e6b79ca46cd358719f1033d290e88bca3ae2164f3394cb62acd","observation_id":"5374ae97-75af-47ac-9644-2c5eecd9220a","resolution":{"observed_at":"2026-08-12T16:47:26.164550Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:25.951185Z","title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.951185Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:afee5f35c69c970297a6d186548f5a1be65ab91b28fa78fc03c1be1dffcfcc2f","observation_id":"9244c02e-7823-42e2-ae91-34d505058800","resolution":{"observed_at":"2026-08-12T16:47:25.951185Z","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":"2026-08-12T16:47:26.323274Z","title":"Nonlinear residual echo sup- pression using a recurrent neural network","venue":null,"work_id":"a03b59ca-e3c9-45aa-9109-3c3ca2b47af6","year":2020},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.954576Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:53542112dfdaf3231b771c83afe204f51bba5f1d0059d9b7a98b4d6da68d6841","observation_id":"c3180c84-01bc-4dcd-ba19-e0170fd3c921","resolution":{"observed_at":"2026-08-12T16:47:26.327222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.09237","last_updated":"2020-05-19T06:25:52Z","snapshot_observed_at":"2026-08-13T22:40:43.335242Z","submitted_at":"2020-05-19T06:25:52Z","title":"Acoustic Echo Cancellation by Combining Adaptive Digital Filter and Recurrent Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.09237","snapshot_observed_at":"2026-08-12T16:47:25.958214Z","title":"Acoustic echo cancellation by combining adaptive digital filter and recurrent neural network,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.958214Z"},"links":{"cited_paper":"/paper/2005.09237","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:7a876ba415eacd55b234dbad9fed78628dbf89f5cbcfc4afa9f7b15ab327552f","observation_id":"1f7f7795-488c-4347-81c8-8c89efbedb99","resolution":{"observed_at":"2026-08-12T16:47:25.958214Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:25.961800Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.961800Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:30a2c8f4e1d684a75d364c956732c18d14d515503d2142c3d3ebf5aab940e815","observation_id":"e668f69f-ed9a-49cd-948b-20a1b58c69b3","resolution":{"observed_at":"2026-08-12T16:47:25.961800Z","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":"2026-08-12T16:47:26.303330Z","title":"Gate-variants of gated recurrent unit (gru) neural networks,","venue":null,"work_id":"e8fdd208-2c5a-4c1d-92fc-6521a2940103","year":2017},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.965311Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:136fc7f0114f76aa61f1789e45d5abd7cee9aa337c7ec220706a605d4c19eff3","observation_id":"4fe06d07-22ba-4577-ac27-a4a1ce20afd0","resolution":{"observed_at":"2026-08-12T16:47:26.307340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.291333Z","title":"Light gated recurrent units for speech recognition,","venue":null,"work_id":"65a487f7-e783-4062-a1b0-da118299b9c8","year":2018},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.968616Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:cf1a95719f3642423755ccd0701702511ff04571b2430b877d3352f69fb0f4ac","observation_id":"075d4fcf-6ea0-4876-aaec-c133df461daf","resolution":{"observed_at":"2026-08-12T16:47:26.295638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.277952Z","title":"An optimized recurrent unit for ultra- low-power keyword spotting,","venue":null,"work_id":"523f5e6f-4143-4e73-8fc4-33561a8cc3c0","year":2019},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.972172Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:ebf1bb73b3d818cf74c23c6d7256dea898727968112ee9860a4e773922a18915","observation_id":"17923d87-e2d7-4c91-8750-11d14ff961e2","resolution":{"observed_at":"2026-08-12T16:47:26.281785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.266062Z","title":"Sitgru: single-tunnelled gated re- current unit for abnormality detection,","venue":null,"work_id":"77612f06-dfd7-418e-849d-9111307ff6d5","year":2020},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.975655Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:42f69cc2e3a19473bf926966698728c5ceef127b8b484d55c36295c17cafb939","observation_id":"deff5774-f97a-4b5d-9cf7-f366d794e7cb","resolution":{"observed_at":"2026-08-12T16:47:26.269867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.12546","last_updated":"2018-10-30T06:55:23Z","snapshot_observed_at":"2026-07-06T07:11:21.870009Z","submitted_at":"2018-10-30T06:55:23Z","title":"Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks","version":1},"cited_work":{"arxiv_id":"1810.12546","doi":null,"metadata_source":"pith","pith_arxiv_id":"1810.12546","snapshot_observed_at":"2026-08-12T16:47:26.086086Z","title":"Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks","venue":"cs.CL","work_id":"8ed1a778-664e-45c6-a077-fefb243e44bb","year":2018},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.979428Z"},"links":{"cited_paper":"/paper/1810.12546","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:fa5d5798716a8353c306cf79cfd6ce3646a96372eeac88dd116287cb37467086","observation_id":"2b53ce4a-d6cb-4ea4-a403-040f112acd88","resolution":{"observed_at":"2026-08-12T16:47:26.092088Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.255016Z","title":"Ghost- net: More features from cheap operations,","venue":null,"work_id":"e6201369-06cd-42b2-88e9-6a4bc68a195c","year":2020},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.983076Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:9b63dc4d8a70ed21b2a9a3a8f328caaff378759782ff7b68cb61d2be0f175340","observation_id":"a4a77769-d9b4-4746-87b6-bdf97643cf0b","resolution":{"observed_at":"2026-08-12T16:47:26.258852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.242880Z","title":"Learning long-term de- pendencies with gradient descent is difficult,","venue":null,"work_id":"f007ba49-6a9b-46c4-a29b-ed3d65baed6e","year":1994},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.986652Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:b7a07a4144ff43fae91fba59695f674f1740f1b3871a0586c568086de542b1e6","observation_id":"dc5f7d78-60bc-4768-aea4-c7d5b7d45bff","resolution":{"observed_at":"2026-08-12T16:47:26.246616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-07-06T06:32:32.083176Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-08-12T16:47:25.990379Z","title":"Speech commands: A dataset for limited-vocabulary speech recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.990379Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:86434c0dd8b2d705d4222b6874c3521aa38354194702b60ef6cd68ae2b52304b","observation_id":"845bdd0f-c5af-43f9-b3ea-f1b5eccd1fe9","resolution":{"observed_at":"2026-08-12T16:47:25.990379Z","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":"2026-08-12T16:47:26.231337Z","title":"End-to-end low resource keyword spotting through character recognition and beam-search re-scoring,","venue":null,"work_id":"880f6856-be5e-453e-b5da-66e7e442d600","year":2022},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.993990Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:b0b2c6337aa0cff4dfb36fb91e38e3edb6c118232b1ee44be6a04fe606364472","observation_id":"6f62c89c-bb19-4c9d-a1a8-176ef37e330e","resolution":{"observed_at":"2026-08-12T16:47:26.235390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.11262","last_updated":"2020-05-22T16:26:54Z","snapshot_observed_at":"2026-08-10T10:54:26.224254Z","submitted_at":"2020-05-22T16:26:54Z","title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.11262","snapshot_observed_at":"2026-08-12T16:47:25.997599Z","title":"Librimix: An open-source dataset for generalizable speech separation,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:25.997599Z"},"links":{"cited_paper":"/paper/2005.11262","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:9fd2d2f637defad3f923d45e2d3344bbde95feeed01f11eaae9fe456eeb2f62c","observation_id":"7619ca74-a52c-444c-9310-ace1ec8b0838","resolution":{"observed_at":"2026-08-12T16:47:25.997599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.001398Z","title":"Lib- rispeech: an asr corpus based on public domain audio books,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:26.001398Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:3987332cacf7820395a5e46b42eea9d5708dbe5aaf7619808c5d43b463a0b1a7","observation_id":"efa4e11b-432b-47a1-a513-18bff2d8ace4","resolution":{"observed_at":"2026-08-12T16:47:26.001398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.01160","last_updated":"2019-07-02T04:27:55Z","snapshot_observed_at":"2026-07-06T08:04:17.909965Z","submitted_at":"2019-07-02T04:27:55Z","title":"WHAM!: Extending Speech Separation to Noisy Environments","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.01160","snapshot_observed_at":"2026-08-12T16:47:26.005454Z","title":"Wham!: Extend- ing speech separation to noisy environments,","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:26.005454Z"},"links":{"cited_paper":"/paper/1907.01160","citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:24b1b8d6204f6b28c362390f80eb9f8deed8489f75b7b517de89432e1da6708b","observation_id":"77ce84e3-9121-4d41-ab6d-f94e2fb956b9","resolution":{"observed_at":"2026-08-12T16:47:26.005454Z","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":"2026-08-12T16:47:26.213257Z","title":"As- teroid: the PyTorch-based audio source separation toolkit for re- searchers,","venue":null,"work_id":"a26f80b0-b971-40dd-8109-c9a148ac9508","year":2020},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:26.009193Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:b4eae2a686efd51ab58677a0bf954f1dcf352123d151664d1d461fce1b7f13d0","observation_id":"2a1d9669-c51f-4158-a5ba-0c344b9106e3","resolution":{"observed_at":"2026-08-12T16:47:26.217298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.200612Z","title":"Real-time single-channel dereverbera- tion and separation with time-domain audio separation network","venue":null,"work_id":"26609a27-0b7f-4d7c-ad79-f5dffb891e49","year":2018},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:26.012509Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:a8ac07b6ab22d5142a46eb0c7fe88e97f58e694b78429a9465c97d80c9bac750","observation_id":"d2d9582c-95e1-4159-91a0-4f73c16de4da","resolution":{"observed_at":"2026-08-12T16:47:26.204677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.016503Z","title":"Sdr– half-baked or well done?","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:26.016503Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:841b5089eabde0765093259d43b26f124f8b5dbeec83e362386074cd27b76c76","observation_id":"5b794d19-376e-43b9-90b7-9baef6cb5a66","resolution":{"observed_at":"2026-08-12T16:47:26.016503Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:47:26.019934Z","title":"An al- gorithm for intelligibility prediction of time–frequency weighted noisy speech,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:26.019934Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:84255f2c5fd4fd8df6062f57192df03d5be11c6115c02187066609e3df210496","observation_id":"11185d92-5f08-4e1a-8684-697908774185","resolution":{"observed_at":"2026-08-12T16:47:26.019934Z","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":"2026-08-12T16:47:26.173002Z","title":"Mindspore,","venue":null,"work_id":"82d49f44-0839-4fe0-bf82-25c79027e916","year":2020},"citing_paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T16:47:26.023182Z"},"links":{"citing_paper":"/paper/2411.14489"},"observation_digest":"sha256:b230e8ea26defd63478db895ef29f84e9df23e992fed40be8989717c1625af09","observation_id":"e28ef1ee-d7a3-463d-a36a-f2485f9c79b0","resolution":{"observed_at":"2026-08-12T16:47:26.177286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.14489","last_updated":"2024-11-20T11:37:14Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-14T00:03:16.885025Z","submitted_at":"2024-11-20T11:37:14Z","title":"GhostRNN: Reducing State Redundancy in RNN with Cheap Operations"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":17,"verified_exact":1,"verified_fuzzy":14},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 1 inbound Pith citation observation for arXiv:2411.14489."}