{"as_of":"2026-08-08T01:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:09ee0ee2fac4a4b09d039c749593f9ad13a4eb9cdad823765dee558eea4e62a2","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:44:22.463974Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:44:17.627464Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-09T06:00:36.671800Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.21245","snapshot_observed_at":"2026-08-07T13:44:17.627464Z","title":"I love speech","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:17.627464Z"},"links":{"cited_paper":"/paper/2505.21245","citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:5edcfa15043b2bc747b2cdd231fb3e9193474e0758f99a1ca5be282c9c4b258a","observation_id":"58fa2f1c-41f9-4086-8d6e-b92e68a5b606","resolution":{"observed_at":"2026-08-07T13:44:17.627464Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.21245","snapshot_observed_at":"2026-08-02T18:35:51.825052Z","title":"Towards one-bit asr: Extremely low-bit con- former quantization using co-training and stochastic precision,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-07T18:54:26.046430Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:51.825052Z"},"links":{"cited_paper":"/paper/2505.21245","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:31bd53b08d79eac41fbf155ebb632baa15b32f37d6bb4deef9c66cdba5a2a0b6","observation_id":"89dc3a56-2a50-44f8-a0cf-4f27dce61e0f","resolution":{"observed_at":"2026-08-02T18:35:51.825052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"cited_work":{"arxiv_id":"2505.21245","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.21245","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards one-bit asr: Extremely low-bit conformer quantization using co-training and stochastic precision","venue":null,"work_id":"618966ba-930d-4fd9-8efe-ef2551aedc29","year":2025},"citing_paper":{"arxiv_id":"2605.03039","last_updated":"2026-05-04T18:06:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-04T18:06:17Z","title":"Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-05-08T19:11:30.638672Z"},"links":{"cited_paper":"/paper/2505.21245","citing_paper":"/paper/2605.03039"},"observation_digest":"sha256:be2a3dc00cf37eefa61dc3d31176dbbb6705f8bc058a3badd146877c6165518e","observation_id":"53466c5b-b27d-49b0-a4d8-43f95ea83a94","resolution":{"observed_at":"2026-05-09T06:00:36.675160Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.21245/citation-record","integrity":"/paper/2505.21245/integrity","json":"/paper/2505.21245/citation-record.json","paper":"/paper/2505.21245"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:44:30.062726Z","title":"However, performance progress tends to accompany an increasing number of model parameters and the need for computation and storage resources [7]","venue":null,"work_id":"38e96d89-a5df-447e-be8d-84ca3240ee5b","year":null},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:17.517077Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:086bdcea91458223dc70cea40887b4ab24f9a9f5700ffe6680e07955fe80eb62","observation_id":"cfb7af36-e904-437e-b18f-0dafb1d8d1e9","resolution":{"observed_at":"2026-08-07T13:44:30.160284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.21245","snapshot_observed_at":"2026-08-07T13:44:17.627464Z","title":"I love speech","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:17.627464Z"},"links":{"cited_paper":"/paper/2505.21245","citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:5edcfa15043b2bc747b2cdd231fb3e9193474e0758f99a1ca5be282c9c4b258a","observation_id":"58fa2f1c-41f9-4086-8d6e-b92e68a5b606","resolution":{"observed_at":"2026-08-07T13:44:17.627464Z","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":"2026-08-07T13:44:29.872442Z","title":"Conformer) is a popular E2E ASR architecture that achieves state-of-the-art performance on many speech recognition tasks [1]","venue":null,"work_id":"1beb958d-2be5-48c8-a115-910d9d9dd644","year":null},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:17.742043Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:932648505ffd74e0b08bfc593a94921fbd8d9426c4792f6bb9a478a6d31b0120","observation_id":"fc31bfd2-0df8-468d-8010-b0024d83df23","resolution":{"observed_at":"2026-08-07T13:44:29.971626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:29.688568Z","title":null,"venue":null,"work_id":"aa7806fd-2de0-49b8-a469-8ba300057688","year":null},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:17.831227Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:d19ed59536f92ce36655e920f854d490c50a6a31c09ff890a7580bfd57a2a0ec","observation_id":"40ff06b2-2dd8-48dd-a1b9-00a0458760cd","resolution":{"observed_at":"2026-08-07T13:44:29.776718Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:29.531730Z","title":"Experimental Setup We conduct experiments on two commonly used ASR datasets:","venue":null,"work_id":"ae0d722e-257d-4b3d-a02d-5981ab219aa4","year":null},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:18.020534Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:26a803773da5931c908fc18778d6fab08a663795a2793bfbb10c00aa28e58f1f","observation_id":"40d89875-2cee-40cb-bc30-810b485c28d5","resolution":{"observed_at":"2026-08-07T13:44:29.600730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:29.365357Z","title":"espnet/egs2","venue":null,"work_id":"a60de976-dd66-43ea-8c20-b884f8ff2881","year":null},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:18.167549Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:b0d856d54488eee129b7c777ec178368f7f73aeb83e76e57c64c48fab677bd15","observation_id":"f5bf84ac-c73a-4a40-b7b2-1f870dea6eae","resolution":{"observed_at":"2026-08-07T13:44:29.434015Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:29.169830Z","title":"We achieved performance-lossless 2-bit and 1-bit quantization of Conformer systems","venue":null,"work_id":"45a54948-70dd-4b18-a378-194960597703","year":null},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:18.292686Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:dd1d887a35b877eaba24d574d66524dec28fe2d65c1fa628267da18c24ee069e","observation_id":"0fabc46b-f9bb-47a8-8d65-3183379724f6","resolution":{"observed_at":"2026-08-07T13:44:29.276206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:18.466620Z","title":"14200220, 14200021, 14200324 and Innovation Technology Fund grant No","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:18.466620Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:7835d36aed492e12424d9f3635d80ea044431239e9ce8501ddefcbc7b63eeccc","observation_id":"1139263b-93f7-45fb-bcbd-949a08caaabd","resolution":{"observed_at":"2026-08-07T13:44:18.466620Z","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":"2026-08-07T13:44:18.599658Z","title":"Conformer: Convolution- augmented transformer for speech recognition,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:18.599658Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:f315f1ddf099711ea2f47474ae1ce4002e3ee596fafeebc285e9dcd1ddbfbffd","observation_id":"4d1b62d6-40b4-4ee5-9a4e-18ccf2601336","resolution":{"observed_at":"2026-08-07T13:44:18.599658Z","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":"2026-08-07T13:44:28.995929Z","title":"Branchformer: Parallel MLP-attention architectures to capture local and global context for speech recognition and understanding,","venue":null,"work_id":"8b0a306c-f26d-481b-88ca-b75be2ff7c0f","year":2022},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:18.807731Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:48c974fae6a7599d50d3a879fdebfc88b96801a4592b35eebbad6c7a88380e1c","observation_id":"b256af62-bb36-426a-94a5-d317295ff7ae","resolution":{"observed_at":"2026-08-07T13:44:29.096736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:18.994311Z","title":"wav2vec 2.0: A framework for self-supervised learning of speech representa- tions,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:18.994311Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:4a16f34a9acea98ec56741f481e003bfffe78944266faeac350522dda76e58d9","observation_id":"bfef0b33-801d-4897-a6c4-de8ddf06cf4d","resolution":{"observed_at":"2026-08-07T13:44:18.994311Z","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":"2026-08-07T13:44:28.800200Z","title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units,","venue":null,"work_id":"4a613f19-0f54-47b2-8332-bb9bfc9d87db","year":2021},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:19.118758Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:2570c108dbc360e7801daacd19e659dacc5ed18bb15e663960cd8e53c5ebc531","observation_id":"f60906ee-61ea-4614-9cf0-1e43f4729880","resolution":{"observed_at":"2026-08-07T13:44:28.896269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:28.619599Z","title":"Zipformer: A faster and better encoder for automatic speech recognition,","venue":null,"work_id":"f5fd1a65-909b-4ac6-a2ba-82ea848083bc","year":2023},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:19.233941Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:7d388cdf26339f67192236197a9afdafe518d9599cf28c1a9d40cba9c2cd3d6f","observation_id":"85fe9dfe-ec92-4ad5-a523-3dfd362798f9","resolution":{"observed_at":"2026-08-07T13:44:28.703874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:28.453944Z","title":"Hybrid CTC/attention architecture for end-to-end speech recog- nition,","venue":null,"work_id":"a921cc5c-be55-4ecd-abba-5d28fb0cb456","year":2017},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:19.379503Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:39be16c3388c68e92f94c1b97f29707e10f933fae3f7c1db02d99838c80cc992","observation_id":"cdc826eb-6225-4c4c-b637-dd66b2a48353","resolution":{"observed_at":"2026-08-07T13:44:28.536573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00652","last_updated":"2022-12-14T06:09:08Z","snapshot_observed_at":"2026-07-06T14:36:45.845182Z","submitted_at":"2022-12-14T06:09:08Z","title":"Efficient Speech Representation Learning with Low-Bit Quantization","version":1},"cited_work":{"arxiv_id":"2301.00652","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.00652","snapshot_observed_at":"2026-08-07T13:44:22.627655Z","title":"Efficient Speech Representation Learning with Low-Bit Quantization","venue":"eess.AS","work_id":"357093c5-851f-4d6a-8ae5-070d23cdb2b4","year":2022},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:19.512158Z"},"links":{"cited_paper":"/paper/2301.00652","citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:d6404cc327b5662ac3e31cca95b1436c9c709cb483bab9cb166e13a3a269241b","observation_id":"460f0035-df1f-4ca1-8bd3-8a377f4e402b","resolution":{"observed_at":"2026-08-07T13:44:22.733487Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:28.137645Z","title":"A survey of quantization methods for efficient neu- ral network inference,","venue":null,"work_id":"b9a5fed3-ca26-47a6-be44-ab6e50ee2274","year":2022},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:19.652326Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:058b337ca1e068e75bf83f78a68d18043171b7d3bfab540b7aa9d0224c0e00de","observation_id":"faeb25b3-5f7d-4c4c-91b5-46bc9d349790","resolution":{"observed_at":"2026-08-07T13:44:28.232850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:27.957894Z","title":"Binarized neural networks,","venue":null,"work_id":"a7cde0ef-7186-4324-bd33-808f7e1e1544","year":2016},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:19.768349Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:835baab01d69917aee2bbab138f596285fa3a81d85d98d61a579195bd66e6ede","observation_id":"f01857c3-c2a1-49a7-8840-8d482b0b4269","resolution":{"observed_at":"2026-08-07T13:44:28.026739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:27.709558Z","title":"XNOR- Net: Imagenet classification using binary convolutional neural networks,","venue":null,"work_id":"280ed4f2-e8ce-44f6-bef7-660c3ef4b7d4","year":2016},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:19.956614Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:360655c4f4b5a0e439262b4e5378bf77ed18ad2a8b071f1c1a94bef97842af1b","observation_id":"63ba8edc-f4d4-4f41-9766-b3022558da16","resolution":{"observed_at":"2026-08-07T13:44:27.846054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:27.434932Z","title":"Towards accurate binary convolu- tional neural network,","venue":null,"work_id":"b61dcb25-0d5c-47ab-86c6-14a1974b4a3f","year":2017},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.114560Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:109a0d0c119477c3de21796be5c4cba8b3dd597fbfbabd7de3366a077b080b2c","observation_id":"724bd2c4-dcc3-4403-b3ba-57815e6b02d2","resolution":{"observed_at":"2026-08-07T13:44:27.590242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:27.216435Z","title":"Bi-Real Net: Enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algo- rithm,","venue":null,"work_id":"47784419-e981-4c95-a3e9-211bb228a35b","year":2018},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.212242Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:cae6342ce1dce8e614c13a9f2f7c1cc782e2307a0c45505ab78144da299e01bf","observation_id":"a422b608-e969-4bba-8e51-a75b0e78b5bd","resolution":{"observed_at":"2026-08-07T13:44:27.330194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:26.952744Z","title":"Accurate and efficient 2-bit quantized neural networks,","venue":null,"work_id":"f5461e9f-635a-45e0-a1e3-0ea57f7601de","year":2019},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.320254Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:5e5231bec76dc1e70682120b26a0fe65d8785c523f4bb0d5ea8ddf5993756289","observation_id":"e3ffaab8-7c17-4ee1-9d78-876c4248baf4","resolution":{"observed_at":"2026-08-07T13:44:27.121282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11453","last_updated":"2023-10-17T17:59:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-17T17:59:15Z","title":"BitNet: Scaling 1-bit Transformers for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.11453","snapshot_observed_at":"2026-08-07T13:44:20.391763Z","title":"BitNet: Scaling 1-bit transform- ers for large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.391763Z"},"links":{"cited_paper":"/paper/2310.11453","citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:34538756f6ff9ae197ec668738d20e1d57cb3f455c3409fc4617404bbca8c5b9","observation_id":"6aa75516-0fdf-498d-9b6a-66664289a1ce","resolution":{"observed_at":"2026-08-07T13:44:20.391763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17764","last_updated":"2024-02-27T18:56:19Z","snapshot_observed_at":"2026-08-03T00:59:01.026576Z","submitted_at":"2024-02-27T18:56:19Z","title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17764","snapshot_observed_at":"2026-08-07T13:44:20.452480Z","title":"The era of 1-bit LLMs: All large language models are in 1.58 bits,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.452480Z"},"links":{"cited_paper":"/paper/2402.17764","citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:8389926ff67520eda9f341c81a8ef5858c42f4925d653d4e5e97634edb7ac1d2","observation_id":"7ac0e8c3-8980-4f1a-b4ed-17e7271a73a8","resolution":{"observed_at":"2026-08-07T13:44:20.452480Z","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":"2026-08-07T13:44:26.666737Z","title":"BiT: Robustly binarized multi- distilled transformer,","venue":null,"work_id":"be4753bf-eb3a-4e18-94a3-05921b615379","year":2022},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.509072Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:892a5d4d29899fb867003439ed80d2066143f639bf24c748d73fc823d607ef83","observation_id":"806e42b3-7c0e-468c-99ec-9dab988229a7","resolution":{"observed_at":"2026-08-07T13:44:26.790479Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:26.456260Z","title":"BinaryBERT: Pushing the limit of bert quantization,","venue":null,"work_id":"ffa32c3f-f89e-42ca-8113-9deade7b0644","year":2021},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.584249Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:04e3060e88078d1178c630ffa3f51eeba5517edb80b671e81caee065deeefc8d","observation_id":"d9aad0fc-f122-4e52-bbee-371db6c014d0","resolution":{"observed_at":"2026-08-07T13:44:26.562199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:26.146309Z","title":"Binary deep neural networks for speech recognition","venue":null,"work_id":"1c8c3afb-ca02-4155-901a-17465bf77a85","year":2017},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.658033Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:d42f869406c1de62336e05334a346f081817f8254742f92ab872ae7e67d4202d","observation_id":"1752829b-8c91-41f0-a284-bf0b22fa859d","resolution":{"observed_at":"2026-08-07T13:44:26.251127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:25.921002Z","title":"Binary neural networks for speech recognition,","venue":null,"work_id":"8254558c-3ba9-483a-96c8-ed31005189f2","year":2019},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.730572Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:f68c7f87c57c37079cf7e6ed91c053ad4f58950a59ab90d485c4cbc69b883805","observation_id":"30bd7d4e-2dfa-4189-83d3-62b846ec364b","resolution":{"observed_at":"2026-08-07T13:44:26.051167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:25.701643Z","title":"4-bit conformer with native quantization aware training for speech recognition,","venue":null,"work_id":"984d2798-0ab6-4ece-828b-207b3154ea58","year":2022},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.805393Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:a378eba0436ebee40cfe11ad3b7f6b649946744bf7d268f00472c8c2633cb5b8","observation_id":"e568158a-d73a-4c04-8a51-38e4fcd94763","resolution":{"observed_at":"2026-08-07T13:44:25.787545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:25.416494Z","title":"Integer- only zero-shot quantization for efficient speech recognition,","venue":null,"work_id":"0908009e-f414-4199-94ab-872443e8748d","year":2022},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:20.891913Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:639fd73cf1567eaa59110d9df036df35828943ae81969275328e73908c259c42","observation_id":"37742126-4412-48d1-ab85-50d86458ca84","resolution":{"observed_at":"2026-08-07T13:44:25.593675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:25.257396Z","title":"Lossless 4-bit quantization of architecture compressed conformer asr systems on the 300-hr switchboard corpus,","venue":null,"work_id":"92950262-9b37-48e9-9eeb-e73e10ae27b9","year":2023},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.031601Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:ac67bae25dc2d02bafedefadd52d1efd002cb5077b3cb7bfad8d665f705a06ed","observation_id":"504c4179-fb13-45c9-a2e1-8b465b9c1770","resolution":{"observed_at":"2026-08-07T13:44:25.296765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:25.131552Z","title":"4-bit quantization of LSTM-based speech recognition models,","venue":null,"work_id":"ec3fa60a-06a3-4b96-b810-52273dbf6920","year":2021},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.102110Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:42777beefae41653e5109c65ee67b170ac0c23887d6393106a4d7ccd300cfb0d","observation_id":"d19758bc-0c88-4566-8acc-ec4f7b76ee4c","resolution":{"observed_at":"2026-08-07T13:44:25.224851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:24.968280Z","title":"Mixed precision quan- tization of transformer language models for speech recognition,","venue":null,"work_id":"e63bf93f-e082-4f32-ac75-e3951031ec47","year":2021},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.207146Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:d523c629e76548c85987196152a857b5d2c43f9ae52fe6445c0c98ee965bc0c5","observation_id":"220843e9-8579-4d33-a4d5-fd4222bdcf74","resolution":{"observed_at":"2026-08-07T13:44:25.062269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:24.743601Z","title":"One-pass multiple conformer and founda- tion speech systems compression and quantization using an all-in- one neural model,","venue":null,"work_id":"79c63c04-ccb3-4039-89d9-61900ee97651","year":2024},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.312916Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:10bcf9b5e5477a959d20ac98491f2afa1b52f7997166315d109e4d13e9f853e5","observation_id":"d5f2d557-1cba-4475-b231-1ea685315310","resolution":{"observed_at":"2026-08-07T13:44:24.824174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:24.572212Z","title":"Mixed precision low- bit quantization of neural network language models for speech recognition,","venue":null,"work_id":"7062e1bd-7112-4c2c-9159-1c0e243932ce","year":2021},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.411837Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:fa33270f9d8f275896daec91d4b8035d32a139c906a29c1d1c3b967e74e1f514","observation_id":"b68f287a-4419-4ea4-b7b1-77915e6c5696","resolution":{"observed_at":"2026-08-07T13:44:24.647873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:24.395918Z","title":"USM-Lite: Quantization and sparsity aware fine-tuning for speech recogni- tion with universal speech models,","venue":null,"work_id":"a994a06e-b2ab-49a0-8e2f-3d42a733158e","year":2024},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.490181Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:dab35a0b2e1b7a167c62840c1eafa8c8d170d277e35de6543e349c31113f86a7","observation_id":"b37e05fc-6512-4f90-be11-92578e46a2ab","resolution":{"observed_at":"2026-08-07T13:44:24.464584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:24.231687Z","title":"2-bit conformer quantization for automatic speech recog- nition,","venue":null,"work_id":"1c935e55-de1e-4f50-9a39-366b39bcaffc","year":2023},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.564625Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:92c05b53e4df5c59a4436bfc758fa1788023f8cd83d0df93050d54e1627ac45c","observation_id":"2dfdb50b-6109-439c-8882-3fad39c3c32e","resolution":{"observed_at":"2026-08-07T13:44:24.295566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:24.064494Z","title":"USM RNN-T model weights binarization,","venue":null,"work_id":"a05f6c08-5f22-4103-a0f4-f3be8eb8eaac","year":2024},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.647814Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:f73db93ed3d5bec1e83e9d6d8dde761cb751e0fefb4e2a0944b0e225634fc44f","observation_id":"e82d3d6a-d321-4be0-80ab-f4640ce74fa3","resolution":{"observed_at":"2026-08-07T13:44:24.159586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:23.743733Z","title":"Compressed MoE asr model based on knowledge distillation and quantization,","venue":null,"work_id":"5a93f630-8789-4a59-bed9-89459a2f807e","year":2023},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.794058Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:c98e574bb7c1879749e4bcf88d857c0c9537edb90dea51c760d778963880919e","observation_id":"cd4ba8f7-a81c-4b43-b2f2-d82cc3c9295e","resolution":{"observed_at":"2026-08-07T13:44:23.893377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1308.3432","last_updated":"2013-08-15T15:19:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-08-15T15:19:34Z","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.3432","snapshot_observed_at":"2026-08-07T13:44:21.880840Z","title":"Estimating or propa- gating gradients through stochastic neurons for conditional com- putation,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.880840Z"},"links":{"cited_paper":"/paper/1308.3432","citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:220d570d1d95d2eed212023528ac08b3ae110507d94bb6f914fadc4fe76bfa46","observation_id":"a1767f14-4762-4326-8a36-b5c82a9d822b","resolution":{"observed_at":"2026-08-07T13:44:21.880840Z","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":"2026-08-07T13:44:23.369881Z","title":"Co-training 2L submodels for visual recognition,","venue":null,"work_id":"79d20f5b-6f14-4ee9-9942-352e118eaa39","year":2023},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:21.979672Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:d102af12d5e2c3729ca104d0d1fd644549bdf1dfe0e227730c22058f0144d263","observation_id":"111c15a0-f846-4451-a01d-136ef9f367d4","resolution":{"observed_at":"2026-08-07T13:44:23.530009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.12491","last_updated":"2019-11-28T02:27:27Z","snapshot_observed_at":"2026-07-06T08:40:33.992386Z","submitted_at":"2019-11-28T02:27:27Z","title":"QKD: Quantization-aware Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.12491","snapshot_observed_at":"2026-08-07T13:44:22.079463Z","title":"QKD: Quantization-aware knowledge distillation,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:22.079463Z"},"links":{"cited_paper":"/paper/1911.12491","citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:ba3aeecde56e42001e59a4a54ed635edb756a56772bda1baffb5aa892da7f850","observation_id":"1fd0ae67-49c5-4927-80de-3c8f346f909e","resolution":{"observed_at":"2026-08-07T13:44:22.079463Z","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":"2026-08-07T13:44:23.157537Z","title":"SWITCH- BOARD: Telephone speech corpus for research and develop- ment,","venue":null,"work_id":"1ce0296e-a17e-46ba-8fbd-c803e3c6c0f2","year":1992},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:22.185983Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:91ded168cfff6562adf02df1e848989a490ab69669b7725a0eeac431068fd76c","observation_id":"f056287d-49e8-43b8-b2c1-e79334ba86d6","resolution":{"observed_at":"2026-08-07T13:44:23.258319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T13:44:22.875645Z","title":"Lib- riSpeech: An ASR corpus based on public domain audio books,","venue":null,"work_id":"7945c1c5-32a1-4f74-89ab-56e3cb0d5628","year":2015},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:22.290286Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:47cbd44afb66367b4ccf941a4f43632196a373a2819db366f220e1124e2b0f93","observation_id":"90504003-ba90-4572-841e-f60d8cf6a93c","resolution":{"observed_at":"2026-08-07T13:44:23.045184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.00015","last_updated":"2018-03-30T18:09:39Z","snapshot_observed_at":"2026-07-06T06:31:07.605442Z","submitted_at":"2018-03-30T18:09:39Z","title":"ESPnet: End-to-End Speech Processing Toolkit","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.00015","snapshot_observed_at":"2026-08-07T13:44:22.368716Z","title":"ESPnet: End-to-end speech processing toolkit,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:22.368716Z"},"links":{"cited_paper":"/paper/1804.00015","citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:6e12a5ee7fc0d622f00bb89c4d44199539f7644aabd88b93e38d7dd872556a3a","observation_id":"501930b1-7d83-4c3d-a1c1-239a69651536","resolution":{"observed_at":"2026-08-07T13:44:22.368716Z","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":"2026-08-07T13:44:22.463974Z","title":"Some statistical issues in the comparison of speech recognition algorithms,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:44:22.463974Z"},"links":{"citing_paper":"/paper/2505.21245"},"observation_digest":"sha256:9cc9a889caf280edc95bdaea1b73c7e9c71ec1610fac737540a4ae0e0bf8999f","observation_id":"572ba3cf-b209-4ef5-9232-4610b59f2fc5","resolution":{"observed_at":"2026-08-07T13:44:22.463974Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.21245","last_updated":"2025-05-27T14:25:33Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-07T13:30:31.980491Z","submitted_at":"2025-05-27T14:25:33Z","title":"Towards One-bit ASR: Extremely Low-bit Conformer Quantization Using Co-training and Stochastic Precision"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":1,"verified_fuzzy":32},"total_outbound_references":45},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 3 inbound Pith citation observations for arXiv:2505.21245."}