{"as_of":"2026-08-11T20:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7b525353a1cc3aa041ffac2d52079ac71abee5cefe824f479629d56ff874a8d0","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T18:35:56.660731Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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":"2026-08-02T18:35:48.848722Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.08173","snapshot_observed_at":"2026-08-02T18:35:48.848722Z","title":"However, deploying these models in real-world scenarios with limited memory and computational resources typically requires quantization into hardware-friendly integer formats","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:48.848722Z"},"links":{"cited_paper":"/paper/2603.08173","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:348f8d76aa8de87aa34a98cea8c7aa550ac8091d81e315068801e05a1bec5e08","observation_id":"9feaedd3-7a58-4f7d-8420-4fc21866379b","resolution":{"observed_at":"2026-08-02T18:35:48.848722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2603.08173/citation-record","integrity":"/paper/2603.08173/integrity","json":"/paper/2603.08173/citation-record.json","paper":"/paper/2603.08173"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.08173","snapshot_observed_at":"2026-08-02T18:35:48.848722Z","title":"However, deploying these models in real-world scenarios with limited memory and computational resources typically requires quantization into hardware-friendly integer formats","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:48.848722Z"},"links":{"cited_paper":"/paper/2603.08173","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:348f8d76aa8de87aa34a98cea8c7aa550ac8091d81e315068801e05a1bec5e08","observation_id":"9feaedd3-7a58-4f7d-8420-4fc21866379b","resolution":{"observed_at":"2026-08-02T18:35:48.848722Z","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":"2026-08-02T18:35:48.911964Z","title":"Quantization Quantization enables deployment of neural networks in resource-constrained settings by reducing memory and compu- tational requirements [5]","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:48.911964Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:b79ac05194d3f722c866335c527fb2a2ea1350e33b829bf45f9d4040ecc78c9c","observation_id":"d5dcb6d3-1b35-41fe-b29d-cd6a5f655201","resolution":{"observed_at":"2026-08-02T18:35:48.911964Z","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":"2026-08-02T18:35:49.054670Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:49.054670Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:80544120d17714690b413d612febcc6971161588118557bbdbce17b4b4b5b592","observation_id":"4731f9c0-d2d4-4659-990c-6fc0b16f4057","resolution":{"observed_at":"2026-08-02T18:35:49.054670Z","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":"2026-08-02T18:35:49.256975Z","title":"MSE(sN) MSE(s2) MSE(s1) Output: ŷ s1, s2,…, sN Parameters Objective function 𝓔(y,ŷ) CMA-ES","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:49.256975Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:151473c8b14728bee47606971beeb3278590102a022673c99841769cff92f012","observation_id":"657bdea9-f668-4ddf-b9ba-238df4f85e0d","resolution":{"observed_at":"2026-08-02T18:35:49.256975Z","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":"2026-08-02T18:35:49.432310Z","title":"First, each layer-wise activation scaling factor is locally optimized by min- imizing the MSE between the FP32 and quantized layer outputs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:49.432310Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:1f4ab6bcad658afeb8bcba0d819c739b1cf18961ea380ad0c8d43fc821fecfaf","observation_id":"1d6ded52-ec1a-45b5-ba34-0fc65c698a78","resolution":{"observed_at":"2026-08-02T18:35:49.432310Z","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":"2026-08-02T18:35:49.581213Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:49.581213Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:01f83d2f523f8cf47876275e2c66af0c69d1b5d7986a382c0ba7943283b1cf48","observation_id":"e40190e1-7f22-4878-884d-6d70f94ef083","resolution":{"observed_at":"2026-08-02T18:35:49.581213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05426","last_updated":"2021-07-25T09:34:39Z","snapshot_observed_at":"2026-08-10T19:57:21.389202Z","submitted_at":"2021-02-10T13:46:16Z","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.05426","snapshot_observed_at":"2026-08-02T18:35:51.194647Z","title":"Brecq: Pushing the limit of post-training quantization by block reconstruction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:51.194647Z"},"links":{"cited_paper":"/paper/2102.05426","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:e6240b82b12c027e3d17133a482beab00f397b98dde0998876e05d25a2284210","observation_id":"cade12a6-e144-4aff-a94f-a3e2aac0a295","resolution":{"observed_at":"2026-08-02T18:35:51.194647Z","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":"2026-08-02T18:35:49.922082Z","title":"Our study highlights that, unlike in vision or NLP, audio models are particularly sensitive to activation quan- tization, providing strong motivation for our approach","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:49.922082Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:e6de506e4d3f7f26252478b4927ac81e22b547f3063fb9e392932eedec9027b4","observation_id":"a1cbf680-81b0-4ea6-ac21-4ff052ef7a9f","resolution":{"observed_at":"2026-08-02T18:35:49.922082Z","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":"2026-08-02T18:35:50.112085Z","title":"Robust speech recognition via large-scale weak supervision,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:50.112085Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:8aa59db1c9cbc40024bb150aab9ac73614a435656ccc5fcdba92d470ce23091b","observation_id":"87660877-f178-4801-904d-9c55edb40692","resolution":{"observed_at":"2026-08-02T18:35:50.112085Z","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":"2026-08-02T18:35:50.270699Z","title":"wav2vec 2.0: A framework for self-supervised learning of speech repre- sentations,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:50.270699Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:caa9e84b4a827e274855fb179246d685a258fc9ead364b25dd3c7f3463bd386c","observation_id":"a0e855e8-99dd-40de-9763-79b802444c77","resolution":{"observed_at":"2026-08-02T18:35:50.270699Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.08100","last_updated":"2020-05-16T20:56:25Z","snapshot_observed_at":"2026-08-08T15:18:32.322111Z","submitted_at":"2020-05-16T20:56:25Z","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.08100","snapshot_observed_at":"2026-08-02T18:35:50.419650Z","title":"Conformer: Convolution- augmented transformer for speech recognition,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:50.419650Z"},"links":{"cited_paper":"/paper/2005.08100","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:0d6516514ee29b82d524af075acb09dfd59db87b09790e284ee5d1f69fe2890c","observation_id":"bfd8d8b4-0d06-45a6-8bf3-3feaa79919e9","resolution":{"observed_at":"2026-08-02T18:35:50.419650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.01778","last_updated":"2021-07-08T20:16:28Z","snapshot_observed_at":"2026-08-08T11:33:21.735489Z","submitted_at":"2021-04-05T05:26:29Z","title":"AST: Audio Spectrogram Transformer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.01778","snapshot_observed_at":"2026-08-02T18:35:50.568237Z","title":"Ast: Audio spectrogram transformer,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:50.568237Z"},"links":{"cited_paper":"/paper/2104.01778","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:19e3861e80cdde1dc464169e006d7f57d15d780e37dd28f754f834e114622f2b","observation_id":"9b53fdc8-ce7d-4013-8433-d8ec055fe305","resolution":{"observed_at":"2026-08-02T18:35:50.568237Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09748","last_updated":"2024-02-15T06:58:30Z","snapshot_observed_at":"2026-08-10T10:02:13.549979Z","submitted_at":"2024-02-15T06:58:30Z","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09748","snapshot_observed_at":"2026-08-02T18:35:50.708362Z","title":"Model compression and efficient infer- ence for large language models: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:50.708362Z"},"links":{"cited_paper":"/paper/2402.09748","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:f5cfd3bde3a244f85c0a21b3dddf2a6cea35685134dda7c3a666c8932dddf8a8","observation_id":"a3eccf1f-c30e-4128-a5f4-2a3659e5b6db","resolution":{"observed_at":"2026-08-02T18:35:50.708362Z","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":"2026-08-02T18:35:50.959063Z","title":"Up or down? adaptive rounding for post-training quantization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:50.959063Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:d98eed7aed42577df174c1ed18301856b93fb451d8d90b42e343dedf0853f370","observation_id":"e58b30f6-bffa-40d2-bed2-e157a5d3167d","resolution":{"observed_at":"2026-08-02T18:35:50.959063Z","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":"2026-08-02T18:35:52.573152Z","title":"Whisper-kdq: A lightweight whisper via guided knowledge dis- tillation and quantization for efficient asr,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:52.573152Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:a2d015082729e6ac4cdfd910ea9c78364ba413e56ad57c21e61ab185440721ab","observation_id":"abbd0a67-6932-4018-a9cf-c2ebd6be24ad","resolution":{"observed_at":"2026-08-02T18:35:52.573152Z","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":"2026-08-02T18:35:51.392923Z","title":"Smoothquant: Accurate and efficient post-training quantization for large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:51.392923Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:4d706c82f3dff9a6119022afec53e7b31204fc604ba3cda151f99c1979f88464","observation_id":"e7f0a706-7d1e-47cd-8214-d5cae633651e","resolution":{"observed_at":"2026-08-02T18:35:51.392923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-07T08:38:54.025062Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-02T18:35:51.568185Z","title":"Gptq: Ac- curate post-training quantization for generative pre-trained trans- formers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:51.568185Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:9c1256076ce1443d8f76cf0ab3a718fb5918fdfdad5ec83b3ffc87cd973503b7","observation_id":"35231719-3eb9-443d-8a17-60577d2bf000","resolution":{"observed_at":"2026-08-02T18:35:51.568185Z","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":"2026-08-10T19:41:58.785482Z","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:cbce97e989febe9fb15cd07528a0afd10f8a501b4637aa1fa431404480e059fd","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":"2506.03515","last_updated":"2025-06-04T03:02:18Z","snapshot_observed_at":"2026-08-08T02:14:58.494663Z","submitted_at":"2025-06-04T03:02:18Z","title":"BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.03515","snapshot_observed_at":"2026-08-02T18:35:52.019662Z","title":"Bittts: Highly compact text-to-speech using 1.58-bit quanti- zation and weight indexing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:52.019662Z"},"links":{"cited_paper":"/paper/2506.03515","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:b7c464bc8ca0c257294a5a1449b92bd8e4436b3ed23f9e3ea371b505a2b68e25","observation_id":"6e6c3700-f386-4b40-be90-0d514395735b","resolution":{"observed_at":"2026-08-02T18:35:52.019662Z","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":"2026-08-02T18:35:52.136019Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:52.136019Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:9ce3657b4a420387e9aef3dad2adbb001ca028138ac6a6b8b80fe9c5390d5b9f","observation_id":"cba13595-e9da-4985-9e93-c534abbaf99b","resolution":{"observed_at":"2026-08-02T18:35:52.136019Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.11022","last_updated":"2024-06-16T17:32:45Z","snapshot_observed_at":"2026-08-09T14:22:43.635033Z","submitted_at":"2024-06-16T17:32:45Z","title":"Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.11022","snapshot_observed_at":"2026-08-02T18:35:52.277812Z","title":"Outlier reduction with gated attention for improved post-training quanti- zation in large sequence-to-sequence speech foundation models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:52.277812Z"},"links":{"cited_paper":"/paper/2406.11022","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:d598ba3173d1d100acc8dd2eefd54a73589a6b93cae695a1c075b6055c55dbaf","observation_id":"bfbfc3ed-a734-464b-b5df-9fa9b0dac4a1","resolution":{"observed_at":"2026-08-02T18:35:52.277812Z","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":"2026-08-02T18:35:52.407709Z","title":"Ultra-low bit post-training quantization of large speech models via k-means clustering and mixed precision allocation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:52.407709Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:31acdbb0e68a7c17227cbb1746cdc573b773a0c38071c8d2daad9096f71d154a","observation_id":"c8943af6-f2b8-4051-ab82-08df00cd71e3","resolution":{"observed_at":"2026-08-02T18:35:52.407709Z","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":"2026-08-02T18:35:53.598683Z","title":"A survey of quantization methods for efficient neural network inference,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.598683Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:f6f58c566dffa3c566e492191524640ad248f102c4651025a584e3d1ebe35b23","observation_id":"c411d9c7-e474-4894-88d6-5abe734e2f44","resolution":{"observed_at":"2026-08-02T18:35:53.598683Z","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":"2026-08-02T18:35:52.739320Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:52.739320Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:89e01583e72eec95a33f9a9e7feb2d986093d2235beab34758f1e89f9bf5d6c4","observation_id":"d6e86e5e-6e7f-4f64-ad5e-cec2906fe788","resolution":{"observed_at":"2026-08-02T18:35:52.739320Z","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":"2026-08-02T18:35:52.836890Z","title":"Bert: Pre- training of deep bidirectional transformers for language under- standing,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:52.836890Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:0e810cdca6424ecefe941c17db4f4c44718f771420deba949838c74d54846a70","observation_id":"9cfdb54b-96ee-4eaa-8928-a8af1c69ac1d","resolution":{"observed_at":"2026-08-02T18:35:52.836890Z","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":"2026-08-02T18:35:52.978188Z","title":"Improving the speed of neural networks on cpus,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:52.978188Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:6456701badff95a190a1577722018290e3ad0ce95d0b5359d79c008c68c289a8","observation_id":"e9827d67-dc42-4971-9373-8bf2b734237c","resolution":{"observed_at":"2026-08-02T18:35:52.978188Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.04191","last_updated":"2019-02-25T01:49:04Z","snapshot_observed_at":"2026-08-09T01:06:12.014592Z","submitted_at":"2018-09-11T22:51:55Z","title":"Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.04191","snapshot_observed_at":"2026-08-02T18:35:53.045463Z","title":"Discovering low-precision networks close to full-precision networks for efficient embedded inference,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.045463Z"},"links":{"cited_paper":"/paper/1809.04191","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:d607b9b97f3f7e66f79855d42cf6fbf39065107a7747def6106efbcd3264a2c9","observation_id":"ea491315-d5a9-4b25-aae8-ef65d58cfef0","resolution":{"observed_at":"2026-08-02T18:35:53.045463Z","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":"2026-08-02T18:35:53.149094Z","title":"Nvidia 8-bit inference with tensorrt,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.149094Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:7feea11ec6d956587d405e6aaaf5c6c21b25af9196fc79cc42cbb212f970cbe6","observation_id":"89463f21-4346-4381-9fe8-b3d6c47c31f0","resolution":{"observed_at":"2026-08-02T18:35:53.149094Z","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":"2026-08-02T18:35:53.241690Z","title":"Low-bit quantization of neural networks for efficient inference,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.241690Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:f65237467ea2593e7bee50033d0f5502e3ee059feaab50f226d0ea8f90f92116","observation_id":"cc470520-017d-4f67-8be3-dc2f4ce3835e","resolution":{"observed_at":"2026-08-02T18:35:53.241690Z","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":"2026-08-02T18:35:53.377810Z","title":"Evolutionsstrategien,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.377810Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:d66ffddb6daeedf44597da351d2348286f13df4ff643a39ef2d4d670a5de9d82","observation_id":"3f96582c-db94-43b4-ad9e-1932723cac15","resolution":{"observed_at":"2026-08-02T18:35:53.377810Z","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":"2026-08-02T18:35:54.336618Z","title":"Natural evolution strategies,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:54.336618Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:7cd37e17652f1dc8dfd54db6168f343887f3f5ed330ed413ef28a5b8dca4f34e","observation_id":"d9a5f4f5-a8c6-42e9-9a79-befdc9bee2b5","resolution":{"observed_at":"2026-08-02T18:35:54.336618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.03864","last_updated":"2017-09-07T23:28:48Z","snapshot_observed_at":"2026-07-06T05:33:17.404544Z","submitted_at":"2017-03-10T23:02:19Z","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.03864","snapshot_observed_at":"2026-08-02T18:35:54.476587Z","title":"Evolu- tion strategies as a scalable alternative to reinforcement learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:54.476587Z"},"links":{"cited_paper":"/paper/1703.03864","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:90f3d8c09ebec83d6860a4dd91edd6b5de013b922041e80bbd7bf3d7a0462910","observation_id":"c5315b06-910d-47ce-8993-2bb3295d73e6","resolution":{"observed_at":"2026-08-02T18:35:54.476587Z","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":"2026-08-02T18:35:53.700081Z","title":"Noisyquant: Noisy bias-enhanced post-training activation quan- tization for vision transformers,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.700081Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:1d6d152349ab60869add816b5ccba42157c345c527496b1f48780ac012dfd01e","observation_id":"cc4b90c5-c49f-4f5f-a2c6-71dfefa391f9","resolution":{"observed_at":"2026-08-02T18:35:53.700081Z","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":"2026-08-02T18:35:53.809968Z","title":"Hyq: Hardware-friendly post- training quantization for cnn-transformer hybrid networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.809968Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:8228b69f08ad6d3b5af5effdd942b7441ba54a52535efc5e887b927e183d53f0","observation_id":"691dbcc2-e502-4b41-ba59-81c7e686fcd4","resolution":{"observed_at":"2026-08-02T18:35:53.809968Z","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":"2026-08-02T18:35:53.885249Z","title":"Ditas: Quantizing diffusion trans- formers via enhanced activation smoothing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.885249Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:22a09b24f530099d1603f88df0a98ff4cb9248522de6d238d54623c1803e4846","observation_id":"8a764bfd-fc28-4cf0-9266-46b1d73bbe35","resolution":{"observed_at":"2026-08-02T18:35:53.885249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01892","last_updated":"2024-04-02T12:29:31Z","snapshot_observed_at":"2026-08-04T20:03:51.303396Z","submitted_at":"2024-04-02T12:29:31Z","title":"Minimize Quantization Output Error with Bias Compensation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01892","snapshot_observed_at":"2026-08-02T18:35:53.995518Z","title":"Minimize quantization output error with bias compensa- tion,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.995518Z"},"links":{"cited_paper":"/paper/2404.01892","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:f7408a84fe60e91451324a1144393b8b28cc3c9ef4ef7c6acf4f23abd5b38a4b","observation_id":"2f71155e-cd7c-4447-94cd-8e15db4d0e29","resolution":{"observed_at":"2026-08-02T18:35:53.995518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.08870","last_updated":"2019-06-03T20:48:57Z","snapshot_observed_at":"2026-08-11T02:17:33.023141Z","submitted_at":"2019-06-03T20:48:57Z","title":"2019 Evolutionary Algorithms Review","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.08870","snapshot_observed_at":"2026-08-02T18:35:54.081604Z","title":"2019 evolutionary algorithms re- view,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:54.081604Z"},"links":{"cited_paper":"/paper/1906.08870","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:d1f7b8cda3b6784ca0193f26183609fdea8f99c5d93ef019e927a708f9d562e4","observation_id":"ec61ca2a-6947-4589-bcdc-18d5780db898","resolution":{"observed_at":"2026-08-02T18:35:54.081604Z","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":"2026-08-02T18:35:54.143295Z","title":"The cma evolution strategy: a comparing review,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:54.143295Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:e0cfea63a2f72f995c9b45b302543f1fdbf0991ce2e42e82972e5005473549c1","observation_id":"09d9bd5f-6bc2-40dd-9284-fb57b88c765f","resolution":{"observed_at":"2026-08-02T18:35:54.143295Z","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":"2026-08-02T18:35:54.228649Z","title":"High dimensions and heavy tails for natural evolution strategies,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:54.228649Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:601e228ac0b8ee06370a76d4a06a7be44ce18a7350a3b69c5f6f80d8ca1edb27","observation_id":"224d1e25-3f2c-4f73-8c17-6fb2db2eeb23","resolution":{"observed_at":"2026-08-02T18:35:54.228649Z","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":"2026-08-02T18:35:56.011072Z","title":"Inves- tigating rnn-based speech enhancement methods for noise-robust text-to-speech,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.011072Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:1b8e837442052b5dbfea17fb3b0a52cdb5deacc899d4d710a8a6e69310924366","observation_id":"96fc2c92-9f77-4d26-9dcd-9571d55d0cc4","resolution":{"observed_at":"2026-08-02T18:35:56.011072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04558","last_updated":"2022-08-08T01:53:05Z","snapshot_observed_at":"2026-08-06T18:05:37.673476Z","submitted_at":"2020-06-08T13:05:40Z","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04558","snapshot_observed_at":"2026-08-02T18:35:56.164869Z","title":"Fastspeech 2: Fast and high-quality end-to-end text to speech,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.164869Z"},"links":{"cited_paper":"/paper/2006.04558","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:306ec7c6f34733dbbf985fb11254cdaea6539c3ae1aca16b3bb1a4985d7bf1c9","observation_id":"8d0d5933-a97a-415d-99c4-b9cfd8414a70","resolution":{"observed_at":"2026-08-02T18:35:56.164869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.01477","last_updated":"2019-08-05T05:44:52Z","snapshot_observed_at":"2026-08-07T05:21:51.687860Z","submitted_at":"2019-08-05T05:44:52Z","title":"GDRQ: Group-based Distribution Reshaping for Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01477","snapshot_observed_at":"2026-08-02T18:35:54.615425Z","title":"Gdrq: Group-based distribution reshaping for quantization,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:54.615425Z"},"links":{"cited_paper":"/paper/1908.01477","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:92b083d3075b515cc6904761eeb8380a4bed126bd139ca511197548619c5fead","observation_id":"5f0c0fdf-6664-47f6-931d-653bcd61dcf8","resolution":{"observed_at":"2026-08-02T18:35:54.615425Z","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":"2026-08-02T18:35:54.754104Z","title":"Squashed weight distribution for low bit quantization of deep models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:54.754104Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:592d0efd19a372c8a0235f3fb60a72854847c05757561c99f6628220a7f11673","observation_id":"0d974da5-5134-4c45-beea-b0bc6353bb91","resolution":{"observed_at":"2026-08-02T18:35:54.754104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1604.07269","last_updated":"2016-04-25T14:17:08Z","snapshot_observed_at":"2026-07-06T04:53:59.754200Z","submitted_at":"2016-04-25T14:17:08Z","title":"CMA-ES for Hyperparameter Optimization of Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1604.07269","snapshot_observed_at":"2026-08-02T18:35:54.890104Z","title":"Cma-es for hyperparame- ter optimization of deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:54.890104Z"},"links":{"cited_paper":"/paper/1604.07269","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:768de069c2d87475ff22771fc86b3a20b71437b6aa05a70f557525d257fdea72","observation_id":"0a031e33-5f00-4df1-8140-e0cb2598b9c5","resolution":{"observed_at":"2026-08-02T18:35:54.890104Z","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":"2026-08-02T18:35:49.804213Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:49.804213Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:e3ed67ff4ea56a1e233ab6f8a07c95e3eaefdf0050c2445876bbd9b74a5f9eda","observation_id":"6b431f79-38fc-4ac1-9f18-870764e90472","resolution":{"observed_at":"2026-08-02T18:35:49.804213Z","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":"2026-08-02T18:35:55.071529Z","title":"Lib- rispeech: an asr corpus based on public domain audio books,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:55.071529Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:ece2261765990a7d08da6a69bab4f5be6fdd3b1f6ecd770bb2364be19870cefe","observation_id":"640e59ff-b116-4e46-b9a1-048ed5213fbb","resolution":{"observed_at":"2026-08-02T18:35:55.071529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.07143","last_updated":"2020-08-10T13:50:24Z","snapshot_observed_at":"2026-08-07T15:21:18.262728Z","submitted_at":"2020-05-14T17:02:15Z","title":"ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.07143","snapshot_observed_at":"2026-08-02T18:35:55.245104Z","title":"Ecapa- tdnn: Emphasized channel attention, propagation and ag- gregation in tdnn based speaker verification,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:55.245104Z"},"links":{"cited_paper":"/paper/2005.07143","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:0683d925e917fd48f274ef6ae301ffef54fe56881479c9f670f715956acb6789","observation_id":"57d8505f-ae95-413a-8b7d-15b9a0a55926","resolution":{"observed_at":"2026-08-02T18:35:55.245104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.05622","last_updated":"2018-06-27T01:49:17Z","snapshot_observed_at":"2026-08-08T04:36:13.309903Z","submitted_at":"2018-06-14T15:59:12Z","title":"VoxCeleb2: Deep Speaker Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.05622","snapshot_observed_at":"2026-08-02T18:35:55.501929Z","title":"V oxceleb2: Deep speaker recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:55.501929Z"},"links":{"cited_paper":"/paper/1806.05622","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:c1c1f411f3ff91bbf9a49e49f9857e2e040dd3baa272181c21268ed527fc1dba","observation_id":"dba0b92b-fc7c-441e-b381-325febe0a543","resolution":{"observed_at":"2026-08-02T18:35:55.501929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13686","last_updated":"2023-05-23T04:48:51Z","snapshot_observed_at":"2026-08-11T11:13:37.823021Z","submitted_at":"2023-05-23T04:48:51Z","title":"MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13686","snapshot_observed_at":"2026-08-02T18:35:55.751326Z","title":"Mp-senet: A speech enhance- ment model with parallel denoising of magnitude and phase spec- tra,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:55.751326Z"},"links":{"cited_paper":"/paper/2305.13686","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:f4045ca709104a1e27a7d22101771a1074de903e456b6907c88e71a7839699fd","observation_id":"5b1fc747-1fda-4b1f-a6e4-4608bfe243ca","resolution":{"observed_at":"2026-08-02T18:35:55.751326Z","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":"2026-08-02T18:35:56.235448Z","title":"The lj speech dataset,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.235448Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:9d8b524d92c7d3efaaf25000cd0edd3cf01a16f270f80eb4ae06e771d73f63b2","observation_id":"e222283b-6028-4eb2-bba3-bec57304df9e","resolution":{"observed_at":"2026-08-02T18:35:56.235448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-02T18:35:56.296415Z","title":"Speech commands: A dataset for limited-vocabulary speech recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.296415Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:009dfdb650152145c34167b3e3b75ee29fb6b8c2e61e163e517085e8cdbf5bf6","observation_id":"8b2d21c9-f315-4f50-bfd7-f07229486b13","resolution":{"observed_at":"2026-08-02T18:35:56.296415Z","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":"2026-08-02T18:35:56.359887Z","title":"pytorch quantization: http://github.com/nvidia/tensorrt","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.359887Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:e9357f80cf12e6c70de5ac19dadeb8c1da25d75d3cade2b85a79884140284ccf","observation_id":"2c7361ba-3592-4f7e-b50c-67493abdc8d1","resolution":{"observed_at":"2026-08-02T18:35:56.359887Z","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":"2026-08-02T18:35:56.416119Z","title":"Pytorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.416119Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:0eb91b637a10d0827364c9b9d0c4cce5420e0716d91b40f380fe4a9673fba465","observation_id":"e5974c2d-5ff1-45f2-84ee-c12269397da5","resolution":{"observed_at":"2026-08-02T18:35:56.416119Z","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":"2026-08-02T18:35:56.478899Z","title":"TensorRT: https://developer.nvidia.com/tensorrt","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.478899Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:512af334b0a17cf8d43cbabf789a550ab51265eb5dd64a5a1a995977dcd72309","observation_id":"6e800ee6-6a9d-4b2a-909f-85f9b878fc2c","resolution":{"observed_at":"2026-08-02T18:35:56.478899Z","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":"2026-08-02T18:35:56.542126Z","title":"11.3 metis aipu: A 12nm 15tops/w 209.6 tops soc for cost-and energy-efficient inference at the edge,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.542126Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:f71c1fc307d504116be5be22813604e2fb4db3a12885ebdb21979a8f9fa37d16","observation_id":"fc41297d-7de4-471b-b9ae-f402c4088a3d","resolution":{"observed_at":"2026-08-02T18:35:56.542126Z","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":"2026-08-02T18:35:56.660731Z","title":"Survey of machine learning accelerators,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:56.660731Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:0e6234c0a7ebe425ae737839f6553a18a18413c42fe1361d038d5f699f2a96ee","observation_id":"e44940be-20db-4eb7-ba17-033fcd79addf","resolution":{"observed_at":"2026-08-02T18:35:56.660731Z","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":"2026-08-02T18:35:53.451569Z","title":null,"venue":null,"work_id":null,"year":1978},"citing_paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models","version":2},"reference_index":1977,"source":"pdf_text","source_observed_at":"2026-08-02T18:35:53.451569Z"},"links":{"citing_paper":"/paper/2603.08173"},"observation_digest":"sha256:b0f910544b2c2ee708790c9ac3de6717cef33687d5046f0df3851edccdf25793","observation_id":"4f61e6cf-a97c-4702-bd58-2850f10eedaf","resolution":{"observed_at":"2026-08-02T18:35:53.451569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.08173","last_updated":"2026-07-18T12:50:12Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-10T19:41:58.785482Z","submitted_at":"2026-03-09T09:53:05Z","title":"Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":57,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":57},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 1 inbound Pith citation observation for arXiv:2603.08173."}