{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GOPV4J5RA7A4OGMXWEY7EIRCTH","short_pith_number":"pith:GOPV4J5R","schema_version":"1.0","canonical_sha256":"339f5e27b107c1c71997b131f2222299de8dbf2de252d1259582a7012c7b23ee","source":{"kind":"arxiv","id":"2501.03643","version":2},"attestation_state":"computed","paper":{"title":"Effective and Efficient Mixed Precision Quantization of Speech Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guinan Li, Haoning Xu, Huimeng Wang, Jiajun Deng, Mengzhe Geng, Shujie Hu, Xunying Liu, Youjun Chen, Zengrui Jin, Zhaoqing Li","submitted_at":"2025-01-07T09:21:52Z","abstract_excerpt":"This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments conducted on LibriSpeech dataset with fine-tuned wav2vec2.0-base and HuBERT-large models suggest the resulting mixed-precision quantized models increased the lossless compression ratio by factors up to 1.7x and 1.9x over the respective uniform-precision and two-stage mixed-precision quantized baselines that perform precision learning and model parameters quant"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.03643","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-07T09:21:52Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"fadfdad1fd41affc0b90f74c20ede827be5764af5a916e21f4497cb708eecb85","abstract_canon_sha256":"5de98e96958eb411dfdc48b830575a37ba0b720cf690145b6d05fde8d4cf646f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:58.993898Z","signature_b64":"/EZbJH8VMq3ezrYI5RhHWqCjHBlvNuVkcchJEsxm1/gh5Jj27B14n7KkUt32lYa1OY+AvPVWlI97MlYtTMCJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"339f5e27b107c1c71997b131f2222299de8dbf2de252d1259582a7012c7b23ee","last_reissued_at":"2026-07-05T09:59:58.993438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:58.993438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective and Efficient Mixed Precision Quantization of Speech Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guinan Li, Haoning Xu, Huimeng Wang, Jiajun Deng, Mengzhe Geng, Shujie Hu, Xunying Liu, Youjun Chen, Zengrui Jin, Zhaoqing Li","submitted_at":"2025-01-07T09:21:52Z","abstract_excerpt":"This paper presents a novel mixed-precision quantization approach for speech foundation models that tightly integrates mixed-precision learning and quantized model parameter estimation into one single model compression stage. Experiments conducted on LibriSpeech dataset with fine-tuned wav2vec2.0-base and HuBERT-large models suggest the resulting mixed-precision quantized models increased the lossless compression ratio by factors up to 1.7x and 1.9x over the respective uniform-precision and two-stage mixed-precision quantized baselines that perform precision learning and model parameters quant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03643","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.03643/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.03643","created_at":"2026-07-05T09:59:58.993491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03643v2","created_at":"2026-07-05T09:59:58.993491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03643","created_at":"2026-07-05T09:59:58.993491+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOPV4J5RA7A4","created_at":"2026-07-05T09:59:58.993491+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOPV4J5RA7A4OGMX","created_at":"2026-07-05T09:59:58.993491+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOPV4J5R","created_at":"2026-07-05T09:59:58.993491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03039","citing_title":"Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH","json":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH.json","graph_json":"https://pith.science/api/pith-number/GOPV4J5RA7A4OGMXWEY7EIRCTH/graph.json","events_json":"https://pith.science/api/pith-number/GOPV4J5RA7A4OGMXWEY7EIRCTH/events.json","paper":"https://pith.science/paper/GOPV4J5R"},"agent_actions":{"view_html":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH","download_json":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH.json","view_paper":"https://pith.science/paper/GOPV4J5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03643&json=true","fetch_graph":"https://pith.science/api/pith-number/GOPV4J5RA7A4OGMXWEY7EIRCTH/graph.json","fetch_events":"https://pith.science/api/pith-number/GOPV4J5RA7A4OGMXWEY7EIRCTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH/action/storage_attestation","attest_author":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH/action/author_attestation","sign_citation":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH/action/citation_signature","submit_replication":"https://pith.science/pith/GOPV4J5RA7A4OGMXWEY7EIRCTH/action/replication_record"}},"created_at":"2026-07-05T09:59:58.993491+00:00","updated_at":"2026-07-05T09:59:58.993491+00:00"}