{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QRVFCBIC5YH63ZIXKAOCIDBDL3","short_pith_number":"pith:QRVFCBIC","schema_version":"1.0","canonical_sha256":"846a510502ee0fede517501c240c235ee0df8f91af2e9b4a70af5e71982b88ab","source":{"kind":"arxiv","id":"2505.14723","version":1},"attestation_state":"computed","paper":{"title":"QUADS: QUAntized Distillation Framework for Efficient Speech Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bashima Islam, Mohammad Nur Hossain Khan, Subrata Biswas","submitted_at":"2025-05-19T16:09:51Z","abstract_excerpt":"Spoken Language Understanding (SLU) systems must balance performance and efficiency, particularly in resource-constrained environments. Existing methods apply distillation and quantization separately, leading to suboptimal compression as distillation ignores quantization constraints. We propose QUADS, a unified framework that optimizes both through multi-stage training with a pre-tuned model, enhancing adaptability to low-bit regimes while maintaining accuracy. QUADS achieves 71.13\\% accuracy on SLURP and 99.20\\% on FSC, with only minor degradations of up to 5.56\\% compared to state-of-the-art"},"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":"2505.14723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-19T16:09:51Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"bf5b6c94d9821e2ff969245be42686367d317ea29ff2b581942e5607354664a1","abstract_canon_sha256":"7658be62da93ed7a7ce572f1a79be577162367385ec43e211e9b35ac14021b08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:30.857381Z","signature_b64":"fgYfYklcUc0tgDGxvROdShaC41OztshZtNzJZFcZXaExF7wpy0XIe6qwR9yC3fP+I2eoG5aiUfRkL9eL0xYcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"846a510502ee0fede517501c240c235ee0df8f91af2e9b4a70af5e71982b88ab","last_reissued_at":"2026-07-05T11:54:30.856884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:30.856884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QUADS: QUAntized Distillation Framework for Efficient Speech Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bashima Islam, Mohammad Nur Hossain Khan, Subrata Biswas","submitted_at":"2025-05-19T16:09:51Z","abstract_excerpt":"Spoken Language Understanding (SLU) systems must balance performance and efficiency, particularly in resource-constrained environments. Existing methods apply distillation and quantization separately, leading to suboptimal compression as distillation ignores quantization constraints. We propose QUADS, a unified framework that optimizes both through multi-stage training with a pre-tuned model, enhancing adaptability to low-bit regimes while maintaining accuracy. QUADS achieves 71.13\\% accuracy on SLURP and 99.20\\% on FSC, with only minor degradations of up to 5.56\\% compared to state-of-the-art"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14723","kind":"arxiv","version":1},"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/2505.14723/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":"2505.14723","created_at":"2026-07-05T11:54:30.856941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14723v1","created_at":"2026-07-05T11:54:30.856941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14723","created_at":"2026-07-05T11:54:30.856941+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRVFCBIC5YH6","created_at":"2026-07-05T11:54:30.856941+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRVFCBIC5YH63ZIX","created_at":"2026-07-05T11:54:30.856941+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRVFCBIC","created_at":"2026-07-05T11:54:30.856941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07885","citing_title":"UnIT: Scalable Unstructured Inference-Time Pruning for MAC-efficient Neural Inference on MCUs","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3","json":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3.json","graph_json":"https://pith.science/api/pith-number/QRVFCBIC5YH63ZIXKAOCIDBDL3/graph.json","events_json":"https://pith.science/api/pith-number/QRVFCBIC5YH63ZIXKAOCIDBDL3/events.json","paper":"https://pith.science/paper/QRVFCBIC"},"agent_actions":{"view_html":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3","download_json":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3.json","view_paper":"https://pith.science/paper/QRVFCBIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14723&json=true","fetch_graph":"https://pith.science/api/pith-number/QRVFCBIC5YH63ZIXKAOCIDBDL3/graph.json","fetch_events":"https://pith.science/api/pith-number/QRVFCBIC5YH63ZIXKAOCIDBDL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3/action/storage_attestation","attest_author":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3/action/author_attestation","sign_citation":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3/action/citation_signature","submit_replication":"https://pith.science/pith/QRVFCBIC5YH63ZIXKAOCIDBDL3/action/replication_record"}},"created_at":"2026-07-05T11:54:30.856941+00:00","updated_at":"2026-07-05T11:54:30.856941+00:00"}