{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C3FBQ23XCNQMLBO2DADGSSFGNE","short_pith_number":"pith:C3FBQ23X","schema_version":"1.0","canonical_sha256":"16ca186b771360c585da18066948a6690491b5d0d215a1dd89d41f20f788642d","source":{"kind":"arxiv","id":"2405.08019","version":1},"attestation_state":"computed","paper":{"title":"AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Prathosh AP, Rakshith Rao, Roshan Nayak, Shreyan Ganguly, Ujan Deb","submitted_at":"2024-05-11T15:06:24Z","abstract_excerpt":"Knowledge distillation, a widely used model compression technique, works on the basis of transferring knowledge from a cumbersome teacher model to a lightweight student model. The technique involves jointly optimizing the task specific and knowledge distillation losses with a weight assigned to them. Despite these weights playing a crucial role in the performance of the distillation process, current methods provide equal weight to both losses, leading to suboptimal performance. In this paper, we propose Adaptive Knowledge Distillation, a novel technique inspired by curriculum learning to adapt"},"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":"2405.08019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-11T15:06:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"882478de0cf86b53af50697c9ee72328ed98515e501e1d87401e24307f2e4d70","abstract_canon_sha256":"0c910858adeafe7778ee457c45f6bd90f5eb4e9b5b4a965f79040346ecdfa765"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:54.171420Z","signature_b64":"z970/pHProeKMs7ZYkjbJe5wWd71vCU1iHjfTakcuTZYHDS9Zrg0+YoKR0bCKI4cFTDsRT6/l0sB516cwZnlCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16ca186b771360c585da18066948a6690491b5d0d215a1dd89d41f20f788642d","last_reissued_at":"2026-07-05T08:18:54.170978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:54.170978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Prathosh AP, Rakshith Rao, Roshan Nayak, Shreyan Ganguly, Ujan Deb","submitted_at":"2024-05-11T15:06:24Z","abstract_excerpt":"Knowledge distillation, a widely used model compression technique, works on the basis of transferring knowledge from a cumbersome teacher model to a lightweight student model. The technique involves jointly optimizing the task specific and knowledge distillation losses with a weight assigned to them. Despite these weights playing a crucial role in the performance of the distillation process, current methods provide equal weight to both losses, leading to suboptimal performance. In this paper, we propose Adaptive Knowledge Distillation, a novel technique inspired by curriculum learning to adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08019","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/2405.08019/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":"2405.08019","created_at":"2026-07-05T08:18:54.171039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08019v1","created_at":"2026-07-05T08:18:54.171039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08019","created_at":"2026-07-05T08:18:54.171039+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3FBQ23XCNQM","created_at":"2026-07-05T08:18:54.171039+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3FBQ23XCNQMLBO2","created_at":"2026-07-05T08:18:54.171039+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3FBQ23X","created_at":"2026-07-05T08:18:54.171039+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE","json":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE.json","graph_json":"https://pith.science/api/pith-number/C3FBQ23XCNQMLBO2DADGSSFGNE/graph.json","events_json":"https://pith.science/api/pith-number/C3FBQ23XCNQMLBO2DADGSSFGNE/events.json","paper":"https://pith.science/paper/C3FBQ23X"},"agent_actions":{"view_html":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE","download_json":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE.json","view_paper":"https://pith.science/paper/C3FBQ23X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08019&json=true","fetch_graph":"https://pith.science/api/pith-number/C3FBQ23XCNQMLBO2DADGSSFGNE/graph.json","fetch_events":"https://pith.science/api/pith-number/C3FBQ23XCNQMLBO2DADGSSFGNE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE/action/storage_attestation","attest_author":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE/action/author_attestation","sign_citation":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE/action/citation_signature","submit_replication":"https://pith.science/pith/C3FBQ23XCNQMLBO2DADGSSFGNE/action/replication_record"}},"created_at":"2026-07-05T08:18:54.171039+00:00","updated_at":"2026-07-05T08:18:54.171039+00:00"}