{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IJN6AP72LIV33DAZ56HQMVBL7D","short_pith_number":"pith:IJN6AP72","schema_version":"1.0","canonical_sha256":"425be03ffa5a2bbd8c19ef8f06542bf8c2972995fd6f9fde76b1646797204eb2","source":{"kind":"arxiv","id":"2507.02911","version":1},"attestation_state":"computed","paper":{"title":"DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Ahmed Hussen Abdelaziz, Hyung Gun Chi, Li-Wei Chen, Oggi Rudovic, Shinji Watanabe, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","submitted_at":"2025-06-25T00:39:33Z","abstract_excerpt":"We introduce DiceHuBERT, a knowledge distillation framework for compressing HuBERT, a widely used self-supervised learning (SSL)-based speech foundation model. Unlike existing distillation methods that rely on layer-wise and feature-wise mapping between teacher and student models, DiceHuBERT leverages HuBERT's iterative self-distillation mechanism by directly replacing the original model with a student model. This replacement allows the student to be trained using the same SSL objective used when pre-training HuBERT, eliminating the need for additional modules or architectural constraints. Exp"},"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":"2507.02911","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-25T00:39:33Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"29833e88c35d3eab683e24ff84d1176569a890b4c804e6704f88772d55472482","abstract_canon_sha256":"7fb93d86fcb9fec162d1f5a895f6eb28f8ff957b4707a0ea6c88ad4a835715bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:48.523899Z","signature_b64":"G41ugEWDdRE66S0jw8Cq2syHLDfWJhr+DU9Prg9n7e6sA+1l05q7rmqwr3hDhooBmMyPU2E0a/PZXNSJi5aVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"425be03ffa5a2bbd8c19ef8f06542bf8c2972995fd6f9fde76b1646797204eb2","last_reissued_at":"2026-07-05T11:31:48.523494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:48.523494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Ahmed Hussen Abdelaziz, Hyung Gun Chi, Li-Wei Chen, Oggi Rudovic, Shinji Watanabe, Takuya Higuchi, Tatiana Likhomanenko, Zakaria Aldeneh","submitted_at":"2025-06-25T00:39:33Z","abstract_excerpt":"We introduce DiceHuBERT, a knowledge distillation framework for compressing HuBERT, a widely used self-supervised learning (SSL)-based speech foundation model. Unlike existing distillation methods that rely on layer-wise and feature-wise mapping between teacher and student models, DiceHuBERT leverages HuBERT's iterative self-distillation mechanism by directly replacing the original model with a student model. This replacement allows the student to be trained using the same SSL objective used when pre-training HuBERT, eliminating the need for additional modules or architectural constraints. Exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02911","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/2507.02911/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":"2507.02911","created_at":"2026-07-05T11:31:48.523552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02911v1","created_at":"2026-07-05T11:31:48.523552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02911","created_at":"2026-07-05T11:31:48.523552+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJN6AP72LIV3","created_at":"2026-07-05T11:31:48.523552+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJN6AP72LIV33DAZ","created_at":"2026-07-05T11:31:48.523552+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJN6AP72","created_at":"2026-07-05T11:31:48.523552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02911","citing_title":"DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D","json":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D.json","graph_json":"https://pith.science/api/pith-number/IJN6AP72LIV33DAZ56HQMVBL7D/graph.json","events_json":"https://pith.science/api/pith-number/IJN6AP72LIV33DAZ56HQMVBL7D/events.json","paper":"https://pith.science/paper/IJN6AP72"},"agent_actions":{"view_html":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D","download_json":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D.json","view_paper":"https://pith.science/paper/IJN6AP72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02911&json=true","fetch_graph":"https://pith.science/api/pith-number/IJN6AP72LIV33DAZ56HQMVBL7D/graph.json","fetch_events":"https://pith.science/api/pith-number/IJN6AP72LIV33DAZ56HQMVBL7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D/action/storage_attestation","attest_author":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D/action/author_attestation","sign_citation":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D/action/citation_signature","submit_replication":"https://pith.science/pith/IJN6AP72LIV33DAZ56HQMVBL7D/action/replication_record"}},"created_at":"2026-07-05T11:31:48.523552+00:00","updated_at":"2026-07-05T11:31:48.523552+00:00"}