{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LZXSH2YAJQ4IDY6NQMYXC2PQRQ","short_pith_number":"pith:LZXSH2YA","schema_version":"1.0","canonical_sha256":"5e6f23eb004c3881e3cd83317169f08c159a38b864ed137239357d15e909dd50","source":{"kind":"arxiv","id":"2501.13497","version":1},"attestation_state":"computed","paper":{"title":"DQ-Data2vec: Decoupling Quantization for Multilingual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kun Wei, Lei Xie, Linhao Dong, Qijie Shao, Sining Sun","submitted_at":"2025-01-23T09:25:31Z","abstract_excerpt":"Data2vec is a self-supervised learning (SSL) approach that employs a teacher-student architecture for contextual representation learning via masked prediction, demonstrating remarkable performance in monolingual ASR. Previous studies have revealed that data2vec's shallow layers capture speaker and language information, middle layers encode phoneme and word features, while deep layers are responsible for reconstruction. Language and phoneme features are crucial for multilingual ASR. However, data2vec's masked representation generation relies on multi-layer averaging, inevitably coupling these f"},"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":"2501.13497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-23T09:25:31Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"02d8209b88b70b6b0cb94056ff2998b5b3ee9fcb40273328b67ef50f046919a7","abstract_canon_sha256":"b4daaee7feefe563efa7c8068d3b74424a0fe005da6c42f617a13536736e3630"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:29.564802Z","signature_b64":"VADjbKS7duper2rhPOSM8hKGWn/ECQNE1ZaGz0It66b9Dlz6xLTt/7dSBG5YjK4U54+guxDF+cpN4d3Lk4oTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e6f23eb004c3881e3cd83317169f08c159a38b864ed137239357d15e909dd50","last_reissued_at":"2026-07-05T10:04:29.564304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:29.564304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DQ-Data2vec: Decoupling Quantization for Multilingual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kun Wei, Lei Xie, Linhao Dong, Qijie Shao, Sining Sun","submitted_at":"2025-01-23T09:25:31Z","abstract_excerpt":"Data2vec is a self-supervised learning (SSL) approach that employs a teacher-student architecture for contextual representation learning via masked prediction, demonstrating remarkable performance in monolingual ASR. Previous studies have revealed that data2vec's shallow layers capture speaker and language information, middle layers encode phoneme and word features, while deep layers are responsible for reconstruction. Language and phoneme features are crucial for multilingual ASR. However, data2vec's masked representation generation relies on multi-layer averaging, inevitably coupling these f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13497","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/2501.13497/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":"2501.13497","created_at":"2026-07-05T10:04:29.564367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13497v1","created_at":"2026-07-05T10:04:29.564367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13497","created_at":"2026-07-05T10:04:29.564367+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZXSH2YAJQ4I","created_at":"2026-07-05T10:04:29.564367+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZXSH2YAJQ4IDY6N","created_at":"2026-07-05T10:04:29.564367+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZXSH2YA","created_at":"2026-07-05T10:04:29.564367+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/LZXSH2YAJQ4IDY6NQMYXC2PQRQ","json":"https://pith.science/pith/LZXSH2YAJQ4IDY6NQMYXC2PQRQ.json","graph_json":"https://pith.science/api/pith-number/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/graph.json","events_json":"https://pith.science/api/pith-number/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/events.json","paper":"https://pith.science/paper/LZXSH2YA"},"agent_actions":{"view_html":"https://pith.science/pith/LZXSH2YAJQ4IDY6NQMYXC2PQRQ","download_json":"https://pith.science/pith/LZXSH2YAJQ4IDY6NQMYXC2PQRQ.json","view_paper":"https://pith.science/paper/LZXSH2YA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13497&json=true","fetch_graph":"https://pith.science/api/pith-number/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/action/storage_attestation","attest_author":"https://pith.science/pith/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/action/author_attestation","sign_citation":"https://pith.science/pith/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/action/citation_signature","submit_replication":"https://pith.science/pith/LZXSH2YAJQ4IDY6NQMYXC2PQRQ/action/replication_record"}},"created_at":"2026-07-05T10:04:29.564367+00:00","updated_at":"2026-07-05T10:04:29.564367+00:00"}