{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DU2SASNM2UJREX23CHGYDZNZAR","short_pith_number":"pith:DU2SASNM","schema_version":"1.0","canonical_sha256":"1d352049acd513125f5b11cd81e5b9045450f57bbf21bf44684ef35f6cea8c02","source":{"kind":"arxiv","id":"2506.00981","version":2},"attestation_state":"computed","paper":{"title":"What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Charlotte Pouw, Gaofei Shen, Hosein Mohebbi, Marianne de Heer Kloots, Martijn Bentum, Willem Zuidema","submitted_at":"2025-06-01T12:25:13Z","abstract_excerpt":"How language-specific are speech representations learned by self-supervised models? Existing work has shown that a range of linguistic features can be successfully decoded from end-to-end models trained only on speech recordings. However, it's less clear to what extent pre-training on specific languages improves language-specific linguistic information. Here we test the encoding of Dutch phonetic and lexical information in internal representations of self-supervised Wav2Vec2 models. Pre-training exclusively on Dutch improves the representation of Dutch linguistic features as compared to pre-tr"},"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":"2506.00981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:25:13Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"62ce8cf8d9d101cfef6d28a45934eda1e235ec968fc14e2f4d1a7a188f570016","abstract_canon_sha256":"416f5a9b5b8d36430f12ba2de1d0876a9206f681c7f820dbce266254fe5883c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:51.781701Z","signature_b64":"r7568Zubi2OsnAcOfnuqm1e3P1GrEjivl+Bo0InKyDB4W3KGlVvzFYc3NoeNKMJKeL7Gjd9wGZbPqqu9eNfFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d352049acd513125f5b11cd81e5b9045450f57bbf21bf44684ef35f6cea8c02","last_reissued_at":"2026-07-05T11:34:51.781226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:51.781226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Charlotte Pouw, Gaofei Shen, Hosein Mohebbi, Marianne de Heer Kloots, Martijn Bentum, Willem Zuidema","submitted_at":"2025-06-01T12:25:13Z","abstract_excerpt":"How language-specific are speech representations learned by self-supervised models? Existing work has shown that a range of linguistic features can be successfully decoded from end-to-end models trained only on speech recordings. However, it's less clear to what extent pre-training on specific languages improves language-specific linguistic information. Here we test the encoding of Dutch phonetic and lexical information in internal representations of self-supervised Wav2Vec2 models. Pre-training exclusively on Dutch improves the representation of Dutch linguistic features as compared to pre-tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00981","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/2506.00981/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":"2506.00981","created_at":"2026-07-05T11:34:51.781282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00981v2","created_at":"2026-07-05T11:34:51.781282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00981","created_at":"2026-07-05T11:34:51.781282+00:00"},{"alias_kind":"pith_short_12","alias_value":"DU2SASNM2UJR","created_at":"2026-07-05T11:34:51.781282+00:00"},{"alias_kind":"pith_short_16","alias_value":"DU2SASNM2UJREX23","created_at":"2026-07-05T11:34:51.781282+00:00"},{"alias_kind":"pith_short_8","alias_value":"DU2SASNM","created_at":"2026-07-05T11:34:51.781282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00981","citing_title":"What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR","json":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR.json","graph_json":"https://pith.science/api/pith-number/DU2SASNM2UJREX23CHGYDZNZAR/graph.json","events_json":"https://pith.science/api/pith-number/DU2SASNM2UJREX23CHGYDZNZAR/events.json","paper":"https://pith.science/paper/DU2SASNM"},"agent_actions":{"view_html":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR","download_json":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR.json","view_paper":"https://pith.science/paper/DU2SASNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00981&json=true","fetch_graph":"https://pith.science/api/pith-number/DU2SASNM2UJREX23CHGYDZNZAR/graph.json","fetch_events":"https://pith.science/api/pith-number/DU2SASNM2UJREX23CHGYDZNZAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR/action/storage_attestation","attest_author":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR/action/author_attestation","sign_citation":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR/action/citation_signature","submit_replication":"https://pith.science/pith/DU2SASNM2UJREX23CHGYDZNZAR/action/replication_record"}},"created_at":"2026-07-05T11:34:51.781282+00:00","updated_at":"2026-07-05T11:34:51.781282+00:00"}