{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DU2SASNM2UJREX23CHGYDZNZAR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"416f5a9b5b8d36430f12ba2de1d0876a9206f681c7f820dbce266254fe5883c8","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:25:13Z","title_canon_sha256":"62ce8cf8d9d101cfef6d28a45934eda1e235ec968fc14e2f4d1a7a188f570016"},"schema_version":"1.0","source":{"id":"2506.00981","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00981","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00981v2","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00981","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_12","alias_value":"DU2SASNM2UJR","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_16","alias_value":"DU2SASNM2UJREX23","created_at":"2026-07-05T11:34:51Z"},{"alias_kind":"pith_short_8","alias_value":"DU2SASNM","created_at":"2026-07-05T11:34:51Z"}],"graph_snapshots":[{"event_id":"sha256:c5996c9ebca91869f546fa240756fb5d4477bfce2cbebd9c973084cf1fda8338","target":"graph","created_at":"2026-07-05T11:34:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.00981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Charlotte Pouw, Gaofei Shen, Hosein Mohebbi, Marianne de Heer Kloots, Martijn Bentum, Willem Zuidema","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:25:13Z","title":"What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00981","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f8bf35a889b74ba40ed9e6b96b8a8815fb79402ba98170a7031e75febef23d85","target":"record","created_at":"2026-07-05T11:34:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"416f5a9b5b8d36430f12ba2de1d0876a9206f681c7f820dbce266254fe5883c8","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-01T12:25:13Z","title_canon_sha256":"62ce8cf8d9d101cfef6d28a45934eda1e235ec968fc14e2f4d1a7a188f570016"},"schema_version":"1.0","source":{"id":"2506.00981","kind":"arxiv","version":2}},"canonical_sha256":"1d352049acd513125f5b11cd81e5b9045450f57bbf21bf44684ef35f6cea8c02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d352049acd513125f5b11cd81e5b9045450f57bbf21bf44684ef35f6cea8c02","first_computed_at":"2026-07-05T11:34:51.781226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:51.781226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r7568Zubi2OsnAcOfnuqm1e3P1GrEjivl+Bo0InKyDB4W3KGlVvzFYc3NoeNKMJKeL7Gjd9wGZbPqqu9eNfFBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:51.781701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00981","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8bf35a889b74ba40ed9e6b96b8a8815fb79402ba98170a7031e75febef23d85","sha256:c5996c9ebca91869f546fa240756fb5d4477bfce2cbebd9c973084cf1fda8338"],"state_sha256":"6190c4afbbbdb52b25379e7896481eef2b2e3e63a5f21fd1b909cdd396c9c611"}