{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TMFV3JCE2FHI2TH5BEH33UAXEA","short_pith_number":"pith:TMFV3JCE","schema_version":"1.0","canonical_sha256":"9b0b5da444d14e8d4cfd090fbdd0172003e197c5ed635d194eaa0931265eeca3","source":{"kind":"arxiv","id":"2512.19612","version":2},"attestation_state":"computed","paper":{"title":"MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Angelo Ortiz Tandazo, Emmanuel Dupoux, Manel Khentout, Thomas Hueber, Youssef Benchekroun","submitted_at":"2025-12-22T17:47:49Z","abstract_excerpt":"This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a phonetic-to-articulatory feature mapping in 55 languages. Our models learn from multilingual data to predict articulatory features or phones, resulting in language-independent representations that capture multilingual phonetic properties. Through comprehensive ABX discriminability testing, we show MauBERT models produce more context-invariant representations than state-of-the"},"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":"2512.19612","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-22T17:47:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"96e36704b95734ab7aa0245538a69be7f5dfcc54a5c562cf5699d55590f31321","abstract_canon_sha256":"de48c0522b8c260cfd214f0e473a69c05af39d759760e1ce6ba592c29df584f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:31.484603Z","signature_b64":"d50YeqrznIKMdHCZUgSjyIKnqvBl1as/XAlovlIZZKdOcxSXikzTWKWxiTZ31Pv3cMiY8YHQFJ2tKDnwqMwHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b0b5da444d14e8d4cfd090fbdd0172003e197c5ed635d194eaa0931265eeca3","last_reissued_at":"2026-06-30T01:17:31.483650Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:31.483650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Angelo Ortiz Tandazo, Emmanuel Dupoux, Manel Khentout, Thomas Hueber, Youssef Benchekroun","submitted_at":"2025-12-22T17:47:49Z","abstract_excerpt":"This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT pre-training with supervision based on a phonetic-to-articulatory feature mapping in 55 languages. Our models learn from multilingual data to predict articulatory features or phones, resulting in language-independent representations that capture multilingual phonetic properties. Through comprehensive ABX discriminability testing, we show MauBERT models produce more context-invariant representations than state-of-the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.19612","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/2512.19612/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":"2512.19612","created_at":"2026-06-30T01:17:31.483771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.19612v2","created_at":"2026-06-30T01:17:31.483771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.19612","created_at":"2026-06-30T01:17:31.483771+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMFV3JCE2FHI","created_at":"2026-06-30T01:17:31.483771+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMFV3JCE2FHI2TH5","created_at":"2026-06-30T01:17:31.483771+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMFV3JCE","created_at":"2026-06-30T01:17:31.483771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.21204","citing_title":"SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA","json":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA.json","graph_json":"https://pith.science/api/pith-number/TMFV3JCE2FHI2TH5BEH33UAXEA/graph.json","events_json":"https://pith.science/api/pith-number/TMFV3JCE2FHI2TH5BEH33UAXEA/events.json","paper":"https://pith.science/paper/TMFV3JCE"},"agent_actions":{"view_html":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA","download_json":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA.json","view_paper":"https://pith.science/paper/TMFV3JCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.19612&json=true","fetch_graph":"https://pith.science/api/pith-number/TMFV3JCE2FHI2TH5BEH33UAXEA/graph.json","fetch_events":"https://pith.science/api/pith-number/TMFV3JCE2FHI2TH5BEH33UAXEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA/action/storage_attestation","attest_author":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA/action/author_attestation","sign_citation":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA/action/citation_signature","submit_replication":"https://pith.science/pith/TMFV3JCE2FHI2TH5BEH33UAXEA/action/replication_record"}},"created_at":"2026-06-30T01:17:31.483771+00:00","updated_at":"2026-06-30T01:17:31.483771+00:00"}