{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KOIBEEX3S34ZB5YVC5ZTMDIACX","short_pith_number":"pith:KOIBEEX3","schema_version":"1.0","canonical_sha256":"53901212fb96f990f7151773360d0015c31946e41d1a91ebe0e497fd3a52fea3","source":{"kind":"arxiv","id":"2607.26350","version":1},"attestation_state":"computed","paper":{"title":"Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Daigo Takizawa, Samuele Cornell, Satoru Fukayama, Shinji Watanabe, Tomohiko Nakamura, William Chen","submitted_at":"2026-07-28T23:46:37Z","abstract_excerpt":"Neural audio codecs (NACs) have become popular for obtaining speech representations as discrete tokens. Beyond compression, discrete tokens can be used to train self-supervised learning (SSL) models. Such models, referred to as codec-based SSL models, reduce data storage and computational cost, enabling scalable SSL pre-training. However, their language sensitivity remains unclear. When the language changes, codec-based SSL models may require retraining, which undermines their efficiency. In this paper, we present a systematic analysis of language sensitivity by varying either the NAC training"},"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":"2607.26350","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-28T23:46:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"08e799553bb32e09c3e70ce02320b8f52b82d569e3491239500875e9c006ad59","abstract_canon_sha256":"107da409bf77d989d29acf4d301f098c5b62584936c943d72ae0e9fb47b9d9c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53901212fb96f990f7151773360d0015c31946e41d1a91ebe0e497fd3a52fea3","last_reissued_at":"2026-07-30T01:18:08.718627Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:18:08.718627Z"},"graph_snapshot":{"paper":{"title":"Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Daigo Takizawa, Samuele Cornell, Satoru Fukayama, Shinji Watanabe, Tomohiko Nakamura, William Chen","submitted_at":"2026-07-28T23:46:37Z","abstract_excerpt":"Neural audio codecs (NACs) have become popular for obtaining speech representations as discrete tokens. Beyond compression, discrete tokens can be used to train self-supervised learning (SSL) models. Such models, referred to as codec-based SSL models, reduce data storage and computational cost, enabling scalable SSL pre-training. However, their language sensitivity remains unclear. When the language changes, codec-based SSL models may require retraining, which undermines their efficiency. In this paper, we present a systematic analysis of language sensitivity by varying either the NAC training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26350","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/2607.26350/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":"2607.26350","created_at":"2026-07-30T01:18:08.724016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26350v1","created_at":"2026-07-30T01:18:08.724016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26350","created_at":"2026-07-30T01:18:08.724016+00:00"},{"alias_kind":"pith_short_12","alias_value":"KOIBEEX3S34Z","created_at":"2026-07-30T01:18:08.724016+00:00"},{"alias_kind":"pith_short_16","alias_value":"KOIBEEX3S34ZB5YV","created_at":"2026-07-30T01:18:08.724016+00:00"},{"alias_kind":"pith_short_8","alias_value":"KOIBEEX3","created_at":"2026-07-30T01:18:08.724016+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/KOIBEEX3S34ZB5YVC5ZTMDIACX","json":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX.json","graph_json":"https://pith.science/api/pith-number/KOIBEEX3S34ZB5YVC5ZTMDIACX/graph.json","events_json":"https://pith.science/api/pith-number/KOIBEEX3S34ZB5YVC5ZTMDIACX/events.json","paper":"https://pith.science/paper/KOIBEEX3"},"agent_actions":{"view_html":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX","download_json":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX.json","view_paper":"https://pith.science/paper/KOIBEEX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26350&json=true","fetch_graph":"https://pith.science/api/pith-number/KOIBEEX3S34ZB5YVC5ZTMDIACX/graph.json","fetch_events":"https://pith.science/api/pith-number/KOIBEEX3S34ZB5YVC5ZTMDIACX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/action/storage_attestation","attest_author":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/action/author_attestation","sign_citation":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/action/citation_signature","submit_replication":"https://pith.science/pith/KOIBEEX3S34ZB5YVC5ZTMDIACX/action/replication_record"}},"created_at":"2026-07-30T01:18:08.724016+00:00","updated_at":"2026-07-30T01:18:08.724016+00:00"}