{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4CQAKHTSAR6DB7CIHHCKZNAE3W","short_pith_number":"pith:4CQAKHTS","schema_version":"1.0","canonical_sha256":"e0a0051e72047c30fc4839c4acb404dda864197440e17840f324b11f3885cf26","source":{"kind":"arxiv","id":"2606.11514","version":1},"attestation_state":"computed","paper":{"title":"CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Alexander Polok, Anuj Diwan, Brian Yan, David R. Mortensen, Injy Hamed, Iris Emerman Thomas Hain, Matthew Wiesner, Olga Iakovenko, Peter Viechnicki, Qingzheng Wang, Shinji Watanabe, Shuichiro Shimizu","submitted_at":"2026-06-09T23:29:00Z","abstract_excerpt":"We present CS-YODAS, a Creative Commons-licensed dataset of in-the-wild code-switched speech mined from multilingual YouTube data. Code-switching (CS), or the alternation between languages within an utterance or conversation, is common in multilingual settings but remains underrepresented in existing CS speech resources, which are typically small, domain-specific, or artificially constructed. Building on the YODAS corpus, we develop a scalable, human-in-the-loop pipeline for identifying and validating naturally occurring code-switching. The resulting dataset, which totals 313 hours and spans 7"},"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":"2606.11514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T23:29:00Z","cross_cats_sorted":[],"title_canon_sha256":"dc873e988ba12f22fcd3416a03fc852323b8f42827fcec1bde4233bc022f0a31","abstract_canon_sha256":"2d5168b60bcafd708da576ae4b37391fb105273c37d40b0e3dc5747291fd6865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:53.557565Z","signature_b64":"vhkBdGqjFdetp3uVqy4U08lJwDpbc1k8HhY2R5qr6YPmDVNv2GlugTburCj2gNOlOxeZuX86EyBYucKd5KRcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0a0051e72047c30fc4839c4acb404dda864197440e17840f324b11f3885cf26","last_reissued_at":"2026-06-11T01:09:53.556662Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:53.556662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Alexander Polok, Anuj Diwan, Brian Yan, David R. Mortensen, Injy Hamed, Iris Emerman Thomas Hain, Matthew Wiesner, Olga Iakovenko, Peter Viechnicki, Qingzheng Wang, Shinji Watanabe, Shuichiro Shimizu","submitted_at":"2026-06-09T23:29:00Z","abstract_excerpt":"We present CS-YODAS, a Creative Commons-licensed dataset of in-the-wild code-switched speech mined from multilingual YouTube data. Code-switching (CS), or the alternation between languages within an utterance or conversation, is common in multilingual settings but remains underrepresented in existing CS speech resources, which are typically small, domain-specific, or artificially constructed. Building on the YODAS corpus, we develop a scalable, human-in-the-loop pipeline for identifying and validating naturally occurring code-switching. The resulting dataset, which totals 313 hours and spans 7"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11514","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/2606.11514/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":"2606.11514","created_at":"2026-06-11T01:09:53.556807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11514v1","created_at":"2026-06-11T01:09:53.556807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11514","created_at":"2026-06-11T01:09:53.556807+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CQAKHTSAR6D","created_at":"2026-06-11T01:09:53.556807+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CQAKHTSAR6DB7CI","created_at":"2026-06-11T01:09:53.556807+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CQAKHTS","created_at":"2026-06-11T01:09:53.556807+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/4CQAKHTSAR6DB7CIHHCKZNAE3W","json":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W.json","graph_json":"https://pith.science/api/pith-number/4CQAKHTSAR6DB7CIHHCKZNAE3W/graph.json","events_json":"https://pith.science/api/pith-number/4CQAKHTSAR6DB7CIHHCKZNAE3W/events.json","paper":"https://pith.science/paper/4CQAKHTS"},"agent_actions":{"view_html":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W","download_json":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W.json","view_paper":"https://pith.science/paper/4CQAKHTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11514&json=true","fetch_graph":"https://pith.science/api/pith-number/4CQAKHTSAR6DB7CIHHCKZNAE3W/graph.json","fetch_events":"https://pith.science/api/pith-number/4CQAKHTSAR6DB7CIHHCKZNAE3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/action/storage_attestation","attest_author":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/action/author_attestation","sign_citation":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/action/citation_signature","submit_replication":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/action/replication_record"}},"created_at":"2026-06-11T01:09:53.556807+00:00","updated_at":"2026-06-11T01:09:53.556807+00:00"}