{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4CQAKHTSAR6DB7CIHHCKZNAE3W","short_pith_number":"pith:4CQAKHTS","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"},"canonical_sha256":"e0a0051e72047c30fc4839c4acb404dda864197440e17840f324b11f3885cf26","source":{"kind":"arxiv","id":"2606.11514","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11514","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11514v1","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11514","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"4CQAKHTSAR6D","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"4CQAKHTSAR6DB7CI","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"4CQAKHTS","created_at":"2026-06-11T01:09:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4CQAKHTSAR6DB7CIHHCKZNAE3W","target":"record","payload":{"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"},"canonical_sha256":"e0a0051e72047c30fc4839c4acb404dda864197440e17840f324b11f3885cf26","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"},"source_kind":"arxiv","source_id":"2606.11514","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NgLOEVZ1Yw8aSUTisNQT5TwNSCKy0kmMxJPuePoEbWMNYa/d7ewiqs+K5Omaa6LH1WAMl/1VygeMBISWaXD0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T00:24:58.560857Z"},"content_sha256":"5eb74f890d1a90dbae31016d21390b6f66d090d59c8043624e6f80a967752ca9","schema_version":"1.0","event_id":"sha256:5eb74f890d1a90dbae31016d21390b6f66d090d59c8043624e6f80a967752ca9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4CQAKHTSAR6DB7CIHHCKZNAE3W","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v32YFy61JuMcUEu0sL2H6/evEC8BdUui8wl9N7KEsKeOK899bRZe1pvB5b7nIurnob0+kGJMyykRcifn2L48DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T00:24:58.561232Z"},"content_sha256":"c547adcdbaada8f7c2985ae00efceb20b4af998d19a79f248d8c61ad1dcd1549","schema_version":"1.0","event_id":"sha256:c547adcdbaada8f7c2985ae00efceb20b4af998d19a79f248d8c61ad1dcd1549"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/bundle.json","state_url":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-26T00:24:58Z","links":{"resolver":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W","bundle":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/bundle.json","state":"https://pith.science/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4CQAKHTSAR6DB7CIHHCKZNAE3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4CQAKHTSAR6DB7CIHHCKZNAE3W","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":"2d5168b60bcafd708da576ae4b37391fb105273c37d40b0e3dc5747291fd6865","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T23:29:00Z","title_canon_sha256":"dc873e988ba12f22fcd3416a03fc852323b8f42827fcec1bde4233bc022f0a31"},"schema_version":"1.0","source":{"id":"2606.11514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11514","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11514v1","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11514","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"4CQAKHTSAR6D","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"4CQAKHTSAR6DB7CI","created_at":"2026-06-11T01:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"4CQAKHTS","created_at":"2026-06-11T01:09:53Z"}],"graph_snapshots":[{"event_id":"sha256:c547adcdbaada8f7c2985ae00efceb20b4af998d19a79f248d8c61ad1dcd1549","target":"graph","created_at":"2026-06-11T01:09:53Z","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/2606.11514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T23:29:00Z","title":"CS-YODAS: A Mined Dataset of In-the-Wild Code-Switched Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11514","kind":"arxiv","version":1},"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":"sha256:5eb74f890d1a90dbae31016d21390b6f66d090d59c8043624e6f80a967752ca9","target":"record","created_at":"2026-06-11T01:09:53Z","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":"2d5168b60bcafd708da576ae4b37391fb105273c37d40b0e3dc5747291fd6865","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-09T23:29:00Z","title_canon_sha256":"dc873e988ba12f22fcd3416a03fc852323b8f42827fcec1bde4233bc022f0a31"},"schema_version":"1.0","source":{"id":"2606.11514","kind":"arxiv","version":1}},"canonical_sha256":"e0a0051e72047c30fc4839c4acb404dda864197440e17840f324b11f3885cf26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0a0051e72047c30fc4839c4acb404dda864197440e17840f324b11f3885cf26","first_computed_at":"2026-06-11T01:09:53.556662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:53.556662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vhkBdGqjFdetp3uVqy4U08lJwDpbc1k8HhY2R5qr6YPmDVNv2GlugTburCj2gNOlOxeZuX86EyBYucKd5KRcBQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:53.557565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5eb74f890d1a90dbae31016d21390b6f66d090d59c8043624e6f80a967752ca9","sha256:c547adcdbaada8f7c2985ae00efceb20b4af998d19a79f248d8c61ad1dcd1549"],"state_sha256":"1f42adf33abc25f69c35d1bd42d8008c1717d228ea6cf6838255a9947e192f9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Krzwlt4/tj5ChUOV45qEMsfmR0aaruJsqKrEp0lTWFpObNSiao6zvGMUNYxxuwAs9MxRTsCVd+Ba34Mv6H9TDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T00:24:58.563335Z","bundle_sha256":"427855820ca7651feadf07e873dfa13f50780f50bca61342a816168b17691b47"}}