{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QVFHQB6PZ4SLDL5PYM76FYZ6BY","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":"aa713d2e2d0f8effee265ad75dcdd1420fc9f537012ef5cf470923c7f74fface","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:39:18Z","title_canon_sha256":"57c87e11edd523efc06b1eca487996da3b8e539bef9cddb3cea3ab1b3d10d585"},"schema_version":"1.0","source":{"id":"2106.07699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07699","created_at":"2026-07-05T02:49:32Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07699v1","created_at":"2026-07-05T02:49:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07699","created_at":"2026-07-05T02:49:32Z"},{"alias_kind":"pith_short_12","alias_value":"QVFHQB6PZ4SL","created_at":"2026-07-05T02:49:32Z"},{"alias_kind":"pith_short_16","alias_value":"QVFHQB6PZ4SLDL5P","created_at":"2026-07-05T02:49:32Z"},{"alias_kind":"pith_short_8","alias_value":"QVFHQB6P","created_at":"2026-07-05T02:49:32Z"}],"graph_snapshots":[{"event_id":"sha256:cdd43c5b0cf5f05f869c1ccb770b82d3dd691ccb95eceb78452917c405b76f59","target":"graph","created_at":"2026-07-05T02:49:32Z","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/2106.07699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modeling code-switched speech is an important problem in automatic speech recognition (ASR). Labeled code-switched data are rare, so monolingual data are often used to model code-switched speech. These monolingual data may be more closely matched to one of the languages in the code-switch pair. We show that such asymmetry can bias prediction toward the better-matched language and degrade overall model performance. To address this issue, we propose a semi-supervised approach for code-switched ASR. We consider the case of English-Mandarin code-switching, and the problem of using monolingual data","authors_text":"Andrew Slottje, Matthew Snover, Owen Kimball, Shannon Wotherspoon, William Hartmann","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:39:18Z","title":"Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07699","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":"sha256:8ae84ab2a1374efbc2796261193def096437cd5e07861a094819f998cf812445","target":"record","created_at":"2026-07-05T02:49:32Z","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":"aa713d2e2d0f8effee265ad75dcdd1420fc9f537012ef5cf470923c7f74fface","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:39:18Z","title_canon_sha256":"57c87e11edd523efc06b1eca487996da3b8e539bef9cddb3cea3ab1b3d10d585"},"schema_version":"1.0","source":{"id":"2106.07699","kind":"arxiv","version":1}},"canonical_sha256":"854a7807cfcf24b1afafc33fe2e33e0e20c8e8724c2c998986d24422c99af6d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"854a7807cfcf24b1afafc33fe2e33e0e20c8e8724c2c998986d24422c99af6d9","first_computed_at":"2026-07-05T02:49:32.918041Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:32.918041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8pBIw2fP9ZmHMr777YeRRjvymjWP0qPM3wwzwhaWP4V8EW9Zzeo5NuDr2uRXbzBra+aa+kFXQsTte6QpmyvkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:32.918451Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.07699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ae84ab2a1374efbc2796261193def096437cd5e07861a094819f998cf812445","sha256:cdd43c5b0cf5f05f869c1ccb770b82d3dd691ccb95eceb78452917c405b76f59"],"state_sha256":"ddefe00cd7358091713267775d008fdb9c8dfcae5543aea66175d14a3fa09776"}