{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2RWDQ5VDVF5TGMTO2DR6D3QMTQ","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":"9d213f1f09151839f1ef0efaf4b496192d4cfd45bb8b1a7ece8fea5f59543b4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-12T11:37:25Z","title_canon_sha256":"2cb6d6a89cb5f637ee2e86adfba253329453ec4507591b38d94a5b8ce18d23da"},"schema_version":"1.0","source":{"id":"2006.07094","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07094","created_at":"2026-07-05T01:34:55Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07094v2","created_at":"2026-07-05T01:34:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07094","created_at":"2026-07-05T01:34:55Z"},{"alias_kind":"pith_short_12","alias_value":"2RWDQ5VDVF5T","created_at":"2026-07-05T01:34:55Z"},{"alias_kind":"pith_short_16","alias_value":"2RWDQ5VDVF5TGMTO","created_at":"2026-07-05T01:34:55Z"},{"alias_kind":"pith_short_8","alias_value":"2RWDQ5VD","created_at":"2026-07-05T01:34:55Z"}],"graph_snapshots":[{"event_id":"sha256:5546a5e79b279f5b680a6cff90ce3145c2d1242908e27fd316240d620e9b828f","target":"graph","created_at":"2026-07-05T01:34:55Z","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/2006.07094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we conduct data selection analysis in building an English-Mandarin code-switching (CS) speech recognition (CSSR) system, which is aimed for a real CSSR contest in China. The overall training sets have three subsets, i.e., a code-switching data set, an English (LibriSpeech) and a Mandarin data set respectively. The code-switching data are Mandarin dominated. First of all, it is found using the overall data yields worse results, and hence data selection study is necessary. Then to exploit monolingual data, we find data matching is crucial. Mandarin data is closely matched with the","authors_text":"Eng Siong Chng, Haihua Xu, Haobo Zhang, Hao Huang, Van Tung Pham","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-12T11:37:25Z","title":"Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-switching Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07094","kind":"arxiv","version":2},"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":"sha256:7ef152f4f6cd9c20026db622de21be65d1a7499c307a2cde9fbcd10b268b3f07","target":"record","created_at":"2026-07-05T01:34:55Z","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":"9d213f1f09151839f1ef0efaf4b496192d4cfd45bb8b1a7ece8fea5f59543b4a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-12T11:37:25Z","title_canon_sha256":"2cb6d6a89cb5f637ee2e86adfba253329453ec4507591b38d94a5b8ce18d23da"},"schema_version":"1.0","source":{"id":"2006.07094","kind":"arxiv","version":2}},"canonical_sha256":"d46c3876a3a97b33326ed0e3e1ee0c9c206950e005251adb196b48dbfa3f19e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d46c3876a3a97b33326ed0e3e1ee0c9c206950e005251adb196b48dbfa3f19e2","first_computed_at":"2026-07-05T01:34:55.243670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:34:55.243670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SqJb09qpaYj//dXXbVGbrVNRV+19mcaFZ5ogbU2iMhixX0zVYg8YSCTcDunjDbQmhvXQfqpvCXate77MsUr3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T01:34:55.244031Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07094","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ef152f4f6cd9c20026db622de21be65d1a7499c307a2cde9fbcd10b268b3f07","sha256:5546a5e79b279f5b680a6cff90ce3145c2d1242908e27fd316240d620e9b828f"],"state_sha256":"eac81d8f46750f207645304e404644fa9b876410f9599f9e41f3d75437318453"}