{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CY7SB2QSKHFLBKFV6ADRSY7RFD","short_pith_number":"pith:CY7SB2QS","canonical_record":{"source":{"id":"2206.13135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-27T09:30:25Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"054d374a6f34aeab889768bb8a4fb48c543c7b3ad476de5451d176a809ceb3cb","abstract_canon_sha256":"b08e77a9f4401f23285a3cf7c1c82611b28fa2ddc0bf03ec56494691fbb9aef9"},"schema_version":"1.0"},"canonical_sha256":"163f20ea1251cab0a8b5f0071963f128fa3f2b6723f9483014de75dd4e79083c","source":{"kind":"arxiv","id":"2206.13135","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13135","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13135v1","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13135","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"CY7SB2QSKHFL","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"pith_short_16","alias_value":"CY7SB2QSKHFLBKFV","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"pith_short_8","alias_value":"CY7SB2QS","created_at":"2026-07-05T04:35:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CY7SB2QSKHFLBKFV6ADRSY7RFD","target":"record","payload":{"canonical_record":{"source":{"id":"2206.13135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-27T09:30:25Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"054d374a6f34aeab889768bb8a4fb48c543c7b3ad476de5451d176a809ceb3cb","abstract_canon_sha256":"b08e77a9f4401f23285a3cf7c1c82611b28fa2ddc0bf03ec56494691fbb9aef9"},"schema_version":"1.0"},"canonical_sha256":"163f20ea1251cab0a8b5f0071963f128fa3f2b6723f9483014de75dd4e79083c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:02.919191Z","signature_b64":"PcCI8cKhl0N+cG0Ytn/LgEmxFJdpSSMHP0FZVC9U6+Z53ap+GBXwfZVZ3fPNbXWfztnl+/2aTXOD+XwYJJzBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"163f20ea1251cab0a8b5f0071963f128fa3f2b6723f9483014de75dd4e79083c","last_reissued_at":"2026-07-05T04:35:02.918787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:02.918787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.13135","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":"2026-07-05T04:35:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xt90tHt7H9ZLq3yTfDv6t31F2vlKeIIEjCWRxSLMg4ATbryb+TpNGZlzTtC0et5LqqGTk619lRXWAwnT5ctAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:56:26.213169Z"},"content_sha256":"9214c0564b3f1e612559f773099e0679dbc9871f23ad84ffef949d5754591493","schema_version":"1.0","event_id":"sha256:9214c0564b3f1e612559f773099e0679dbc9871f23ad84ffef949d5754591493"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CY7SB2QSKHFLBKFV6ADRSY7RFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Changbin Chen, Chengfei Li, Guangjing Wang, Jinfeng Bai, Shuhao Deng, Yaguang Gong, Yaoping Wang","submitted_at":"2022-06-27T09:30:25Z","abstract_excerpt":"This paper introduces a new corpus of Mandarin-English code-switching speech recognition--TALCS corpus, suitable for training and evaluating code-switching speech recognition systems. TALCS corpus is derived from real online one-to-one English teaching scenes in TAL education group, which contains roughly 587 hours of speech sampled at 16 kHz. To our best knowledge, TALCS corpus is the largest well labeled Mandarin-English code-switching open source automatic speech recognition (ASR) dataset in the world. In this paper, we will introduce the recording procedure in detail, including audio captu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13135","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/2206.13135/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":"2026-07-05T04:35:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zN88o0sz5SLUaFRzeXDI4XAzvMCoIP/89b1/MmqttKS45zanfzi6FKs1G2vpaS2xDTVNfq4EriGjT68RtnCyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T06:56:26.214021Z"},"content_sha256":"69445a78b17ffa221fae0178a7457c645cdda7e4697d0074da5be8851675cc7d","schema_version":"1.0","event_id":"sha256:69445a78b17ffa221fae0178a7457c645cdda7e4697d0074da5be8851675cc7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CY7SB2QSKHFLBKFV6ADRSY7RFD/bundle.json","state_url":"https://pith.science/pith/CY7SB2QSKHFLBKFV6ADRSY7RFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CY7SB2QSKHFLBKFV6ADRSY7RFD/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":"2026-08-01T06:56:26Z","links":{"resolver":"https://pith.science/pith/CY7SB2QSKHFLBKFV6ADRSY7RFD","bundle":"https://pith.science/pith/CY7SB2QSKHFLBKFV6ADRSY7RFD/bundle.json","state":"https://pith.science/pith/CY7SB2QSKHFLBKFV6ADRSY7RFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CY7SB2QSKHFLBKFV6ADRSY7RFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CY7SB2QSKHFLBKFV6ADRSY7RFD","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":"b08e77a9f4401f23285a3cf7c1c82611b28fa2ddc0bf03ec56494691fbb9aef9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-27T09:30:25Z","title_canon_sha256":"054d374a6f34aeab889768bb8a4fb48c543c7b3ad476de5451d176a809ceb3cb"},"schema_version":"1.0","source":{"id":"2206.13135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13135","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13135v1","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13135","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"CY7SB2QSKHFL","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"pith_short_16","alias_value":"CY7SB2QSKHFLBKFV","created_at":"2026-07-05T04:35:02Z"},{"alias_kind":"pith_short_8","alias_value":"CY7SB2QS","created_at":"2026-07-05T04:35:02Z"}],"graph_snapshots":[{"event_id":"sha256:69445a78b17ffa221fae0178a7457c645cdda7e4697d0074da5be8851675cc7d","target":"graph","created_at":"2026-07-05T04:35:02Z","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/2206.13135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a new corpus of Mandarin-English code-switching speech recognition--TALCS corpus, suitable for training and evaluating code-switching speech recognition systems. TALCS corpus is derived from real online one-to-one English teaching scenes in TAL education group, which contains roughly 587 hours of speech sampled at 16 kHz. To our best knowledge, TALCS corpus is the largest well labeled Mandarin-English code-switching open source automatic speech recognition (ASR) dataset in the world. In this paper, we will introduce the recording procedure in detail, including audio captu","authors_text":"Changbin Chen, Chengfei Li, Guangjing Wang, Jinfeng Bai, Shuhao Deng, Yaguang Gong, Yaoping Wang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-27T09:30:25Z","title":"TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13135","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":"sha256:9214c0564b3f1e612559f773099e0679dbc9871f23ad84ffef949d5754591493","target":"record","created_at":"2026-07-05T04:35:02Z","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":"b08e77a9f4401f23285a3cf7c1c82611b28fa2ddc0bf03ec56494691fbb9aef9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-27T09:30:25Z","title_canon_sha256":"054d374a6f34aeab889768bb8a4fb48c543c7b3ad476de5451d176a809ceb3cb"},"schema_version":"1.0","source":{"id":"2206.13135","kind":"arxiv","version":1}},"canonical_sha256":"163f20ea1251cab0a8b5f0071963f128fa3f2b6723f9483014de75dd4e79083c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"163f20ea1251cab0a8b5f0071963f128fa3f2b6723f9483014de75dd4e79083c","first_computed_at":"2026-07-05T04:35:02.918787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:35:02.918787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PcCI8cKhl0N+cG0Ytn/LgEmxFJdpSSMHP0FZVC9U6+Z53ap+GBXwfZVZ3fPNbXWfztnl+/2aTXOD+XwYJJzBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:35:02.919191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.13135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9214c0564b3f1e612559f773099e0679dbc9871f23ad84ffef949d5754591493","sha256:69445a78b17ffa221fae0178a7457c645cdda7e4697d0074da5be8851675cc7d"],"state_sha256":"c3dbcea5c11a6aa5da9c498df28362c2857753dfa75bf49f12d6a034f55aad42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G7m7RZnkFqW1sEfvuECmRYyK9TMEdKEJ/ph55OrqmiUTS+ACmOde8e/H3ruvUMnK7CkIuuAds/rIy7FQyiUTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T06:56:26.223670Z","bundle_sha256":"19652261de19163211089ec7f965c9332c879b2347a08f241a2d210ce42ad183"}}