{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:P4MSDKC2FWUXXY2QZLRLOCCBJ2","short_pith_number":"pith:P4MSDKC2","canonical_record":{"source":{"id":"1811.00241","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T05:29:02Z","cross_cats_sorted":[],"title_canon_sha256":"000dd962815340dd97aeae4ce7811882011d39e25fb2c4ce16c85490ad357dda","abstract_canon_sha256":"a378c1ca4f8d974ee557dd0250d2a29b80d352e6614a05f9d49b12081832d68d"},"schema_version":"1.0"},"canonical_sha256":"7f1921a85a2da97be350cae2b708414ea69ab5e28add6bff845d4da88bc05431","source":{"kind":"arxiv","id":"1811.00241","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00241","created_at":"2026-05-17T23:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00241v2","created_at":"2026-05-17T23:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00241","created_at":"2026-05-17T23:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"P4MSDKC2FWUX","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"P4MSDKC2FWUXXY2Q","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"P4MSDKC2","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:P4MSDKC2FWUXXY2QZLRLOCCBJ2","target":"record","payload":{"canonical_record":{"source":{"id":"1811.00241","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T05:29:02Z","cross_cats_sorted":[],"title_canon_sha256":"000dd962815340dd97aeae4ce7811882011d39e25fb2c4ce16c85490ad357dda","abstract_canon_sha256":"a378c1ca4f8d974ee557dd0250d2a29b80d352e6614a05f9d49b12081832d68d"},"schema_version":"1.0"},"canonical_sha256":"7f1921a85a2da97be350cae2b708414ea69ab5e28add6bff845d4da88bc05431","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:55.759273Z","signature_b64":"YQ+xLMUI5q+kaIIBGb0oEZZkdssyotVCNmgUGAovI/zu7X1r+tHbszihAyDbmEKgUzg+c3Q6EBrru1mjBtplBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f1921a85a2da97be350cae2b708414ea69ab5e28add6bff845d4da88bc05431","last_reissued_at":"2026-05-17T23:40:55.758665Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:55.758665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.00241","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yP3wv3Q/lV8+LN9VNlwIEKyhK+nPo9yHwtedkWdlNhMZTGoAivr9Be15HufmXt1SLnFvP/AnrEhYH8EZ1qLeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:04:36.189255Z"},"content_sha256":"f78bcdabeb523682b13596f477e96e5d9051f817a475ff35da8194beb51fcd51","schema_version":"1.0","event_id":"sha256:f78bcdabeb523682b13596f477e96e5d9051f817a475ff35da8194beb51fcd51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:P4MSDKC2FWUXXY2QZLRLOCCBJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eng Siong Chng, Haihua Xu, Haizhou Li, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2018-11-01T05:29:02Z","abstract_excerpt":"Code-switching (CS) refers to a linguistic phenomenon where a speaker uses different languages in an utterance or between alternating utterances. In this work, we study end-to-end (E2E) approaches to the Mandarin-English code-switching speech recognition (CSSR) task. We first examine the effectiveness of using data augmentation and byte-pair encoding (BPE) subword units. More importantly, we propose a multitask learning recipe, where a language identification task is explicitly learned in addition to the E2E speech recognition task. Furthermore, we introduce an efficient word vocabulary expans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00241","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7AIw6UOoXnawOY17fzflB39ygY9xibKQnP5IyPL5vEKI0nMw4MXz090vxh/1NssvJ6AdzzeFLr6c6beLkaiOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T07:04:36.189620Z"},"content_sha256":"664f89c3f129a5d79c1b57a7a294fa0348dbacfbc2cd881e5f7251d44f1ce677","schema_version":"1.0","event_id":"sha256:664f89c3f129a5d79c1b57a7a294fa0348dbacfbc2cd881e5f7251d44f1ce677"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/bundle.json","state_url":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/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":"2026-06-03T07:04:36Z","links":{"resolver":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2","bundle":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/bundle.json","state":"https://pith.science/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4MSDKC2FWUXXY2QZLRLOCCBJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:P4MSDKC2FWUXXY2QZLRLOCCBJ2","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":"a378c1ca4f8d974ee557dd0250d2a29b80d352e6614a05f9d49b12081832d68d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T05:29:02Z","title_canon_sha256":"000dd962815340dd97aeae4ce7811882011d39e25fb2c4ce16c85490ad357dda"},"schema_version":"1.0","source":{"id":"1811.00241","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.00241","created_at":"2026-05-17T23:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"1811.00241v2","created_at":"2026-05-17T23:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00241","created_at":"2026-05-17T23:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"P4MSDKC2FWUX","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"P4MSDKC2FWUXXY2Q","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"P4MSDKC2","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:664f89c3f129a5d79c1b57a7a294fa0348dbacfbc2cd881e5f7251d44f1ce677","target":"graph","created_at":"2026-05-17T23:40:55Z","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"},"paper":{"abstract_excerpt":"Code-switching (CS) refers to a linguistic phenomenon where a speaker uses different languages in an utterance or between alternating utterances. In this work, we study end-to-end (E2E) approaches to the Mandarin-English code-switching speech recognition (CSSR) task. We first examine the effectiveness of using data augmentation and byte-pair encoding (BPE) subword units. More importantly, we propose a multitask learning recipe, where a language identification task is explicitly learned in addition to the E2E speech recognition task. Furthermore, we introduce an efficient word vocabulary expans","authors_text":"Eng Siong Chng, Haihua Xu, Haizhou Li, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T05:29:02Z","title":"On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00241","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:f78bcdabeb523682b13596f477e96e5d9051f817a475ff35da8194beb51fcd51","target":"record","created_at":"2026-05-17T23:40:55Z","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":"a378c1ca4f8d974ee557dd0250d2a29b80d352e6614a05f9d49b12081832d68d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T05:29:02Z","title_canon_sha256":"000dd962815340dd97aeae4ce7811882011d39e25fb2c4ce16c85490ad357dda"},"schema_version":"1.0","source":{"id":"1811.00241","kind":"arxiv","version":2}},"canonical_sha256":"7f1921a85a2da97be350cae2b708414ea69ab5e28add6bff845d4da88bc05431","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f1921a85a2da97be350cae2b708414ea69ab5e28add6bff845d4da88bc05431","first_computed_at":"2026-05-17T23:40:55.758665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:55.758665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YQ+xLMUI5q+kaIIBGb0oEZZkdssyotVCNmgUGAovI/zu7X1r+tHbszihAyDbmEKgUzg+c3Q6EBrru1mjBtplBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:55.759273Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.00241","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f78bcdabeb523682b13596f477e96e5d9051f817a475ff35da8194beb51fcd51","sha256:664f89c3f129a5d79c1b57a7a294fa0348dbacfbc2cd881e5f7251d44f1ce677"],"state_sha256":"0353002d5175f08222d9c74c85a91d58b812d085e07d3fa7102338b12f708377"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mQMBWa7m+mJiHj2j76S0K9kvHVycWH4jwioehWUixHToFXrZy6XKCg3mNLg2hZIS6+v3thSlE2Qy0pRrJcRFCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T07:04:36.191553Z","bundle_sha256":"1264f56389b109db2e4b09051091223f22fd1c4197b1f056b0b296b050438576"}}