{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:N6OQWXT7Q2TTXRQDPKUZ3D4ESW","short_pith_number":"pith:N6OQWXT7","canonical_record":{"source":{"id":"2407.04219","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T02:14:28Z","cross_cats_sorted":[],"title_canon_sha256":"25efe66d985bb7dc393e4e72b1fd49f9079c247f46693a040655948aa27ef238","abstract_canon_sha256":"93722a25dda0c892efd99d0f30197961b55f9c22187e6a90a95c738a24d5cec5"},"schema_version":"1.0"},"canonical_sha256":"6f9d0b5e7f86a73bc6037aa99d8f8495ae5b867b3806ebfe094ded706b77fe37","source":{"kind":"arxiv","id":"2407.04219","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04219","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04219v2","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04219","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"N6OQWXT7Q2TT","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"N6OQWXT7Q2TTXRQD","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"N6OQWXT7","created_at":"2026-07-05T09:09:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:N6OQWXT7Q2TTXRQDPKUZ3D4ESW","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04219","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T02:14:28Z","cross_cats_sorted":[],"title_canon_sha256":"25efe66d985bb7dc393e4e72b1fd49f9079c247f46693a040655948aa27ef238","abstract_canon_sha256":"93722a25dda0c892efd99d0f30197961b55f9c22187e6a90a95c738a24d5cec5"},"schema_version":"1.0"},"canonical_sha256":"6f9d0b5e7f86a73bc6037aa99d8f8495ae5b867b3806ebfe094ded706b77fe37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:24.166859Z","signature_b64":"vgQeJ5pacqzdi7OFCyDoCIbU9gjC6VSHuTTibTLJwPOoz2r2yr0+Ffc9hpX0AcZyirGzv0ODIPH7dxjO/2pWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f9d0b5e7f86a73bc6037aa99d8f8495ae5b867b3806ebfe094ded706b77fe37","last_reissued_at":"2026-07-05T09:09:24.166354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:24.166354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04219","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":"2026-07-05T09:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6azPWb/l3aK1S/AMxDdq9ImECvt7qeKSa5uRKOrarMAZr7p4eBSWKswCJzZWO89SUwTWANRKKBreOanF2d8UAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:58:46.064828Z"},"content_sha256":"2212f91a5b71e34fff5c141c9d0742009bfdac4fd22f89f26db5f0071ff18417","schema_version":"1.0","event_id":"sha256:2212f91a5b71e34fff5c141c9d0742009bfdac4fd22f89f26db5f0071ff18417"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:N6OQWXT7Q2TTXRQDPKUZ3D4ESW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Junjie Lai, Kai Yu, Wen Ding, Yu Xi","submitted_at":"2024-07-05T02:14:28Z","abstract_excerpt":"Code-switching (CS) phenomenon occurs when words or phrases from different languages are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic Speech Recognition (ASR) system remains challenging. In this paper, we propose to enhance CS-ASR systems by utilizing rich unsupervised monolingual speech data within a semi-supervised learning framework, particularly when access to CS data is limited. To achieve this, we establish a general paradigm for applying noisy student training (NST) to the CS-ASR task. Specifically, we introduce the LLM-Filter, which leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04219","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.04219/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":"2026-07-05T09:09:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7bsF2JmLyN6RVtHxd0TsAJGRz5U2AKUV0mYEtDjxB8WHUBLzWIG2eJ5+HBL2UJs4Al7O8xohAJ6uNIY0Sb6TAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:58:46.065322Z"},"content_sha256":"2aaea062cca623fe83ad369c1cdffedbd0206c9b7c2377c30f19ecff0692ac6c","schema_version":"1.0","event_id":"sha256:2aaea062cca623fe83ad369c1cdffedbd0206c9b7c2377c30f19ecff0692ac6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N6OQWXT7Q2TTXRQDPKUZ3D4ESW/bundle.json","state_url":"https://pith.science/pith/N6OQWXT7Q2TTXRQDPKUZ3D4ESW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N6OQWXT7Q2TTXRQDPKUZ3D4ESW/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":"2026-08-09T02:58:46Z","links":{"resolver":"https://pith.science/pith/N6OQWXT7Q2TTXRQDPKUZ3D4ESW","bundle":"https://pith.science/pith/N6OQWXT7Q2TTXRQDPKUZ3D4ESW/bundle.json","state":"https://pith.science/pith/N6OQWXT7Q2TTXRQDPKUZ3D4ESW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N6OQWXT7Q2TTXRQDPKUZ3D4ESW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N6OQWXT7Q2TTXRQDPKUZ3D4ESW","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":"93722a25dda0c892efd99d0f30197961b55f9c22187e6a90a95c738a24d5cec5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T02:14:28Z","title_canon_sha256":"25efe66d985bb7dc393e4e72b1fd49f9079c247f46693a040655948aa27ef238"},"schema_version":"1.0","source":{"id":"2407.04219","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04219","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04219v2","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04219","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"pith_short_12","alias_value":"N6OQWXT7Q2TT","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"pith_short_16","alias_value":"N6OQWXT7Q2TTXRQD","created_at":"2026-07-05T09:09:24Z"},{"alias_kind":"pith_short_8","alias_value":"N6OQWXT7","created_at":"2026-07-05T09:09:24Z"}],"graph_snapshots":[{"event_id":"sha256:2aaea062cca623fe83ad369c1cdffedbd0206c9b7c2377c30f19ecff0692ac6c","target":"graph","created_at":"2026-07-05T09:09:24Z","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/2407.04219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-switching (CS) phenomenon occurs when words or phrases from different languages are alternated in a single sentence. Due to data scarcity, building an effective CS Automatic Speech Recognition (ASR) system remains challenging. In this paper, we propose to enhance CS-ASR systems by utilizing rich unsupervised monolingual speech data within a semi-supervised learning framework, particularly when access to CS data is limited. To achieve this, we establish a general paradigm for applying noisy student training (NST) to the CS-ASR task. Specifically, we introduce the LLM-Filter, which leverage","authors_text":"Junjie Lai, Kai Yu, Wen Ding, Yu Xi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T02:14:28Z","title":"Semi-supervised Learning for Code-Switching ASR with Large Language Model Filter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04219","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":"sha256:2212f91a5b71e34fff5c141c9d0742009bfdac4fd22f89f26db5f0071ff18417","target":"record","created_at":"2026-07-05T09:09:24Z","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":"93722a25dda0c892efd99d0f30197961b55f9c22187e6a90a95c738a24d5cec5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-05T02:14:28Z","title_canon_sha256":"25efe66d985bb7dc393e4e72b1fd49f9079c247f46693a040655948aa27ef238"},"schema_version":"1.0","source":{"id":"2407.04219","kind":"arxiv","version":2}},"canonical_sha256":"6f9d0b5e7f86a73bc6037aa99d8f8495ae5b867b3806ebfe094ded706b77fe37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f9d0b5e7f86a73bc6037aa99d8f8495ae5b867b3806ebfe094ded706b77fe37","first_computed_at":"2026-07-05T09:09:24.166354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:24.166354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vgQeJ5pacqzdi7OFCyDoCIbU9gjC6VSHuTTibTLJwPOoz2r2yr0+Ffc9hpX0AcZyirGzv0ODIPH7dxjO/2pWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:24.166859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04219","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2212f91a5b71e34fff5c141c9d0742009bfdac4fd22f89f26db5f0071ff18417","sha256:2aaea062cca623fe83ad369c1cdffedbd0206c9b7c2377c30f19ecff0692ac6c"],"state_sha256":"31e9eb4053230234fdada7d64ac875068d981ee7d76b182af8d6279cb794ae0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CXsgTw6lYMD6KheDgCMA4uOUDRVwyO6MCOVJDlHTQOLR8VQRH3yORfEVt8sBxNyB6YDDeL9h7q4D18e+ZsxFAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:58:46.068909Z","bundle_sha256":"427458d065e95bc075acee51344080f9173510cc293da6e1d7e5b97f7e58a8df"}}