{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PY2VMWUX6PKCJQONF6DZH4Q5YQ","short_pith_number":"pith:PY2VMWUX","schema_version":"1.0","canonical_sha256":"7e35565a97f3d424c1cd2f8793f21dc430c6b9ff305906752d6ec97845afe63e","source":{"kind":"arxiv","id":"2507.07741","version":1},"attestation_state":"computed","paper":{"title":"Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Atharva Kulkarni, Hanan Aldarmaki, Karima Kadaoui, Maha Tufail Agro, Zeerak Talat","submitted_at":"2025-07-10T13:21:12Z","abstract_excerpt":"Motivated by a growing research interest into automatic speech recognition (ASR), and the growing body of work for languages in which code-switching (CS) often occurs, we present a systematic literature review of code-switching in end-to-end ASR models. We collect and manually annotate papers published in peer reviewed venues. We document the languages considered, datasets, metrics, model choices, and performance, and present a discussion of challenges in end-to-end ASR for code-switching. Our analysis thus provides insights on current research efforts and available resources as well as opport"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.07741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T13:21:12Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6af5821222e8978ab8e8a69fdd05e9d803e77ee463f09bad832893b1a775f64d","abstract_canon_sha256":"8270be0290086a59f9164b080f3c1ee80b4eeeb27540e83fe0cebdb09dbd914c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:04.353359Z","signature_b64":"kRUyi8q3GzzK9qQ5WXdLS2qMTToIyABQT8Ih7Kh6eWmhcNNJegFq3cPzbr6nBlahqLUadRab3dqxnwV2SrcMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e35565a97f3d424c1cd2f8793f21dc430c6b9ff305906752d6ec97845afe63e","last_reissued_at":"2026-07-05T11:35:04.352904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:04.352904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Atharva Kulkarni, Hanan Aldarmaki, Karima Kadaoui, Maha Tufail Agro, Zeerak Talat","submitted_at":"2025-07-10T13:21:12Z","abstract_excerpt":"Motivated by a growing research interest into automatic speech recognition (ASR), and the growing body of work for languages in which code-switching (CS) often occurs, we present a systematic literature review of code-switching in end-to-end ASR models. We collect and manually annotate papers published in peer reviewed venues. We document the languages considered, datasets, metrics, model choices, and performance, and present a discussion of challenges in end-to-end ASR for code-switching. Our analysis thus provides insights on current research efforts and available resources as well as opport"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07741","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/2507.07741/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.07741","created_at":"2026-07-05T11:35:04.352961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07741v1","created_at":"2026-07-05T11:35:04.352961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07741","created_at":"2026-07-05T11:35:04.352961+00:00"},{"alias_kind":"pith_short_12","alias_value":"PY2VMWUX6PKC","created_at":"2026-07-05T11:35:04.352961+00:00"},{"alias_kind":"pith_short_16","alias_value":"PY2VMWUX6PKCJQON","created_at":"2026-07-05T11:35:04.352961+00:00"},{"alias_kind":"pith_short_8","alias_value":"PY2VMWUX","created_at":"2026-07-05T11:35:04.352961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21408","citing_title":"Vaani Benchmark V1.0: An Inclusive Multimodal Benchmark Dataset for Hindi","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17826","citing_title":"When Multiple Scripts Matter: Evaluating ASR in Clinical Settings","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29430","citing_title":"Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ","json":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ.json","graph_json":"https://pith.science/api/pith-number/PY2VMWUX6PKCJQONF6DZH4Q5YQ/graph.json","events_json":"https://pith.science/api/pith-number/PY2VMWUX6PKCJQONF6DZH4Q5YQ/events.json","paper":"https://pith.science/paper/PY2VMWUX"},"agent_actions":{"view_html":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ","download_json":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ.json","view_paper":"https://pith.science/paper/PY2VMWUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07741&json=true","fetch_graph":"https://pith.science/api/pith-number/PY2VMWUX6PKCJQONF6DZH4Q5YQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PY2VMWUX6PKCJQONF6DZH4Q5YQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ/action/storage_attestation","attest_author":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ/action/author_attestation","sign_citation":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ/action/citation_signature","submit_replication":"https://pith.science/pith/PY2VMWUX6PKCJQONF6DZH4Q5YQ/action/replication_record"}},"created_at":"2026-07-05T11:35:04.352961+00:00","updated_at":"2026-07-05T11:35:04.352961+00:00"}