{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AQFCRS3LN5KT5FRIWVMYKW4XHS","short_pith_number":"pith:AQFCRS3L","canonical_record":{"source":{"id":"2506.14177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T04:37:16Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"f8f48c7f5335078cd14557a13d608b98fa616755c484ae5899e43ce78630fb84","abstract_canon_sha256":"f55f5601709c66602b64304a873855a9c00a2ceba2de28f42348960a8a1cd058"},"schema_version":"1.0"},"canonical_sha256":"040a28cb6b6f553e9628b559855b973c993c925263e2944ad72661a34548b290","source":{"kind":"arxiv","id":"2506.14177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14177","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14177v1","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14177","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"AQFCRS3LN5KT","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"AQFCRS3LN5KT5FRI","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"AQFCRS3L","created_at":"2026-07-05T11:22:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AQFCRS3LN5KT5FRIWVMYKW4XHS","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T04:37:16Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"f8f48c7f5335078cd14557a13d608b98fa616755c484ae5899e43ce78630fb84","abstract_canon_sha256":"f55f5601709c66602b64304a873855a9c00a2ceba2de28f42348960a8a1cd058"},"schema_version":"1.0"},"canonical_sha256":"040a28cb6b6f553e9628b559855b973c993c925263e2944ad72661a34548b290","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:50.370985Z","signature_b64":"I+F1WUidMc6J9CMlHf/bMvdejUOVoWO9tKR61GXSU9b5isBx6dubd+nTCL4+yHVkxdMYBPi+5kY8QSfYEzSzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"040a28cb6b6f553e9628b559855b973c993c925263e2944ad72661a34548b290","last_reissued_at":"2026-07-05T11:22:50.370506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:50.370506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14177","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":"2026-07-05T11:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2yndgdtbJQ+F88mFtcf4wSxRUjhRogEg6gwndrBu01DA9bSZi3D836WI7uLqkUgsyElLkgc2aQfe4eJJgwgvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:20:35.974919Z"},"content_sha256":"fc630b3c7d39c26674dd4e5cfc4911b5b1ef037ab8cee52711f27e4b6db9eae7","schema_version":"1.0","event_id":"sha256:fc630b3c7d39c26674dd4e5cfc4911b5b1ef037ab8cee52711f27e4b6db9eae7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AQFCRS3LN5KT5FRIWVMYKW4XHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Huy-Dat Tran, Tuan Nguyen","submitted_at":"2025-06-17T04:37:16Z","abstract_excerpt":"Code-switching (CS), common in multilingual settings, presents challenges for ASR due to scarce and costly transcribed data caused by linguistic complexity. This study investigates building CS-ASR using synthetic CS data. We propose a phrase-level mixing method to generate synthetic CS data that mimics natural patterns. Utilizing monolingual augmented with synthetic phrase-mixed CS data to fine-tune large pretrained ASR models (Whisper, MMS, SeamlessM4T). This paper focuses on three under-resourced Southeast Asian language pairs: Malay-English (BM-EN), Mandarin-Malay (ZH-BM), and Tamil-English"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14177","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/2506.14177/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":"2026-07-05T11:22:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MwyV/PgpFiuTUT3RtwXJ4cOxCgSoSSDNJZzZ9O/gHLEz37PWAvfXByaYKZ29OR4v35LLUe8kGH44i1Z7PFnaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:20:35.975481Z"},"content_sha256":"e59ef6f96db9e9e780455e4c40b0c96c38fa6137a3d58633c925779555cb6952","schema_version":"1.0","event_id":"sha256:e59ef6f96db9e9e780455e4c40b0c96c38fa6137a3d58633c925779555cb6952"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQFCRS3LN5KT5FRIWVMYKW4XHS/bundle.json","state_url":"https://pith.science/pith/AQFCRS3LN5KT5FRIWVMYKW4XHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQFCRS3LN5KT5FRIWVMYKW4XHS/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":"2026-08-08T09:20:35Z","links":{"resolver":"https://pith.science/pith/AQFCRS3LN5KT5FRIWVMYKW4XHS","bundle":"https://pith.science/pith/AQFCRS3LN5KT5FRIWVMYKW4XHS/bundle.json","state":"https://pith.science/pith/AQFCRS3LN5KT5FRIWVMYKW4XHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQFCRS3LN5KT5FRIWVMYKW4XHS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AQFCRS3LN5KT5FRIWVMYKW4XHS","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":"f55f5601709c66602b64304a873855a9c00a2ceba2de28f42348960a8a1cd058","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T04:37:16Z","title_canon_sha256":"f8f48c7f5335078cd14557a13d608b98fa616755c484ae5899e43ce78630fb84"},"schema_version":"1.0","source":{"id":"2506.14177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14177","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14177v1","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14177","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"pith_short_12","alias_value":"AQFCRS3LN5KT","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"pith_short_16","alias_value":"AQFCRS3LN5KT5FRI","created_at":"2026-07-05T11:22:50Z"},{"alias_kind":"pith_short_8","alias_value":"AQFCRS3L","created_at":"2026-07-05T11:22:50Z"}],"graph_snapshots":[{"event_id":"sha256:e59ef6f96db9e9e780455e4c40b0c96c38fa6137a3d58633c925779555cb6952","target":"graph","created_at":"2026-07-05T11:22:50Z","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/2506.14177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-switching (CS), common in multilingual settings, presents challenges for ASR due to scarce and costly transcribed data caused by linguistic complexity. This study investigates building CS-ASR using synthetic CS data. We propose a phrase-level mixing method to generate synthetic CS data that mimics natural patterns. Utilizing monolingual augmented with synthetic phrase-mixed CS data to fine-tune large pretrained ASR models (Whisper, MMS, SeamlessM4T). This paper focuses on three under-resourced Southeast Asian language pairs: Malay-English (BM-EN), Mandarin-Malay (ZH-BM), and Tamil-English","authors_text":"Huy-Dat Tran, Tuan Nguyen","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T04:37:16Z","title":"Can we train ASR systems on Code-switch without real code-switch data? Case study for Singapore's languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14177","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:fc630b3c7d39c26674dd4e5cfc4911b5b1ef037ab8cee52711f27e4b6db9eae7","target":"record","created_at":"2026-07-05T11:22:50Z","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":"f55f5601709c66602b64304a873855a9c00a2ceba2de28f42348960a8a1cd058","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T04:37:16Z","title_canon_sha256":"f8f48c7f5335078cd14557a13d608b98fa616755c484ae5899e43ce78630fb84"},"schema_version":"1.0","source":{"id":"2506.14177","kind":"arxiv","version":1}},"canonical_sha256":"040a28cb6b6f553e9628b559855b973c993c925263e2944ad72661a34548b290","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"040a28cb6b6f553e9628b559855b973c993c925263e2944ad72661a34548b290","first_computed_at":"2026-07-05T11:22:50.370506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:50.370506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I+F1WUidMc6J9CMlHf/bMvdejUOVoWO9tKR61GXSU9b5isBx6dubd+nTCL4+yHVkxdMYBPi+5kY8QSfYEzSzCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:50.370985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc630b3c7d39c26674dd4e5cfc4911b5b1ef037ab8cee52711f27e4b6db9eae7","sha256:e59ef6f96db9e9e780455e4c40b0c96c38fa6137a3d58633c925779555cb6952"],"state_sha256":"1eccad72bf2524d4256bb247cdda8a5d5574cfefff8cf1f533d51a8ba1f74a15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66nJ79FB5X8U7BVsrlP5ecnca2+DQGlm4YM5FBu7MoeFbuPD8amrm5s8sNd23TsFaWgLSLebG9h+O4I7ltneCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:20:35.980380Z","bundle_sha256":"59d3562df9f10f94e9c522b8f57d8796598bb19e183766e04a7d5550e132119e"}}