{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WN24Z7I2KR7YQQSVES46UETKLP","short_pith_number":"pith:WN24Z7I2","canonical_record":{"source":{"id":"2607.05224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T15:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"42854c355e3110b3ea81fa9db2c6caafa70f5aae006b8701b89f789bcf46e5c0","abstract_canon_sha256":"49eee8bb87972176ad3f38414183b14e64cc0ece1185b2ad0f17639281f1c7a1"},"schema_version":"1.0"},"canonical_sha256":"b375ccfd1a547f88425524b9ea126a5bc09e23bec29827e5d66922359ffa7800","source":{"kind":"arxiv","id":"2607.05224","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05224","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05224v1","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05224","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"WN24Z7I2KR7Y","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"WN24Z7I2KR7YQQSV","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"WN24Z7I2","created_at":"2026-07-07T03:19:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WN24Z7I2KR7YQQSVES46UETKLP","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05224","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T15:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"42854c355e3110b3ea81fa9db2c6caafa70f5aae006b8701b89f789bcf46e5c0","abstract_canon_sha256":"49eee8bb87972176ad3f38414183b14e64cc0ece1185b2ad0f17639281f1c7a1"},"schema_version":"1.0"},"canonical_sha256":"b375ccfd1a547f88425524b9ea126a5bc09e23bec29827e5d66922359ffa7800","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:20.150489Z","signature_b64":"lUbHVrkwGY7z9t1ZFYbVgsmmTcz330q5CgAdHr5kG37gNRio18dWsR4WWGDeHf4YCezIyOZ1Q0Y0/mBbf1QrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b375ccfd1a547f88425524b9ea126a5bc09e23bec29827e5d66922359ffa7800","last_reissued_at":"2026-07-07T03:19:20.150062Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:20.150062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05224","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":"2026-07-07T03:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ys1M/i2a+ApKTnmnzzqnjhdoeLnPJ8PQGN8JeEaVSwUvTDVNP1I1kgtnwnzJL/a0uleCJ3b89jy8Y93K8lyjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:38:22.127003Z"},"content_sha256":"1a3005eadd0ef65de1bd001b79ed0ca9472b35417d5f2fb2b4f0a57bb0d55493","schema_version":"1.0","event_id":"sha256:1a3005eadd0ef65de1bd001b79ed0ca9472b35417d5f2fb2b4f0a57bb0d55493"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WN24Z7I2KR7YQQSVES46UETKLP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cakra Wardhana, Qu Yang, Tim Ng","submitted_at":"2026-07-06T15:39:30Z","abstract_excerpt":"Code-switching (CS), alternating languages within the same utterance, poses significant challenges for automatic speech recognition (ASR) due to limited CS training data. This paper applies an iterative pseudo-labeling training approach to CS-ASR for the first time, demonstrating its effectiveness in leveraging unlabeled data to improve CS-ASR performance. The approach comprises three phases: pseudo-label generation, two-stage bilingual model training, and iterative improvements. It begins by generating pseudo-labels from a large unlabeled corpus, creating a semi-supervised dataset. This datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05224","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/2607.05224/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":"2026-07-07T03:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3kBtYPvQzIXHuR2rGNmUqocQF1vLE7Lu34Waj4U/rTV5VRW7ZwgW4Nm6INwcybG2u+ICO5/4yVds4qCT8EVpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:38:22.127955Z"},"content_sha256":"7acfca1f20d11ea66640988c10a86adc3f3c5b8ac9890ef7e15e6b38e8dd2132","schema_version":"1.0","event_id":"sha256:7acfca1f20d11ea66640988c10a86adc3f3c5b8ac9890ef7e15e6b38e8dd2132"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WN24Z7I2KR7YQQSVES46UETKLP/bundle.json","state_url":"https://pith.science/pith/WN24Z7I2KR7YQQSVES46UETKLP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WN24Z7I2KR7YQQSVES46UETKLP/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":"2026-08-11T19:38:22Z","links":{"resolver":"https://pith.science/pith/WN24Z7I2KR7YQQSVES46UETKLP","bundle":"https://pith.science/pith/WN24Z7I2KR7YQQSVES46UETKLP/bundle.json","state":"https://pith.science/pith/WN24Z7I2KR7YQQSVES46UETKLP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WN24Z7I2KR7YQQSVES46UETKLP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WN24Z7I2KR7YQQSVES46UETKLP","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":"49eee8bb87972176ad3f38414183b14e64cc0ece1185b2ad0f17639281f1c7a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T15:39:30Z","title_canon_sha256":"42854c355e3110b3ea81fa9db2c6caafa70f5aae006b8701b89f789bcf46e5c0"},"schema_version":"1.0","source":{"id":"2607.05224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05224","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05224v1","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05224","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"WN24Z7I2KR7Y","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"WN24Z7I2KR7YQQSV","created_at":"2026-07-07T03:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"WN24Z7I2","created_at":"2026-07-07T03:19:20Z"}],"graph_snapshots":[{"event_id":"sha256:7acfca1f20d11ea66640988c10a86adc3f3c5b8ac9890ef7e15e6b38e8dd2132","target":"graph","created_at":"2026-07-07T03:19:20Z","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/2607.05224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-switching (CS), alternating languages within the same utterance, poses significant challenges for automatic speech recognition (ASR) due to limited CS training data. This paper applies an iterative pseudo-labeling training approach to CS-ASR for the first time, demonstrating its effectiveness in leveraging unlabeled data to improve CS-ASR performance. The approach comprises three phases: pseudo-label generation, two-stage bilingual model training, and iterative improvements. It begins by generating pseudo-labels from a large unlabeled corpus, creating a semi-supervised dataset. This datas","authors_text":"Cakra Wardhana, Qu Yang, Tim Ng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T15:39:30Z","title":"Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05224","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":"sha256:1a3005eadd0ef65de1bd001b79ed0ca9472b35417d5f2fb2b4f0a57bb0d55493","target":"record","created_at":"2026-07-07T03:19:20Z","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":"49eee8bb87972176ad3f38414183b14e64cc0ece1185b2ad0f17639281f1c7a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T15:39:30Z","title_canon_sha256":"42854c355e3110b3ea81fa9db2c6caafa70f5aae006b8701b89f789bcf46e5c0"},"schema_version":"1.0","source":{"id":"2607.05224","kind":"arxiv","version":1}},"canonical_sha256":"b375ccfd1a547f88425524b9ea126a5bc09e23bec29827e5d66922359ffa7800","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b375ccfd1a547f88425524b9ea126a5bc09e23bec29827e5d66922359ffa7800","first_computed_at":"2026-07-07T03:19:20.150062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T03:19:20.150062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lUbHVrkwGY7z9t1ZFYbVgsmmTcz330q5CgAdHr5kG37gNRio18dWsR4WWGDeHf4YCezIyOZ1Q0Y0/mBbf1QrAA==","signature_status":"signed_v1","signed_at":"2026-07-07T03:19:20.150489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a3005eadd0ef65de1bd001b79ed0ca9472b35417d5f2fb2b4f0a57bb0d55493","sha256:7acfca1f20d11ea66640988c10a86adc3f3c5b8ac9890ef7e15e6b38e8dd2132"],"state_sha256":"dd1bf5659cc5e9137b8e588cdebd5270d2e8a9ae497be9662a7694fef5eeaaa4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cO+H79RpvUVzWBcyQ2ZejP7rOGNVMZO7bYzpPL6DTRI0h9nolAA5fnhjPALFCBjeIphw2YYPgVkd1FkmgPGbBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:38:22.138395Z","bundle_sha256":"f04a80a46cb2e4db340647de0049fc530a2d0c22204697aef0ae596334a9df81"}}