{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GUZEYA6KIZTVRYDM54S6S66I5V","short_pith_number":"pith:GUZEYA6K","canonical_record":{"source":{"id":"2306.08753","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-14T21:24:11Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"7434306b0b0daa3ec54912db714e83978989afe1f574eb0d52aa93a3b971275e","abstract_canon_sha256":"9ff07b7f3aa70636e9bc1d6ba7864d86e85eea324b1cfee7819d528257e32fcc"},"schema_version":"1.0"},"canonical_sha256":"35324c03ca466758e06cef25e97bc8ed7658f67b40c08b7f76d7d19fd0ef5402","source":{"kind":"arxiv","id":"2306.08753","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08753","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08753v3","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08753","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_12","alias_value":"GUZEYA6KIZTV","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_16","alias_value":"GUZEYA6KIZTVRYDM","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_8","alias_value":"GUZEYA6K","created_at":"2026-07-05T06:51:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GUZEYA6KIZTVRYDM54S6S66I5V","target":"record","payload":{"canonical_record":{"source":{"id":"2306.08753","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-14T21:24:11Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"7434306b0b0daa3ec54912db714e83978989afe1f574eb0d52aa93a3b971275e","abstract_canon_sha256":"9ff07b7f3aa70636e9bc1d6ba7864d86e85eea324b1cfee7819d528257e32fcc"},"schema_version":"1.0"},"canonical_sha256":"35324c03ca466758e06cef25e97bc8ed7658f67b40c08b7f76d7d19fd0ef5402","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:26.509685Z","signature_b64":"SZ2xIKuQ6xMIvdc6d9gmhDYjMoWDt1d/utKDUpXRq4yn8Coa51oP54gPTRLKiwZUX8KTmvY9WQamxJewcgBYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35324c03ca466758e06cef25e97bc8ed7658f67b40c08b7f76d7d19fd0ef5402","last_reissued_at":"2026-07-05T06:51:26.508407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:26.508407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.08753","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:51:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0KdPl3GdKYMq1Zcf4xKUuc6h9ND8DqNbZl1XHtLmw09ymM70+ug8LW2hXknix2NBIPn5Db1a2vFtqZcU0IXLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:07:20.203182Z"},"content_sha256":"ef5196f88a8f98341a285c056b2f4b7155dbda6e66535c82117463b0f28ddb03","schema_version":"1.0","event_id":"sha256:ef5196f88a8f98341a285c056b2f4b7155dbda6e66535c82117463b0f28ddb03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GUZEYA6KIZTVRYDM54S6S66I5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Dima Rekesh, Kunal Dhawan","submitted_at":"2023-06-14T21:24:11Z","abstract_excerpt":"Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR datasets from purely monolingual data sources, and (2) a novel Concatenated Tokenizer that enables ASR models to generate language ID for each emitted text token while reusing existing monolingual tokenizers. The efficacy of these approaches for building CS ASR models is demonstrated for two language pairs, English-Hindi and English-Spanish, where we achieve new s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08753","kind":"arxiv","version":3},"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/2306.08753/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":"2026-07-05T06:51:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+wLuOqXTrDkQLbNkA/v0iDD9tQikGiy7FZpvcqgi03XJoGcbt2BqRIY6hf/kNslOrh/2WHwPaUZ7uoH6KTq5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:07:20.203713Z"},"content_sha256":"05e6d94a04e3ce6ce77cbcff067c425c9ddbfc58e9c7d720b328dd49f73680e7","schema_version":"1.0","event_id":"sha256:05e6d94a04e3ce6ce77cbcff067c425c9ddbfc58e9c7d720b328dd49f73680e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUZEYA6KIZTVRYDM54S6S66I5V/bundle.json","state_url":"https://pith.science/pith/GUZEYA6KIZTVRYDM54S6S66I5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUZEYA6KIZTVRYDM54S6S66I5V/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":"2026-08-05T22:07:20Z","links":{"resolver":"https://pith.science/pith/GUZEYA6KIZTVRYDM54S6S66I5V","bundle":"https://pith.science/pith/GUZEYA6KIZTVRYDM54S6S66I5V/bundle.json","state":"https://pith.science/pith/GUZEYA6KIZTVRYDM54S6S66I5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUZEYA6KIZTVRYDM54S6S66I5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GUZEYA6KIZTVRYDM54S6S66I5V","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":"9ff07b7f3aa70636e9bc1d6ba7864d86e85eea324b1cfee7819d528257e32fcc","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-14T21:24:11Z","title_canon_sha256":"7434306b0b0daa3ec54912db714e83978989afe1f574eb0d52aa93a3b971275e"},"schema_version":"1.0","source":{"id":"2306.08753","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08753","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08753v3","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08753","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_12","alias_value":"GUZEYA6KIZTV","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_16","alias_value":"GUZEYA6KIZTVRYDM","created_at":"2026-07-05T06:51:26Z"},{"alias_kind":"pith_short_8","alias_value":"GUZEYA6K","created_at":"2026-07-05T06:51:26Z"}],"graph_snapshots":[{"event_id":"sha256:05e6d94a04e3ce6ce77cbcff067c425c9ddbfc58e9c7d720b328dd49f73680e7","target":"graph","created_at":"2026-07-05T06:51:26Z","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/2306.08753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-Switching (CS) multilingual Automatic Speech Recognition (ASR) models can transcribe speech containing two or more alternating languages during a conversation. This paper proposes (1) a new method for creating code-switching ASR datasets from purely monolingual data sources, and (2) a novel Concatenated Tokenizer that enables ASR models to generate language ID for each emitted text token while reusing existing monolingual tokenizers. The efficacy of these approaches for building CS ASR models is demonstrated for two language pairs, English-Hindi and English-Spanish, where we achieve new s","authors_text":"Boris Ginsburg, Dima Rekesh, Kunal Dhawan","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-14T21:24:11Z","title":"Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08753","kind":"arxiv","version":3},"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:ef5196f88a8f98341a285c056b2f4b7155dbda6e66535c82117463b0f28ddb03","target":"record","created_at":"2026-07-05T06:51:26Z","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":"9ff07b7f3aa70636e9bc1d6ba7864d86e85eea324b1cfee7819d528257e32fcc","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-14T21:24:11Z","title_canon_sha256":"7434306b0b0daa3ec54912db714e83978989afe1f574eb0d52aa93a3b971275e"},"schema_version":"1.0","source":{"id":"2306.08753","kind":"arxiv","version":3}},"canonical_sha256":"35324c03ca466758e06cef25e97bc8ed7658f67b40c08b7f76d7d19fd0ef5402","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35324c03ca466758e06cef25e97bc8ed7658f67b40c08b7f76d7d19fd0ef5402","first_computed_at":"2026-07-05T06:51:26.508407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:26.508407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SZ2xIKuQ6xMIvdc6d9gmhDYjMoWDt1d/utKDUpXRq4yn8Coa51oP54gPTRLKiwZUX8KTmvY9WQamxJewcgBYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:26.509685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08753","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef5196f88a8f98341a285c056b2f4b7155dbda6e66535c82117463b0f28ddb03","sha256:05e6d94a04e3ce6ce77cbcff067c425c9ddbfc58e9c7d720b328dd49f73680e7"],"state_sha256":"f49e44f16df3a4496a47e354458f6d62a73915763b58ce5d6f29dea1aba3a009"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZbZWRRu4IFnYUtWrRU7KG+PP50QgPJVw6l5dHpuRA9bSU48babAQll3/JLOOgGyFGwJNHBks7FVd12lwQHnRDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:07:20.208355Z","bundle_sha256":"69efce9ba2aa13d773741c51c3b6650ccb40b21839ffc4fd89c00c5c6410efc9"}}