{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TYFBZBALMABKWDKQBJN36VXX6H","short_pith_number":"pith:TYFBZBAL","canonical_record":{"source":{"id":"2305.18881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T09:26:20Z","cross_cats_sorted":[],"title_canon_sha256":"cfb50aa0c1f8c5cf22f18014c6b5c8c0ffe3d9e875780b2d795b55bb5a3ace42","abstract_canon_sha256":"3402160863ab0f9841924eef2f1854d53c1b8c71e80338f4dbe27172ef0f703b"},"schema_version":"1.0"},"canonical_sha256":"9e0a1c840b6002ab0d500a5bbf56f7f1c8d0d72a7cbef386e79eb165fd3a494f","source":{"kind":"arxiv","id":"2305.18881","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18881","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18881v1","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18881","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"TYFBZBALMABK","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"TYFBZBALMABKWDKQ","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"TYFBZBAL","created_at":"2026-07-05T06:15:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TYFBZBALMABKWDKQBJN36VXX6H","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T09:26:20Z","cross_cats_sorted":[],"title_canon_sha256":"cfb50aa0c1f8c5cf22f18014c6b5c8c0ffe3d9e875780b2d795b55bb5a3ace42","abstract_canon_sha256":"3402160863ab0f9841924eef2f1854d53c1b8c71e80338f4dbe27172ef0f703b"},"schema_version":"1.0"},"canonical_sha256":"9e0a1c840b6002ab0d500a5bbf56f7f1c8d0d72a7cbef386e79eb165fd3a494f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:34.355354Z","signature_b64":"1mwLvLjEZe3sI89nLBLKSk8uVmgM28ZOSXWXlXEd/SKc4iX/snzVbpCaJP6iLw0LVx1rI7FyhwvfHy6wrdgeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e0a1c840b6002ab0d500a5bbf56f7f1c8d0d72a7cbef386e79eb165fd3a494f","last_reissued_at":"2026-07-05T06:15:34.354915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:34.354915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18881","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":"2026-07-05T06:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FsMZ2I7UlczI5ayhDAtyvLs54Z16v62+FSYS66kN5q6qFfFyMRHCD1xHBMP1WNn71K27DxTHE2QnWAq6hwoEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:54:24.792733Z"},"content_sha256":"6843fa3ede24079710bb9dbae00838e84190ab5521a3435adcb1597176e75e82","schema_version":"1.0","event_id":"sha256:6843fa3ede24079710bb9dbae00838e84190ab5521a3435adcb1597176e75e82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TYFBZBALMABKWDKQBJN36VXX6H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andy W. H. Khong, Fei Ting Woon, Hexin Liu, Jinyi Wong, Justin Dauwels, Leibny Paola Garcia Perera, Sanjeev Khudanpur, Suzy J. Styles, Victoria Y. H. Chua, Xiangyu Zhang","submitted_at":"2023-05-30T09:26:20Z","abstract_excerpt":"To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns. We present the MERLIon CCS challenge, featuring a first-of-its-kind Zoom video call dataset of parent-child shared book reading, of over 30 hours with over 300 recordings, annotated by multilingual transcribers using a high-fidelity linguistic transcription protocol. The audio corpus features spontaneous and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18881","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/2305.18881/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":"2026-07-05T06:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zbLDQWfT55adTD65D9d1jRdAa0kee5kTuVJEzHTzjAJDcrN6RbpfWgcJWMUcrANlHBOnyfbEq54DFk24KF7WCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T02:54:24.793228Z"},"content_sha256":"1dfbe12e77d90448c3111af789740593063d5c922a94633f2f1095d2011faf27","schema_version":"1.0","event_id":"sha256:1dfbe12e77d90448c3111af789740593063d5c922a94633f2f1095d2011faf27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/bundle.json","state_url":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYFBZBALMABKWDKQBJN36VXX6H/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":"2026-08-15T02:54:24Z","links":{"resolver":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H","bundle":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/bundle.json","state":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYFBZBALMABKWDKQBJN36VXX6H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TYFBZBALMABKWDKQBJN36VXX6H","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":"3402160863ab0f9841924eef2f1854d53c1b8c71e80338f4dbe27172ef0f703b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T09:26:20Z","title_canon_sha256":"cfb50aa0c1f8c5cf22f18014c6b5c8c0ffe3d9e875780b2d795b55bb5a3ace42"},"schema_version":"1.0","source":{"id":"2305.18881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18881","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18881v1","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18881","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"TYFBZBALMABK","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"TYFBZBALMABKWDKQ","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"TYFBZBAL","created_at":"2026-07-05T06:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:1dfbe12e77d90448c3111af789740593063d5c922a94633f2f1095d2011faf27","target":"graph","created_at":"2026-07-05T06:15:34Z","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/2305.18881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns. We present the MERLIon CCS challenge, featuring a first-of-its-kind Zoom video call dataset of parent-child shared book reading, of over 30 hours with over 300 recordings, annotated by multilingual transcribers using a high-fidelity linguistic transcription protocol. The audio corpus features spontaneous and ","authors_text":"Andy W. H. Khong, Fei Ting Woon, Hexin Liu, Jinyi Wong, Justin Dauwels, Leibny Paola Garcia Perera, Sanjeev Khudanpur, Suzy J. Styles, Victoria Y. H. Chua, Xiangyu Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T09:26:20Z","title":"MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18881","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":"sha256:6843fa3ede24079710bb9dbae00838e84190ab5521a3435adcb1597176e75e82","target":"record","created_at":"2026-07-05T06:15:34Z","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":"3402160863ab0f9841924eef2f1854d53c1b8c71e80338f4dbe27172ef0f703b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T09:26:20Z","title_canon_sha256":"cfb50aa0c1f8c5cf22f18014c6b5c8c0ffe3d9e875780b2d795b55bb5a3ace42"},"schema_version":"1.0","source":{"id":"2305.18881","kind":"arxiv","version":1}},"canonical_sha256":"9e0a1c840b6002ab0d500a5bbf56f7f1c8d0d72a7cbef386e79eb165fd3a494f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e0a1c840b6002ab0d500a5bbf56f7f1c8d0d72a7cbef386e79eb165fd3a494f","first_computed_at":"2026-07-05T06:15:34.354915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:34.354915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1mwLvLjEZe3sI89nLBLKSk8uVmgM28ZOSXWXlXEd/SKc4iX/snzVbpCaJP6iLw0LVx1rI7FyhwvfHy6wrdgeBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:34.355354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6843fa3ede24079710bb9dbae00838e84190ab5521a3435adcb1597176e75e82","sha256:1dfbe12e77d90448c3111af789740593063d5c922a94633f2f1095d2011faf27"],"state_sha256":"3eae05dcfc067e482265895d347c67c667f75ec8ae8468d788820bcbb40592bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ENKeu7NdRidklYp0pzlnk6STLD3B6C8JrXkx69vVyY34/CDX505x/iHPeS8MbE/367J/JmLFVi0/STu5rCgsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T02:54:24.796716Z","bundle_sha256":"b901de9954769b751c889cf5025da4b0fbb92aaa51a1186f2cf34021ac827682"}}