{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YIBO5FN4YG27QQXOBGTNE7E6ON","short_pith_number":"pith:YIBO5FN4","schema_version":"1.0","canonical_sha256":"c202ee95bcc1b5f842ee09a6d27c9e7360454f40cafb1fe3838fa17a8b586166","source":{"kind":"arxiv","id":"2603.27043","version":2},"attestation_state":"computed","paper":{"title":"Introducing MELI: the Mandarin-English Language Interview Corpus","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"The MELI Corpus provides matched Mandarin and English speech from 51 bilingual speakers to enable acoustic comparisons linked to language attitudes.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Molly Babel, Suyuan Liu","submitted_at":"2026-03-27T23:15:30Z","abstract_excerpt":"We introduce the Mandarin-English Language Interview (MELI) Corpus, an open-source resource of 29.8 hours of speech from 51 Mandarin-English bilingual speakers. MELI combines matched sessions in Mandarin and English with two speaking styles: read sentences and spontaneous interviews about language varieties, standardness, and learning experiences. Audio was recorded at 44.1 kHz (16-bit, stereo). Interviews were fully transcribed, force-aligned at word and phone levels, and anonymized. Descriptively, the Mandarin component totals ~14.7 hours (mean duration 17.3 minutes) and the English componen"},"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":"2603.27043","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-27T23:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"8f63c6ced1a4475a87c943dc025cbecd3e109db788c1b5d9e39255aed279cf57","abstract_canon_sha256":"6a01f451ce4d2d9a8e94d136ee698a12b306a8d41761e0bbc54cb2fea91fbd3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:37.149100Z","signature_b64":"2Nb6MkK5Wsu1ULhFY4aJnDw6IGsgBX52jycE2eZMvXl+RnHoJbUqqJUUsVdD4y8J4jivLLCNRbTuoIa2w2kSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c202ee95bcc1b5f842ee09a6d27c9e7360454f40cafb1fe3838fa17a8b586166","last_reissued_at":"2026-05-20T00:00:37.148583Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:37.148583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Introducing MELI: the Mandarin-English Language Interview Corpus","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"The MELI Corpus provides matched Mandarin and English speech from 51 bilingual speakers to enable acoustic comparisons linked to language attitudes.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Molly Babel, Suyuan Liu","submitted_at":"2026-03-27T23:15:30Z","abstract_excerpt":"We introduce the Mandarin-English Language Interview (MELI) Corpus, an open-source resource of 29.8 hours of speech from 51 Mandarin-English bilingual speakers. MELI combines matched sessions in Mandarin and English with two speaking styles: read sentences and spontaneous interviews about language varieties, standardness, and learning experiences. Audio was recorded at 44.1 kHz (16-bit, stereo). Interviews were fully transcribed, force-aligned at word and phone levels, and anonymized. Descriptively, the Mandarin component totals ~14.7 hours (mean duration 17.3 minutes) and the English componen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The MELI Corpus design supports within-/cross-speaker, within/cross-language acoustic comparison and links acoustics to speakers' stated language attitudes, enabling both quantitative and qualitative analyses.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 51 speakers and their recorded sessions provide a representative sample of Mandarin-English bilingual speech and attitudes without major biases from recruitment, recording conditions, or self-reporting.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MELI is a new 29.8-hour open-source speech corpus from 51 Mandarin-English bilinguals including full transcriptions, word/phone alignments, metadata, and attitude data for quantitative and qualitative bilingual research.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The MELI Corpus provides matched Mandarin and English speech from 51 bilingual speakers to enable acoustic comparisons linked to language attitudes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8d44c39d9027eb72635634d60f7bfdde61f0082e2d907c5608c020f406d7694f"},"source":{"id":"2603.27043","kind":"arxiv","version":2},"verdict":{"id":"06b79db3-ddbc-44a6-9058-8d786962b289","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:12:39.577800Z","strongest_claim":"The MELI Corpus design supports within-/cross-speaker, within/cross-language acoustic comparison and links acoustics to speakers' stated language attitudes, enabling both quantitative and qualitative analyses.","one_line_summary":"MELI is a new 29.8-hour open-source speech corpus from 51 Mandarin-English bilinguals including full transcriptions, word/phone alignments, metadata, and attitude data for quantitative and qualitative bilingual research.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 51 speakers and their recorded sessions provide a representative sample of Mandarin-English bilingual speech and attitudes without major biases from recruitment, recording conditions, or self-reporting.","pith_extraction_headline":"The MELI Corpus provides matched Mandarin and English speech from 51 bilingual speakers to enable acoustic comparisons linked to language attitudes."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.27043/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":"2603.27043","created_at":"2026-05-20T00:00:37.148674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.27043v2","created_at":"2026-05-20T00:00:37.148674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27043","created_at":"2026-05-20T00:00:37.148674+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIBO5FN4YG27","created_at":"2026-05-20T00:00:37.148674+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIBO5FN4YG27QQXO","created_at":"2026-05-20T00:00:37.148674+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIBO5FN4","created_at":"2026-05-20T00:00:37.148674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON","json":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON.json","graph_json":"https://pith.science/api/pith-number/YIBO5FN4YG27QQXOBGTNE7E6ON/graph.json","events_json":"https://pith.science/api/pith-number/YIBO5FN4YG27QQXOBGTNE7E6ON/events.json","paper":"https://pith.science/paper/YIBO5FN4"},"agent_actions":{"view_html":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON","download_json":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON.json","view_paper":"https://pith.science/paper/YIBO5FN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.27043&json=true","fetch_graph":"https://pith.science/api/pith-number/YIBO5FN4YG27QQXOBGTNE7E6ON/graph.json","fetch_events":"https://pith.science/api/pith-number/YIBO5FN4YG27QQXOBGTNE7E6ON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON/action/storage_attestation","attest_author":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON/action/author_attestation","sign_citation":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON/action/citation_signature","submit_replication":"https://pith.science/pith/YIBO5FN4YG27QQXOBGTNE7E6ON/action/replication_record"}},"created_at":"2026-05-20T00:00:37.148674+00:00","updated_at":"2026-05-20T00:00:37.148674+00:00"}