{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EXZD4E3ESNHOOAYYZ2GK4TNPDW","short_pith_number":"pith:EXZD4E3E","schema_version":"1.0","canonical_sha256":"25f23e1364934ee70318ce8cae4daf1da8354f80d7a5391d42ff5c2cd071baea","source":{"kind":"arxiv","id":"2409.14666","version":1},"attestation_state":"computed","paper":{"title":"Semi-supervised Learning For Robust Speech Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Geyu Lin, Huayun Zhang, Jeremy H.M. Wong, Nancy F. Chen","submitted_at":"2024-09-23T02:11:24Z","abstract_excerpt":"Speech evaluation measures a learners oral proficiency using automatic models. Corpora for training such models often pose sparsity challenges given that there often is limited scored data from teachers, in addition to the score distribution across proficiency levels being often imbalanced among student cohorts. Automatic scoring is thus not robust when faced with under-represented samples or out-of-distribution samples, which inevitably exist in real-world deployment scenarios. This paper proposes to address such challenges by exploiting semi-supervised pre-training and objective regularizati"},"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":"2409.14666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-09-23T02:11:24Z","cross_cats_sorted":[],"title_canon_sha256":"22049e632c6d04731669bfb28bcbd753cfbfccb4691507d6be46fcd4fc395e4e","abstract_canon_sha256":"0ffc93fc570882e0879fc3d14cbb829e97e20fc26204e7ec319b89a383f0cfb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:19.882689Z","signature_b64":"d8xl28jRzXtV6fD7iUdC1AJIacoSQ1fTO4UCm5DmyHqSy4wlLkSbb+Z0jgW27SZg3yICL7NCAkH5LE9RtWrnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25f23e1364934ee70318ce8cae4daf1da8354f80d7a5391d42ff5c2cd071baea","last_reissued_at":"2026-07-05T09:10:19.882256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:19.882256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Learning For Robust Speech Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Geyu Lin, Huayun Zhang, Jeremy H.M. Wong, Nancy F. Chen","submitted_at":"2024-09-23T02:11:24Z","abstract_excerpt":"Speech evaluation measures a learners oral proficiency using automatic models. Corpora for training such models often pose sparsity challenges given that there often is limited scored data from teachers, in addition to the score distribution across proficiency levels being often imbalanced among student cohorts. Automatic scoring is thus not robust when faced with under-represented samples or out-of-distribution samples, which inevitably exist in real-world deployment scenarios. This paper proposes to address such challenges by exploiting semi-supervised pre-training and objective regularizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14666","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/2409.14666/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":"2409.14666","created_at":"2026-07-05T09:10:19.882320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14666v1","created_at":"2026-07-05T09:10:19.882320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14666","created_at":"2026-07-05T09:10:19.882320+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXZD4E3ESNHO","created_at":"2026-07-05T09:10:19.882320+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXZD4E3ESNHOOAYY","created_at":"2026-07-05T09:10:19.882320+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXZD4E3E","created_at":"2026-07-05T09:10:19.882320+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/EXZD4E3ESNHOOAYYZ2GK4TNPDW","json":"https://pith.science/pith/EXZD4E3ESNHOOAYYZ2GK4TNPDW.json","graph_json":"https://pith.science/api/pith-number/EXZD4E3ESNHOOAYYZ2GK4TNPDW/graph.json","events_json":"https://pith.science/api/pith-number/EXZD4E3ESNHOOAYYZ2GK4TNPDW/events.json","paper":"https://pith.science/paper/EXZD4E3E"},"agent_actions":{"view_html":"https://pith.science/pith/EXZD4E3ESNHOOAYYZ2GK4TNPDW","download_json":"https://pith.science/pith/EXZD4E3ESNHOOAYYZ2GK4TNPDW.json","view_paper":"https://pith.science/paper/EXZD4E3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14666&json=true","fetch_graph":"https://pith.science/api/pith-number/EXZD4E3ESNHOOAYYZ2GK4TNPDW/graph.json","fetch_events":"https://pith.science/api/pith-number/EXZD4E3ESNHOOAYYZ2GK4TNPDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXZD4E3ESNHOOAYYZ2GK4TNPDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXZD4E3ESNHOOAYYZ2GK4TNPDW/action/storage_attestation","attest_author":"https://pith.science/pith/EXZD4E3ESNHOOAYYZ2GK4TNPDW/action/author_attestation","sign_citation":"https://pith.science/pith/EXZD4E3ESNHOOAYYZ2GK4TNPDW/action/citation_signature","submit_replication":"https://pith.science/pith/EXZD4E3ESNHOOAYYZ2GK4TNPDW/action/replication_record"}},"created_at":"2026-07-05T09:10:19.882320+00:00","updated_at":"2026-07-05T09:10:19.882320+00:00"}