{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L77LUSDFSPJ4LORDGBKMJONR6Z","short_pith_number":"pith:L77LUSDF","schema_version":"1.0","canonical_sha256":"5ffeba486593d3c5ba233054c4b9b1f64ddbacd030add3273e07a3352312764a","source":{"kind":"arxiv","id":"2509.03256","version":1},"attestation_state":"computed","paper":{"title":"Comparison of End-to-end Speech Assessment Models for the NOCASA 2025 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aleksei \\v{Z}avoronkov, Tanel Alum\\\"ae","submitted_at":"2025-09-03T12:17:59Z","abstract_excerpt":"This paper presents an analysis of three end-to-end models developed for the NOCASA 2025 Challenge, aimed at automatic word-level pronunciation assessment for children learning Norwegian as a second language. Our models include an encoder-decoder Siamese architecture (E2E-R), a prefix-tuned direct classification model leveraging pretrained wav2vec2.0 representations, and a novel model integrating alignment-free goodness-of-pronunciation (GOP) features computed via CTC. We introduce a weighted ordinal cross-entropy loss tailored for optimizing metrics such as unweighted average recall and mean "},"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":"2509.03256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-03T12:17:59Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31cb1028595d5ab908644940502604a0de8a0311c42aad62c78e7dd86f24c1dc","abstract_canon_sha256":"972111490aebe48c41f56e60b9054bdbc3cd6ebd425b32684870c480819a0317"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:07.492177Z","signature_b64":"Knc1HvaewoxhSAT4suaTKIzMmRvmr9Z3sfZW+sc2ljILV6f3MfRkd+UrwDDXVcaP1qh/LOuBSlV6tVuBPCjcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ffeba486593d3c5ba233054c4b9b1f64ddbacd030add3273e07a3352312764a","last_reissued_at":"2026-07-05T12:04:07.491670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:07.491670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparison of End-to-end Speech Assessment Models for the NOCASA 2025 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aleksei \\v{Z}avoronkov, Tanel Alum\\\"ae","submitted_at":"2025-09-03T12:17:59Z","abstract_excerpt":"This paper presents an analysis of three end-to-end models developed for the NOCASA 2025 Challenge, aimed at automatic word-level pronunciation assessment for children learning Norwegian as a second language. Our models include an encoder-decoder Siamese architecture (E2E-R), a prefix-tuned direct classification model leveraging pretrained wav2vec2.0 representations, and a novel model integrating alignment-free goodness-of-pronunciation (GOP) features computed via CTC. We introduce a weighted ordinal cross-entropy loss tailored for optimizing metrics such as unweighted average recall and mean "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03256","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/2509.03256/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":"2509.03256","created_at":"2026-07-05T12:04:07.491728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03256v1","created_at":"2026-07-05T12:04:07.491728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03256","created_at":"2026-07-05T12:04:07.491728+00:00"},{"alias_kind":"pith_short_12","alias_value":"L77LUSDFSPJ4","created_at":"2026-07-05T12:04:07.491728+00:00"},{"alias_kind":"pith_short_16","alias_value":"L77LUSDFSPJ4LORD","created_at":"2026-07-05T12:04:07.491728+00:00"},{"alias_kind":"pith_short_8","alias_value":"L77LUSDF","created_at":"2026-07-05T12:04:07.491728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03256","citing_title":"Comparison of End-to-end Speech Assessment Models for the NOCASA 2025 Challenge","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z","json":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z.json","graph_json":"https://pith.science/api/pith-number/L77LUSDFSPJ4LORDGBKMJONR6Z/graph.json","events_json":"https://pith.science/api/pith-number/L77LUSDFSPJ4LORDGBKMJONR6Z/events.json","paper":"https://pith.science/paper/L77LUSDF"},"agent_actions":{"view_html":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z","download_json":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z.json","view_paper":"https://pith.science/paper/L77LUSDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03256&json=true","fetch_graph":"https://pith.science/api/pith-number/L77LUSDFSPJ4LORDGBKMJONR6Z/graph.json","fetch_events":"https://pith.science/api/pith-number/L77LUSDFSPJ4LORDGBKMJONR6Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z/action/storage_attestation","attest_author":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z/action/author_attestation","sign_citation":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z/action/citation_signature","submit_replication":"https://pith.science/pith/L77LUSDFSPJ4LORDGBKMJONR6Z/action/replication_record"}},"created_at":"2026-07-05T12:04:07.491728+00:00","updated_at":"2026-07-05T12:04:07.491728+00:00"}