{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KERCT6SSZLSMJTMKNNZ5BNWZSH","short_pith_number":"pith:KERCT6SS","schema_version":"1.0","canonical_sha256":"512229fa52cae4c4cd8a6b73d0b6d991cbfc323a52161869c9f013b375a9c590","source":{"kind":"arxiv","id":"2606.19910","version":1},"attestation_state":"computed","paper":{"title":"Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Shammur Absar Chowdhury, Syeda Faiza Ahmed Sara","submitted_at":"2026-06-18T08:04:16Z","abstract_excerpt":"Training automated pronunciation assessment often relies on labeled learner errors or non-native corpora that are costly to collect. We propose a lightweight framework trained only on native speech resources, operating unsupervised or lightly calibrated with a small set of scored utterances. At inference, learner speech is discretized with an SSL encoder and a K-means codebook. A token language model trained on native sequences computes surprisal where higher surprisal indicates phonotactic deviation. We add a transcript-guided Text2DUnit--DTW module that predicts native token sequences from r"},"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":"2606.19910","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T08:04:16Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"05d7f4419fa741e758a542dfcb06ab7e46f1093a4efa168961d7020da6832b4d","abstract_canon_sha256":"38dd9b654df254703be985df2bca67121ca8366d096aed8fdc776c194941ba68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:38.442709Z","signature_b64":"ziKy9ptAFzmidpO038sXswLH3t/v3rolM5o5ku5GGHcSjrWNNG6Fe7cWzj9occd9qXX4zhukGtM85GaMy2KrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"512229fa52cae4c4cd8a6b73d0b6d991cbfc323a52161869c9f013b375a9c590","last_reissued_at":"2026-06-19T16:12:38.442254Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:38.442254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Shammur Absar Chowdhury, Syeda Faiza Ahmed Sara","submitted_at":"2026-06-18T08:04:16Z","abstract_excerpt":"Training automated pronunciation assessment often relies on labeled learner errors or non-native corpora that are costly to collect. We propose a lightweight framework trained only on native speech resources, operating unsupervised or lightly calibrated with a small set of scored utterances. At inference, learner speech is discretized with an SSL encoder and a K-means codebook. A token language model trained on native sequences computes surprisal where higher surprisal indicates phonotactic deviation. We add a transcript-guided Text2DUnit--DTW module that predicts native token sequences from r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19910","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/2606.19910/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":"2606.19910","created_at":"2026-06-19T16:12:38.442325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19910v1","created_at":"2026-06-19T16:12:38.442325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19910","created_at":"2026-06-19T16:12:38.442325+00:00"},{"alias_kind":"pith_short_12","alias_value":"KERCT6SSZLSM","created_at":"2026-06-19T16:12:38.442325+00:00"},{"alias_kind":"pith_short_16","alias_value":"KERCT6SSZLSMJTMK","created_at":"2026-06-19T16:12:38.442325+00:00"},{"alias_kind":"pith_short_8","alias_value":"KERCT6SS","created_at":"2026-06-19T16:12:38.442325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.19910","citing_title":"Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH","json":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH.json","graph_json":"https://pith.science/api/pith-number/KERCT6SSZLSMJTMKNNZ5BNWZSH/graph.json","events_json":"https://pith.science/api/pith-number/KERCT6SSZLSMJTMKNNZ5BNWZSH/events.json","paper":"https://pith.science/paper/KERCT6SS"},"agent_actions":{"view_html":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH","download_json":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH.json","view_paper":"https://pith.science/paper/KERCT6SS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19910&json=true","fetch_graph":"https://pith.science/api/pith-number/KERCT6SSZLSMJTMKNNZ5BNWZSH/graph.json","fetch_events":"https://pith.science/api/pith-number/KERCT6SSZLSMJTMKNNZ5BNWZSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/action/storage_attestation","attest_author":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/action/author_attestation","sign_citation":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/action/citation_signature","submit_replication":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/action/replication_record"}},"created_at":"2026-06-19T16:12:38.442325+00:00","updated_at":"2026-06-19T16:12:38.442325+00:00"}