{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KERCT6SSZLSMJTMKNNZ5BNWZSH","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":"38dd9b654df254703be985df2bca67121ca8366d096aed8fdc776c194941ba68","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T08:04:16Z","title_canon_sha256":"05d7f4419fa741e758a542dfcb06ab7e46f1093a4efa168961d7020da6832b4d"},"schema_version":"1.0","source":{"id":"2606.19910","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19910","created_at":"2026-06-19T16:12:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19910v1","created_at":"2026-06-19T16:12:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19910","created_at":"2026-06-19T16:12:38Z"},{"alias_kind":"pith_short_12","alias_value":"KERCT6SSZLSM","created_at":"2026-06-19T16:12:38Z"},{"alias_kind":"pith_short_16","alias_value":"KERCT6SSZLSMJTMK","created_at":"2026-06-19T16:12:38Z"},{"alias_kind":"pith_short_8","alias_value":"KERCT6SS","created_at":"2026-06-19T16:12:38Z"}],"graph_snapshots":[{"event_id":"sha256:1c02e84aef8146c72fcdbc0722be451927c5106ec80eb8dfb4894c75760d8ce9","target":"graph","created_at":"2026-06-19T16:12:38Z","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/2606.19910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Shammur Absar Chowdhury, Syeda Faiza Ahmed Sara","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T08:04:16Z","title":"Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19910","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":"sha256:173e24d20f8cedc449ed3ab09278941be405ba6d39d52c37ebd2fb33d01a4183","target":"record","created_at":"2026-06-19T16:12:38Z","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":"38dd9b654df254703be985df2bca67121ca8366d096aed8fdc776c194941ba68","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-18T08:04:16Z","title_canon_sha256":"05d7f4419fa741e758a542dfcb06ab7e46f1093a4efa168961d7020da6832b4d"},"schema_version":"1.0","source":{"id":"2606.19910","kind":"arxiv","version":1}},"canonical_sha256":"512229fa52cae4c4cd8a6b73d0b6d991cbfc323a52161869c9f013b375a9c590","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"512229fa52cae4c4cd8a6b73d0b6d991cbfc323a52161869c9f013b375a9c590","first_computed_at":"2026-06-19T16:12:38.442254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:38.442254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ziKy9ptAFzmidpO038sXswLH3t/v3rolM5o5ku5GGHcSjrWNNG6Fe7cWzj9occd9qXX4zhukGtM85GaMy2KrDg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:38.442709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19910","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:173e24d20f8cedc449ed3ab09278941be405ba6d39d52c37ebd2fb33d01a4183","sha256:1c02e84aef8146c72fcdbc0722be451927c5106ec80eb8dfb4894c75760d8ce9"],"state_sha256":"071d4136d104154576071ab0b19be6508e27e3befc7e6c0b55b4fef59011a3d5"}