{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KERCT6SSZLSMJTMKNNZ5BNWZSH","short_pith_number":"pith:KERCT6SS","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"},"canonical_sha256":"512229fa52cae4c4cd8a6b73d0b6d991cbfc323a52161869c9f013b375a9c590","source":{"kind":"arxiv","id":"2606.19910","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KERCT6SSZLSMJTMKNNZ5BNWZSH","target":"record","payload":{"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"},"canonical_sha256":"512229fa52cae4c4cd8a6b73d0b6d991cbfc323a52161869c9f013b375a9c590","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"},"source_kind":"arxiv","source_id":"2606.19910","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"au1mg62OIpyvUBFPILu4HH9QmxjbUfKHF01C+OrlhIOCCFxrYdHZt8VtdI+Vr56m7vYDTyuhFeEJ6z6hQO3HCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:02:35.727817Z"},"content_sha256":"173e24d20f8cedc449ed3ab09278941be405ba6d39d52c37ebd2fb33d01a4183","schema_version":"1.0","event_id":"sha256:173e24d20f8cedc449ed3ab09278941be405ba6d39d52c37ebd2fb33d01a4183"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KERCT6SSZLSMJTMKNNZ5BNWZSH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-19T16:12:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Soin0NbiHMQhJ/91UR70xGDqqUtn3hYXfInOmh0Oe7HZAXersBs6Ne2EAHuU8cp6wlylJl+UrnvfsTpDZLWhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:02:35.728211Z"},"content_sha256":"1c02e84aef8146c72fcdbc0722be451927c5106ec80eb8dfb4894c75760d8ce9","schema_version":"1.0","event_id":"sha256:1c02e84aef8146c72fcdbc0722be451927c5106ec80eb8dfb4894c75760d8ce9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/bundle.json","state_url":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T06:02:35Z","links":{"resolver":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH","bundle":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/bundle.json","state":"https://pith.science/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KERCT6SSZLSMJTMKNNZ5BNWZSH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pdHKRgQZ0lrcSLMFMAClZCoXLwC6xfwQcNIAgtd/Zx5rTkIgkC7q8PaiCluL5v5OfsPMX83sN5nQC/PdcYR1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:02:35.730724Z","bundle_sha256":"5c150aea24dee02763bf80f1a581ad32814c878991d09d563c73d4d1c84e35cf"}}