{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:67K5ARIEPCFN2Z6B7PL5ISLD4R","short_pith_number":"pith:67K5ARIE","canonical_record":{"source":{"id":"2607.21332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T14:00:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7ef8eb3ae5a90341fe5d5d1ca440e7aa01f16dc791197a82e880ecc78cab65e8","abstract_canon_sha256":"3fc5278b40cf99bbf08d9480ee3af36b612e0f51a675f19e4d39c8b3ca58c487"},"schema_version":"1.0"},"canonical_sha256":"f7d5d04504788add67c1fbd7d44963e469aa7da5758133d658707935d0336035","source":{"kind":"arxiv","id":"2607.21332","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21332","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21332v1","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21332","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"pith_short_12","alias_value":"67K5ARIEPCFN","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"pith_short_16","alias_value":"67K5ARIEPCFN2Z6B","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"pith_short_8","alias_value":"67K5ARIE","created_at":"2026-07-24T01:24:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:67K5ARIEPCFN2Z6B7PL5ISLD4R","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T14:00:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7ef8eb3ae5a90341fe5d5d1ca440e7aa01f16dc791197a82e880ecc78cab65e8","abstract_canon_sha256":"3fc5278b40cf99bbf08d9480ee3af36b612e0f51a675f19e4d39c8b3ca58c487"},"schema_version":"1.0"},"canonical_sha256":"f7d5d04504788add67c1fbd7d44963e469aa7da5758133d658707935d0336035","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:26.277287Z","signature_b64":"To0Cg/jxhWgVofsGkVqILkaEJSsmEl0OIlEDFeMbMv9BdaW7kkQ8V73tn3/pxe/F8ia/ZwuJcQxh/4hdkLsFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7d5d04504788add67c1fbd7d44963e469aa7da5758133d658707935d0336035","last_reissued_at":"2026-07-24T01:24:26.276369Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:26.276369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21332","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":"2026-07-24T01:24:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TfSZYJc2KsxCs9GD3oe9bKq+w/m1O8A8B+jP+76oowsF/Puhd+ugSP1VKB7ndyFxhEkhnq6bxO5EFOLnqikGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:40:12.860694Z"},"content_sha256":"da79d6960bdc296c68b0d3b71d78f12ae6802c2844f2c1b56e1109830a8bfdb6","schema_version":"1.0","event_id":"sha256:da79d6960bdc296c68b0d3b71d78f12ae6802c2844f2c1b56e1109830a8bfdb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:67K5ARIEPCFN2Z6B7PL5ISLD4R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aini Li, Hai Hu, Liang Zhao, Zhiheng Qian","submitted_at":"2026-07-23T14:00:09Z","abstract_excerpt":"Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties. We address this by training text-dependent and text-independent aligners for Chengdu Mandarin using a 17-hour corpus and a custom G2P dictionary. We trained a text-dependent GMM-HMM model (Chengdu-MFA) and fine-tuned a pretrained audio encoder on frame classification with Chengdu-MFA's pseudo label for text-independent alignment (Chengdu-FC). Evaluation on an expert-annotated test set show that both methods significantly outperform Stand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21332","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/2607.21332/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":"2026-07-24T01:24:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y2/DN5WZcgKfblq7uv26SD9iDfgy3MduMJnOlwdfWTDr3uP03uALRPI/LBs5/5v+CFJ4I5A5tIwvEMzTcz/DAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:40:12.861203Z"},"content_sha256":"2a4356a9e59c78d1392c18a1e2f703aaafc84052b32841d158551429b09d9317","schema_version":"1.0","event_id":"sha256:2a4356a9e59c78d1392c18a1e2f703aaafc84052b32841d158551429b09d9317"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67K5ARIEPCFN2Z6B7PL5ISLD4R/bundle.json","state_url":"https://pith.science/pith/67K5ARIEPCFN2Z6B7PL5ISLD4R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67K5ARIEPCFN2Z6B7PL5ISLD4R/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":"2026-08-17T22:40:12Z","links":{"resolver":"https://pith.science/pith/67K5ARIEPCFN2Z6B7PL5ISLD4R","bundle":"https://pith.science/pith/67K5ARIEPCFN2Z6B7PL5ISLD4R/bundle.json","state":"https://pith.science/pith/67K5ARIEPCFN2Z6B7PL5ISLD4R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67K5ARIEPCFN2Z6B7PL5ISLD4R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:67K5ARIEPCFN2Z6B7PL5ISLD4R","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":"3fc5278b40cf99bbf08d9480ee3af36b612e0f51a675f19e4d39c8b3ca58c487","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T14:00:09Z","title_canon_sha256":"7ef8eb3ae5a90341fe5d5d1ca440e7aa01f16dc791197a82e880ecc78cab65e8"},"schema_version":"1.0","source":{"id":"2607.21332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21332","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21332v1","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21332","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"pith_short_12","alias_value":"67K5ARIEPCFN","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"pith_short_16","alias_value":"67K5ARIEPCFN2Z6B","created_at":"2026-07-24T01:24:26Z"},{"alias_kind":"pith_short_8","alias_value":"67K5ARIE","created_at":"2026-07-24T01:24:26Z"}],"graph_snapshots":[{"event_id":"sha256:2a4356a9e59c78d1392c18a1e2f703aaafc84052b32841d158551429b09d9317","target":"graph","created_at":"2026-07-24T01:24:26Z","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/2607.21332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties. We address this by training text-dependent and text-independent aligners for Chengdu Mandarin using a 17-hour corpus and a custom G2P dictionary. We trained a text-dependent GMM-HMM model (Chengdu-MFA) and fine-tuned a pretrained audio encoder on frame classification with Chengdu-MFA's pseudo label for text-independent alignment (Chengdu-FC). Evaluation on an expert-annotated test set show that both methods significantly outperform Stand","authors_text":"Aini Li, Hai Hu, Liang Zhao, Zhiheng Qian","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T14:00:09Z","title":"Phonetic forced alignment for low-resource language varieties: Model training and evaluation on Chengdu Mandarin"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21332","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:da79d6960bdc296c68b0d3b71d78f12ae6802c2844f2c1b56e1109830a8bfdb6","target":"record","created_at":"2026-07-24T01:24:26Z","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":"3fc5278b40cf99bbf08d9480ee3af36b612e0f51a675f19e4d39c8b3ca58c487","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T14:00:09Z","title_canon_sha256":"7ef8eb3ae5a90341fe5d5d1ca440e7aa01f16dc791197a82e880ecc78cab65e8"},"schema_version":"1.0","source":{"id":"2607.21332","kind":"arxiv","version":1}},"canonical_sha256":"f7d5d04504788add67c1fbd7d44963e469aa7da5758133d658707935d0336035","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7d5d04504788add67c1fbd7d44963e469aa7da5758133d658707935d0336035","first_computed_at":"2026-07-24T01:24:26.276369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:24:26.276369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"To0Cg/jxhWgVofsGkVqILkaEJSsmEl0OIlEDFeMbMv9BdaW7kkQ8V73tn3/pxe/F8ia/ZwuJcQxh/4hdkLsFDg==","signature_status":"signed_v1","signed_at":"2026-07-24T01:24:26.277287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da79d6960bdc296c68b0d3b71d78f12ae6802c2844f2c1b56e1109830a8bfdb6","sha256:2a4356a9e59c78d1392c18a1e2f703aaafc84052b32841d158551429b09d9317"],"state_sha256":"8e5fd17b936320e6ee192817102c64bf4e7788700116a109b9d944d0d76020a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JMAdVXwXrQ6r31beI/DYFgSKZxvrXhTYWDEUPa4wC1Al/uZBHr3ktE1URLFcMNFEI13A3XpATyYXo+a+/Q+EBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:40:12.866126Z","bundle_sha256":"1440d4461a6ec9b563e3563a35769cf2d2c85083259d34afd3d9c45d3003394c"}}