{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:O6SPJ5VZE2NWOOL4DBJUUNFODL","short_pith_number":"pith:O6SPJ5VZ","canonical_record":{"source":{"id":"2606.03504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T11:23:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6291b51f123418f9f477f4452621d854b3db91f76c6e8b547d2894f4581e6bd5","abstract_canon_sha256":"efcda8d389d5bda24055cf49c0f4f2ee89dafee28690483dad40bf68943edac9"},"schema_version":"1.0"},"canonical_sha256":"77a4f4f6b9269b67397c18534a34ae1adb5f730c4c46fc5907fedc8e3208aa84","source":{"kind":"arxiv","id":"2606.03504","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03504","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03504v1","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03504","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"O6SPJ5VZE2NW","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"O6SPJ5VZE2NWOOL4","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"O6SPJ5VZ","created_at":"2026-06-03T01:05:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:O6SPJ5VZE2NWOOL4DBJUUNFODL","target":"record","payload":{"canonical_record":{"source":{"id":"2606.03504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T11:23:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6291b51f123418f9f477f4452621d854b3db91f76c6e8b547d2894f4581e6bd5","abstract_canon_sha256":"efcda8d389d5bda24055cf49c0f4f2ee89dafee28690483dad40bf68943edac9"},"schema_version":"1.0"},"canonical_sha256":"77a4f4f6b9269b67397c18534a34ae1adb5f730c4c46fc5907fedc8e3208aa84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:59.476365Z","signature_b64":"4rqM9RKAGu7GSDjGavnKNdjXVokWzVyU/zQgWgY1cs1wZqfVjHmrfoqUc5aoZ/8eXPZu1ZnZsGabEyIdrOlFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77a4f4f6b9269b67397c18534a34ae1adb5f730c4c46fc5907fedc8e3208aa84","last_reissued_at":"2026-06-03T01:05:59.475673Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:59.475673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.03504","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":"2026-06-03T01:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7o+HCuy2jPNLE4f7sr6ImnTFjAOvvEwqVBxD2ZzWRXL5OkCsKKGrIY/BHgQMIcMNdc6RHJmWJ3KKdsJ+kwmVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:09:08.719428Z"},"content_sha256":"dcc7e0bf7115886e0a211b8b38755d4fbb9615d66e7613b5e5248df99e934cc4","schema_version":"1.0","event_id":"sha256:dcc7e0bf7115886e0a211b8b38755d4fbb9615d66e7613b5e5248df99e934cc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:O6SPJ5VZE2NWOOL4DBJUUNFODL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Muhammad Ali","submitted_at":"2026-06-02T11:23:49Z","abstract_excerpt":"We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources. The corpus contains 10,060 validated utterances in native Nastaliq script, derived from Mozilla Common Voice recordings. We fine-tune OpenAI Whisper-small on this corpus and report a Word Error Rate (WER) of 30.07% on a held-out validation set of 538 utterances, down from a measured zero-shot baseline of 182.18% for Whisper-small on Balti. The dataset, fine-tuned model, and a live transcription demo are public"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03504","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/2606.03504/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":"2026-06-03T01:05:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E0YZaAHRinIvf0sTfLEf3ZzLmif5eXoY4hoN3BwowTHyN+lDOZ1CFFvmq7baUYjghM+NDu8TssTtOztO+q5vAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:09:08.719830Z"},"content_sha256":"7f31d881afc0ce0f9ee02b14b12c2086b02ce4ba73c59086461085184f89141b","schema_version":"1.0","event_id":"sha256:7f31d881afc0ce0f9ee02b14b12c2086b02ce4ba73c59086461085184f89141b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/bundle.json","state_url":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/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":"2026-06-10T21:09:08Z","links":{"resolver":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL","bundle":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/bundle.json","state":"https://pith.science/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O6SPJ5VZE2NWOOL4DBJUUNFODL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O6SPJ5VZE2NWOOL4DBJUUNFODL","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":"efcda8d389d5bda24055cf49c0f4f2ee89dafee28690483dad40bf68943edac9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T11:23:49Z","title_canon_sha256":"6291b51f123418f9f477f4452621d854b3db91f76c6e8b547d2894f4581e6bd5"},"schema_version":"1.0","source":{"id":"2606.03504","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03504","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03504v1","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03504","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_12","alias_value":"O6SPJ5VZE2NW","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_16","alias_value":"O6SPJ5VZE2NWOOL4","created_at":"2026-06-03T01:05:59Z"},{"alias_kind":"pith_short_8","alias_value":"O6SPJ5VZ","created_at":"2026-06-03T01:05:59Z"}],"graph_snapshots":[{"event_id":"sha256:7f31d881afc0ce0f9ee02b14b12c2086b02ce4ba73c59086461085184f89141b","target":"graph","created_at":"2026-06-03T01:05:59Z","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/2606.03504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources. The corpus contains 10,060 validated utterances in native Nastaliq script, derived from Mozilla Common Voice recordings. We fine-tune OpenAI Whisper-small on this corpus and report a Word Error Rate (WER) of 30.07% on a held-out validation set of 538 utterances, down from a measured zero-shot baseline of 182.18% for Whisper-small on Balti. The dataset, fine-tuned model, and a live transcription demo are public","authors_text":"Muhammad Ali","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T11:23:49Z","title":"BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03504","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:dcc7e0bf7115886e0a211b8b38755d4fbb9615d66e7613b5e5248df99e934cc4","target":"record","created_at":"2026-06-03T01:05:59Z","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":"efcda8d389d5bda24055cf49c0f4f2ee89dafee28690483dad40bf68943edac9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T11:23:49Z","title_canon_sha256":"6291b51f123418f9f477f4452621d854b3db91f76c6e8b547d2894f4581e6bd5"},"schema_version":"1.0","source":{"id":"2606.03504","kind":"arxiv","version":1}},"canonical_sha256":"77a4f4f6b9269b67397c18534a34ae1adb5f730c4c46fc5907fedc8e3208aa84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77a4f4f6b9269b67397c18534a34ae1adb5f730c4c46fc5907fedc8e3208aa84","first_computed_at":"2026-06-03T01:05:59.475673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:59.475673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4rqM9RKAGu7GSDjGavnKNdjXVokWzVyU/zQgWgY1cs1wZqfVjHmrfoqUc5aoZ/8eXPZu1ZnZsGabEyIdrOlFDw==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:59.476365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03504","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcc7e0bf7115886e0a211b8b38755d4fbb9615d66e7613b5e5248df99e934cc4","sha256:7f31d881afc0ce0f9ee02b14b12c2086b02ce4ba73c59086461085184f89141b"],"state_sha256":"b7e1448694e586e6b4927138cd0ba8e9ac3db315f08d7102e6083d5fce14ec82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FTcFSBaYyx2DJGTL4XY+eufufuNet+Euf00cdN7/jm+8e8BZriV4txfr+pa6MyGej6Jfcgras+dB9XDZ20c0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T21:09:08.722755Z","bundle_sha256":"df14f8ed9040d1ce726a9bae4eb2aac832e021b787a4b8e67de69a9fa978cb3c"}}