{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_5a7735313683a75ea52481d977f3467a3b8ff03f7e4391c19085a5605aba1c1e","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_5a7735313683a75ea52481d977f3467a3b8ff03f7e4391c19085a5605aba1c1e","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"faeb740fa24c95009ef79f9c9e446659e077708185aed82437f74d0f5d64583a","published":"Wed, 03 Jun 2026 00:00:00 -0400","receipt_hash":"faeb740fa24c95009ef79f9c9e446659e077708185aed82437f74d0f5d64583a","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"faeb740fa24c95009ef79f9c9e446659e077708185aed82437f74d0f5d64583a","observed_at":"2026-06-03T04:43:57.136784Z","parent_run_hash":"62ae9c8eda846b00bc49666345b338d00756c5203438666c4c1fc694cc364b84","published":"Wed, 03 Jun 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2606.03504v1 Announce Type: cross \nAbstract: 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 publicly available on HuggingFace.","title":"BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language","url":"https://arxiv.org/abs/2606.03504","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.03504v1 Announce Type: cross \nAbstract: 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 publicly available on HuggingFace.","title":"BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-03T04:43:57Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.03504"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:b869bebbedc229fd375e8fb0e59e2900fd3ac75fc457d6a7468345a939c78edefb3790602de7de2e8212227744b1a2481815166c3ddc2195151fbb30f37bd30b","signer":"crovia.substrate","subject":{"observed_at":"2026-06-03T04:43:57Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.03504"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"c4ed4e40daa72ceb401c882d17908c8e3045375ce6752299cfd3989020e63f3d","leaf_index":209230,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"1acadac6b0fab24e5449d3efd24a20426df7ec2c64ac39a227ba7a64505f01c1","side":"right"},{"sibling":"1e0a1f0051c17a0440c07d54f0586fbbfa75eaa54bfd581531b983e55d673424","side":"left"},{"sibling":"d5c3522f9d70d2d2d649d634676b5d16b917026af404e94eed7720149e1ed072","side":"left"},{"sibling":"d49b050fbffa96f1bdef2a407603efd040737161f9477d13b1af4caffaa916db","side":"left"},{"sibling":"4ed1a3667df6d6a5cdc2805cfa1e7598522566d8889163c27666cf5583e9d10b","side":"right"},{"sibling":"c66d6819eaeb69bf5b82f4e9bc61265e66c2276396e54ce87cbea4b2cf78cef6","side":"right"},{"sibling":"801b1ba88a919eeea0ffe1d64b4aaf9af369587100583a6d3683ef9572bb5fe1","side":"left"},{"sibling":"2ef1f1a576d002b7a433f7807e3e3de79248e5d1145c4394fef6eb45b8063603","side":"right"},{"sibling":"2b9867040ec52d22722edc26b204e15651723dcc66d361cc1af11490a854d461","side":"left"},{"sibling":"2abcec6d14b256f82b270a3141886de6129141dec525543607b760f02588a877","side":"right"},{"sibling":"2b6b45743f97ac502854e489ac38a3366f8ae7ede58a2728b45daadbf29e9d03","side":"right"},{"sibling":"a81babbd79ea0da9e030dd7f43bffb6519d214317decd50727bea4e78189d970","side":"right"},{"sibling":"2dca509b3eb767a47cf215d4315f230ce9103a76264412008ae23a349b519ef1","side":"left"},{"sibling":"24d1bb4b13e0e46131b27b70a48e65fcf4e2e14b95e3bb83ade821e9df530f6b","side":"left"},{"sibling":"8d3baa674a45fd8bc6d3e8d25298f4bec86c72fa8259d576c330d12955c7b4f7","side":"right"},{"sibling":"e32819d1eff909db08066d1703f2db3f091cddac19378b2c0c625ab11e3fdbc0","side":"right"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":209569,"merkle_root":"c852efc8ad7dfffc196c71380f79e6398bcaf566974cbae7c9950b0f600d5bc8","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260603T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-03T05:37:57Z","sig_algorithm":"ed25519","signature":"1ca417607effc813341721cfdade0a2d2d4ba96a90d361dbc3e864b6991b90abc326ec41d9ba3e7110cc04adb29d7b8d95abea7ff2ab8c591b2f864ed7270c03","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_5a7735313683a75ea52481d977f3467a3b8ff03f7e4391c19085a5605aba1c1e"}}