{"_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_049f1828b23eb447776696e17732fcca2e87daefa146d6389dab253f69a2c8a4","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_049f1828b23eb447776696e17732fcca2e87daefa146d6389dab253f69a2c8a4","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"6d7a8cd6bb3e8fd301432666c6fc5b3d5f42f50f7be1917134164a37f5115a5e","published":"Tue, 28 Jul 2026 00:00:00 -0400","receipt_hash":"6d7a8cd6bb3e8fd301432666c6fc5b3d5f42f50f7be1917134164a37f5115a5e","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":"6d7a8cd6bb3e8fd301432666c6fc5b3d5f42f50f7be1917134164a37f5115a5e","observed_at":"2026-07-28T04:43:08.282317Z","parent_run_hash":"23a1ef85134515049ced29518443d084afc46fd7c967741e6c6acdbdbbf29939","published":"Tue, 28 Jul 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:2606.25365v2 Announce Type: replace-cross \nAbstract: We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair. Tangkhul is a severely under-resourced Tibeto-Burman language spoken primarily in Manipur, India, with virtually no prior natural language processing infrastructure. We describe two systems: (1) a primary system based on ByT5-large fine-tuned on 38,336 Tangkhul-English parallel sentence pairs, and (2) a contrastive system based on mT5-small fine-tuned on the same corpus. Our primary ByT5-large system achieves a corpus BLEU score of 39.97, chrF++ of 58.07, BERTScore F1 of 0.8104, and COMET (wmt22-comet-da) of 0.7302 on a held-out test set of 3,856 sentences. We further discuss the orthographic challenges specific to Tangkhul's Latin-script diacritics, the domain bias of our training corpus (which comprises biblical text, stories, and conversational data), and avenues for future improvement through data diversification and doma","title":"Neural Machine Translation for Low-Resource Tangkhul--English","url":"https://arxiv.org/abs/2606.25365","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.25365v2 Announce Type: replace-cross \nAbstract: We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair. Tangkhul is a severely under-resourced Tibeto-Burman language spoken primarily in Manipur, India, with virtually no prior natural language processing infrastructure. We describe two systems: (1) a primary system based on ByT5-large fine-tuned on 38,336 Tangkhul-English parallel sentence pairs, and (2) a contrastive system based on mT5-small fine-tuned on the same corpus. Our primary ByT5-large system achieves a corpus BLEU score of 39.97, chrF++ of 58.07, BERTScore F1 of 0.8104, and COMET (wmt22-comet-da) of 0.7302 on a held-out test set of 3,856 sentences. We further discuss the orthographic challenges specific to Tangkhul's Latin-script diacritics, the domain bias of our training corpus (which comprises biblical text, stories, and conversational data), and avenues for future improvement through data diversification and doma","title":"Neural Machine Translation for Low-Resource Tangkhul--English","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-28T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.25365"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:667658aeddd8725dab37a39852b102fe61d8a6977400832b5606af26860fc026e25f9fe4f397e53f99ad04efab755bc84b0b65bd7847983ed82a3b4dbecc7007","signer":"crovia.substrate","subject":{"observed_at":"2026-07-28T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.25365"},"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":"20178e8c733c2c84fa4c045a9fb267c4a151cb367aed2d2515ebdc779a767d37","leaf_index":360858,"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":"5fa43e5cbbd631c761418629f4a4f402cc8a2ac5792bc5d343a9a85219a17a57","side":"right"},{"sibling":"635f200a3ddcdbaed340b28237f3dc96dcaa8127e9be2e47f2579c00ee205da4","side":"left"},{"sibling":"f88897317372eed80278e5e58cf2aec951e0c7ab54b18ce787670351ea67b37c","side":"right"},{"sibling":"571e6de50c1c1bbef0045730230ed2263c9eee8ad3219cb7d46d987bc259aa03","side":"left"},{"sibling":"30a5b896d05384189e133316f1157db64a6c57c9bd2bd092d2bb79078c529de5","side":"left"},{"sibling":"bdc833b2540ff1e8ae92dc6e82d8d0df1d4888e6edf0625716acaf4fff369c1e","side":"right"},{"sibling":"3624810eba28b73089ab25eb96ab3b98f4fccbf630cdc8ce257ab18ffa11f60a","side":"right"},{"sibling":"2269d88b8ead175347e1333136f38876970c71eeededc634500c20d221068882","side":"left"},{"sibling":"f05fa4d2088913dc5410109b6c9f2c28b5e413f06a98f46cd68973c567c3b416","side":"left"},{"sibling":"fe03c6d0b083c4097049d7fc6d7d08dfdb05d9c198b2786336689712d66eabf0","side":"right"},{"sibling":"590ea76fdfc1b9e8072055c378be3182f916709e8d06bd955232e650a7188b86","side":"right"},{"sibling":"d92781c59301ffd5bfb0bad75d9fdf6d73879f715518149d383f7362213e0daf","side":"right"},{"sibling":"f315303d4402b57497416d48eb4c4bb50405b40862d41c7caf318cb3d29c5237","side":"right"},{"sibling":"36973eb5f586cd67e0c0dc055dd87e734aa544c35d4400d2c9f932f8ef8fb27f","side":"right"},{"sibling":"e39f7900355489c4718b21cc2d3d06382e1d2f22b864d10be9ebc9d498b279a1","side":"right"},{"sibling":"1f9a970b25dd938c98cabc9e0a55c5a6f46292b9fa37cc89d90ef0cbb1e05a8c","side":"left"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"3b50864499c874394ea0928567747666eaf59b01380e46cd52164ec5acec0f71","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":361008,"merkle_root":"3065e8369ea437c06beba806dc4e4bb159979adeb21fe632242c1906a7204647","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260728T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-28T05:38:48Z","sig_algorithm":"ed25519","signature":"9141644407577a82611c1579110f667de2d46dc6b93c6322edf26f4c3056ea99f0e56502853908e30d87c38bcf95eb6e0ab5130525aa51505bd6f61938120609","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_049f1828b23eb447776696e17732fcca2e87daefa146d6389dab253f69a2c8a4"}}