{"_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_9dd59edbeba7b68528214430b90d1490fe42b6d8a4c49dac07c9c9b24b1b7c30","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_9dd59edbeba7b68528214430b90d1490fe42b6d8a4c49dac07c9c9b24b1b7c30","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"7bcbf53328a3ad6070c31398417eb7339360f9acd82e13751ed60585558cc65e","published":"Tue, 19 May 2026 00:00:00 -0400","receipt_hash":"7bcbf53328a3ad6070c31398417eb7339360f9acd82e13751ed60585558cc65e","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":"7bcbf53328a3ad6070c31398417eb7339360f9acd82e13751ed60585558cc65e","observed_at":"2026-05-19T04:43:36.782648Z","parent_run_hash":"fefa4c726316a95c5dda9fc1ca07a38a811cf7ffa9825b2f09b365abacd9b32d","published":"Tue, 19 May 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:2605.17442v1 Announce Type: cross \nAbstract: Multilingual NLP often relies on dataset counts from centralized catalogues to characterize which languages are resource-rich or resource-poor. However, these catalogues record only one layer of dataset visibility: what has been registered or institutionally distributed. They do not necessarily reflect which datasets are created, cited, or reused in the research literature. To examine this gap, we combine a catalogue-based baseline with literature-backed evidence of dataset circulation. We introduce the Resource Density Index (RDI), defined as the number of catalogued datasets per one million speakers, and compute it for the 200 most widely spoken languages in Ethnologue. Among them, 118 languages (59%) have an average RDI of zero across the LRE Map and the Linguistic Data Consortium (LDC), and another 23 fall below 0.1, corresponding to at most one catalogued dataset per ten million speakers. We then apply an LLM-assisted citation-min","title":"Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP","url":"https://arxiv.org/abs/2605.17442","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.17442v1 Announce Type: cross \nAbstract: Multilingual NLP often relies on dataset counts from centralized catalogues to characterize which languages are resource-rich or resource-poor. However, these catalogues record only one layer of dataset visibility: what has been registered or institutionally distributed. They do not necessarily reflect which datasets are created, cited, or reused in the research literature. To examine this gap, we combine a catalogue-based baseline with literature-backed evidence of dataset circulation. We introduce the Resource Density Index (RDI), defined as the number of catalogued datasets per one million speakers, and compute it for the 200 most widely spoken languages in Ethnologue. Among them, 118 languages (59%) have an average RDI of zero across the LRE Map and the Linguistic Data Consortium (LDC), and another 23 fall below 0.1, corresponding to at most one catalogued dataset per ten million speakers. We then apply an LLM-assisted citation-min","title":"Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-19T04:43:36Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.17442"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:25c891ce32399f48fbd27884b56cc31abc074168ec0017f086b2bdd4bae2db1c9295fc6d98bb3a8083c3b9b29d8f5cbba07bd605994cbcda51d1bc00c00d7709","signer":"crovia.substrate","subject":{"observed_at":"2026-05-19T04:43:36Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.17442"},"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":"8ceebfc1e9d287e4dd7f214ee5b0d925555f6fa19e0b720bd2099f6bf78eafa7","leaf_index":142742,"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":"f3cf68bd4094c214a3b16bc45a59bef1815b970d98ca01a530326d878ab29fef","side":"right"},{"sibling":"845dac54895eb07f10dcc17ca98981274e412b307660f9ec8ef00eabfcbffb41","side":"left"},{"sibling":"fd1a750d32e4556763ca40569015a4f3e004cc510fe4770332d048ffaba1d864","side":"left"},{"sibling":"c6abeca748764f3c99e248a399b3ff63fd10001499763e5e336cf517d2a67783","side":"right"},{"sibling":"cd259c87898b2b4952319a5ad7f249d2ad30aff0accecdb3244bdf47b638e8c9","side":"left"},{"sibling":"5b96c198dbef2b0959c887616bb5b175adf0309d23c263eef954f42dd105718e","side":"right"},{"sibling":"fc791956c7f3340d3c458603b3d8eb2cf5b9c49d863090e0c16aa81ddd04a07e","side":"right"},{"sibling":"bda8ed627eb0c8b21066bfa3a60b10b3fd1daf60f49295408a27bab24b140eb3","side":"left"},{"sibling":"f1c796d3bd453570426dcee9ab20072f19762202f84b7993afba2c7c0ee9ec3b","side":"left"},{"sibling":"2e0ce989d789c88e796991ef014ce7e4e1f96c0d4ede9da8d31afcf5ba6a8f46","side":"right"},{"sibling":"202f1bead178ef3785968d50d3d188264a95192a077654c331612e04a34cbfbe","side":"left"},{"sibling":"72249c8c8b068386e35d16f4bd0bbeb9ba820ca217ef0f0d28396c9fe493f5f0","side":"left"},{"sibling":"ea64599340f7ffdf17ad0cbc1d9401ef8870a347e3847bdc106d06b1673df09c","side":"right"},{"sibling":"8f4c0fbe56b6c010fbb8c782ebcd478079bb3f991d8704e2534209a075d9163c","side":"left"},{"sibling":"4db1f363729507e27a60851cf6ed334d7b9acdef194ed7d419aba4d2bd367a4a","side":"right"},{"sibling":"a86ee18c45e7fcc408b6007eaece05aa75b2d9ae30252e9e878462b4dffbef7b","side":"right"},{"sibling":"1d18e7663d43ccff0122ecc7ee12645bb16afb607b218e81b1ea2408f863cb78","side":"right"},{"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":143302,"merkle_root":"999156d40a7c61d9ddd52b7338f3cbda3e68f53bace070c7b616ea194e23b123","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260519T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-19T05:37:30Z","sig_algorithm":"ed25519","signature":"b1a252cc66ff32bed1d10dd88a6b2a200e3856d3dbcfcc4ee55e02e00f3d548e854ed9c544704b222bd5d315492c4a935ba2d90d727c585a67899b0ad602fc05","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_9dd59edbeba7b68528214430b90d1490fe42b6d8a4c49dac07c9c9b24b1b7c30"}}