{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X2EWY6UZEF4K6POMJNEBEOYTXC","short_pith_number":"pith:X2EWY6UZ","schema_version":"1.0","canonical_sha256":"be896c7a992178af3dcc4b48123b13b88679ac03fb5a37c2346a55a5de6359bc","source":{"kind":"arxiv","id":"2605.17442","version":1},"attestation_state":"computed","paper":{"title":"Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Changxu Duan, Zhiyin Tan","submitted_at":"2026-05-17T13:28:03Z","abstract_excerpt":"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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.17442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T13:28:03Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"6c1deb7eb1e1011683283148173d768835dc2d68d9f9f28579c77e3d80b417cd","abstract_canon_sha256":"90854aee991fd089e0232ea74e3fcd9e6f992b474ab65275017085f90476bd26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:39.075999Z","signature_b64":"qnavdBxtylklkfsmewvP09aLnuXVappiW3kC9E5ExmkeRy+4O+IhUMX562mpLNoU6DrO+3PUv/eOig6W3xZrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be896c7a992178af3dcc4b48123b13b88679ac03fb5a37c2346a55a5de6359bc","last_reissued_at":"2026-05-20T00:04:39.074937Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:39.074937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Changxu Duan, Zhiyin Tan","submitted_at":"2026-05-17T13:28:03Z","abstract_excerpt":"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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17442","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/2605.17442/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.721327Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.671588Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"543d6ab79feed9a82994a2595b16431f2b11d91e0729ef8b918c0b8f0c7b2ab6"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.17442","created_at":"2026-05-20T00:04:39.075077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17442v1","created_at":"2026-05-20T00:04:39.075077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17442","created_at":"2026-05-20T00:04:39.075077+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2EWY6UZEF4K","created_at":"2026-05-20T00:04:39.075077+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2EWY6UZEF4K6POM","created_at":"2026-05-20T00:04:39.075077+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2EWY6UZ","created_at":"2026-05-20T00:04:39.075077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17442","citing_title":"Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC","json":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC.json","graph_json":"https://pith.science/api/pith-number/X2EWY6UZEF4K6POMJNEBEOYTXC/graph.json","events_json":"https://pith.science/api/pith-number/X2EWY6UZEF4K6POMJNEBEOYTXC/events.json","paper":"https://pith.science/paper/X2EWY6UZ"},"agent_actions":{"view_html":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC","download_json":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC.json","view_paper":"https://pith.science/paper/X2EWY6UZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17442&json=true","fetch_graph":"https://pith.science/api/pith-number/X2EWY6UZEF4K6POMJNEBEOYTXC/graph.json","fetch_events":"https://pith.science/api/pith-number/X2EWY6UZEF4K6POMJNEBEOYTXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/action/storage_attestation","attest_author":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/action/author_attestation","sign_citation":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/action/citation_signature","submit_replication":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/action/replication_record"}},"created_at":"2026-05-20T00:04:39.075077+00:00","updated_at":"2026-05-20T00:04:39.075077+00:00"}