{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:X2EWY6UZEF4K6POMJNEBEOYTXC","short_pith_number":"pith:X2EWY6UZ","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"},"canonical_sha256":"be896c7a992178af3dcc4b48123b13b88679ac03fb5a37c2346a55a5de6359bc","source":{"kind":"arxiv","id":"2605.17442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17442","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17442v1","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17442","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"X2EWY6UZEF4K","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"X2EWY6UZEF4K6POM","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"X2EWY6UZ","created_at":"2026-05-20T00:04:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:X2EWY6UZEF4K6POMJNEBEOYTXC","target":"record","payload":{"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"},"canonical_sha256":"be896c7a992178af3dcc4b48123b13b88679ac03fb5a37c2346a55a5de6359bc","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"},"source_kind":"arxiv","source_id":"2605.17442","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":"2026-05-20T00:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m7aZl4+U9pHbSCOrJXAOFmLt05DV+gO7bNFOfp2kqnb5OWKn1rYeSKK9FMrCVjn5OObsS6eRn3gOc52rcOWXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:25:07.477049Z"},"content_sha256":"ab437eef77102a470c1cad524590ef4f58cbc6d063ac2f00711200ec7a4f910d","schema_version":"1.0","event_id":"sha256:ab437eef77102a470c1cad524590ef4f58cbc6d063ac2f00711200ec7a4f910d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:X2EWY6UZEF4K6POMJNEBEOYTXC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cR+5l0ZMGwrzcTb+I0jwDrv8+cCG0aFVnlKQwSYrIMCH9tFgFk4Gy9FhDy67OCpgKETVkKvvwF7vfj7IpLEDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:25:07.478096Z"},"content_sha256":"522890c10534ad24c4faba9abb2c1f39d06dd3859572eeec2dc1390b2312d12d","schema_version":"1.0","event_id":"sha256:522890c10534ad24c4faba9abb2c1f39d06dd3859572eeec2dc1390b2312d12d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/bundle.json","state_url":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/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":"2026-05-31T17:25:07Z","links":{"resolver":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC","bundle":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/bundle.json","state":"https://pith.science/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X2EWY6UZEF4K6POMJNEBEOYTXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X2EWY6UZEF4K6POMJNEBEOYTXC","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":"90854aee991fd089e0232ea74e3fcd9e6f992b474ab65275017085f90476bd26","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T13:28:03Z","title_canon_sha256":"6c1deb7eb1e1011683283148173d768835dc2d68d9f9f28579c77e3d80b417cd"},"schema_version":"1.0","source":{"id":"2605.17442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17442","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17442v1","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17442","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"X2EWY6UZEF4K","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"X2EWY6UZEF4K6POM","created_at":"2026-05-20T00:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"X2EWY6UZ","created_at":"2026-05-20T00:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:522890c10534ad24c4faba9abb2c1f39d06dd3859572eeec2dc1390b2312d12d","target":"graph","created_at":"2026-05-20T00:04:39Z","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":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.17442/integrity.json","findings":[],"snapshot_sha256":"543d6ab79feed9a82994a2595b16431f2b11d91e0729ef8b918c0b8f0c7b2ab6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Changxu Duan, Zhiyin Tan","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T13:28:03Z","title":"Beyond Catalogue Counts: the Dataset Visibility Asymmetry in Low-Resource Multilingual NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17442","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:ab437eef77102a470c1cad524590ef4f58cbc6d063ac2f00711200ec7a4f910d","target":"record","created_at":"2026-05-20T00:04:39Z","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":"90854aee991fd089e0232ea74e3fcd9e6f992b474ab65275017085f90476bd26","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T13:28:03Z","title_canon_sha256":"6c1deb7eb1e1011683283148173d768835dc2d68d9f9f28579c77e3d80b417cd"},"schema_version":"1.0","source":{"id":"2605.17442","kind":"arxiv","version":1}},"canonical_sha256":"be896c7a992178af3dcc4b48123b13b88679ac03fb5a37c2346a55a5de6359bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be896c7a992178af3dcc4b48123b13b88679ac03fb5a37c2346a55a5de6359bc","first_computed_at":"2026-05-20T00:04:39.074937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:39.074937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qnavdBxtylklkfsmewvP09aLnuXVappiW3kC9E5ExmkeRy+4O+IhUMX562mpLNoU6DrO+3PUv/eOig6W3xZrDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:39.075999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab437eef77102a470c1cad524590ef4f58cbc6d063ac2f00711200ec7a4f910d","sha256:522890c10534ad24c4faba9abb2c1f39d06dd3859572eeec2dc1390b2312d12d"],"state_sha256":"07ef9f1fce3411a1435030ccba23299c56580b6db290137b650286e67c465643"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nzJdcRY1zul1LFw69Ip5Ay1kbnPSAXj2ZI1MGXgTB1UhUvUUssu0scPey8TFSwLP4M5ZrgAaLxLiUUzjRY1LAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T17:25:07.483575Z","bundle_sha256":"3d4810a417cbea318ee28bc33d46f0f489532b8619eda61be628843ca5355b0d"}}