{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ENBCFQYV2T7Z476Z3UO42FQUVU","short_pith_number":"pith:ENBCFQYV","canonical_record":{"source":{"id":"2112.03497","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T05:13:50Z","cross_cats_sorted":[],"title_canon_sha256":"21c0c840138f0c373efc0a7c98c1c0c8aef8a64ef4cd2c5eda9808a470af21ba","abstract_canon_sha256":"599e7e635166fe03b30c0da36cb3676856a2f2e2b0d75afbaf4ef79fe5aa198f"},"schema_version":"1.0"},"canonical_sha256":"234222c315d4ff9e7fd9dd1dcd1614ad102433bfef2d98612e05c522a1a834a1","source":{"kind":"arxiv","id":"2112.03497","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03497","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03497v2","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03497","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"ENBCFQYV2T7Z","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"pith_short_16","alias_value":"ENBCFQYV2T7Z476Z","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"pith_short_8","alias_value":"ENBCFQYV","created_at":"2026-07-05T04:08:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ENBCFQYV2T7Z476Z3UO42FQUVU","target":"record","payload":{"canonical_record":{"source":{"id":"2112.03497","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T05:13:50Z","cross_cats_sorted":[],"title_canon_sha256":"21c0c840138f0c373efc0a7c98c1c0c8aef8a64ef4cd2c5eda9808a470af21ba","abstract_canon_sha256":"599e7e635166fe03b30c0da36cb3676856a2f2e2b0d75afbaf4ef79fe5aa198f"},"schema_version":"1.0"},"canonical_sha256":"234222c315d4ff9e7fd9dd1dcd1614ad102433bfef2d98612e05c522a1a834a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:27.638045Z","signature_b64":"IOIovjM0ipR1zBSfvoFsfoBvOqGhtf3930JWFy8JzKBeQS/kZkkoPLYsFOgNTttpcnlEamaoGqp5Vlzhu2VyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"234222c315d4ff9e7fd9dd1dcd1614ad102433bfef2d98612e05c522a1a834a1","last_reissued_at":"2026-07-05T04:08:27.637534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:27.637534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.03497","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/q6tAcXICm3EmbRED6qJ6o347PKTAlkolPXNI/u70A018LW557QMf0lcRzKiOsGiPoxb7lP5iB/JruY/4rKlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:37:38.719744Z"},"content_sha256":"1d782f329962824095d4ff05528dd4d72285232b645cabfc0e21fe0309f21e54","schema_version":"1.0","event_id":"sha256:1d782f329962824095d4ff05528dd4d72285232b645cabfc0e21fe0309f21e54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ENBCFQYV2T7Z476Z3UO42FQUVU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dataset Geography: Mapping Language Data to Language Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Fahim Faisal, Yinkai Wang","submitted_at":"2021-12-07T05:13:50Z","abstract_excerpt":"As language technologies become more ubiquitous, there are increasing efforts towards expanding the language diversity and coverage of natural language processing (NLP) systems. Arguably, the most important factor influencing the quality of modern NLP systems is data availability. In this work, we study the geographical representativeness of NLP datasets, aiming to quantify if and by how much do NLP datasets match the expected needs of the language speakers. In doing so, we use entity recognition and linking systems, also making important observations about their cross-lingual consistency and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03497","kind":"arxiv","version":2},"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/2112.03497/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:08:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"09HIIfxFXKMVVm7/uf+7s5uvwcvQDEqgOC+KlOIDK5JN7YvPIV12muY1i7Fjo6wlXRetK9sraP+HUoJIFDFPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:37:38.720250Z"},"content_sha256":"0097f3ec82e42ba8fc7badec20a5d5594a15db690eabdc0dee54a5ddeeb43e56","schema_version":"1.0","event_id":"sha256:0097f3ec82e42ba8fc7badec20a5d5594a15db690eabdc0dee54a5ddeeb43e56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ENBCFQYV2T7Z476Z3UO42FQUVU/bundle.json","state_url":"https://pith.science/pith/ENBCFQYV2T7Z476Z3UO42FQUVU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ENBCFQYV2T7Z476Z3UO42FQUVU/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":"2026-08-05T10:37:38Z","links":{"resolver":"https://pith.science/pith/ENBCFQYV2T7Z476Z3UO42FQUVU","bundle":"https://pith.science/pith/ENBCFQYV2T7Z476Z3UO42FQUVU/bundle.json","state":"https://pith.science/pith/ENBCFQYV2T7Z476Z3UO42FQUVU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ENBCFQYV2T7Z476Z3UO42FQUVU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ENBCFQYV2T7Z476Z3UO42FQUVU","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":"599e7e635166fe03b30c0da36cb3676856a2f2e2b0d75afbaf4ef79fe5aa198f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T05:13:50Z","title_canon_sha256":"21c0c840138f0c373efc0a7c98c1c0c8aef8a64ef4cd2c5eda9808a470af21ba"},"schema_version":"1.0","source":{"id":"2112.03497","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03497","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03497v2","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03497","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"ENBCFQYV2T7Z","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"pith_short_16","alias_value":"ENBCFQYV2T7Z476Z","created_at":"2026-07-05T04:08:27Z"},{"alias_kind":"pith_short_8","alias_value":"ENBCFQYV","created_at":"2026-07-05T04:08:27Z"}],"graph_snapshots":[{"event_id":"sha256:0097f3ec82e42ba8fc7badec20a5d5594a15db690eabdc0dee54a5ddeeb43e56","target":"graph","created_at":"2026-07-05T04:08:27Z","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":[],"endpoint":"/pith/2112.03497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language technologies become more ubiquitous, there are increasing efforts towards expanding the language diversity and coverage of natural language processing (NLP) systems. Arguably, the most important factor influencing the quality of modern NLP systems is data availability. In this work, we study the geographical representativeness of NLP datasets, aiming to quantify if and by how much do NLP datasets match the expected needs of the language speakers. In doing so, we use entity recognition and linking systems, also making important observations about their cross-lingual consistency and ","authors_text":"Antonios Anastasopoulos, Fahim Faisal, Yinkai Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T05:13:50Z","title":"Dataset Geography: Mapping Language Data to Language Users"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03497","kind":"arxiv","version":2},"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":"sha256:1d782f329962824095d4ff05528dd4d72285232b645cabfc0e21fe0309f21e54","target":"record","created_at":"2026-07-05T04:08:27Z","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":"599e7e635166fe03b30c0da36cb3676856a2f2e2b0d75afbaf4ef79fe5aa198f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T05:13:50Z","title_canon_sha256":"21c0c840138f0c373efc0a7c98c1c0c8aef8a64ef4cd2c5eda9808a470af21ba"},"schema_version":"1.0","source":{"id":"2112.03497","kind":"arxiv","version":2}},"canonical_sha256":"234222c315d4ff9e7fd9dd1dcd1614ad102433bfef2d98612e05c522a1a834a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"234222c315d4ff9e7fd9dd1dcd1614ad102433bfef2d98612e05c522a1a834a1","first_computed_at":"2026-07-05T04:08:27.637534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:27.637534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IOIovjM0ipR1zBSfvoFsfoBvOqGhtf3930JWFy8JzKBeQS/kZkkoPLYsFOgNTttpcnlEamaoGqp5Vlzhu2VyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:27.638045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03497","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d782f329962824095d4ff05528dd4d72285232b645cabfc0e21fe0309f21e54","sha256:0097f3ec82e42ba8fc7badec20a5d5594a15db690eabdc0dee54a5ddeeb43e56"],"state_sha256":"a06500b12ba3561c48220a83974b9df0db44d156395afa6a3534b0d01ea1c5e8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fG5fd8TxUt+he1ee5dgEA0DWgU/TaiGCtKT53BeEvRuNFRrtbS/uopMCQwALtOtCo8Ik+2wnBeXBlUixcWl5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:37:38.725199Z","bundle_sha256":"a79bda45d92feac3fc9a56615fdbf810c96e7bb40185fd10c48a23bac7406bef"}}