{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4KX4T7HLILSEMR6OXD6QCFME74","short_pith_number":"pith:4KX4T7HL","schema_version":"1.0","canonical_sha256":"e2afc9fceb42e44647ceb8fd011584ff27d5a9e1088f4d06ce0c1b2bdfa5e558","source":{"kind":"arxiv","id":"1711.08536","version":1},"attestation_state":"computed","paper":{"title":"No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"D. Sculley, Eric Breck, James Atwood, Jimbo Wilson, Shreya Shankar, Yoni Halpern","submitted_at":"2017-11-22T23:56:37Z","abstract_excerpt":"Modern machine learning systems such as image classifiers rely heavily on large scale data sets for training. Such data sets are costly to create, thus in practice a small number of freely available, open source data sets are widely used. We suggest that examining the geo-diversity of open data sets is critical before adopting a data set for use cases in the developing world. We analyze two large, publicly available image data sets to assess geo-diversity and find that these data sets appear to exhibit an observable amerocentric and eurocentric representation bias. Further, we analyze classifi"},"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":"1711.08536","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-22T23:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"bcc93d0e4a9a52a9b427d8e3581b2829a82c57b4baacb01e6be11a53bdddaa94","abstract_canon_sha256":"bcddf9444393838f9d5545b967f1ab8fd48fc9d7e311c85d0d916ba4d1c21e3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:44.748735Z","signature_b64":"ScgFhuxlefA96WQX2EJA2i0VBD+o1VkFLWJHBcgOQ+41H1Fx0aJlBMvYIl9V3L5/c1ZBBntZ2ztvPOlGDu1vAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2afc9fceb42e44647ceb8fd011584ff27d5a9e1088f4d06ce0c1b2bdfa5e558","last_reissued_at":"2026-05-18T00:29:44.748166Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:44.748166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"D. Sculley, Eric Breck, James Atwood, Jimbo Wilson, Shreya Shankar, Yoni Halpern","submitted_at":"2017-11-22T23:56:37Z","abstract_excerpt":"Modern machine learning systems such as image classifiers rely heavily on large scale data sets for training. Such data sets are costly to create, thus in practice a small number of freely available, open source data sets are widely used. We suggest that examining the geo-diversity of open data sets is critical before adopting a data set for use cases in the developing world. We analyze two large, publicly available image data sets to assess geo-diversity and find that these data sets appear to exhibit an observable amerocentric and eurocentric representation bias. Further, we analyze classifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08536","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":""},"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":"1711.08536","created_at":"2026-05-18T00:29:44.748237+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08536v1","created_at":"2026-05-18T00:29:44.748237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08536","created_at":"2026-05-18T00:29:44.748237+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KX4T7HLILSE","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KX4T7HLILSEMR6O","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KX4T7HL","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74","json":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74.json","graph_json":"https://pith.science/api/pith-number/4KX4T7HLILSEMR6OXD6QCFME74/graph.json","events_json":"https://pith.science/api/pith-number/4KX4T7HLILSEMR6OXD6QCFME74/events.json","paper":"https://pith.science/paper/4KX4T7HL"},"agent_actions":{"view_html":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74","download_json":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74.json","view_paper":"https://pith.science/paper/4KX4T7HL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08536&json=true","fetch_graph":"https://pith.science/api/pith-number/4KX4T7HLILSEMR6OXD6QCFME74/graph.json","fetch_events":"https://pith.science/api/pith-number/4KX4T7HLILSEMR6OXD6QCFME74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74/action/storage_attestation","attest_author":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74/action/author_attestation","sign_citation":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74/action/citation_signature","submit_replication":"https://pith.science/pith/4KX4T7HLILSEMR6OXD6QCFME74/action/replication_record"}},"created_at":"2026-05-18T00:29:44.748237+00:00","updated_at":"2026-05-18T00:29:44.748237+00:00"}