{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4KX4T7HLILSEMR6OXD6QCFME74","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":"bcddf9444393838f9d5545b967f1ab8fd48fc9d7e311c85d0d916ba4d1c21e3c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-22T23:56:37Z","title_canon_sha256":"bcc93d0e4a9a52a9b427d8e3581b2829a82c57b4baacb01e6be11a53bdddaa94"},"schema_version":"1.0","source":{"id":"1711.08536","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.08536","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"1711.08536v1","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08536","created_at":"2026-05-18T00:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"4KX4T7HLILSE","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4KX4T7HLILSEMR6O","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4KX4T7HL","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:38b1cef74eedc636a884ce49295d0b78cc68f73d714d04d99c71eb1caa6e4d38","target":"graph","created_at":"2026-05-18T00:29:44Z","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"},"paper":{"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","authors_text":"D. Sculley, Eric Breck, James Atwood, Jimbo Wilson, Shreya Shankar, Yoni Halpern","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-22T23:56:37Z","title":"No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08536","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:cd55cab1a94ddc946c5efe207e258e4566d44a18b3ebadbbcea01e2f23a3e739","target":"record","created_at":"2026-05-18T00:29:44Z","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":"bcddf9444393838f9d5545b967f1ab8fd48fc9d7e311c85d0d916ba4d1c21e3c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-11-22T23:56:37Z","title_canon_sha256":"bcc93d0e4a9a52a9b427d8e3581b2829a82c57b4baacb01e6be11a53bdddaa94"},"schema_version":"1.0","source":{"id":"1711.08536","kind":"arxiv","version":1}},"canonical_sha256":"e2afc9fceb42e44647ceb8fd011584ff27d5a9e1088f4d06ce0c1b2bdfa5e558","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2afc9fceb42e44647ceb8fd011584ff27d5a9e1088f4d06ce0c1b2bdfa5e558","first_computed_at":"2026-05-18T00:29:44.748166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:44.748166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ScgFhuxlefA96WQX2EJA2i0VBD+o1VkFLWJHBcgOQ+41H1Fx0aJlBMvYIl9V3L5/c1ZBBntZ2ztvPOlGDu1vAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:44.748735Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.08536","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd55cab1a94ddc946c5efe207e258e4566d44a18b3ebadbbcea01e2f23a3e739","sha256:38b1cef74eedc636a884ce49295d0b78cc68f73d714d04d99c71eb1caa6e4d38"],"state_sha256":"6675394903c4a0021280fc341ed6c6d2f381f8f780e0d9c01f7233822bbcf5fe"}