{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ALOA4K4EGAMM7UGZPXNNQBKQEY","short_pith_number":"pith:ALOA4K4E","schema_version":"1.0","canonical_sha256":"02dc0e2b843018cfd0d97ddad80550263bba491681f04fc4070f361861ec1da5","source":{"kind":"arxiv","id":"2301.02560","version":4},"attestation_state":"computed","paper":{"title":"GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaron B. Adcock, Deepti Ghadiyaram, Dora Zhao, Laurens van der Maaten, Olga Russakovsky, Sing Yu Lin, Vikram V. Ramaswamy","submitted_at":"2023-01-05T18:21:50Z","abstract_excerpt":"Current dataset collection methods typically scrape large amounts of data from the web. While this technique is extremely scalable, data collected in this way tends to reinforce stereotypical biases, can contain personally identifiable information, and typically originates from Europe and North America. In this work, we rethink the dataset collection paradigm and introduce GeoDE, a geographically diverse dataset with 61,940 images from 40 classes and 6 world regions, with no personally identifiable information, collected by soliciting images from people around the world. We analyse GeoDE to un"},"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":"2301.02560","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-05T18:21:50Z","cross_cats_sorted":[],"title_canon_sha256":"ac579ce825e63ccc03dedcf860a773bca3b007e0857650a2da5edbeddc7d653d","abstract_canon_sha256":"d964042048c1aa9772f5b9e7e37d3eb38a6ff541ff90ca3b4c3e72c1252328ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:41.224862Z","signature_b64":"j8YSJ3LBxEoXKgFMponD5mmQZGMyihz0V3e9as64VRPEls3uT6TZD61b+Z83e8rYiD4yHI9KvyjTy8ns0+9lAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02dc0e2b843018cfd0d97ddad80550263bba491681f04fc4070f361861ec1da5","last_reissued_at":"2026-07-05T12:09:41.224402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:41.224402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaron B. Adcock, Deepti Ghadiyaram, Dora Zhao, Laurens van der Maaten, Olga Russakovsky, Sing Yu Lin, Vikram V. Ramaswamy","submitted_at":"2023-01-05T18:21:50Z","abstract_excerpt":"Current dataset collection methods typically scrape large amounts of data from the web. While this technique is extremely scalable, data collected in this way tends to reinforce stereotypical biases, can contain personally identifiable information, and typically originates from Europe and North America. In this work, we rethink the dataset collection paradigm and introduce GeoDE, a geographically diverse dataset with 61,940 images from 40 classes and 6 world regions, with no personally identifiable information, collected by soliciting images from people around the world. We analyse GeoDE to un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.02560","kind":"arxiv","version":4},"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/2301.02560/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.02560","created_at":"2026-07-05T12:09:41.224464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.02560v4","created_at":"2026-07-05T12:09:41.224464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02560","created_at":"2026-07-05T12:09:41.224464+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALOA4K4EGAMM","created_at":"2026-07-05T12:09:41.224464+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALOA4K4EGAMM7UGZ","created_at":"2026-07-05T12:09:41.224464+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALOA4K4E","created_at":"2026-07-05T12:09:41.224464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05961","citing_title":"The Human Labour of Data Work: Capturing Cultural Diversity through World Wide Dishes","ref_index":95,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY","json":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY.json","graph_json":"https://pith.science/api/pith-number/ALOA4K4EGAMM7UGZPXNNQBKQEY/graph.json","events_json":"https://pith.science/api/pith-number/ALOA4K4EGAMM7UGZPXNNQBKQEY/events.json","paper":"https://pith.science/paper/ALOA4K4E"},"agent_actions":{"view_html":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY","download_json":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY.json","view_paper":"https://pith.science/paper/ALOA4K4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.02560&json=true","fetch_graph":"https://pith.science/api/pith-number/ALOA4K4EGAMM7UGZPXNNQBKQEY/graph.json","fetch_events":"https://pith.science/api/pith-number/ALOA4K4EGAMM7UGZPXNNQBKQEY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY/action/storage_attestation","attest_author":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY/action/author_attestation","sign_citation":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY/action/citation_signature","submit_replication":"https://pith.science/pith/ALOA4K4EGAMM7UGZPXNNQBKQEY/action/replication_record"}},"created_at":"2026-07-05T12:09:41.224464+00:00","updated_at":"2026-07-05T12:09:41.224464+00:00"}