{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GEWRSXZDXLK4UF5SSSH4IBTWUC","short_pith_number":"pith:GEWRSXZD","schema_version":"1.0","canonical_sha256":"312d195f23bad5ca17b2948fc40676a09849f5d71378ebde9f0aa7e709277b60","source":{"kind":"arxiv","id":"2108.00114","version":1},"attestation_state":"computed","paper":{"title":"On The State of Data In Computer Vision: Human Annotations Remain Indispensable for Developing Deep Learning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aerin Kim, Andrew Kondrich, Elliot Branson, Felix Lau, Sasha Harrison, Yushi Wang, Zeyad Emam","submitted_at":"2021-07-31T00:08:21Z","abstract_excerpt":"High-quality labeled datasets play a crucial role in fueling the development of machine learning (ML), and in particular the development of deep learning (DL). However, since the emergence of the ImageNet dataset and the AlexNet model in 2012, the size of new open-source labeled vision datasets has remained roughly constant. Consequently, only a minority of publications in the computer vision community tackle supervised learning on datasets that are orders of magnitude larger than Imagenet. In this paper, we survey computer vision research domains that study the effects of such large datasets "},"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":"2108.00114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-31T00:08:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dab3b03e24c993bf8c7bcd4eb2832b7f0968bc6182200c29de633786edb0eeee","abstract_canon_sha256":"ab1e1bf6573ee60a36ecaa847fea585d975d1ccb1b55ace5fe0938baa4ddb0f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:02:19.041094Z","signature_b64":"UpJK9jnPfNwObh7IyXxw8wU1+70qL4S8Pi9zi0LXodCYhWit2Xf26QyBx9XgqZOlwyDeyQ2dDLc8bmTa8E/aDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"312d195f23bad5ca17b2948fc40676a09849f5d71378ebde9f0aa7e709277b60","last_reissued_at":"2026-07-05T03:02:19.040742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:02:19.040742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On The State of Data In Computer Vision: Human Annotations Remain Indispensable for Developing Deep Learning Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aerin Kim, Andrew Kondrich, Elliot Branson, Felix Lau, Sasha Harrison, Yushi Wang, Zeyad Emam","submitted_at":"2021-07-31T00:08:21Z","abstract_excerpt":"High-quality labeled datasets play a crucial role in fueling the development of machine learning (ML), and in particular the development of deep learning (DL). However, since the emergence of the ImageNet dataset and the AlexNet model in 2012, the size of new open-source labeled vision datasets has remained roughly constant. Consequently, only a minority of publications in the computer vision community tackle supervised learning on datasets that are orders of magnitude larger than Imagenet. In this paper, we survey computer vision research domains that study the effects of such large datasets "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00114","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/2108.00114/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":"2108.00114","created_at":"2026-07-05T03:02:19.040789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00114v1","created_at":"2026-07-05T03:02:19.040789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00114","created_at":"2026-07-05T03:02:19.040789+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEWRSXZDXLK4","created_at":"2026-07-05T03:02:19.040789+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEWRSXZDXLK4UF5S","created_at":"2026-07-05T03:02:19.040789+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEWRSXZD","created_at":"2026-07-05T03:02:19.040789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02488","citing_title":"Building the Ipseome: Large, Free, Open, Human Identity Data","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09716","citing_title":"Medical Model Synthesis Architectures: A Case Study","ref_index":223,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC","json":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC.json","graph_json":"https://pith.science/api/pith-number/GEWRSXZDXLK4UF5SSSH4IBTWUC/graph.json","events_json":"https://pith.science/api/pith-number/GEWRSXZDXLK4UF5SSSH4IBTWUC/events.json","paper":"https://pith.science/paper/GEWRSXZD"},"agent_actions":{"view_html":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC","download_json":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC.json","view_paper":"https://pith.science/paper/GEWRSXZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00114&json=true","fetch_graph":"https://pith.science/api/pith-number/GEWRSXZDXLK4UF5SSSH4IBTWUC/graph.json","fetch_events":"https://pith.science/api/pith-number/GEWRSXZDXLK4UF5SSSH4IBTWUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC/action/storage_attestation","attest_author":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC/action/author_attestation","sign_citation":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC/action/citation_signature","submit_replication":"https://pith.science/pith/GEWRSXZDXLK4UF5SSSH4IBTWUC/action/replication_record"}},"created_at":"2026-07-05T03:02:19.040789+00:00","updated_at":"2026-07-05T03:02:19.040789+00:00"}