{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LR4VBJSIAZBWSJ5WTFEVVXRTMJ","short_pith_number":"pith:LR4VBJSI","schema_version":"1.0","canonical_sha256":"5c7950a64806436927b699495ade33626fd343f95f2d36f8500ca26cc43d8df7","source":{"kind":"arxiv","id":"1807.00493","version":1},"attestation_state":"computed","paper":{"title":"Active Testing: An Efficient and Robust Framework for Estimating Accuracy","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless Fowlkes, Deva Ramanan, Phuc Nguyen","submitted_at":"2018-07-02T07:18:44Z","abstract_excerpt":"Much recent work on visual recognition aims to scale up learning to massive, noisily-annotated datasets. We address the problem of scaling- up the evaluation of such models to large-scale datasets with noisy labels. Current protocols for doing so require a human user to either vet (re-annotate) a small fraction of the test set and ignore the rest, or else correct errors in annotation as they are found through manual inspection of results. In this work, we re-formulate the problem as one of active testing, and examine strategies for efficiently querying a user so as to obtain an accu- rate perf"},"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":"1807.00493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-07-02T07:18:44Z","cross_cats_sorted":[],"title_canon_sha256":"fa54f6ba846a6a1a9611f845caa1156e4124ad48d008825a9bde172a6466f8f8","abstract_canon_sha256":"f4a2dd83acba3ffebc3b0d5d6f5b2db8fed331032d6831434f152d00d711584a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:52.452393Z","signature_b64":"c6Is5yK25WnaFvkXqbK71Y/crqcWjx839bJlUM4qdX0B6O9w4T9VHsssqYZNvv6AQWVh+syKz7j9Sj3tTWYYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c7950a64806436927b699495ade33626fd343f95f2d36f8500ca26cc43d8df7","last_reissued_at":"2026-05-18T00:11:52.451728Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:52.451728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Testing: An Efficient and Robust Framework for Estimating Accuracy","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Charless Fowlkes, Deva Ramanan, Phuc Nguyen","submitted_at":"2018-07-02T07:18:44Z","abstract_excerpt":"Much recent work on visual recognition aims to scale up learning to massive, noisily-annotated datasets. We address the problem of scaling- up the evaluation of such models to large-scale datasets with noisy labels. Current protocols for doing so require a human user to either vet (re-annotate) a small fraction of the test set and ignore the rest, or else correct errors in annotation as they are found through manual inspection of results. In this work, we re-formulate the problem as one of active testing, and examine strategies for efficiently querying a user so as to obtain an accu- rate perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00493","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":"1807.00493","created_at":"2026-05-18T00:11:52.451821+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00493v1","created_at":"2026-05-18T00:11:52.451821+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00493","created_at":"2026-05-18T00:11:52.451821+00:00"},{"alias_kind":"pith_short_12","alias_value":"LR4VBJSIAZBW","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LR4VBJSIAZBWSJ5W","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LR4VBJSI","created_at":"2026-05-18T12:32:37.024351+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/LR4VBJSIAZBWSJ5WTFEVVXRTMJ","json":"https://pith.science/pith/LR4VBJSIAZBWSJ5WTFEVVXRTMJ.json","graph_json":"https://pith.science/api/pith-number/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/graph.json","events_json":"https://pith.science/api/pith-number/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/events.json","paper":"https://pith.science/paper/LR4VBJSI"},"agent_actions":{"view_html":"https://pith.science/pith/LR4VBJSIAZBWSJ5WTFEVVXRTMJ","download_json":"https://pith.science/pith/LR4VBJSIAZBWSJ5WTFEVVXRTMJ.json","view_paper":"https://pith.science/paper/LR4VBJSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00493&json=true","fetch_graph":"https://pith.science/api/pith-number/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/action/storage_attestation","attest_author":"https://pith.science/pith/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/action/author_attestation","sign_citation":"https://pith.science/pith/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/action/citation_signature","submit_replication":"https://pith.science/pith/LR4VBJSIAZBWSJ5WTFEVVXRTMJ/action/replication_record"}},"created_at":"2026-05-18T00:11:52.451821+00:00","updated_at":"2026-05-18T00:11:52.451821+00:00"}