{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FDWALGHBQUFEDGVNYMLJ7O3MQ5","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":"c3f65fe6ddb20cd36423b49d483ef5e4a2bbed32953bcedc3339ec45de70fa3a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-09T10:20:49Z","title_canon_sha256":"2a6f0e88ce2f27afc64d34ada52add145f7c5b15d4a28b715f65e7af3c6ae388"},"schema_version":"1.0","source":{"id":"2103.05331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.05331","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2103.05331v2","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05331","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"FDWALGHBQUFE","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"FDWALGHBQUFEDGVN","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"FDWALGHB","created_at":"2026-07-05T02:49:00Z"}],"graph_snapshots":[{"event_id":"sha256:1d6ace4effd0725d90a390d4865a43d6b5204c7e565b946ca9b8207327ab16bb","target":"graph","created_at":"2026-07-05T02:49:00Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.05331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a new framework for sample-efficient model evaluation that we call active testing. While approaches like active learning reduce the number of labels needed for model training, existing literature largely ignores the cost of labeling test data, typically unrealistically assuming large test sets for model evaluation. This creates a disconnect to real applications, where test labels are important and just as expensive, e.g. for optimizing hyperparameters. Active testing addresses this by carefully selecting the test points to label, ensuring model evaluation is sample-efficient. To t","authors_text":"Jannik Kossen, Sebastian Farquhar, Tom Rainforth, Yarin Gal","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-09T10:20:49Z","title":"Active Testing: Sample-Efficient Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05331","kind":"arxiv","version":2},"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":"sha256:5ce5b3b6d21c562ed18f43c7d8fda68c9c4811f800f2e30f54728f15c6897e1f","target":"record","created_at":"2026-07-05T02:49:00Z","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":"c3f65fe6ddb20cd36423b49d483ef5e4a2bbed32953bcedc3339ec45de70fa3a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-03-09T10:20:49Z","title_canon_sha256":"2a6f0e88ce2f27afc64d34ada52add145f7c5b15d4a28b715f65e7af3c6ae388"},"schema_version":"1.0","source":{"id":"2103.05331","kind":"arxiv","version":2}},"canonical_sha256":"28ec0598e1850a419aadc3169fbb6c8750282bde0847fffb124b29e67cc28746","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28ec0598e1850a419aadc3169fbb6c8750282bde0847fffb124b29e67cc28746","first_computed_at":"2026-07-05T02:49:00.039708Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:00.039708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3eLuPuqLccoB2/62KfORm6OpV+8I7yOmwqnfYYXPPGUg1/WwExHW0dkMRtlDtabi3HJDCGms06oQoE98TjGaCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:00.040174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.05331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ce5b3b6d21c562ed18f43c7d8fda68c9c4811f800f2e30f54728f15c6897e1f","sha256:1d6ace4effd0725d90a390d4865a43d6b5204c7e565b946ca9b8207327ab16bb"],"state_sha256":"052460704a7381caf4d92e3828324f9f9b7fa0ee6cbe22dd7d56b10b30b9a6ff"}