{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XLKC7FNJT536LNSZSV5WERMLOZ","short_pith_number":"pith:XLKC7FNJ","schema_version":"1.0","canonical_sha256":"bad42f95a99f77e5b659957b62458b764df61d045bdc19972e5e2c639fb2a2b4","source":{"kind":"arxiv","id":"2104.04999","version":1},"attestation_state":"computed","paper":{"title":"ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huong Ha, Santu Rana, Sunil Gupta, Svetha Venkatesh","submitted_at":"2021-04-11T12:14:04Z","abstract_excerpt":"Machine learning models are being used extensively in many important areas, but there is no guarantee a model will always perform well or as its developers intended. Understanding the correctness of a model is crucial to prevent potential failures that may have significant detrimental impact in critical application areas. In this paper, we propose a novel framework to efficiently test a machine learning model using only a small amount of labeled test data. The idea is to estimate the metrics of interest for a model-under-test using Bayesian neural network (BNN). We develop a novel data augment"},"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":"2104.04999","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-11T12:14:04Z","cross_cats_sorted":["cs.AI","cs.SE","stat.ML"],"title_canon_sha256":"f5377a051ec8aaa861e3f545a8554c255b3b3c40d13ed989d2eb6bf357b1eba3","abstract_canon_sha256":"88c6ba97c7357a28848a63b940be4f953d82cab28eb3e63807ca52563be3511a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:07.265251Z","signature_b64":"fYbxjigECTDyBR8yeCvAxevZ3fPu97W7dr0N5LhPB63QizdD324R5mQ6EN72H14D+yWs+YWznANBxV5QvtfOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bad42f95a99f77e5b659957b62458b764df61d045bdc19972e5e2c639fb2a2b4","last_reissued_at":"2026-07-05T02:31:07.264779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:07.264779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huong Ha, Santu Rana, Sunil Gupta, Svetha Venkatesh","submitted_at":"2021-04-11T12:14:04Z","abstract_excerpt":"Machine learning models are being used extensively in many important areas, but there is no guarantee a model will always perform well or as its developers intended. Understanding the correctness of a model is crucial to prevent potential failures that may have significant detrimental impact in critical application areas. In this paper, we propose a novel framework to efficiently test a machine learning model using only a small amount of labeled test data. The idea is to estimate the metrics of interest for a model-under-test using Bayesian neural network (BNN). We develop a novel data augment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04999","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/2104.04999/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":"2104.04999","created_at":"2026-07-05T02:31:07.264843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04999v1","created_at":"2026-07-05T02:31:07.264843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04999","created_at":"2026-07-05T02:31:07.264843+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLKC7FNJT536","created_at":"2026-07-05T02:31:07.264843+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLKC7FNJT536LNSZ","created_at":"2026-07-05T02:31:07.264843+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLKC7FNJ","created_at":"2026-07-05T02:31:07.264843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18123","citing_title":"Actively evaluating and learning the distinctions that matter: Vaccine safety signal detection from emergency triage notes","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ","json":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ.json","graph_json":"https://pith.science/api/pith-number/XLKC7FNJT536LNSZSV5WERMLOZ/graph.json","events_json":"https://pith.science/api/pith-number/XLKC7FNJT536LNSZSV5WERMLOZ/events.json","paper":"https://pith.science/paper/XLKC7FNJ"},"agent_actions":{"view_html":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ","download_json":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ.json","view_paper":"https://pith.science/paper/XLKC7FNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04999&json=true","fetch_graph":"https://pith.science/api/pith-number/XLKC7FNJT536LNSZSV5WERMLOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XLKC7FNJT536LNSZSV5WERMLOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ/action/storage_attestation","attest_author":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ/action/author_attestation","sign_citation":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ/action/citation_signature","submit_replication":"https://pith.science/pith/XLKC7FNJT536LNSZSV5WERMLOZ/action/replication_record"}},"created_at":"2026-07-05T02:31:07.264843+00:00","updated_at":"2026-07-05T02:31:07.264843+00:00"}