{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EAUDWIK6OYGED3FL6FEX54YXPS","short_pith_number":"pith:EAUDWIK6","schema_version":"1.0","canonical_sha256":"20283b215e760c41ecabf1497ef3177ca640965149377ddffaf899f779e6a679","source":{"kind":"arxiv","id":"2009.14448","version":1},"attestation_state":"computed","paper":{"title":"Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bindya Venkatesh, Jayaraman J. Thiagarajan","submitted_at":"2020-09-30T05:19:56Z","abstract_excerpt":"Deep predictive models rely on human supervision in the form of labeled training data. Obtaining large amounts of annotated training data can be expensive and time consuming, and this becomes a critical bottleneck while building such models in practice. In such scenarios, active learning (AL) strategies are used to achieve faster convergence in terms of labeling efforts. Existing active learning employ a variety of heuristics based on uncertainty and diversity to select query samples. Despite their wide-spread use, in practice, their performance is limited by a number of factors including non-"},"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":"2009.14448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-09-30T05:19:56Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"7143180d0d894c123c8f98af0500d5b3da129a75e4bf43f2cab9db8778063d48","abstract_canon_sha256":"397fc54236e2291432da0cff822c607b72c09ab79383929da67dcf66970489c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:19.439300Z","signature_b64":"2dUG2EwR/7cyvxSwiOkrSAncTQHP41PAAZXzj5GP+wiaKcT0jc1IjshxoXAwOU/4t6mihHloPXZrkonZ5Lf/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20283b215e760c41ecabf1497ef3177ca640965149377ddffaf899f779e6a679","last_reissued_at":"2026-07-05T01:39:19.438959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:19.438959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Bindya Venkatesh, Jayaraman J. Thiagarajan","submitted_at":"2020-09-30T05:19:56Z","abstract_excerpt":"Deep predictive models rely on human supervision in the form of labeled training data. Obtaining large amounts of annotated training data can be expensive and time consuming, and this becomes a critical bottleneck while building such models in practice. In such scenarios, active learning (AL) strategies are used to achieve faster convergence in terms of labeling efforts. Existing active learning employ a variety of heuristics based on uncertainty and diversity to select query samples. Despite their wide-spread use, in practice, their performance is limited by a number of factors including non-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14448","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/2009.14448/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":"2009.14448","created_at":"2026-07-05T01:39:19.439021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.14448v1","created_at":"2026-07-05T01:39:19.439021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14448","created_at":"2026-07-05T01:39:19.439021+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAUDWIK6OYGE","created_at":"2026-07-05T01:39:19.439021+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAUDWIK6OYGED3FL","created_at":"2026-07-05T01:39:19.439021+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAUDWIK6","created_at":"2026-07-05T01:39:19.439021+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/EAUDWIK6OYGED3FL6FEX54YXPS","json":"https://pith.science/pith/EAUDWIK6OYGED3FL6FEX54YXPS.json","graph_json":"https://pith.science/api/pith-number/EAUDWIK6OYGED3FL6FEX54YXPS/graph.json","events_json":"https://pith.science/api/pith-number/EAUDWIK6OYGED3FL6FEX54YXPS/events.json","paper":"https://pith.science/paper/EAUDWIK6"},"agent_actions":{"view_html":"https://pith.science/pith/EAUDWIK6OYGED3FL6FEX54YXPS","download_json":"https://pith.science/pith/EAUDWIK6OYGED3FL6FEX54YXPS.json","view_paper":"https://pith.science/paper/EAUDWIK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.14448&json=true","fetch_graph":"https://pith.science/api/pith-number/EAUDWIK6OYGED3FL6FEX54YXPS/graph.json","fetch_events":"https://pith.science/api/pith-number/EAUDWIK6OYGED3FL6FEX54YXPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAUDWIK6OYGED3FL6FEX54YXPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAUDWIK6OYGED3FL6FEX54YXPS/action/storage_attestation","attest_author":"https://pith.science/pith/EAUDWIK6OYGED3FL6FEX54YXPS/action/author_attestation","sign_citation":"https://pith.science/pith/EAUDWIK6OYGED3FL6FEX54YXPS/action/citation_signature","submit_replication":"https://pith.science/pith/EAUDWIK6OYGED3FL6FEX54YXPS/action/replication_record"}},"created_at":"2026-07-05T01:39:19.439021+00:00","updated_at":"2026-07-05T01:39:19.439021+00:00"}