{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EF5KN3TF7CULPHZMJ43Q7LSA66","short_pith_number":"pith:EF5KN3TF","schema_version":"1.0","canonical_sha256":"217aa6ee65f8a8b79f2c4f370fae40f7b05375e0d38ae8288b673581ef4d49ec","source":{"kind":"arxiv","id":"2210.05770","version":1},"attestation_state":"computed","paper":{"title":"Deep Active Ensemble Sampling For Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donald A. Adjeroh, Gianfranco Doretto, Salman Mohamadi","submitted_at":"2022-10-11T20:20:20Z","abstract_excerpt":"Conventional active learning (AL) frameworks aim to reduce the cost of data annotation by actively requesting the labeling for the most informative data points. However, introducing AL to data hungry deep learning algorithms has been a challenge. Some proposed approaches include uncertainty-based techniques, geometric methods, implicit combination of uncertainty-based and geometric approaches, and more recently, frameworks based on semi/self supervised techniques. In this paper, we address two specific problems in this area. The first is the need for efficient exploitation/exploration trade-of"},"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":"2210.05770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-11T20:20:20Z","cross_cats_sorted":[],"title_canon_sha256":"0ece85b56dd629e6ae4d6ecae3f56fe4210076a51632c0cd27667fab8e6a8d9b","abstract_canon_sha256":"9ee7418aab678d6202938256884d6640c9aa4daa7e09855f6b519584401dd25d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:52.695864Z","signature_b64":"B7Qhf5M1IhQtgbCO/MxdVWui8WNf6XhVLv9r4cXWvGhcxEoJLHZuZN0FZlmSjRaxvBJmss2WU8mujWQVYF3hBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"217aa6ee65f8a8b79f2c4f370fae40f7b05375e0d38ae8288b673581ef4d49ec","last_reissued_at":"2026-07-05T05:05:52.695437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:52.695437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Active Ensemble Sampling For Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Donald A. Adjeroh, Gianfranco Doretto, Salman Mohamadi","submitted_at":"2022-10-11T20:20:20Z","abstract_excerpt":"Conventional active learning (AL) frameworks aim to reduce the cost of data annotation by actively requesting the labeling for the most informative data points. However, introducing AL to data hungry deep learning algorithms has been a challenge. Some proposed approaches include uncertainty-based techniques, geometric methods, implicit combination of uncertainty-based and geometric approaches, and more recently, frameworks based on semi/self supervised techniques. In this paper, we address two specific problems in this area. The first is the need for efficient exploitation/exploration trade-of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05770","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/2210.05770/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":"2210.05770","created_at":"2026-07-05T05:05:52.695500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.05770v1","created_at":"2026-07-05T05:05:52.695500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05770","created_at":"2026-07-05T05:05:52.695500+00:00"},{"alias_kind":"pith_short_12","alias_value":"EF5KN3TF7CUL","created_at":"2026-07-05T05:05:52.695500+00:00"},{"alias_kind":"pith_short_16","alias_value":"EF5KN3TF7CULPHZM","created_at":"2026-07-05T05:05:52.695500+00:00"},{"alias_kind":"pith_short_8","alias_value":"EF5KN3TF","created_at":"2026-07-05T05:05:52.695500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02121","citing_title":"Rethinking Self-Supervised Learning Within the Framework of Partial Information Decomposition","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66","json":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66.json","graph_json":"https://pith.science/api/pith-number/EF5KN3TF7CULPHZMJ43Q7LSA66/graph.json","events_json":"https://pith.science/api/pith-number/EF5KN3TF7CULPHZMJ43Q7LSA66/events.json","paper":"https://pith.science/paper/EF5KN3TF"},"agent_actions":{"view_html":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66","download_json":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66.json","view_paper":"https://pith.science/paper/EF5KN3TF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.05770&json=true","fetch_graph":"https://pith.science/api/pith-number/EF5KN3TF7CULPHZMJ43Q7LSA66/graph.json","fetch_events":"https://pith.science/api/pith-number/EF5KN3TF7CULPHZMJ43Q7LSA66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66/action/storage_attestation","attest_author":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66/action/author_attestation","sign_citation":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66/action/citation_signature","submit_replication":"https://pith.science/pith/EF5KN3TF7CULPHZMJ43Q7LSA66/action/replication_record"}},"created_at":"2026-07-05T05:05:52.695500+00:00","updated_at":"2026-07-05T05:05:52.695500+00:00"}