{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HNAOXMLTAIRUV4LHQWRDHIYWD3","short_pith_number":"pith:HNAOXMLT","schema_version":"1.0","canonical_sha256":"3b40ebb17302234af16785a233a3161efe4c960285671c131497edc3f358756f","source":{"kind":"arxiv","id":"1702.07956","version":5},"attestation_state":"computed","paper":{"title":"Generative Adversarial Active Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jia-Jie Zhu, Jos\\'e Bento","submitted_at":"2017-02-25T22:45:20Z","abstract_excerpt":"We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our idea can work with other active learning principles. We report results from various numerical experiments to demonstrate the effectiveness the proposed approach. In some settings, the proposed algorithm outperforms traditional pool-based approaches. To the best our knowledge, th"},"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":"1702.07956","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-25T22:45:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bc8528ddc0f150277d0d7e2984dcb8ec208762d7ace9d2c08f62b0f22ca77d54","abstract_canon_sha256":"8b9ac703a0d768f398d4c6cff16bd570c12285d02f994da4f51eb57594b1a9ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:28.478347Z","signature_b64":"W8vt8bsl5wRuqAdzP9CxkzSpPjN5Ugvc5JaFgCpNOCq5wlR3uH7aOI8nWhOjaPi3LXvstCibR7j9UA4zaGapDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b40ebb17302234af16785a233a3161efe4c960285671c131497edc3f358756f","last_reissued_at":"2026-05-18T00:30:28.477833Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:28.477833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Adversarial Active Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jia-Jie Zhu, Jos\\'e Bento","submitted_at":"2017-02-25T22:45:20Z","abstract_excerpt":"We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our idea can work with other active learning principles. We report results from various numerical experiments to demonstrate the effectiveness the proposed approach. In some settings, the proposed algorithm outperforms traditional pool-based approaches. To the best our knowledge, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07956","kind":"arxiv","version":5},"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":"1702.07956","created_at":"2026-05-18T00:30:28.477897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07956v5","created_at":"2026-05-18T00:30:28.477897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07956","created_at":"2026-05-18T00:30:28.477897+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNAOXMLTAIRU","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNAOXMLTAIRUV4LH","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNAOXMLT","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.06347","citing_title":"Discriminative Active Learning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22169","citing_title":"Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00832","citing_title":"Synthetic Designed Experiments for Diagnosing Vision Model Failure","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10349","citing_title":"Portable Active Learning for Object Detection","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23290","citing_title":"An Analysis of Active Learning Algorithms using Real-World Crowd-sourced Text Annotations","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3","json":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3.json","graph_json":"https://pith.science/api/pith-number/HNAOXMLTAIRUV4LHQWRDHIYWD3/graph.json","events_json":"https://pith.science/api/pith-number/HNAOXMLTAIRUV4LHQWRDHIYWD3/events.json","paper":"https://pith.science/paper/HNAOXMLT"},"agent_actions":{"view_html":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3","download_json":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3.json","view_paper":"https://pith.science/paper/HNAOXMLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07956&json=true","fetch_graph":"https://pith.science/api/pith-number/HNAOXMLTAIRUV4LHQWRDHIYWD3/graph.json","fetch_events":"https://pith.science/api/pith-number/HNAOXMLTAIRUV4LHQWRDHIYWD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3/action/storage_attestation","attest_author":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3/action/author_attestation","sign_citation":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3/action/citation_signature","submit_replication":"https://pith.science/pith/HNAOXMLTAIRUV4LHQWRDHIYWD3/action/replication_record"}},"created_at":"2026-05-18T00:30:28.477897+00:00","updated_at":"2026-05-18T00:30:28.477897+00:00"}