{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IEIPXHGZRVA76MAMZHLA4UYQTM","short_pith_number":"pith:IEIPXHGZ","schema_version":"1.0","canonical_sha256":"4110fb9cd98d41ff300cc9d60e53109b0918aaa935e97c86912270e421c550d0","source":{"kind":"arxiv","id":"1904.01612","version":4},"attestation_state":"computed","paper":{"title":"Generative-Discriminative Complementary Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junxiang Chen, Kayhan Batmanghelich, Kun Zhang, Mingming Gong, Tongliang Liu, Yanwu Xu","submitted_at":"2019-04-02T18:37:13Z","abstract_excerpt":"Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminati"},"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":"1904.01612","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-02T18:37:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dd2917250dbddd4320027dccda84e4599423d35eeedde0f88e307ce45c6a6fc8","abstract_canon_sha256":"727e5be43f2f55ddece28ee7bcef1da783b9339b529ed6ebed703b3d74a47645"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:07.887014Z","signature_b64":"euLrLJscnUcVql7nd6Ssw+vSQq56taC2YiH8VMsQ+8ABO/NB/vPKXYiz/ct6C5/FJzqOG4CJtDWXr5fdqK1BDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4110fb9cd98d41ff300cc9d60e53109b0918aaa935e97c86912270e421c550d0","last_reissued_at":"2026-07-05T00:04:07.886598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:07.886598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative-Discriminative Complementary Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junxiang Chen, Kayhan Batmanghelich, Kun Zhang, Mingming Gong, Tongliang Liu, Yanwu Xu","submitted_at":"2019-04-02T18:37:13Z","abstract_excerpt":"Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01612","kind":"arxiv","version":4},"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/1904.01612/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":"1904.01612","created_at":"2026-07-05T00:04:07.886661+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01612v4","created_at":"2026-07-05T00:04:07.886661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01612","created_at":"2026-07-05T00:04:07.886661+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEIPXHGZRVA7","created_at":"2026-07-05T00:04:07.886661+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEIPXHGZRVA76MAM","created_at":"2026-07-05T00:04:07.886661+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEIPXHGZ","created_at":"2026-07-05T00:04:07.886661+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/IEIPXHGZRVA76MAMZHLA4UYQTM","json":"https://pith.science/pith/IEIPXHGZRVA76MAMZHLA4UYQTM.json","graph_json":"https://pith.science/api/pith-number/IEIPXHGZRVA76MAMZHLA4UYQTM/graph.json","events_json":"https://pith.science/api/pith-number/IEIPXHGZRVA76MAMZHLA4UYQTM/events.json","paper":"https://pith.science/paper/IEIPXHGZ"},"agent_actions":{"view_html":"https://pith.science/pith/IEIPXHGZRVA76MAMZHLA4UYQTM","download_json":"https://pith.science/pith/IEIPXHGZRVA76MAMZHLA4UYQTM.json","view_paper":"https://pith.science/paper/IEIPXHGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01612&json=true","fetch_graph":"https://pith.science/api/pith-number/IEIPXHGZRVA76MAMZHLA4UYQTM/graph.json","fetch_events":"https://pith.science/api/pith-number/IEIPXHGZRVA76MAMZHLA4UYQTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEIPXHGZRVA76MAMZHLA4UYQTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEIPXHGZRVA76MAMZHLA4UYQTM/action/storage_attestation","attest_author":"https://pith.science/pith/IEIPXHGZRVA76MAMZHLA4UYQTM/action/author_attestation","sign_citation":"https://pith.science/pith/IEIPXHGZRVA76MAMZHLA4UYQTM/action/citation_signature","submit_replication":"https://pith.science/pith/IEIPXHGZRVA76MAMZHLA4UYQTM/action/replication_record"}},"created_at":"2026-07-05T00:04:07.886661+00:00","updated_at":"2026-07-05T00:04:07.886661+00:00"}