{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FO5L4YQYMBXC5BFAYA27G2SPVP","short_pith_number":"pith:FO5L4YQY","schema_version":"1.0","canonical_sha256":"2bbabe6218606e2e84a0c035f36a4fabd45fc5feee82d55a871bf4dcef76db10","source":{"kind":"arxiv","id":"2006.07831","version":2},"attestation_state":"computed","paper":{"title":"Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Haifeng Liu, Mingming Gong, Nannan Wang, Songhua Wu, Tongliang Liu, Xiaobo Xia","submitted_at":"2020-06-14T07:55:32Z","abstract_excerpt":"Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner mitigate label noise? To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class l"},"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":"2006.07831","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T07:55:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0e4f8aaa93f14f48552d23716b24cf998253a0e0bd19953f889f87f045a94485","abstract_canon_sha256":"f21ad166355dd86a6d4a0bca5be5d7b49158a2b2bc90a0bd71c15d73bfa17f90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:05.842172Z","signature_b64":"rIqDDQNIWnreoh2p1HKLWRyDovd3L1r9PJaB7iXJp9pa9trZicubOYh2K22BY+L9kVDiyibOyjbePyuSKHaODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bbabe6218606e2e84a0c035f36a4fabd45fc5feee82d55a871bf4dcef76db10","last_reissued_at":"2026-07-05T02:50:05.841771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:05.841771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Haifeng Liu, Mingming Gong, Nannan Wang, Songhua Wu, Tongliang Liu, Xiaobo Xia","submitted_at":"2020-06-14T07:55:32Z","abstract_excerpt":"Learning with noisy labels has attracted a lot of attention in recent years, where the mainstream approaches are in pointwise manners. Meanwhile, pairwise manners have shown great potential in supervised metric learning and unsupervised contrastive learning. Thus, a natural question is raised: does learning in a pairwise manner mitigate label noise? To give an affirmative answer, in this paper, we propose a framework called Class2Simi: it transforms data points with noisy class labels to data pairs with noisy similarity labels, where a similarity label denotes whether a pair shares the class l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07831","kind":"arxiv","version":2},"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/2006.07831/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":"2006.07831","created_at":"2026-07-05T02:50:05.841833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07831v2","created_at":"2026-07-05T02:50:05.841833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07831","created_at":"2026-07-05T02:50:05.841833+00:00"},{"alias_kind":"pith_short_12","alias_value":"FO5L4YQYMBXC","created_at":"2026-07-05T02:50:05.841833+00:00"},{"alias_kind":"pith_short_16","alias_value":"FO5L4YQYMBXC5BFA","created_at":"2026-07-05T02:50:05.841833+00:00"},{"alias_kind":"pith_short_8","alias_value":"FO5L4YQY","created_at":"2026-07-05T02:50:05.841833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04029","citing_title":"Securing Contrastive mmWave-based Human Activity Recognition against Adversarial Label Flipping","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP","json":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP.json","graph_json":"https://pith.science/api/pith-number/FO5L4YQYMBXC5BFAYA27G2SPVP/graph.json","events_json":"https://pith.science/api/pith-number/FO5L4YQYMBXC5BFAYA27G2SPVP/events.json","paper":"https://pith.science/paper/FO5L4YQY"},"agent_actions":{"view_html":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP","download_json":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP.json","view_paper":"https://pith.science/paper/FO5L4YQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07831&json=true","fetch_graph":"https://pith.science/api/pith-number/FO5L4YQYMBXC5BFAYA27G2SPVP/graph.json","fetch_events":"https://pith.science/api/pith-number/FO5L4YQYMBXC5BFAYA27G2SPVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP/action/storage_attestation","attest_author":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP/action/author_attestation","sign_citation":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP/action/citation_signature","submit_replication":"https://pith.science/pith/FO5L4YQYMBXC5BFAYA27G2SPVP/action/replication_record"}},"created_at":"2026-07-05T02:50:05.841833+00:00","updated_at":"2026-07-05T02:50:05.841833+00:00"}