{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CQ3FF4YBVSNKWSYEPVFK6XZZJM","short_pith_number":"pith:CQ3FF4YB","schema_version":"1.0","canonical_sha256":"143652f301ac9aab4b047d4aaf5f394b1c79ad13812d8fc3bfda4ddeba7f6bdc","source":{"kind":"arxiv","id":"2008.03030","version":2},"attestation_state":"computed","paper":{"title":"Deep Robust Clustering by Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Chen, Huasong Zhong, Xian-Sheng Hua, Zhongming Jin","submitted_at":"2020-08-07T08:05:53Z","abstract_excerpt":"Recently, many unsupervised deep learning methods have been proposed to learn clustering with unlabelled data. By introducing data augmentation, most of the latest methods look into deep clustering from the perspective that the original image and its transformation should share similar semantic clustering assignment. However, the representation features could be quite different even they are assigned to the same cluster since softmax function is only sensitive to the maximum value. This may result in high intra-class diversities in the representation feature space, which will lead to unstable "},"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":"2008.03030","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-07T08:05:53Z","cross_cats_sorted":[],"title_canon_sha256":"9385b2d51a87bd55f76571be116b48b9564807ef671e4dcbd0905879a23b1b12","abstract_canon_sha256":"6b3f52de74e5a4b9172e4280aebf047b423f857e64139f9af637a398c33ed16e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:30:52.813163Z","signature_b64":"aG4BybyiqTifqlkc2jKqGvJDdTmveh+VEE8KX70Mm0zW54wOAezRTHQ5DNcnn+HPCn9rz0eM/yBRU3FcQJNXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"143652f301ac9aab4b047d4aaf5f394b1c79ad13812d8fc3bfda4ddeba7f6bdc","last_reissued_at":"2026-07-05T01:30:52.812826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:30:52.812826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Robust Clustering by Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Chen, Huasong Zhong, Xian-Sheng Hua, Zhongming Jin","submitted_at":"2020-08-07T08:05:53Z","abstract_excerpt":"Recently, many unsupervised deep learning methods have been proposed to learn clustering with unlabelled data. By introducing data augmentation, most of the latest methods look into deep clustering from the perspective that the original image and its transformation should share similar semantic clustering assignment. However, the representation features could be quite different even they are assigned to the same cluster since softmax function is only sensitive to the maximum value. This may result in high intra-class diversities in the representation feature space, which will lead to unstable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03030","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/2008.03030/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":"2008.03030","created_at":"2026-07-05T01:30:52.812881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03030v2","created_at":"2026-07-05T01:30:52.812881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03030","created_at":"2026-07-05T01:30:52.812881+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQ3FF4YBVSNK","created_at":"2026-07-05T01:30:52.812881+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQ3FF4YBVSNKWSYE","created_at":"2026-07-05T01:30:52.812881+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQ3FF4YB","created_at":"2026-07-05T01:30:52.812881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11182","citing_title":"Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learning","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM","json":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM.json","graph_json":"https://pith.science/api/pith-number/CQ3FF4YBVSNKWSYEPVFK6XZZJM/graph.json","events_json":"https://pith.science/api/pith-number/CQ3FF4YBVSNKWSYEPVFK6XZZJM/events.json","paper":"https://pith.science/paper/CQ3FF4YB"},"agent_actions":{"view_html":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM","download_json":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM.json","view_paper":"https://pith.science/paper/CQ3FF4YB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03030&json=true","fetch_graph":"https://pith.science/api/pith-number/CQ3FF4YBVSNKWSYEPVFK6XZZJM/graph.json","fetch_events":"https://pith.science/api/pith-number/CQ3FF4YBVSNKWSYEPVFK6XZZJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM/action/storage_attestation","attest_author":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM/action/author_attestation","sign_citation":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM/action/citation_signature","submit_replication":"https://pith.science/pith/CQ3FF4YBVSNKWSYEPVFK6XZZJM/action/replication_record"}},"created_at":"2026-07-05T01:30:52.812881+00:00","updated_at":"2026-07-05T01:30:52.812881+00:00"}