{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VJOK3XQJN4WMNY2TXBJ4BOWTHC","short_pith_number":"pith:VJOK3XQJ","schema_version":"1.0","canonical_sha256":"aa5cadde096f2cc6e353b853c0bad338a61cd1b69e277e0f01f2391e88f48f8c","source":{"kind":"arxiv","id":"2103.05484","version":1},"attestation_state":"computed","paper":{"title":"Doubly Contrastive Deep Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Deng, Heng Huang, Xu Yang, Zhiyuan Dang","submitted_at":"2021-03-09T15:15:32Z","abstract_excerpt":"Deep clustering successfully provides more effective features than conventional ones and thus becomes an important technique in current unsupervised learning. However, most deep clustering methods ignore the vital positive and negative pairs introduced by data augmentation and further the significance of contrastive learning, which leads to suboptimal performance. In this paper, we present a novel Doubly Contrastive Deep Clustering (DCDC) framework, which constructs contrastive loss over both sample and class views to obtain more discriminative features and competitive results. Specifically, f"},"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":"2103.05484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-09T15:15:32Z","cross_cats_sorted":[],"title_canon_sha256":"60545bcd4edaddf83a8e4af4a4ced4067db03273e02450cba8f5739a3818cac2","abstract_canon_sha256":"39c4b8c1b9dd2b12e51fb6b6db51c76cdb21af993fe0369f6a14f6498014785c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:26.434457Z","signature_b64":"tlMDkCdELgRc3pbMT1tsi4UHCrHnXPmqwVpjk1aOxqmKFE4u81SkB5EcKtKLcw2gyCnhSf1zmhEcC9izbaJNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa5cadde096f2cc6e353b853c0bad338a61cd1b69e277e0f01f2391e88f48f8c","last_reissued_at":"2026-07-05T02:21:26.434022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:26.434022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doubly Contrastive Deep Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Deng, Heng Huang, Xu Yang, Zhiyuan Dang","submitted_at":"2021-03-09T15:15:32Z","abstract_excerpt":"Deep clustering successfully provides more effective features than conventional ones and thus becomes an important technique in current unsupervised learning. However, most deep clustering methods ignore the vital positive and negative pairs introduced by data augmentation and further the significance of contrastive learning, which leads to suboptimal performance. In this paper, we present a novel Doubly Contrastive Deep Clustering (DCDC) framework, which constructs contrastive loss over both sample and class views to obtain more discriminative features and competitive results. Specifically, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05484","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/2103.05484/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":"2103.05484","created_at":"2026-07-05T02:21:26.434078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05484v1","created_at":"2026-07-05T02:21:26.434078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05484","created_at":"2026-07-05T02:21:26.434078+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJOK3XQJN4WM","created_at":"2026-07-05T02:21:26.434078+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJOK3XQJN4WMNY2T","created_at":"2026-07-05T02:21:26.434078+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJOK3XQJ","created_at":"2026-07-05T02:21:26.434078+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07474","citing_title":"Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC","json":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC.json","graph_json":"https://pith.science/api/pith-number/VJOK3XQJN4WMNY2TXBJ4BOWTHC/graph.json","events_json":"https://pith.science/api/pith-number/VJOK3XQJN4WMNY2TXBJ4BOWTHC/events.json","paper":"https://pith.science/paper/VJOK3XQJ"},"agent_actions":{"view_html":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC","download_json":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC.json","view_paper":"https://pith.science/paper/VJOK3XQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05484&json=true","fetch_graph":"https://pith.science/api/pith-number/VJOK3XQJN4WMNY2TXBJ4BOWTHC/graph.json","fetch_events":"https://pith.science/api/pith-number/VJOK3XQJN4WMNY2TXBJ4BOWTHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC/action/storage_attestation","attest_author":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC/action/author_attestation","sign_citation":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC/action/citation_signature","submit_replication":"https://pith.science/pith/VJOK3XQJN4WMNY2TXBJ4BOWTHC/action/replication_record"}},"created_at":"2026-07-05T02:21:26.434078+00:00","updated_at":"2026-07-05T02:21:26.434078+00:00"}