{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XTCWFZAS43LQOYRULBSYQZXT63","short_pith_number":"pith:XTCWFZAS","schema_version":"1.0","canonical_sha256":"bcc562e412e6d707623458658866f3f6f3cb5e889283fd31a39516775ef07daa","source":{"kind":"arxiv","id":"2005.04966","version":5},"attestation_state":"computed","paper":{"title":"Prototypical Contrastive Learning of Unsupervised Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Junnan Li, Pan Zhou, Steven C.H. Hoi","submitted_at":"2020-05-11T09:53:36Z","abstract_excerpt":"This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the task of instance discrimination, but more importantly, it implicitly encodes semantic structures of the data into the learned embedding space. Specifically, we introduce prototypes as latent variables to help find the maximum-likelihood estimation of the network parameters in an Expectation-Maximization framework. We iteratively perform E-step as finding the di"},"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":"2005.04966","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-11T09:53:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8ea027c46b81363de8208d5319744869a0c93f1e3b2c7abf758b53550e42c24a","abstract_canon_sha256":"28707b970f4d7022985c7b4ad182ec92c8b363a6e6d1d73cf5953f9acf0e043d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:20.741707Z","signature_b64":"BzzKri0Oy4WRNId24VqwXYBEKfNh9lbs7uFrnwx3jSZcPfc01/0t8ycEOFLxBTXVp8UDqk4pHZ0QiqdRuTU5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcc562e412e6d707623458658866f3f6f3cb5e889283fd31a39516775ef07daa","last_reissued_at":"2026-07-05T02:27:20.741171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:20.741171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prototypical Contrastive Learning of Unsupervised Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Junnan Li, Pan Zhou, Steven C.H. Hoi","submitted_at":"2020-05-11T09:53:36Z","abstract_excerpt":"This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the task of instance discrimination, but more importantly, it implicitly encodes semantic structures of the data into the learned embedding space. Specifically, we introduce prototypes as latent variables to help find the maximum-likelihood estimation of the network parameters in an Expectation-Maximization framework. We iteratively perform E-step as finding the di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.04966","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.04966/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":"2005.04966","created_at":"2026-07-05T02:27:20.741236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.04966v5","created_at":"2026-07-05T02:27:20.741236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.04966","created_at":"2026-07-05T02:27:20.741236+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTCWFZAS43LQ","created_at":"2026-07-05T02:27:20.741236+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTCWFZAS43LQOYRU","created_at":"2026-07-05T02:27:20.741236+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTCWFZAS","created_at":"2026-07-05T02:27:20.741236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24094","citing_title":"Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03160","citing_title":"SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26194","citing_title":"On the Role of Inductive Bias in Time-Series Pretraining: A Case Study in Learning Generalizable Representations for Clinical Time Series","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02808","citing_title":"CMCC-ReID: Cross-Modality Clothing-Change Person Re-Identification","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16588","citing_title":"Vision Transformers Need Registers","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63","json":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63.json","graph_json":"https://pith.science/api/pith-number/XTCWFZAS43LQOYRULBSYQZXT63/graph.json","events_json":"https://pith.science/api/pith-number/XTCWFZAS43LQOYRULBSYQZXT63/events.json","paper":"https://pith.science/paper/XTCWFZAS"},"agent_actions":{"view_html":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63","download_json":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63.json","view_paper":"https://pith.science/paper/XTCWFZAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.04966&json=true","fetch_graph":"https://pith.science/api/pith-number/XTCWFZAS43LQOYRULBSYQZXT63/graph.json","fetch_events":"https://pith.science/api/pith-number/XTCWFZAS43LQOYRULBSYQZXT63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63/action/storage_attestation","attest_author":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63/action/author_attestation","sign_citation":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63/action/citation_signature","submit_replication":"https://pith.science/pith/XTCWFZAS43LQOYRULBSYQZXT63/action/replication_record"}},"created_at":"2026-07-05T02:27:20.741236+00:00","updated_at":"2026-07-05T02:27:20.741236+00:00"}