{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BLZAARLCB2AW3BOX4IXKXA4FKA","short_pith_number":"pith:BLZAARLC","schema_version":"1.0","canonical_sha256":"0af20045620e816d85d7e22eab8385503554f3cb546c13c23f71cd75804b4153","source":{"kind":"arxiv","id":"2105.11527","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Visual Representation Learning by Online Constrained K-Means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Juhua Hu, Qi Qian, Rong Jin, Yuanhong Xu","submitted_at":"2021-05-24T20:38:32Z","abstract_excerpt":"Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination. The main challenge resides in clustering since prevalent clustering methods (e.g., k-means) have to run in a batch mode. Besides, there can be a trivial solution consisting of a dominating cluster. To address these challenges, we first investigate the objective of clustering-based representation learning. Based on this, we"},"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":"2105.11527","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-24T20:38:32Z","cross_cats_sorted":[],"title_canon_sha256":"c1dce998e9647441fca76467edd0a306958ddc2547103cc338a8ef961fb436b8","abstract_canon_sha256":"4492c385fe3a8e843905bf02c084025886a014f5b29f62bf14da128dd304092c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:14.207372Z","signature_b64":"M1SXD4YX8gfvtBRQExj5ftO291rskfkTA0q8O3NULF0nH2G85fyyC99grQii7StjuzkugiPIxGEHuZTBWgwaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0af20045620e816d85d7e22eab8385503554f3cb546c13c23f71cd75804b4153","last_reissued_at":"2026-07-05T04:09:14.206784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:14.206784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Visual Representation Learning by Online Constrained K-Means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Li, Juhua Hu, Qi Qian, Rong Jin, Yuanhong Xu","submitted_at":"2021-05-24T20:38:32Z","abstract_excerpt":"Cluster discrimination is an effective pretext task for unsupervised representation learning, which often consists of two phases: clustering and discrimination. Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination. The main challenge resides in clustering since prevalent clustering methods (e.g., k-means) have to run in a batch mode. Besides, there can be a trivial solution consisting of a dominating cluster. To address these challenges, we first investigate the objective of clustering-based representation learning. Based on this, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11527","kind":"arxiv","version":3},"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/2105.11527/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":"2105.11527","created_at":"2026-07-05T04:09:14.206845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.11527v3","created_at":"2026-07-05T04:09:14.206845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11527","created_at":"2026-07-05T04:09:14.206845+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLZAARLCB2AW","created_at":"2026-07-05T04:09:14.206845+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLZAARLCB2AW3BOX","created_at":"2026-07-05T04:09:14.206845+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLZAARLC","created_at":"2026-07-05T04:09:14.206845+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/BLZAARLCB2AW3BOX4IXKXA4FKA","json":"https://pith.science/pith/BLZAARLCB2AW3BOX4IXKXA4FKA.json","graph_json":"https://pith.science/api/pith-number/BLZAARLCB2AW3BOX4IXKXA4FKA/graph.json","events_json":"https://pith.science/api/pith-number/BLZAARLCB2AW3BOX4IXKXA4FKA/events.json","paper":"https://pith.science/paper/BLZAARLC"},"agent_actions":{"view_html":"https://pith.science/pith/BLZAARLCB2AW3BOX4IXKXA4FKA","download_json":"https://pith.science/pith/BLZAARLCB2AW3BOX4IXKXA4FKA.json","view_paper":"https://pith.science/paper/BLZAARLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.11527&json=true","fetch_graph":"https://pith.science/api/pith-number/BLZAARLCB2AW3BOX4IXKXA4FKA/graph.json","fetch_events":"https://pith.science/api/pith-number/BLZAARLCB2AW3BOX4IXKXA4FKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLZAARLCB2AW3BOX4IXKXA4FKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLZAARLCB2AW3BOX4IXKXA4FKA/action/storage_attestation","attest_author":"https://pith.science/pith/BLZAARLCB2AW3BOX4IXKXA4FKA/action/author_attestation","sign_citation":"https://pith.science/pith/BLZAARLCB2AW3BOX4IXKXA4FKA/action/citation_signature","submit_replication":"https://pith.science/pith/BLZAARLCB2AW3BOX4IXKXA4FKA/action/replication_record"}},"created_at":"2026-07-05T04:09:14.206845+00:00","updated_at":"2026-07-05T04:09:14.206845+00:00"}