{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D3XZY74WRJVZKCBHU63CLX3EGE","short_pith_number":"pith:D3XZY74W","schema_version":"1.0","canonical_sha256":"1eef9c7f968a6b950827a7b625df64311900056dc181cf80ecd02789df22e2a0","source":{"kind":"arxiv","id":"2410.14242","version":1},"attestation_state":"computed","paper":{"title":"Pseudo-label Refinement for Improving Self-Supervised Learning Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arif Mahmood, Wenxiong Kang, Zia-ur-Rehman","submitted_at":"2024-10-18T07:47:59Z","abstract_excerpt":"Self-supervised learning systems have gained significant attention in recent years by leveraging clustering-based pseudo-labels to provide supervision without the need for human annotations. However, the noise in these pseudo-labels caused by the clustering methods poses a challenge to the learning process leading to degraded performance. In this work, we propose a pseudo-label refinement (SLR) algorithm to address this issue. The cluster labels from the previous epoch are projected to the current epoch cluster-labels space and a linear combination of the new label and the projected label is c"},"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":"2410.14242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-18T07:47:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c441073067bf3182f8c4e107631875399b7a1c712d28bd9933021871d25565c5","abstract_canon_sha256":"7dee11e1d9e5b680607238c3024bce2de074908e022f0180d0ececb7e967ef4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:29.683766Z","signature_b64":"H84b8/or+FUXgTAC4vD9BFtQ7m/FuZc5hLv4B7+c13+zXrUe4ouFkQRfN6vbxNrhWlXjbPOfjLVO4jEkEonGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eef9c7f968a6b950827a7b625df64311900056dc181cf80ecd02789df22e2a0","last_reissued_at":"2026-07-05T09:22:29.683274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:29.683274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pseudo-label Refinement for Improving Self-Supervised Learning Systems","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arif Mahmood, Wenxiong Kang, Zia-ur-Rehman","submitted_at":"2024-10-18T07:47:59Z","abstract_excerpt":"Self-supervised learning systems have gained significant attention in recent years by leveraging clustering-based pseudo-labels to provide supervision without the need for human annotations. However, the noise in these pseudo-labels caused by the clustering methods poses a challenge to the learning process leading to degraded performance. In this work, we propose a pseudo-label refinement (SLR) algorithm to address this issue. The cluster labels from the previous epoch are projected to the current epoch cluster-labels space and a linear combination of the new label and the projected label is c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14242","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/2410.14242/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":"2410.14242","created_at":"2026-07-05T09:22:29.683341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14242v1","created_at":"2026-07-05T09:22:29.683341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14242","created_at":"2026-07-05T09:22:29.683341+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3XZY74WRJVZ","created_at":"2026-07-05T09:22:29.683341+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3XZY74WRJVZKCBH","created_at":"2026-07-05T09:22:29.683341+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3XZY74W","created_at":"2026-07-05T09:22:29.683341+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/D3XZY74WRJVZKCBHU63CLX3EGE","json":"https://pith.science/pith/D3XZY74WRJVZKCBHU63CLX3EGE.json","graph_json":"https://pith.science/api/pith-number/D3XZY74WRJVZKCBHU63CLX3EGE/graph.json","events_json":"https://pith.science/api/pith-number/D3XZY74WRJVZKCBHU63CLX3EGE/events.json","paper":"https://pith.science/paper/D3XZY74W"},"agent_actions":{"view_html":"https://pith.science/pith/D3XZY74WRJVZKCBHU63CLX3EGE","download_json":"https://pith.science/pith/D3XZY74WRJVZKCBHU63CLX3EGE.json","view_paper":"https://pith.science/paper/D3XZY74W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14242&json=true","fetch_graph":"https://pith.science/api/pith-number/D3XZY74WRJVZKCBHU63CLX3EGE/graph.json","fetch_events":"https://pith.science/api/pith-number/D3XZY74WRJVZKCBHU63CLX3EGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3XZY74WRJVZKCBHU63CLX3EGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3XZY74WRJVZKCBHU63CLX3EGE/action/storage_attestation","attest_author":"https://pith.science/pith/D3XZY74WRJVZKCBHU63CLX3EGE/action/author_attestation","sign_citation":"https://pith.science/pith/D3XZY74WRJVZKCBHU63CLX3EGE/action/citation_signature","submit_replication":"https://pith.science/pith/D3XZY74WRJVZKCBHU63CLX3EGE/action/replication_record"}},"created_at":"2026-07-05T09:22:29.683341+00:00","updated_at":"2026-07-05T09:22:29.683341+00:00"}