{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HOVFO5VTPOIL3BOAZAFH2CSVOP","short_pith_number":"pith:HOVFO5VT","schema_version":"1.0","canonical_sha256":"3baa5776b37b90bd85c0c80a7d0a5573ebcf466aec640442ed1af30426cc1a27","source":{"kind":"arxiv","id":"2102.06605","version":2},"attestation_state":"computed","paper":{"title":"Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bryan Hooi, Dapeng Hu, Jian Liang, Jiashi Feng, Yifan Zhang","submitted_at":"2021-02-12T16:31:24Z","abstract_excerpt":"Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative visual features that are uniformly scattered in the feature space. During deployment, the common practice is to directly fine-tune CSL models with cross-entropy, which however may not be the best strategy in practice. Although cross-entropy tends to separate inter-class features, the resulting models still have limited capability for reducing intra-class feature scattering that exists in CSL models. In this paper, we in"},"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":"2102.06605","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-02-12T16:31:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c28cfe1c1fb432d3c9aab93dd25a454aac4fc6824f194b2188bc342b67a75ecd","abstract_canon_sha256":"2e09b27858b269a0d95089eed467da99f352f62ad7094cd14f812f64d9f1541e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:33.801392Z","signature_b64":"rKlCQVIpZnO4/MWkKoqeysHycWO2RLz5qoehF/p24x6ZyojlCQ7z68TqYFnNW95+KlZLKnpdLDXka4ry4YRvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3baa5776b37b90bd85c0c80a7d0a5573ebcf466aec640442ed1af30426cc1a27","last_reissued_at":"2026-07-05T03:22:33.800909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:33.800909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bryan Hooi, Dapeng Hu, Jian Liang, Jiashi Feng, Yifan Zhang","submitted_at":"2021-02-12T16:31:24Z","abstract_excerpt":"Contrastive self-supervised learning (CSL) has attracted increasing attention for model pre-training via unlabeled data. The resulted CSL models provide instance-discriminative visual features that are uniformly scattered in the feature space. During deployment, the common practice is to directly fine-tune CSL models with cross-entropy, which however may not be the best strategy in practice. Although cross-entropy tends to separate inter-class features, the resulting models still have limited capability for reducing intra-class feature scattering that exists in CSL models. In this paper, we in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06605","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/2102.06605/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":"2102.06605","created_at":"2026-07-05T03:22:33.800983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.06605v2","created_at":"2026-07-05T03:22:33.800983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06605","created_at":"2026-07-05T03:22:33.800983+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOVFO5VTPOIL","created_at":"2026-07-05T03:22:33.800983+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOVFO5VTPOIL3BOA","created_at":"2026-07-05T03:22:33.800983+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOVFO5VT","created_at":"2026-07-05T03:22:33.800983+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/HOVFO5VTPOIL3BOAZAFH2CSVOP","json":"https://pith.science/pith/HOVFO5VTPOIL3BOAZAFH2CSVOP.json","graph_json":"https://pith.science/api/pith-number/HOVFO5VTPOIL3BOAZAFH2CSVOP/graph.json","events_json":"https://pith.science/api/pith-number/HOVFO5VTPOIL3BOAZAFH2CSVOP/events.json","paper":"https://pith.science/paper/HOVFO5VT"},"agent_actions":{"view_html":"https://pith.science/pith/HOVFO5VTPOIL3BOAZAFH2CSVOP","download_json":"https://pith.science/pith/HOVFO5VTPOIL3BOAZAFH2CSVOP.json","view_paper":"https://pith.science/paper/HOVFO5VT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.06605&json=true","fetch_graph":"https://pith.science/api/pith-number/HOVFO5VTPOIL3BOAZAFH2CSVOP/graph.json","fetch_events":"https://pith.science/api/pith-number/HOVFO5VTPOIL3BOAZAFH2CSVOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOVFO5VTPOIL3BOAZAFH2CSVOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOVFO5VTPOIL3BOAZAFH2CSVOP/action/storage_attestation","attest_author":"https://pith.science/pith/HOVFO5VTPOIL3BOAZAFH2CSVOP/action/author_attestation","sign_citation":"https://pith.science/pith/HOVFO5VTPOIL3BOAZAFH2CSVOP/action/citation_signature","submit_replication":"https://pith.science/pith/HOVFO5VTPOIL3BOAZAFH2CSVOP/action/replication_record"}},"created_at":"2026-07-05T03:22:33.800983+00:00","updated_at":"2026-07-05T03:22:33.800983+00:00"}