{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4T4HNENRVLW5MCE6UTL2VY4R76","short_pith_number":"pith:4T4HNENR","schema_version":"1.0","canonical_sha256":"e4f87691b1aaedd6089ea4d7aae391ff96171d06be012630d2318ddfa9703739","source":{"kind":"arxiv","id":"2311.16361","version":2},"attestation_state":"computed","paper":{"title":"Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlos Fernandez-Granda, Narges Razavian, Sheng Liu, Weicheng Zhu","submitted_at":"2023-11-27T22:52:45Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. The data representations are able to capture many underlying attributes of data, and be useful in downstream prediction tasks. In real-world settings, spurious correlations between some attributes (e.g. race, gender and age) and labels for downstream tasks often exist, e.g. cancer is usually more prevalent among elderly patients. In this paper, we investigate SSL in the presence of spurious correlations and show that the SSL training loss can be minimized by capturing only "},"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":"2311.16361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-27T22:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"36651067c761c971efe6d37d8c95d7e949e8c130d19d63f716cea49600884432","abstract_canon_sha256":"94d2acba1a6deb4dbbb26fe4a5c263dfb3b0d9f62771756741e8dfa458948c42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:32.868803Z","signature_b64":"CIr2S5v+IeGgyhIdRkzRVjZdICvH3/pMdryJ1UjOyql635/q1DA3STdUn9DLlwYAfdbaMpHZ1tQsVDGaNzsBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4f87691b1aaedd6089ea4d7aae391ff96171d06be012630d2318ddfa9703739","last_reissued_at":"2026-07-05T07:18:32.868343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:32.868343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlos Fernandez-Granda, Narges Razavian, Sheng Liu, Weicheng Zhu","submitted_at":"2023-11-27T22:52:45Z","abstract_excerpt":"Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. The data representations are able to capture many underlying attributes of data, and be useful in downstream prediction tasks. In real-world settings, spurious correlations between some attributes (e.g. race, gender and age) and labels for downstream tasks often exist, e.g. cancer is usually more prevalent among elderly patients. In this paper, we investigate SSL in the presence of spurious correlations and show that the SSL training loss can be minimized by capturing only "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16361","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/2311.16361/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":"2311.16361","created_at":"2026-07-05T07:18:32.868401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16361v2","created_at":"2026-07-05T07:18:32.868401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16361","created_at":"2026-07-05T07:18:32.868401+00:00"},{"alias_kind":"pith_short_12","alias_value":"4T4HNENRVLW5","created_at":"2026-07-05T07:18:32.868401+00:00"},{"alias_kind":"pith_short_16","alias_value":"4T4HNENRVLW5MCE6","created_at":"2026-07-05T07:18:32.868401+00:00"},{"alias_kind":"pith_short_8","alias_value":"4T4HNENR","created_at":"2026-07-05T07:18:32.868401+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/4T4HNENRVLW5MCE6UTL2VY4R76","json":"https://pith.science/pith/4T4HNENRVLW5MCE6UTL2VY4R76.json","graph_json":"https://pith.science/api/pith-number/4T4HNENRVLW5MCE6UTL2VY4R76/graph.json","events_json":"https://pith.science/api/pith-number/4T4HNENRVLW5MCE6UTL2VY4R76/events.json","paper":"https://pith.science/paper/4T4HNENR"},"agent_actions":{"view_html":"https://pith.science/pith/4T4HNENRVLW5MCE6UTL2VY4R76","download_json":"https://pith.science/pith/4T4HNENRVLW5MCE6UTL2VY4R76.json","view_paper":"https://pith.science/paper/4T4HNENR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16361&json=true","fetch_graph":"https://pith.science/api/pith-number/4T4HNENRVLW5MCE6UTL2VY4R76/graph.json","fetch_events":"https://pith.science/api/pith-number/4T4HNENRVLW5MCE6UTL2VY4R76/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4T4HNENRVLW5MCE6UTL2VY4R76/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4T4HNENRVLW5MCE6UTL2VY4R76/action/storage_attestation","attest_author":"https://pith.science/pith/4T4HNENRVLW5MCE6UTL2VY4R76/action/author_attestation","sign_citation":"https://pith.science/pith/4T4HNENRVLW5MCE6UTL2VY4R76/action/citation_signature","submit_replication":"https://pith.science/pith/4T4HNENRVLW5MCE6UTL2VY4R76/action/replication_record"}},"created_at":"2026-07-05T07:18:32.868401+00:00","updated_at":"2026-07-05T07:18:32.868401+00:00"}