{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7V7LK7OZIW6FBSXEB6GGMVS3P2","short_pith_number":"pith:7V7LK7OZ","schema_version":"1.0","canonical_sha256":"fd7eb57dd945bc50cae40f8c66565b7e9c2c375e2bf9a38b508ed712de94649e","source":{"kind":"arxiv","id":"2302.03264","version":1},"attestation_state":"computed","paper":{"title":"Delving Deep into Simplicity Bias for Long-Tailed Image Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anqi Xu, Faen Zhang, Peng Wang, Xiu-Shen Wei, Xuhao Sun, Yang Shen","submitted_at":"2023-02-07T05:29:38Z","abstract_excerpt":"Simplicity Bias (SB) is a phenomenon that deep neural networks tend to rely favorably on simpler predictive patterns but ignore some complex features when applied to supervised discriminative tasks. In this work, we investigate SB in long-tailed image recognition and find the tail classes suffer more severely from SB, which harms the generalization performance of such underrepresented classes. We empirically report that self-supervised learning (SSL) can mitigate SB and perform in complementary to the supervised counterpart by enriching the features extracted from tail samples and consequently"},"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":"2302.03264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-07T05:29:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d5639dd03108b3436824014a77d06e7456d90788b8fa2946f7640f5051aeb08","abstract_canon_sha256":"0050da9832529f01c3e24138fed0ec942ce334cc448350a9f62df1f332949a84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:39:35.634834Z","signature_b64":"RrkINgQMGQ453HByJPWhGHGxHyxYtTblnW5Ovz1L0R6dLcWHzVifikJPDJ3n9RF9FEZa4T28WuytcEGvBluSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd7eb57dd945bc50cae40f8c66565b7e9c2c375e2bf9a38b508ed712de94649e","last_reissued_at":"2026-07-05T05:39:35.634437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:39:35.634437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delving Deep into Simplicity Bias for Long-Tailed Image Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anqi Xu, Faen Zhang, Peng Wang, Xiu-Shen Wei, Xuhao Sun, Yang Shen","submitted_at":"2023-02-07T05:29:38Z","abstract_excerpt":"Simplicity Bias (SB) is a phenomenon that deep neural networks tend to rely favorably on simpler predictive patterns but ignore some complex features when applied to supervised discriminative tasks. In this work, we investigate SB in long-tailed image recognition and find the tail classes suffer more severely from SB, which harms the generalization performance of such underrepresented classes. We empirically report that self-supervised learning (SSL) can mitigate SB and perform in complementary to the supervised counterpart by enriching the features extracted from tail samples and consequently"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03264","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/2302.03264/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":"2302.03264","created_at":"2026-07-05T05:39:35.634488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03264v1","created_at":"2026-07-05T05:39:35.634488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03264","created_at":"2026-07-05T05:39:35.634488+00:00"},{"alias_kind":"pith_short_12","alias_value":"7V7LK7OZIW6F","created_at":"2026-07-05T05:39:35.634488+00:00"},{"alias_kind":"pith_short_16","alias_value":"7V7LK7OZIW6FBSXE","created_at":"2026-07-05T05:39:35.634488+00:00"},{"alias_kind":"pith_short_8","alias_value":"7V7LK7OZ","created_at":"2026-07-05T05:39:35.634488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09453","citing_title":"Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2","json":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2.json","graph_json":"https://pith.science/api/pith-number/7V7LK7OZIW6FBSXEB6GGMVS3P2/graph.json","events_json":"https://pith.science/api/pith-number/7V7LK7OZIW6FBSXEB6GGMVS3P2/events.json","paper":"https://pith.science/paper/7V7LK7OZ"},"agent_actions":{"view_html":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2","download_json":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2.json","view_paper":"https://pith.science/paper/7V7LK7OZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03264&json=true","fetch_graph":"https://pith.science/api/pith-number/7V7LK7OZIW6FBSXEB6GGMVS3P2/graph.json","fetch_events":"https://pith.science/api/pith-number/7V7LK7OZIW6FBSXEB6GGMVS3P2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2/action/storage_attestation","attest_author":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2/action/author_attestation","sign_citation":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2/action/citation_signature","submit_replication":"https://pith.science/pith/7V7LK7OZIW6FBSXEB6GGMVS3P2/action/replication_record"}},"created_at":"2026-07-05T05:39:35.634488+00:00","updated_at":"2026-07-05T05:39:35.634488+00:00"}