{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BLSGIBUJCYKZKDLWOXNCFUISTJ","short_pith_number":"pith:BLSGIBUJ","schema_version":"1.0","canonical_sha256":"0ae46406891615950d7675da22d1129a6a5aa270b45d72b93930a7089659fccf","source":{"kind":"arxiv","id":"2502.09850","version":1},"attestation_state":"computed","paper":{"title":"Elastic Representation: Mitigating Spurious Correlations for Group Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qi Lei, Quan Zhang, Tao Wen, Zihan Wang","submitted_at":"2025-02-14T01:25:27Z","abstract_excerpt":"Deep learning models can suffer from severe performance degradation when relying on spurious correlations between input features and labels, making the models perform well on training data but have poor prediction accuracy for minority groups. This problem arises especially when training data are limited or imbalanced. While most prior work focuses on learning invariant features (with consistent correlations to y), it overlooks the potential harm of spurious correlations between features. We hereby propose Elastic Representation (ElRep) to learn features by imposing Nuclear- and Frobenius-norm"},"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":"2502.09850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T01:25:27Z","cross_cats_sorted":[],"title_canon_sha256":"8306f6161fe7d620a8c3e6be836949315f85bf99c2323c5dd66fba26170fecb7","abstract_canon_sha256":"fb159d780b05967c068a32738dab87a6999dbb6f015df0e9af37b11639c16e15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:13.307756Z","signature_b64":"FRz7av/9OumfLCcGFCQy0N/N55uGPqz9wvLfJLJSuICu18Zgs/29cUaBgmYamYZmaluvaXPhKfd2EbjQo/E0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ae46406891615950d7675da22d1129a6a5aa270b45d72b93930a7089659fccf","last_reissued_at":"2026-07-05T10:14:13.307282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:13.307282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Elastic Representation: Mitigating Spurious Correlations for Group Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qi Lei, Quan Zhang, Tao Wen, Zihan Wang","submitted_at":"2025-02-14T01:25:27Z","abstract_excerpt":"Deep learning models can suffer from severe performance degradation when relying on spurious correlations between input features and labels, making the models perform well on training data but have poor prediction accuracy for minority groups. This problem arises especially when training data are limited or imbalanced. While most prior work focuses on learning invariant features (with consistent correlations to y), it overlooks the potential harm of spurious correlations between features. We hereby propose Elastic Representation (ElRep) to learn features by imposing Nuclear- and Frobenius-norm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09850","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/2502.09850/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":"2502.09850","created_at":"2026-07-05T10:14:13.307336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09850v1","created_at":"2026-07-05T10:14:13.307336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09850","created_at":"2026-07-05T10:14:13.307336+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLSGIBUJCYKZ","created_at":"2026-07-05T10:14:13.307336+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLSGIBUJCYKZKDLW","created_at":"2026-07-05T10:14:13.307336+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLSGIBUJ","created_at":"2026-07-05T10:14:13.307336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24161","citing_title":"Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ","json":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ.json","graph_json":"https://pith.science/api/pith-number/BLSGIBUJCYKZKDLWOXNCFUISTJ/graph.json","events_json":"https://pith.science/api/pith-number/BLSGIBUJCYKZKDLWOXNCFUISTJ/events.json","paper":"https://pith.science/paper/BLSGIBUJ"},"agent_actions":{"view_html":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ","download_json":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ.json","view_paper":"https://pith.science/paper/BLSGIBUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09850&json=true","fetch_graph":"https://pith.science/api/pith-number/BLSGIBUJCYKZKDLWOXNCFUISTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BLSGIBUJCYKZKDLWOXNCFUISTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ/action/storage_attestation","attest_author":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ/action/author_attestation","sign_citation":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ/action/citation_signature","submit_replication":"https://pith.science/pith/BLSGIBUJCYKZKDLWOXNCFUISTJ/action/replication_record"}},"created_at":"2026-07-05T10:14:13.307336+00:00","updated_at":"2026-07-05T10:14:13.307336+00:00"}