{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VATOTHTFI6B7J23JHEPP2C63DK","short_pith_number":"pith:VATOTHTF","schema_version":"1.0","canonical_sha256":"a826e99e654783f4eb69391efd0bdb1abae92adadf76a79be715f90974dbe34d","source":{"kind":"arxiv","id":"2503.07315","version":1},"attestation_state":"computed","paper":{"title":"Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bryan Kian Hsiang Low, Jingtan Wang, Pang Wei Koh, Rui Qiao, Zhaoxuan Wu","submitted_at":"2025-03-10T13:34:18Z","abstract_excerpt":"Machine learning models often have uneven performance among subpopulations (a.k.a., groups) in the data distributions. This poses a significant challenge for the models to generalize when the proportions of the groups shift during deployment. To improve robustness to such shifts, existing approaches have developed strategies that train models or perform hyperparameter tuning using the group-labeled data to minimize the worst-case loss over groups. However, a non-trivial amount of high-quality labels is often required to obtain noticeable improvements. Given the costliness of the labels, we pro"},"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":"2503.07315","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-10T13:34:18Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"158c9d68704e22b329096ce4f8d113c6294925a526e41027fc7f468ddd71dcbc","abstract_canon_sha256":"83614ce68135687f47636891b05b9c136306934ec16d498a08ba3bd31ba190c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:53.742055Z","signature_b64":"Kz+T9JArEt4Dy45Ok5xYo1/XTIttN1wrLofahX/CJdbyVTKMq7RknWOlZA8SF5kQrCPbYmGDcEBp/y1ezBRQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a826e99e654783f4eb69391efd0bdb1abae92adadf76a79be715f90974dbe34d","last_reissued_at":"2026-07-05T10:27:53.741044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:53.741044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bryan Kian Hsiang Low, Jingtan Wang, Pang Wei Koh, Rui Qiao, Zhaoxuan Wu","submitted_at":"2025-03-10T13:34:18Z","abstract_excerpt":"Machine learning models often have uneven performance among subpopulations (a.k.a., groups) in the data distributions. This poses a significant challenge for the models to generalize when the proportions of the groups shift during deployment. To improve robustness to such shifts, existing approaches have developed strategies that train models or perform hyperparameter tuning using the group-labeled data to minimize the worst-case loss over groups. However, a non-trivial amount of high-quality labels is often required to obtain noticeable improvements. Given the costliness of the labels, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07315","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/2503.07315/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":"2503.07315","created_at":"2026-07-05T10:27:53.741184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07315v1","created_at":"2026-07-05T10:27:53.741184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07315","created_at":"2026-07-05T10:27:53.741184+00:00"},{"alias_kind":"pith_short_12","alias_value":"VATOTHTFI6B7","created_at":"2026-07-05T10:27:53.741184+00:00"},{"alias_kind":"pith_short_16","alias_value":"VATOTHTFI6B7J23J","created_at":"2026-07-05T10:27:53.741184+00:00"},{"alias_kind":"pith_short_8","alias_value":"VATOTHTF","created_at":"2026-07-05T10:27:53.741184+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/VATOTHTFI6B7J23JHEPP2C63DK","json":"https://pith.science/pith/VATOTHTFI6B7J23JHEPP2C63DK.json","graph_json":"https://pith.science/api/pith-number/VATOTHTFI6B7J23JHEPP2C63DK/graph.json","events_json":"https://pith.science/api/pith-number/VATOTHTFI6B7J23JHEPP2C63DK/events.json","paper":"https://pith.science/paper/VATOTHTF"},"agent_actions":{"view_html":"https://pith.science/pith/VATOTHTFI6B7J23JHEPP2C63DK","download_json":"https://pith.science/pith/VATOTHTFI6B7J23JHEPP2C63DK.json","view_paper":"https://pith.science/paper/VATOTHTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07315&json=true","fetch_graph":"https://pith.science/api/pith-number/VATOTHTFI6B7J23JHEPP2C63DK/graph.json","fetch_events":"https://pith.science/api/pith-number/VATOTHTFI6B7J23JHEPP2C63DK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VATOTHTFI6B7J23JHEPP2C63DK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VATOTHTFI6B7J23JHEPP2C63DK/action/storage_attestation","attest_author":"https://pith.science/pith/VATOTHTFI6B7J23JHEPP2C63DK/action/author_attestation","sign_citation":"https://pith.science/pith/VATOTHTFI6B7J23JHEPP2C63DK/action/citation_signature","submit_replication":"https://pith.science/pith/VATOTHTFI6B7J23JHEPP2C63DK/action/replication_record"}},"created_at":"2026-07-05T10:27:53.741184+00:00","updated_at":"2026-07-05T10:27:53.741184+00:00"}