{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JOZJLEDKHY3T7CL3OBT4EUMHVU","short_pith_number":"pith:JOZJLEDK","schema_version":"1.0","canonical_sha256":"4bb295906a3e373f897b7067c25187ad04be0d229415ba59126f35f53c204d31","source":{"kind":"arxiv","id":"2311.05054","version":1},"attestation_state":"computed","paper":{"title":"Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Li, Hao Zou, Jiashuo Liu, Jiayun Wu, Peng Cui, Tianyu Wang","submitted_at":"2023-11-08T23:33:39Z","abstract_excerpt":"Machine learning algorithms minimizing average risk are susceptible to distributional shifts. Distributionally Robust Optimization (DRO) addresses this issue by optimizing the worst-case risk within an uncertainty set. However, DRO suffers from over-pessimism, leading to low-confidence predictions, poor parameter estimations as well as poor generalization. In this work, we conduct a theoretical analysis of a probable root cause of over-pessimism: excessive focus on noisy samples. To alleviate the impact of noise, we incorporate data geometry into calibration terms in DRO, resulting in our nove"},"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":"2311.05054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-08T23:33:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"751e2d21dadc46e64dddb69dfd54ce21eddf4830f0eaf6aad99f5c9d5fde082a","abstract_canon_sha256":"577d5eb7445bc6aa3b135df52bb8b88211672f2d3b1b17f83f951bf76e14e731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:54.028020Z","signature_b64":"7tJifyfS9buKXWzdt8mLVal/jZrg/B/R8KCFnfXwKs9vzldv/MHC1GYirR8/YD3cXQ2nqvUV1F+2IOKcIy/MDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bb295906a3e373f897b7067c25187ad04be0d229415ba59126f35f53c204d31","last_reissued_at":"2026-07-05T07:10:54.027555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:54.027555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Li, Hao Zou, Jiashuo Liu, Jiayun Wu, Peng Cui, Tianyu Wang","submitted_at":"2023-11-08T23:33:39Z","abstract_excerpt":"Machine learning algorithms minimizing average risk are susceptible to distributional shifts. Distributionally Robust Optimization (DRO) addresses this issue by optimizing the worst-case risk within an uncertainty set. However, DRO suffers from over-pessimism, leading to low-confidence predictions, poor parameter estimations as well as poor generalization. In this work, we conduct a theoretical analysis of a probable root cause of over-pessimism: excessive focus on noisy samples. To alleviate the impact of noise, we incorporate data geometry into calibration terms in DRO, resulting in our nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05054","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/2311.05054/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":"2311.05054","created_at":"2026-07-05T07:10:54.027612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.05054v1","created_at":"2026-07-05T07:10:54.027612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05054","created_at":"2026-07-05T07:10:54.027612+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOZJLEDKHY3T","created_at":"2026-07-05T07:10:54.027612+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOZJLEDKHY3T7CL3","created_at":"2026-07-05T07:10:54.027612+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOZJLEDK","created_at":"2026-07-05T07:10:54.027612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15555","citing_title":"Distributionally Robust Graph Out-of-Distribution Recommendation via Diffusion Model","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU","json":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU.json","graph_json":"https://pith.science/api/pith-number/JOZJLEDKHY3T7CL3OBT4EUMHVU/graph.json","events_json":"https://pith.science/api/pith-number/JOZJLEDKHY3T7CL3OBT4EUMHVU/events.json","paper":"https://pith.science/paper/JOZJLEDK"},"agent_actions":{"view_html":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU","download_json":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU.json","view_paper":"https://pith.science/paper/JOZJLEDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.05054&json=true","fetch_graph":"https://pith.science/api/pith-number/JOZJLEDKHY3T7CL3OBT4EUMHVU/graph.json","fetch_events":"https://pith.science/api/pith-number/JOZJLEDKHY3T7CL3OBT4EUMHVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU/action/storage_attestation","attest_author":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU/action/author_attestation","sign_citation":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU/action/citation_signature","submit_replication":"https://pith.science/pith/JOZJLEDKHY3T7CL3OBT4EUMHVU/action/replication_record"}},"created_at":"2026-07-05T07:10:54.027612+00:00","updated_at":"2026-07-05T07:10:54.027612+00:00"}