{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3DD6T6BT7GDMYWZ47QZRGPLTW4","short_pith_number":"pith:3DD6T6BT","schema_version":"1.0","canonical_sha256":"d8c7e9f833f986cc5b3cfc33133d73b71d439a87f76b1bdfb776892387f67af5","source":{"kind":"arxiv","id":"2301.13565","version":2},"attestation_state":"computed","paper":{"title":"Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haowei Wang, Jean Honorio, Shixiong Wang, Xinke Li","submitted_at":"2023-01-31T11:33:18Z","abstract_excerpt":"Trustworthy machine learning aims at combating distributional uncertainties in training data distributions compared to population distributions. Typical treatment frameworks include the Bayesian approach, (min-max) distributionally robust optimization (DRO), and regularization. However, three issues have to be raised: 1) the prior distribution in the Bayesian method and the regularizer in the regularization method are difficult to specify; 2) the DRO method tends to be overly conservative; 3) all the three methods are biased estimators of the true optimal cost. This paper studies a new framewo"},"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":"2301.13565","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-31T11:33:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4124c3adc7e9c2d268307cc9a5250263f74a93bdc19af5667225e6edc341778c","abstract_canon_sha256":"0e46eb62989f3f284873ca18fffa2057399943d97db59dbd706142e8d84198e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:24.803079Z","signature_b64":"abQGf6RX9jHOGcLIWG211+9ZXJQB5Tra/3u0z201GaluvPZSJX+YZCIBlN6BemzbusqYNH0q/e9Kx4PXh8bQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8c7e9f833f986cc5b3cfc33133d73b71d439a87f76b1bdfb776892387f67af5","last_reissued_at":"2026-07-05T10:57:24.802556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:24.802556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Haowei Wang, Jean Honorio, Shixiong Wang, Xinke Li","submitted_at":"2023-01-31T11:33:18Z","abstract_excerpt":"Trustworthy machine learning aims at combating distributional uncertainties in training data distributions compared to population distributions. Typical treatment frameworks include the Bayesian approach, (min-max) distributionally robust optimization (DRO), and regularization. However, three issues have to be raised: 1) the prior distribution in the Bayesian method and the regularizer in the regularization method are difficult to specify; 2) the DRO method tends to be overly conservative; 3) all the three methods are biased estimators of the true optimal cost. This paper studies a new framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13565","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/2301.13565/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":"2301.13565","created_at":"2026-07-05T10:57:24.802628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13565v2","created_at":"2026-07-05T10:57:24.802628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13565","created_at":"2026-07-05T10:57:24.802628+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DD6T6BT7GDM","created_at":"2026-07-05T10:57:24.802628+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DD6T6BT7GDMYWZ4","created_at":"2026-07-05T10:57:24.802628+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DD6T6BT","created_at":"2026-07-05T10:57:24.802628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16829","citing_title":"Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4","json":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4.json","graph_json":"https://pith.science/api/pith-number/3DD6T6BT7GDMYWZ47QZRGPLTW4/graph.json","events_json":"https://pith.science/api/pith-number/3DD6T6BT7GDMYWZ47QZRGPLTW4/events.json","paper":"https://pith.science/paper/3DD6T6BT"},"agent_actions":{"view_html":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4","download_json":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4.json","view_paper":"https://pith.science/paper/3DD6T6BT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13565&json=true","fetch_graph":"https://pith.science/api/pith-number/3DD6T6BT7GDMYWZ47QZRGPLTW4/graph.json","fetch_events":"https://pith.science/api/pith-number/3DD6T6BT7GDMYWZ47QZRGPLTW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4/action/storage_attestation","attest_author":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4/action/author_attestation","sign_citation":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4/action/citation_signature","submit_replication":"https://pith.science/pith/3DD6T6BT7GDMYWZ47QZRGPLTW4/action/replication_record"}},"created_at":"2026-07-05T10:57:24.802628+00:00","updated_at":"2026-07-05T10:57:24.802628+00:00"}