{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:37HRDZWJWDMC7BCGWESGU7Q3GM","short_pith_number":"pith:37HRDZWJ","schema_version":"1.0","canonical_sha256":"dfcf11e6c9b0d82f8446b1246a7e1b33379b581781424d0c8e78cc557b4954f4","source":{"kind":"arxiv","id":"2605.30089","version":1},"attestation_state":"computed","paper":{"title":"Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowei He, Hanrong Zhang, Philip S.Yu, Xue (Steve) Liu, Yankai Chen","submitted_at":"2026-05-28T15:35:04Z","abstract_excerpt":"Standard Set Representation Learning methods typically excel on curated data but often overlook the challenge of inference-time element corruption. This refers to scenarios where deployed models encounter element-level degradations, such as outliers or missing components, that may distort set representation and degrade performance. We propose SW-DRSO, a distributionally robust optimization framework tailored for sets. Rather than minimizing loss solely on observed training data, SW-DRSO optimizes a tractable surrogate of the worst-case expected loss over a family of plausible inference-time va"},"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":"2605.30089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T15:35:04Z","cross_cats_sorted":[],"title_canon_sha256":"55a7657f8d4fddadb7f97fc673c5d2a5f1f27bce565a7440127c8e136c37c5c6","abstract_canon_sha256":"83ffae20dbf3ebc5a240378809264860c56bb939cc1a1d1f06c8b1c09371ef08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:09.637747Z","signature_b64":"tVqVkvPMKPZSRYwa9323fJerkmacNWbZ5oxdrJoENX74YGW/ed5xeXeEL4VttCdLnGpUKTxaHSBIgChbWplkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfcf11e6c9b0d82f8446b1246a7e1b33379b581781424d0c8e78cc557b4954f4","last_reissued_at":"2026-05-29T02:06:09.637426Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:09.637426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bowei He, Hanrong Zhang, Philip S.Yu, Xue (Steve) Liu, Yankai Chen","submitted_at":"2026-05-28T15:35:04Z","abstract_excerpt":"Standard Set Representation Learning methods typically excel on curated data but often overlook the challenge of inference-time element corruption. This refers to scenarios where deployed models encounter element-level degradations, such as outliers or missing components, that may distort set representation and degrade performance. We propose SW-DRSO, a distributionally robust optimization framework tailored for sets. Rather than minimizing loss solely on observed training data, SW-DRSO optimizes a tractable surrogate of the worst-case expected loss over a family of plausible inference-time va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30089","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/2605.30089/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":"2605.30089","created_at":"2026-05-29T02:06:09.637480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30089v1","created_at":"2026-05-29T02:06:09.637480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30089","created_at":"2026-05-29T02:06:09.637480+00:00"},{"alias_kind":"pith_short_12","alias_value":"37HRDZWJWDMC","created_at":"2026-05-29T02:06:09.637480+00:00"},{"alias_kind":"pith_short_16","alias_value":"37HRDZWJWDMC7BCG","created_at":"2026-05-29T02:06:09.637480+00:00"},{"alias_kind":"pith_short_8","alias_value":"37HRDZWJ","created_at":"2026-05-29T02:06:09.637480+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/37HRDZWJWDMC7BCGWESGU7Q3GM","json":"https://pith.science/pith/37HRDZWJWDMC7BCGWESGU7Q3GM.json","graph_json":"https://pith.science/api/pith-number/37HRDZWJWDMC7BCGWESGU7Q3GM/graph.json","events_json":"https://pith.science/api/pith-number/37HRDZWJWDMC7BCGWESGU7Q3GM/events.json","paper":"https://pith.science/paper/37HRDZWJ"},"agent_actions":{"view_html":"https://pith.science/pith/37HRDZWJWDMC7BCGWESGU7Q3GM","download_json":"https://pith.science/pith/37HRDZWJWDMC7BCGWESGU7Q3GM.json","view_paper":"https://pith.science/paper/37HRDZWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30089&json=true","fetch_graph":"https://pith.science/api/pith-number/37HRDZWJWDMC7BCGWESGU7Q3GM/graph.json","fetch_events":"https://pith.science/api/pith-number/37HRDZWJWDMC7BCGWESGU7Q3GM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37HRDZWJWDMC7BCGWESGU7Q3GM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37HRDZWJWDMC7BCGWESGU7Q3GM/action/storage_attestation","attest_author":"https://pith.science/pith/37HRDZWJWDMC7BCGWESGU7Q3GM/action/author_attestation","sign_citation":"https://pith.science/pith/37HRDZWJWDMC7BCGWESGU7Q3GM/action/citation_signature","submit_replication":"https://pith.science/pith/37HRDZWJWDMC7BCGWESGU7Q3GM/action/replication_record"}},"created_at":"2026-05-29T02:06:09.637480+00:00","updated_at":"2026-05-29T02:06:09.637480+00:00"}