{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4ZROV4ALCSKAPBOQL2NXSDHN2K","short_pith_number":"pith:4ZROV4AL","schema_version":"1.0","canonical_sha256":"e662eaf00b14940785d05e9b790cedd28a49fc774551562646e0d08366aede9e","source":{"kind":"arxiv","id":"2505.15212","version":1},"attestation_state":"computed","paper":{"title":"Group Distributionally Robust Optimization with Flexible Sample Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Dingzhi Yu, Haipeng Luo, Haomin Bai, Lijun Zhang, Shuai Li","submitted_at":"2025-05-21T07:41:16Z","abstract_excerpt":"Group distributionally robust optimization (GDRO) aims to develop models that perform well across $m$ distributions simultaneously. Existing GDRO algorithms can only process a fixed number of samples per iteration, either 1 or $m$, and therefore can not support scenarios where the sample size varies dynamically. To address this limitation, we investigate GDRO with flexible sample queries and cast it as a two-player game: one player solves an online convex optimization problem, while the other tackles a prediction with limited advice (PLA) problem. Within such a game, we propose a novel PLA alg"},"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":"2505.15212","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T07:41:16Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"6cc633a5d2b4f2858bb266d357d6dd4b3bf967c4165108a4dde09dcd252b871f","abstract_canon_sha256":"5173cfdb1fc7b0b88979b13d267fdba6c92528d0ad5ee002583d548cec2dee34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:42.113584Z","signature_b64":"k8b+9OA+EGZn1SQ7pHGOsRGdRFf9E6VHQCWDceWGiPmTau3/rfHOJzKmidVQhHSTqOxYYNFcKdloo8MCo5DnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e662eaf00b14940785d05e9b790cedd28a49fc774551562646e0d08366aede9e","last_reissued_at":"2026-07-05T11:06:42.113129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:42.113129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group Distributionally Robust Optimization with Flexible Sample Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Dingzhi Yu, Haipeng Luo, Haomin Bai, Lijun Zhang, Shuai Li","submitted_at":"2025-05-21T07:41:16Z","abstract_excerpt":"Group distributionally robust optimization (GDRO) aims to develop models that perform well across $m$ distributions simultaneously. Existing GDRO algorithms can only process a fixed number of samples per iteration, either 1 or $m$, and therefore can not support scenarios where the sample size varies dynamically. To address this limitation, we investigate GDRO with flexible sample queries and cast it as a two-player game: one player solves an online convex optimization problem, while the other tackles a prediction with limited advice (PLA) problem. Within such a game, we propose a novel PLA alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15212","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/2505.15212/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":"2505.15212","created_at":"2026-07-05T11:06:42.113186+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15212v1","created_at":"2026-07-05T11:06:42.113186+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15212","created_at":"2026-07-05T11:06:42.113186+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZROV4ALCSKA","created_at":"2026-07-05T11:06:42.113186+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZROV4ALCSKAPBOQ","created_at":"2026-07-05T11:06:42.113186+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZROV4AL","created_at":"2026-07-05T11:06:42.113186+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15416","citing_title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K","json":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K.json","graph_json":"https://pith.science/api/pith-number/4ZROV4ALCSKAPBOQL2NXSDHN2K/graph.json","events_json":"https://pith.science/api/pith-number/4ZROV4ALCSKAPBOQL2NXSDHN2K/events.json","paper":"https://pith.science/paper/4ZROV4AL"},"agent_actions":{"view_html":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K","download_json":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K.json","view_paper":"https://pith.science/paper/4ZROV4AL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15212&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZROV4ALCSKAPBOQL2NXSDHN2K/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZROV4ALCSKAPBOQL2NXSDHN2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K/action/storage_attestation","attest_author":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K/action/author_attestation","sign_citation":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K/action/citation_signature","submit_replication":"https://pith.science/pith/4ZROV4ALCSKAPBOQL2NXSDHN2K/action/replication_record"}},"created_at":"2026-07-05T11:06:42.113186+00:00","updated_at":"2026-07-05T11:06:42.113186+00:00"}