{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MQBJMK2YQRPCRHYYHDIUNU3T7I","short_pith_number":"pith:MQBJMK2Y","schema_version":"1.0","canonical_sha256":"6402962b58845e289f1838d146d373fa352b704b906e2a14477f24cb831c25f8","source":{"kind":"arxiv","id":"2502.02544","version":1},"attestation_state":"computed","paper":{"title":"Addressing Label Shift in Distributed Learning via Entropy Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Ramezani-Kebrya, Changkyu Choi, Volkan Cevher, Xiangcheng Cao, Zhiyuan Wu","submitted_at":"2025-02-04T18:14:27Z","abstract_excerpt":"We address the challenge of minimizing true risk in multi-node distributed learning. These systems are frequently exposed to both inter-node and intra-node label shifts, which present a critical obstacle to effectively optimizing model performance while ensuring that data remains confined to each node. To tackle this, we propose the Versatile Robust Label Shift (VRLS) method, which enhances the maximum likelihood estimation of the test-to-train label density ratio. VRLS incorporates Shannon entropy-based regularization and adjusts the density ratio during training to better handle label shifts"},"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":"2502.02544","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T18:14:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"69240c365ef7f906b8dfadf9241a8affe379df48997d35144ca387e907324bae","abstract_canon_sha256":"8884382cb43c81629b6fa69fc3e947b149d0d3ab58a29a23c16aec98aafd278a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:29.952908Z","signature_b64":"akUjKodESaOolh8WRF4AD2A0fOKTnDVfCbnOOAWcNxaUIOEkta2xjLeVL39TKdaIhasxDtk28HXJV7vzlvzKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6402962b58845e289f1838d146d373fa352b704b906e2a14477f24cb831c25f8","last_reissued_at":"2026-07-05T10:09:29.952496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:29.952496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Addressing Label Shift in Distributed Learning via Entropy Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Ramezani-Kebrya, Changkyu Choi, Volkan Cevher, Xiangcheng Cao, Zhiyuan Wu","submitted_at":"2025-02-04T18:14:27Z","abstract_excerpt":"We address the challenge of minimizing true risk in multi-node distributed learning. These systems are frequently exposed to both inter-node and intra-node label shifts, which present a critical obstacle to effectively optimizing model performance while ensuring that data remains confined to each node. To tackle this, we propose the Versatile Robust Label Shift (VRLS) method, which enhances the maximum likelihood estimation of the test-to-train label density ratio. VRLS incorporates Shannon entropy-based regularization and adjusts the density ratio during training to better handle label shifts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02544","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/2502.02544/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":"2502.02544","created_at":"2026-07-05T10:09:29.952551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02544v1","created_at":"2026-07-05T10:09:29.952551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02544","created_at":"2026-07-05T10:09:29.952551+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQBJMK2YQRPC","created_at":"2026-07-05T10:09:29.952551+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQBJMK2YQRPCRHYY","created_at":"2026-07-05T10:09:29.952551+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQBJMK2Y","created_at":"2026-07-05T10:09:29.952551+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/MQBJMK2YQRPCRHYYHDIUNU3T7I","json":"https://pith.science/pith/MQBJMK2YQRPCRHYYHDIUNU3T7I.json","graph_json":"https://pith.science/api/pith-number/MQBJMK2YQRPCRHYYHDIUNU3T7I/graph.json","events_json":"https://pith.science/api/pith-number/MQBJMK2YQRPCRHYYHDIUNU3T7I/events.json","paper":"https://pith.science/paper/MQBJMK2Y"},"agent_actions":{"view_html":"https://pith.science/pith/MQBJMK2YQRPCRHYYHDIUNU3T7I","download_json":"https://pith.science/pith/MQBJMK2YQRPCRHYYHDIUNU3T7I.json","view_paper":"https://pith.science/paper/MQBJMK2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02544&json=true","fetch_graph":"https://pith.science/api/pith-number/MQBJMK2YQRPCRHYYHDIUNU3T7I/graph.json","fetch_events":"https://pith.science/api/pith-number/MQBJMK2YQRPCRHYYHDIUNU3T7I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQBJMK2YQRPCRHYYHDIUNU3T7I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQBJMK2YQRPCRHYYHDIUNU3T7I/action/storage_attestation","attest_author":"https://pith.science/pith/MQBJMK2YQRPCRHYYHDIUNU3T7I/action/author_attestation","sign_citation":"https://pith.science/pith/MQBJMK2YQRPCRHYYHDIUNU3T7I/action/citation_signature","submit_replication":"https://pith.science/pith/MQBJMK2YQRPCRHYYHDIUNU3T7I/action/replication_record"}},"created_at":"2026-07-05T10:09:29.952551+00:00","updated_at":"2026-07-05T10:09:29.952551+00:00"}