{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HGZURVAOREN5IGAVVNOCZHGF3M","short_pith_number":"pith:HGZURVAO","schema_version":"1.0","canonical_sha256":"39b348d40e891bd41815ab5c2c9cc5db1162b8d29a3cd81c7c69d2ffc316d33a","source":{"kind":"arxiv","id":"2607.08493","version":1},"attestation_state":"computed","paper":{"title":"Ensemble Diversity Optimization for Subjective Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"N. R. Abeynayake, Xia Cui, Ziyi Huang","submitted_at":"2026-07-09T13:53:02Z","abstract_excerpt":"Subjective NLP tasks often exhibit systematic annotator disagreement, requiring models that represent uncertainty rather than collapse it. We introduce Ensemble Diversity Optimization (EDO), a prediction-space framework that jointly optimizes ensemble weights, effective cardinality, and calibration through a unified differentiable objective. EDO learns ensemble composition and size end-to-end via Gumbel-Softmax relaxation and incorporates a signed diversity regularizer, tuned on validation data, to steer optimization toward either preserving or suppressing disagreement. This regularization pre"},"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":"2607.08493","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T13:53:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4424a4365c45d7a3ea7303bc8cfa367ce9a5a514f89f7180a96e9df5060d018f","abstract_canon_sha256":"fd9f65e1e61110236b59fa1155d3295df87eec165eec9192c13629f0eff9e3ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:52.075731Z","signature_b64":"ledwpmOpkRj5TLKKGxcgQ7Izdk9XWpecpMy+pOg3803YquLfqyG7putZJayi3Ckd8M4QZxJ+Kq9jn6wNc4pDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39b348d40e891bd41815ab5c2c9cc5db1162b8d29a3cd81c7c69d2ffc316d33a","last_reissued_at":"2026-07-10T01:19:52.075340Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:52.075340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble Diversity Optimization for Subjective Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"N. R. Abeynayake, Xia Cui, Ziyi Huang","submitted_at":"2026-07-09T13:53:02Z","abstract_excerpt":"Subjective NLP tasks often exhibit systematic annotator disagreement, requiring models that represent uncertainty rather than collapse it. We introduce Ensemble Diversity Optimization (EDO), a prediction-space framework that jointly optimizes ensemble weights, effective cardinality, and calibration through a unified differentiable objective. EDO learns ensemble composition and size end-to-end via Gumbel-Softmax relaxation and incorporates a signed diversity regularizer, tuned on validation data, to steer optimization toward either preserving or suppressing disagreement. This regularization pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08493","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/2607.08493/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":"2607.08493","created_at":"2026-07-10T01:19:52.075405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08493v1","created_at":"2026-07-10T01:19:52.075405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08493","created_at":"2026-07-10T01:19:52.075405+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGZURVAOREN5","created_at":"2026-07-10T01:19:52.075405+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGZURVAOREN5IGAV","created_at":"2026-07-10T01:19:52.075405+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGZURVAO","created_at":"2026-07-10T01:19:52.075405+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/HGZURVAOREN5IGAVVNOCZHGF3M","json":"https://pith.science/pith/HGZURVAOREN5IGAVVNOCZHGF3M.json","graph_json":"https://pith.science/api/pith-number/HGZURVAOREN5IGAVVNOCZHGF3M/graph.json","events_json":"https://pith.science/api/pith-number/HGZURVAOREN5IGAVVNOCZHGF3M/events.json","paper":"https://pith.science/paper/HGZURVAO"},"agent_actions":{"view_html":"https://pith.science/pith/HGZURVAOREN5IGAVVNOCZHGF3M","download_json":"https://pith.science/pith/HGZURVAOREN5IGAVVNOCZHGF3M.json","view_paper":"https://pith.science/paper/HGZURVAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08493&json=true","fetch_graph":"https://pith.science/api/pith-number/HGZURVAOREN5IGAVVNOCZHGF3M/graph.json","fetch_events":"https://pith.science/api/pith-number/HGZURVAOREN5IGAVVNOCZHGF3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGZURVAOREN5IGAVVNOCZHGF3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGZURVAOREN5IGAVVNOCZHGF3M/action/storage_attestation","attest_author":"https://pith.science/pith/HGZURVAOREN5IGAVVNOCZHGF3M/action/author_attestation","sign_citation":"https://pith.science/pith/HGZURVAOREN5IGAVVNOCZHGF3M/action/citation_signature","submit_replication":"https://pith.science/pith/HGZURVAOREN5IGAVVNOCZHGF3M/action/replication_record"}},"created_at":"2026-07-10T01:19:52.075405+00:00","updated_at":"2026-07-10T01:19:52.075405+00:00"}