{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OHWSMNFDZJMJHBNQOCSZEGOJNS","short_pith_number":"pith:OHWSMNFD","schema_version":"1.0","canonical_sha256":"71ed2634a3ca589385b070a59219c96c994764efcc38c6fb815e47a5217926a2","source":{"kind":"arxiv","id":"2608.02455","version":1},"attestation_state":"computed","paper":{"title":"Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Desheng Zhang, Guang Wang, Xintong Li, Zejun Xie","submitted_at":"2026-08-03T16:30:30Z","abstract_excerpt":"Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground truth. Existing approaches face a dilemma: methods using only human judgments suffer from heterogeneous expertise and inconsistent rating scales, while methods using only model-generated scores must learn from imperfect proxies or incomplete features. We propose Aggregate-then-Calibrate (AtC), a two-stage framework that combines these complementary sources. Stage-1 aggregates heterogeneous comparative judgments into a consensus ranking using a"},"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":"2608.02455","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T16:30:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9ea6ec3929e15c5f9c875f8d8cd24af2b0bd3b4abb794f4c2c0ab940374bd422","abstract_canon_sha256":"a6e67ec8043e5f9a96fab538c0e02ff735b3e1ebad4984ed137f2e75c4a43a77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:43:34.038925Z","signature_b64":"72gAY35mxmGhL8kRzV6x3AzCvQJ1BR2CF0Q6r2rAeC04xK8sUUhzzNfk69K7q3Q/7ewBpQLpnhV2G2cUX61GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71ed2634a3ca589385b070a59219c96c994764efcc38c6fb815e47a5217926a2","last_reissued_at":"2026-08-04T02:43:34.036644Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:43:34.036644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aggregate-then-Calibrate for Human-centered Assessment with Theoretical Guarantees","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Desheng Zhang, Guang Wang, Xintong Li, Zejun Xie","submitted_at":"2026-08-03T16:30:30Z","abstract_excerpt":"Human-centered assessment tasks, which are essential for systematic decision-making, rely heavily on human judgment and typically lack verifiable ground truth. Existing approaches face a dilemma: methods using only human judgments suffer from heterogeneous expertise and inconsistent rating scales, while methods using only model-generated scores must learn from imperfect proxies or incomplete features. We propose Aggregate-then-Calibrate (AtC), a two-stage framework that combines these complementary sources. Stage-1 aggregates heterogeneous comparative judgments into a consensus ranking using a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02455","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/2608.02455/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":"2608.02455","created_at":"2026-08-04T02:43:34.038927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02455v1","created_at":"2026-08-04T02:43:34.038927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02455","created_at":"2026-08-04T02:43:34.038927+00:00"},{"alias_kind":"pith_short_12","alias_value":"OHWSMNFDZJMJ","created_at":"2026-08-04T02:43:34.038927+00:00"},{"alias_kind":"pith_short_16","alias_value":"OHWSMNFDZJMJHBNQ","created_at":"2026-08-04T02:43:34.038927+00:00"},{"alias_kind":"pith_short_8","alias_value":"OHWSMNFD","created_at":"2026-08-04T02:43:34.038927+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/OHWSMNFDZJMJHBNQOCSZEGOJNS","json":"https://pith.science/pith/OHWSMNFDZJMJHBNQOCSZEGOJNS.json","graph_json":"https://pith.science/api/pith-number/OHWSMNFDZJMJHBNQOCSZEGOJNS/graph.json","events_json":"https://pith.science/api/pith-number/OHWSMNFDZJMJHBNQOCSZEGOJNS/events.json","paper":"https://pith.science/paper/OHWSMNFD"},"agent_actions":{"view_html":"https://pith.science/pith/OHWSMNFDZJMJHBNQOCSZEGOJNS","download_json":"https://pith.science/pith/OHWSMNFDZJMJHBNQOCSZEGOJNS.json","view_paper":"https://pith.science/paper/OHWSMNFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02455&json=true","fetch_graph":"https://pith.science/api/pith-number/OHWSMNFDZJMJHBNQOCSZEGOJNS/graph.json","fetch_events":"https://pith.science/api/pith-number/OHWSMNFDZJMJHBNQOCSZEGOJNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OHWSMNFDZJMJHBNQOCSZEGOJNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OHWSMNFDZJMJHBNQOCSZEGOJNS/action/storage_attestation","attest_author":"https://pith.science/pith/OHWSMNFDZJMJHBNQOCSZEGOJNS/action/author_attestation","sign_citation":"https://pith.science/pith/OHWSMNFDZJMJHBNQOCSZEGOJNS/action/citation_signature","submit_replication":"https://pith.science/pith/OHWSMNFDZJMJHBNQOCSZEGOJNS/action/replication_record"}},"created_at":"2026-08-04T02:43:34.038927+00:00","updated_at":"2026-08-04T02:43:34.038927+00:00"}