{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AUJIHS6VN3MFA2L6BHV2MR7WB7","short_pith_number":"pith:AUJIHS6V","schema_version":"1.0","canonical_sha256":"051283cbd56ed850697e09eba647f60ff578b4fffe5ee6e47b0aa046dffa7191","source":{"kind":"arxiv","id":"2007.08259","version":2},"attestation_state":"computed","paper":{"title":"Transferable Calibration with Lower Bias and Variance in Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Michael I. Jordan, Mingsheng Long, Ximei Wang","submitted_at":"2020-07-16T11:09:36Z","abstract_excerpt":"Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one. While remarkable advances have been made, most of the existing DA methods focus on improving the target accuracy at inference. How to estimate the predictive uncertainty of DA models is vital for decision-making in safety-critical scenarios but remains the boundary to explore. In this paper, we delve into the open problem of Calibration in DA, which is extremely challenging due to the coexistence of domain shift and the lack of target labels. We first reveal the dilemma that "},"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":"2007.08259","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-16T11:09:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"940e48397b8af1d8001ceef813274683655773a7474633fae054abab415f2012","abstract_canon_sha256":"20b009a2e372380524ddafb8b187dbdc5b0f0ea29c5a80cf3bf471b570eb2df0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:53.274677Z","signature_b64":"x7NmHCxN/qmm5IhXrb5gAXQ13Wny+9PImFdSzUAEiyLDz0aAClA38ZGyMbB377IX383+nbV5ATae6m8wL1mKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"051283cbd56ed850697e09eba647f60ff578b4fffe5ee6e47b0aa046dffa7191","last_reissued_at":"2026-07-05T01:49:53.274337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:53.274337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferable Calibration with Lower Bias and Variance in Domain Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Michael I. Jordan, Mingsheng Long, Ximei Wang","submitted_at":"2020-07-16T11:09:36Z","abstract_excerpt":"Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one. While remarkable advances have been made, most of the existing DA methods focus on improving the target accuracy at inference. How to estimate the predictive uncertainty of DA models is vital for decision-making in safety-critical scenarios but remains the boundary to explore. In this paper, we delve into the open problem of Calibration in DA, which is extremely challenging due to the coexistence of domain shift and the lack of target labels. We first reveal the dilemma that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.08259","kind":"arxiv","version":2},"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/2007.08259/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":"2007.08259","created_at":"2026-07-05T01:49:53.274393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.08259v2","created_at":"2026-07-05T01:49:53.274393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.08259","created_at":"2026-07-05T01:49:53.274393+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUJIHS6VN3MF","created_at":"2026-07-05T01:49:53.274393+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUJIHS6VN3MFA2L6","created_at":"2026-07-05T01:49:53.274393+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUJIHS6V","created_at":"2026-07-05T01:49:53.274393+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06317","citing_title":"Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Grounding","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7","json":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7.json","graph_json":"https://pith.science/api/pith-number/AUJIHS6VN3MFA2L6BHV2MR7WB7/graph.json","events_json":"https://pith.science/api/pith-number/AUJIHS6VN3MFA2L6BHV2MR7WB7/events.json","paper":"https://pith.science/paper/AUJIHS6V"},"agent_actions":{"view_html":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7","download_json":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7.json","view_paper":"https://pith.science/paper/AUJIHS6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.08259&json=true","fetch_graph":"https://pith.science/api/pith-number/AUJIHS6VN3MFA2L6BHV2MR7WB7/graph.json","fetch_events":"https://pith.science/api/pith-number/AUJIHS6VN3MFA2L6BHV2MR7WB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7/action/storage_attestation","attest_author":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7/action/author_attestation","sign_citation":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7/action/citation_signature","submit_replication":"https://pith.science/pith/AUJIHS6VN3MFA2L6BHV2MR7WB7/action/replication_record"}},"created_at":"2026-07-05T01:49:53.274393+00:00","updated_at":"2026-07-05T01:49:53.274393+00:00"}