{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IUFAZ7RJYCT7JKSQAHWYP35TAD","short_pith_number":"pith:IUFAZ7RJ","schema_version":"1.0","canonical_sha256":"450a0cfe29c0a7f4aa5001ed87efb300ebe760a47c1d640880ad2e13e1503f58","source":{"kind":"arxiv","id":"2210.13440","version":1},"attestation_state":"computed","paper":{"title":"Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shengjin Wang, Weihua Chen, Yali Li, Zhaopeng Dou, Zhongdao Wang","submitted_at":"2022-10-24T17:53:20Z","abstract_excerpt":"Current person image retrieval methods have achieved great improvements in accuracy metrics. However, they rarely describe the reliability of the prediction. In this paper, we propose an Uncertainty-Aware Learning (UAL) method to remedy this issue. UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously. Data uncertainty captures the ``noise\" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction. Specifically, in UAL, (1) we propose a sampling-free data uncertainty learning meth"},"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":"2210.13440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-24T17:53:20Z","cross_cats_sorted":[],"title_canon_sha256":"f7aef4ad1aedf71595fc05db9435ba9301d5dc3ee3cb4ef0c8bf4b992faba144","abstract_canon_sha256":"64eb6e09bee0eda371939c6df05ef171531dd2d7036bba6ad191e13962784ed6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:45.468735Z","signature_b64":"r0yLinxEKayu9L64Ms/T9SmitXExNpk21mvMEJCsmevQo3GLT4BzKZtMAkvCwbYiqU0JRqIxdc/ae39gKIlJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"450a0cfe29c0a7f4aa5001ed87efb300ebe760a47c1d640880ad2e13e1503f58","last_reissued_at":"2026-07-05T05:09:45.468265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:45.468265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shengjin Wang, Weihua Chen, Yali Li, Zhaopeng Dou, Zhongdao Wang","submitted_at":"2022-10-24T17:53:20Z","abstract_excerpt":"Current person image retrieval methods have achieved great improvements in accuracy metrics. However, they rarely describe the reliability of the prediction. In this paper, we propose an Uncertainty-Aware Learning (UAL) method to remedy this issue. UAL aims at providing reliability-aware predictions by considering data uncertainty and model uncertainty simultaneously. Data uncertainty captures the ``noise\" inherent in the sample, while model uncertainty depicts the model's confidence in the sample's prediction. Specifically, in UAL, (1) we propose a sampling-free data uncertainty learning meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13440","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/2210.13440/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":"2210.13440","created_at":"2026-07-05T05:09:45.468324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13440v1","created_at":"2026-07-05T05:09:45.468324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13440","created_at":"2026-07-05T05:09:45.468324+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUFAZ7RJYCT7","created_at":"2026-07-05T05:09:45.468324+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUFAZ7RJYCT7JKSQ","created_at":"2026-07-05T05:09:45.468324+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUFAZ7RJ","created_at":"2026-07-05T05:09:45.468324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08877","citing_title":"Harnessing Weak Pair Uncertainty for Text-based Person Search","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD","json":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD.json","graph_json":"https://pith.science/api/pith-number/IUFAZ7RJYCT7JKSQAHWYP35TAD/graph.json","events_json":"https://pith.science/api/pith-number/IUFAZ7RJYCT7JKSQAHWYP35TAD/events.json","paper":"https://pith.science/paper/IUFAZ7RJ"},"agent_actions":{"view_html":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD","download_json":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD.json","view_paper":"https://pith.science/paper/IUFAZ7RJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13440&json=true","fetch_graph":"https://pith.science/api/pith-number/IUFAZ7RJYCT7JKSQAHWYP35TAD/graph.json","fetch_events":"https://pith.science/api/pith-number/IUFAZ7RJYCT7JKSQAHWYP35TAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD/action/storage_attestation","attest_author":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD/action/author_attestation","sign_citation":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD/action/citation_signature","submit_replication":"https://pith.science/pith/IUFAZ7RJYCT7JKSQAHWYP35TAD/action/replication_record"}},"created_at":"2026-07-05T05:09:45.468324+00:00","updated_at":"2026-07-05T05:09:45.468324+00:00"}