{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ISO3WKKK34CWABVE4GGO3WSFOC","short_pith_number":"pith:ISO3WKKK","schema_version":"1.0","canonical_sha256":"449dbb294adf056006a4e18cedda4570b9f8d4ac0028473b195cdd5d296b95f7","source":{"kind":"arxiv","id":"2011.08595","version":1},"attestation_state":"computed","paper":{"title":"DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guoqiang Zhang, Jing-Hao Xue, Jiyang Xie, Jun Guo, Zhanyu Ma","submitted_at":"2020-11-17T12:35:02Z","abstract_excerpt":"This paper proposes a dual-supervised uncertainty inference (DS-UI) framework for improving Bayesian estimation-based uncertainty inference (UI) in deep neural network (DNN)-based image recognition. In the DS-UI, we combine the classifier of a DNN, i.e., the last fully-connected (FC) layer, with a mixture of Gaussian mixture models (MoGMM) to obtain an MoGMM-FC layer. Unlike existing UI methods for DNNs, which only calculate the means or modes of the DNN outputs' distributions, the proposed MoGMM-FC layer acts as a probabilistic interpreter for the features that are inputs of the classifier to"},"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":"2011.08595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-17T12:35:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"caef4f3e0da29f535dc46c4ba39c4f82798bb6f7b55b87d5335c3daee44ebca3","abstract_canon_sha256":"0de0b311b45c346042e21bd34e5dd04bd413726232ada510d3cdfa32694b61b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:20.730126Z","signature_b64":"RKCPWGPEuzYwG1xXuAXGH66ibyS+nQWwH0slLELBpKDdKZf3AJg9Esi58UjA4Uoh/cwM5zU2+Hf74ZK4QL7TDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"449dbb294adf056006a4e18cedda4570b9f8d4ac0028473b195cdd5d296b95f7","last_reissued_at":"2026-07-05T03:34:20.729682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:20.729682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guoqiang Zhang, Jing-Hao Xue, Jiyang Xie, Jun Guo, Zhanyu Ma","submitted_at":"2020-11-17T12:35:02Z","abstract_excerpt":"This paper proposes a dual-supervised uncertainty inference (DS-UI) framework for improving Bayesian estimation-based uncertainty inference (UI) in deep neural network (DNN)-based image recognition. In the DS-UI, we combine the classifier of a DNN, i.e., the last fully-connected (FC) layer, with a mixture of Gaussian mixture models (MoGMM) to obtain an MoGMM-FC layer. Unlike existing UI methods for DNNs, which only calculate the means or modes of the DNN outputs' distributions, the proposed MoGMM-FC layer acts as a probabilistic interpreter for the features that are inputs of the classifier to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.08595","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/2011.08595/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":"2011.08595","created_at":"2026-07-05T03:34:20.729740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.08595v1","created_at":"2026-07-05T03:34:20.729740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.08595","created_at":"2026-07-05T03:34:20.729740+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISO3WKKK34CW","created_at":"2026-07-05T03:34:20.729740+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISO3WKKK34CWABVE","created_at":"2026-07-05T03:34:20.729740+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISO3WKKK","created_at":"2026-07-05T03:34:20.729740+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/ISO3WKKK34CWABVE4GGO3WSFOC","json":"https://pith.science/pith/ISO3WKKK34CWABVE4GGO3WSFOC.json","graph_json":"https://pith.science/api/pith-number/ISO3WKKK34CWABVE4GGO3WSFOC/graph.json","events_json":"https://pith.science/api/pith-number/ISO3WKKK34CWABVE4GGO3WSFOC/events.json","paper":"https://pith.science/paper/ISO3WKKK"},"agent_actions":{"view_html":"https://pith.science/pith/ISO3WKKK34CWABVE4GGO3WSFOC","download_json":"https://pith.science/pith/ISO3WKKK34CWABVE4GGO3WSFOC.json","view_paper":"https://pith.science/paper/ISO3WKKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.08595&json=true","fetch_graph":"https://pith.science/api/pith-number/ISO3WKKK34CWABVE4GGO3WSFOC/graph.json","fetch_events":"https://pith.science/api/pith-number/ISO3WKKK34CWABVE4GGO3WSFOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISO3WKKK34CWABVE4GGO3WSFOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISO3WKKK34CWABVE4GGO3WSFOC/action/storage_attestation","attest_author":"https://pith.science/pith/ISO3WKKK34CWABVE4GGO3WSFOC/action/author_attestation","sign_citation":"https://pith.science/pith/ISO3WKKK34CWABVE4GGO3WSFOC/action/citation_signature","submit_replication":"https://pith.science/pith/ISO3WKKK34CWABVE4GGO3WSFOC/action/replication_record"}},"created_at":"2026-07-05T03:34:20.729740+00:00","updated_at":"2026-07-05T03:34:20.729740+00:00"}