{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7BM2GTZNDYDYC6HFSKMNAK726D","short_pith_number":"pith:7BM2GTZN","schema_version":"1.0","canonical_sha256":"f859a34f2d1e078178e59298d02bfaf0f8e2e00fc9414b11917ec12e4d24b6bb","source":{"kind":"arxiv","id":"2302.03271","version":2},"attestation_state":"computed","paper":{"title":"IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Hao Wu, Ling Guo, Tao Zhou, Wenwen Zhou, Yan Wang","submitted_at":"2023-02-07T05:56:42Z","abstract_excerpt":"We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks, including deep neural network (DNN) regression and neural operator learning (DeepONet). Specifically, we incorporate the bottleneck by a confidence-aware encoder, which encodes inputs into latent representations according to the confidence of the input data belonging to the region where training data is located, and utilize a Gaussian decoder to predict means and variances of outputs conditional on representation variables. Furthermore, we propose a data augment"},"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":"2302.03271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.NA","submitted_at":"2023-02-07T05:56:42Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"56de12bbf8ca2d7e534cf123142c97b81acd9976cd89808557e81aae8cc56462","abstract_canon_sha256":"a16fa78c8dcaf40b92507dfb08d726b9301731185d6a8e7b608c6c3fc47574ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:57.440429Z","signature_b64":"pY2RfEsR2Js4iZEjqC+29tHdV2xTNjOXzt/mVTpcgKS7e+ogDwewEXmNDBLy15udh78Y04SwpDtQqSitOoaYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f859a34f2d1e078178e59298d02bfaf0f8e2e00fc9414b11917ec12e4d24b6bb","last_reissued_at":"2026-07-05T06:14:57.439907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:57.439907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Hao Wu, Ling Guo, Tao Zhou, Wenwen Zhou, Yan Wang","submitted_at":"2023-02-07T05:56:42Z","abstract_excerpt":"We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks, including deep neural network (DNN) regression and neural operator learning (DeepONet). Specifically, we incorporate the bottleneck by a confidence-aware encoder, which encodes inputs into latent representations according to the confidence of the input data belonging to the region where training data is located, and utilize a Gaussian decoder to predict means and variances of outputs conditional on representation variables. Furthermore, we propose a data augment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03271","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/2302.03271/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":"2302.03271","created_at":"2026-07-05T06:14:57.439968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03271v2","created_at":"2026-07-05T06:14:57.439968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03271","created_at":"2026-07-05T06:14:57.439968+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BM2GTZNDYDY","created_at":"2026-07-05T06:14:57.439968+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BM2GTZNDYDYC6HF","created_at":"2026-07-05T06:14:57.439968+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BM2GTZN","created_at":"2026-07-05T06:14:57.439968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22493","citing_title":"LVM-GP: Uncertainty-Aware PDE Solver via coupling latent variable model and Gaussian process","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D","json":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D.json","graph_json":"https://pith.science/api/pith-number/7BM2GTZNDYDYC6HFSKMNAK726D/graph.json","events_json":"https://pith.science/api/pith-number/7BM2GTZNDYDYC6HFSKMNAK726D/events.json","paper":"https://pith.science/paper/7BM2GTZN"},"agent_actions":{"view_html":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D","download_json":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D.json","view_paper":"https://pith.science/paper/7BM2GTZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03271&json=true","fetch_graph":"https://pith.science/api/pith-number/7BM2GTZNDYDYC6HFSKMNAK726D/graph.json","fetch_events":"https://pith.science/api/pith-number/7BM2GTZNDYDYC6HFSKMNAK726D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D/action/storage_attestation","attest_author":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D/action/author_attestation","sign_citation":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D/action/citation_signature","submit_replication":"https://pith.science/pith/7BM2GTZNDYDYC6HFSKMNAK726D/action/replication_record"}},"created_at":"2026-07-05T06:14:57.439968+00:00","updated_at":"2026-07-05T06:14:57.439968+00:00"}