{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7PGJXSRT3PV46YTOHUMFK5KNNJ","short_pith_number":"pith:7PGJXSRT","schema_version":"1.0","canonical_sha256":"fbcc9bca33dbebcf626e3d1855754d6a7e87f0c82001e2fbc5ccf3bcee140e96","source":{"kind":"arxiv","id":"2003.11566","version":1},"attestation_state":"computed","paper":{"title":"Interval Neural Networks: Uncertainty Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cosmas Hei{\\ss}, Gitta Kutyniok, Jan Macdonald, Luis Oala, Maximilian M\\\"arz, Wojciech Samek","submitted_at":"2020-03-25T18:03:51Z","abstract_excerpt":"We propose a fast, non-Bayesian method for producing uncertainty scores in the output of pre-trained deep neural networks (DNNs) using a data-driven interval propagating network. This interval neural network (INN) has interval valued parameters and propagates its input using interval arithmetic. The INN produces sensible lower and upper bounds encompassing the ground truth. We provide theoretical justification for the validity of these bounds. Furthermore, its asymmetric uncertainty scores offer additional, directional information beyond what Gaussian-based, symmetric variance estimation can p"},"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":"2003.11566","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-25T18:03:51Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"ad7e2e98f07cc7262d538db5005b9b947356a4cf4ff152ce7280c8463407e1fd","abstract_canon_sha256":"9cbab9118e2405fc50f496f0c6612daa5fbce1acafd9f8dbb3736160c98f35e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:36.478542Z","signature_b64":"VN28ZY/e2aNwX595bVtbBR9qfu5uQVQJ5zJMmKsie7R5lHtfo0GG4hAooRxHcjy5U/rcT27t360eRixkOZOjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbcc9bca33dbebcf626e3d1855754d6a7e87f0c82001e2fbc5ccf3bcee140e96","last_reissued_at":"2026-07-05T00:50:36.478047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:36.478047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interval Neural Networks: Uncertainty Scores","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cosmas Hei{\\ss}, Gitta Kutyniok, Jan Macdonald, Luis Oala, Maximilian M\\\"arz, Wojciech Samek","submitted_at":"2020-03-25T18:03:51Z","abstract_excerpt":"We propose a fast, non-Bayesian method for producing uncertainty scores in the output of pre-trained deep neural networks (DNNs) using a data-driven interval propagating network. This interval neural network (INN) has interval valued parameters and propagates its input using interval arithmetic. The INN produces sensible lower and upper bounds encompassing the ground truth. We provide theoretical justification for the validity of these bounds. Furthermore, its asymmetric uncertainty scores offer additional, directional information beyond what Gaussian-based, symmetric variance estimation can p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.11566","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/2003.11566/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":"2003.11566","created_at":"2026-07-05T00:50:36.478103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.11566v1","created_at":"2026-07-05T00:50:36.478103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.11566","created_at":"2026-07-05T00:50:36.478103+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PGJXSRT3PV4","created_at":"2026-07-05T00:50:36.478103+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PGJXSRT3PV46YTO","created_at":"2026-07-05T00:50:36.478103+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PGJXSRT","created_at":"2026-07-05T00:50:36.478103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11460","citing_title":"Beyond Prediction: Interval Neural Networks for Uncertainty-Aware System Identification","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ","json":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ.json","graph_json":"https://pith.science/api/pith-number/7PGJXSRT3PV46YTOHUMFK5KNNJ/graph.json","events_json":"https://pith.science/api/pith-number/7PGJXSRT3PV46YTOHUMFK5KNNJ/events.json","paper":"https://pith.science/paper/7PGJXSRT"},"agent_actions":{"view_html":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ","download_json":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ.json","view_paper":"https://pith.science/paper/7PGJXSRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.11566&json=true","fetch_graph":"https://pith.science/api/pith-number/7PGJXSRT3PV46YTOHUMFK5KNNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7PGJXSRT3PV46YTOHUMFK5KNNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ/action/storage_attestation","attest_author":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ/action/author_attestation","sign_citation":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ/action/citation_signature","submit_replication":"https://pith.science/pith/7PGJXSRT3PV46YTOHUMFK5KNNJ/action/replication_record"}},"created_at":"2026-07-05T00:50:36.478103+00:00","updated_at":"2026-07-05T00:50:36.478103+00:00"}