{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G45JBWQ3JVPSGS4E2KWTUUTSZD","short_pith_number":"pith:G45JBWQ3","schema_version":"1.0","canonical_sha256":"373a90da1b4d5f234b84d2ad3a5272c8dc130d9d95211fadee86a6a52ac113c2","source":{"kind":"arxiv","id":"2206.07609","version":1},"attestation_state":"computed","paper":{"title":"Epistemic Deep Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Cuzzolin, Shireen Kudukkil Manchingal","submitted_at":"2022-06-15T15:39:52Z","abstract_excerpt":"The belief function approach to uncertainty quantification as proposed in the Demspter-Shafer theory of evidence is established upon the general mathematical models for set-valued observations, called random sets. Set-valued predictions are the most natural representations of uncertainty in machine learning. In this paper, we introduce a concept called epistemic deep learning based on the random-set interpretation of belief functions to model epistemic learning in deep neural networks. We propose a novel random-set convolutional neural network for classification that produces scores for sets o"},"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":"2206.07609","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T15:39:52Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"71f57db165cf38cfca0dd512883066590dec14fc6a89c929e7599e7611fe2914","abstract_canon_sha256":"0afc5a88be68edd0e91ea702407222afa5c3eb400e7e94f9b3fa55e66bf30514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:06.882768Z","signature_b64":"Z1WbRiXnmHPUN4xlvw7notivd91hqrejnRMNN7O6WHW6PPORsmp7l6bOL1r5US0Oegi5wJEyalFZAuYRmdeYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"373a90da1b4d5f234b84d2ad3a5272c8dc130d9d95211fadee86a6a52ac113c2","last_reissued_at":"2026-07-05T04:32:06.882297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:06.882297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Epistemic Deep Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Cuzzolin, Shireen Kudukkil Manchingal","submitted_at":"2022-06-15T15:39:52Z","abstract_excerpt":"The belief function approach to uncertainty quantification as proposed in the Demspter-Shafer theory of evidence is established upon the general mathematical models for set-valued observations, called random sets. Set-valued predictions are the most natural representations of uncertainty in machine learning. In this paper, we introduce a concept called epistemic deep learning based on the random-set interpretation of belief functions to model epistemic learning in deep neural networks. We propose a novel random-set convolutional neural network for classification that produces scores for sets o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07609","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/2206.07609/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":"2206.07609","created_at":"2026-07-05T04:32:06.882360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07609v1","created_at":"2026-07-05T04:32:06.882360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07609","created_at":"2026-07-05T04:32:06.882360+00:00"},{"alias_kind":"pith_short_12","alias_value":"G45JBWQ3JVPS","created_at":"2026-07-05T04:32:06.882360+00:00"},{"alias_kind":"pith_short_16","alias_value":"G45JBWQ3JVPSGS4E","created_at":"2026-07-05T04:32:06.882360+00:00"},{"alias_kind":"pith_short_8","alias_value":"G45JBWQ3","created_at":"2026-07-05T04:32:06.882360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25182","citing_title":"What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18871","citing_title":"Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11987","citing_title":"Random-Set Graph Neural Networks","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD","json":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD.json","graph_json":"https://pith.science/api/pith-number/G45JBWQ3JVPSGS4E2KWTUUTSZD/graph.json","events_json":"https://pith.science/api/pith-number/G45JBWQ3JVPSGS4E2KWTUUTSZD/events.json","paper":"https://pith.science/paper/G45JBWQ3"},"agent_actions":{"view_html":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD","download_json":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD.json","view_paper":"https://pith.science/paper/G45JBWQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07609&json=true","fetch_graph":"https://pith.science/api/pith-number/G45JBWQ3JVPSGS4E2KWTUUTSZD/graph.json","fetch_events":"https://pith.science/api/pith-number/G45JBWQ3JVPSGS4E2KWTUUTSZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD/action/storage_attestation","attest_author":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD/action/author_attestation","sign_citation":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD/action/citation_signature","submit_replication":"https://pith.science/pith/G45JBWQ3JVPSGS4E2KWTUUTSZD/action/replication_record"}},"created_at":"2026-07-05T04:32:06.882360+00:00","updated_at":"2026-07-05T04:32:06.882360+00:00"}