{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LKBQC3E2K6J35PXXNLVWBYFH3P","short_pith_number":"pith:LKBQC3E2","schema_version":"1.0","canonical_sha256":"5a83016c9a5793bebef76aeb60e0a7dbe37ef7c959b5606ac0feebf061efc79d","source":{"kind":"arxiv","id":"2605.26477","version":1},"attestation_state":"computed","paper":{"title":"Variational Inference for Evidential Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hui Liu, Jiawei Tang, Junhui Hou, Xinyan Du, Yuheng Jia","submitted_at":"2026-05-26T02:32:59Z","abstract_excerpt":"While Deep Neural Networks (DNNs) achieve remarkable performance, their tendency to produce overconfident predictions. Evidential Deep Learning (EDL) mitigates this by formulating predictions as a Dirichlet distribution over class probabilities to explicitly quantify epistemic uncertainty. However, we found that the conventional EDL suffers from two fundamental limitations: a Kullback-Leibler (KL) penalty that only suppresses the evidence of negative classes, producing excessively high evidence therefore decreasing the model's ability to quantify uncertainty, and an absence in theoretical guar"},"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":"2605.26477","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T02:32:59Z","cross_cats_sorted":[],"title_canon_sha256":"4b1bb7df6ce2b7c0932fe326831cedf71fb3b0cc830c5c53af8a58c9a7d2a5ba","abstract_canon_sha256":"e5992ff3aa3c23b79b494d3bf01c8433cce23584a3bf03e1feb89998d2a3efa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:20.279685Z","signature_b64":"7sfRXrVhGBI5FH9Jcbh9ZygJhEyAbHyo5MH4uM+vJxWR9/zJ/JvpoU/FnCIKpEz2V02esqqJVW9v9TfCPQH/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a83016c9a5793bebef76aeb60e0a7dbe37ef7c959b5606ac0feebf061efc79d","last_reissued_at":"2026-05-27T01:05:20.278973Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:20.278973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Inference for Evidential Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hui Liu, Jiawei Tang, Junhui Hou, Xinyan Du, Yuheng Jia","submitted_at":"2026-05-26T02:32:59Z","abstract_excerpt":"While Deep Neural Networks (DNNs) achieve remarkable performance, their tendency to produce overconfident predictions. Evidential Deep Learning (EDL) mitigates this by formulating predictions as a Dirichlet distribution over class probabilities to explicitly quantify epistemic uncertainty. However, we found that the conventional EDL suffers from two fundamental limitations: a Kullback-Leibler (KL) penalty that only suppresses the evidence of negative classes, producing excessively high evidence therefore decreasing the model's ability to quantify uncertainty, and an absence in theoretical guar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26477","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/2605.26477/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":"2605.26477","created_at":"2026-05-27T01:05:20.279088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26477v1","created_at":"2026-05-27T01:05:20.279088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26477","created_at":"2026-05-27T01:05:20.279088+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKBQC3E2K6J3","created_at":"2026-05-27T01:05:20.279088+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKBQC3E2K6J35PXX","created_at":"2026-05-27T01:05:20.279088+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKBQC3E2","created_at":"2026-05-27T01:05:20.279088+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/LKBQC3E2K6J35PXXNLVWBYFH3P","json":"https://pith.science/pith/LKBQC3E2K6J35PXXNLVWBYFH3P.json","graph_json":"https://pith.science/api/pith-number/LKBQC3E2K6J35PXXNLVWBYFH3P/graph.json","events_json":"https://pith.science/api/pith-number/LKBQC3E2K6J35PXXNLVWBYFH3P/events.json","paper":"https://pith.science/paper/LKBQC3E2"},"agent_actions":{"view_html":"https://pith.science/pith/LKBQC3E2K6J35PXXNLVWBYFH3P","download_json":"https://pith.science/pith/LKBQC3E2K6J35PXXNLVWBYFH3P.json","view_paper":"https://pith.science/paper/LKBQC3E2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26477&json=true","fetch_graph":"https://pith.science/api/pith-number/LKBQC3E2K6J35PXXNLVWBYFH3P/graph.json","fetch_events":"https://pith.science/api/pith-number/LKBQC3E2K6J35PXXNLVWBYFH3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKBQC3E2K6J35PXXNLVWBYFH3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKBQC3E2K6J35PXXNLVWBYFH3P/action/storage_attestation","attest_author":"https://pith.science/pith/LKBQC3E2K6J35PXXNLVWBYFH3P/action/author_attestation","sign_citation":"https://pith.science/pith/LKBQC3E2K6J35PXXNLVWBYFH3P/action/citation_signature","submit_replication":"https://pith.science/pith/LKBQC3E2K6J35PXXNLVWBYFH3P/action/replication_record"}},"created_at":"2026-05-27T01:05:20.279088+00:00","updated_at":"2026-05-27T01:05:20.279088+00:00"}