{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:23K2ZIN3NZA6NRIINENAQXAAY4","short_pith_number":"pith:23K2ZIN3","schema_version":"1.0","canonical_sha256":"d6d5aca1bb6e41e6c508691a085c00c71d360fa083e380e8392fe8996019a11c","source":{"kind":"arxiv","id":"2410.00393","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Essential and Nonessential Settings of Evidential Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changsheng Xu, Junyu Gao, Mengyuan Chen","submitted_at":"2024-10-01T04:27:07Z","abstract_excerpt":"Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that provides reliable predictive uncertainty in a single forward pass, attracting significant attention. Grounded in subjective logic, EDL derives Dirichlet concentration parameters from neural networks to construct a Dirichlet probability density function (PDF), modeling the distribution of class probabilities. Despite its success, EDL incorporates several nonessential settings: In model construction, (1) a commonly ignored prior weight parameter is fixed to the number of classes, while its value actually impacts"},"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":"2410.00393","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T04:27:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"796fce6a57bc7558e454abbd47ba7ceeb7e658c5c9d2fd7ae26718288b841ceb","abstract_canon_sha256":"8937b0697baeeb7f6753756ca8d0536a8c1f8f5c405ff4d6cdaa12f98d17380c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:04.412955Z","signature_b64":"wJVIBWcK1Na4Z+gdZrADJb93mk1Ho8EM6eQmdPc91bJlo+PPUze8w1Z4HxWa6iH776qaCkYG3DdT9B0Dy/muBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6d5aca1bb6e41e6c508691a085c00c71d360fa083e380e8392fe8996019a11c","last_reissued_at":"2026-07-05T09:14:04.412490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:04.412490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Essential and Nonessential Settings of Evidential Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changsheng Xu, Junyu Gao, Mengyuan Chen","submitted_at":"2024-10-01T04:27:07Z","abstract_excerpt":"Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation that provides reliable predictive uncertainty in a single forward pass, attracting significant attention. Grounded in subjective logic, EDL derives Dirichlet concentration parameters from neural networks to construct a Dirichlet probability density function (PDF), modeling the distribution of class probabilities. Despite its success, EDL incorporates several nonessential settings: In model construction, (1) a commonly ignored prior weight parameter is fixed to the number of classes, while its value actually impacts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00393","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/2410.00393/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":"2410.00393","created_at":"2026-07-05T09:14:04.412548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00393v1","created_at":"2026-07-05T09:14:04.412548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00393","created_at":"2026-07-05T09:14:04.412548+00:00"},{"alias_kind":"pith_short_12","alias_value":"23K2ZIN3NZA6","created_at":"2026-07-05T09:14:04.412548+00:00"},{"alias_kind":"pith_short_16","alias_value":"23K2ZIN3NZA6NRII","created_at":"2026-07-05T09:14:04.412548+00:00"},{"alias_kind":"pith_short_8","alias_value":"23K2ZIN3","created_at":"2026-07-05T09:14:04.412548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03750","citing_title":"GEM-FI: Gated Evidential Mixtures with Fisher Modulation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06382","citing_title":"Rethinking Vacuity for OOD Detection in Evidential Deep Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06032","citing_title":"Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4","json":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4.json","graph_json":"https://pith.science/api/pith-number/23K2ZIN3NZA6NRIINENAQXAAY4/graph.json","events_json":"https://pith.science/api/pith-number/23K2ZIN3NZA6NRIINENAQXAAY4/events.json","paper":"https://pith.science/paper/23K2ZIN3"},"agent_actions":{"view_html":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4","download_json":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4.json","view_paper":"https://pith.science/paper/23K2ZIN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00393&json=true","fetch_graph":"https://pith.science/api/pith-number/23K2ZIN3NZA6NRIINENAQXAAY4/graph.json","fetch_events":"https://pith.science/api/pith-number/23K2ZIN3NZA6NRIINENAQXAAY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4/action/storage_attestation","attest_author":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4/action/author_attestation","sign_citation":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4/action/citation_signature","submit_replication":"https://pith.science/pith/23K2ZIN3NZA6NRIINENAQXAAY4/action/replication_record"}},"created_at":"2026-07-05T09:14:04.412548+00:00","updated_at":"2026-07-05T09:14:04.412548+00:00"}