{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:74OZS2BYAMV3MSIX2DXCIK4I6F","short_pith_number":"pith:74OZS2BY","schema_version":"1.0","canonical_sha256":"ff1d996838032bb64917d0ee242b88f16dfba8b7a903437b951bf87e01f7a0e1","source":{"kind":"arxiv","id":"2307.05772","version":5},"attestation_state":"computed","paper":{"title":"Random-Set Neural Networks (RS-NN)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Cuzzolin, Kaizheng Wang, Keivan Shariatmadar, Muhammad Mubashar, Shireen Kudukkil Manchingal","submitted_at":"2023-07-11T20:00:35Z","abstract_excerpt":"Machine learning is increasingly deployed in safety-critical domains where erroneous predictions may lead to potentially catastrophic consequences, highlighting the need for learning systems to be aware of how confident they are in their own predictions: in other words, 'to know when they do not know'. In this paper, we propose a novel Random-Set Neural Network (RS-NN) approach to classification which predicts belief functions (rather than classical probability vectors) over the class list using the mathematics of random sets, i.e., distributions over the collection of sets of classes. RS-NN e"},"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":"2307.05772","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-11T20:00:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8474aa24cfbbc60fb989baa3523f56956828c368fa40624dab85b13c316a8170","abstract_canon_sha256":"283e6d9451c32516d8ca558bbe79f4c0b18fc1f0ab7d05575524075734c958e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:35.958512Z","signature_b64":"wCScPu5DjDn3tYdhBxI16YPsCtQtrdhg0Xl18oeHxP1UJWolJ/eaSzIIoVpOm8M5i4cKx6Hmnkhv7bILO/B1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff1d996838032bb64917d0ee242b88f16dfba8b7a903437b951bf87e01f7a0e1","last_reissued_at":"2026-07-05T10:14:35.958050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:35.958050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random-Set Neural Networks (RS-NN)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Cuzzolin, Kaizheng Wang, Keivan Shariatmadar, Muhammad Mubashar, Shireen Kudukkil Manchingal","submitted_at":"2023-07-11T20:00:35Z","abstract_excerpt":"Machine learning is increasingly deployed in safety-critical domains where erroneous predictions may lead to potentially catastrophic consequences, highlighting the need for learning systems to be aware of how confident they are in their own predictions: in other words, 'to know when they do not know'. In this paper, we propose a novel Random-Set Neural Network (RS-NN) approach to classification which predicts belief functions (rather than classical probability vectors) over the class list using the mathematics of random sets, i.e., distributions over the collection of sets of classes. RS-NN e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05772","kind":"arxiv","version":5},"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/2307.05772/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":"2307.05772","created_at":"2026-07-05T10:14:35.958099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05772v5","created_at":"2026-07-05T10:14:35.958099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05772","created_at":"2026-07-05T10:14:35.958099+00:00"},{"alias_kind":"pith_short_12","alias_value":"74OZS2BYAMV3","created_at":"2026-07-05T10:14:35.958099+00:00"},{"alias_kind":"pith_short_16","alias_value":"74OZS2BYAMV3MSIX","created_at":"2026-07-05T10:14:35.958099+00:00"},{"alias_kind":"pith_short_8","alias_value":"74OZS2BY","created_at":"2026-07-05T10:14:35.958099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11987","citing_title":"Random-Set Graph Neural Networks","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F","json":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F.json","graph_json":"https://pith.science/api/pith-number/74OZS2BYAMV3MSIX2DXCIK4I6F/graph.json","events_json":"https://pith.science/api/pith-number/74OZS2BYAMV3MSIX2DXCIK4I6F/events.json","paper":"https://pith.science/paper/74OZS2BY"},"agent_actions":{"view_html":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F","download_json":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F.json","view_paper":"https://pith.science/paper/74OZS2BY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05772&json=true","fetch_graph":"https://pith.science/api/pith-number/74OZS2BYAMV3MSIX2DXCIK4I6F/graph.json","fetch_events":"https://pith.science/api/pith-number/74OZS2BYAMV3MSIX2DXCIK4I6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F/action/storage_attestation","attest_author":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F/action/author_attestation","sign_citation":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F/action/citation_signature","submit_replication":"https://pith.science/pith/74OZS2BYAMV3MSIX2DXCIK4I6F/action/replication_record"}},"created_at":"2026-07-05T10:14:35.958099+00:00","updated_at":"2026-07-05T10:14:35.958099+00:00"}