{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PWFMKP57MNQ66TEQHTNPWI6GXL","short_pith_number":"pith:PWFMKP57","schema_version":"1.0","canonical_sha256":"7d8ac53fbf6361ef4c903cdafb23c6baf4ede26f52bc12bc868085893aa43a50","source":{"kind":"arxiv","id":"2504.18085","version":1},"attestation_state":"computed","paper":{"title":"Random-Set Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fabio Cuzzolin, Muhammad Mubashar, Shireen Kudukkil Manchingal","submitted_at":"2025-04-25T05:25:27Z","abstract_excerpt":"Large Language Models (LLMs) are known to produce very high-quality tests and responses to our queries. But how much can we trust this generated text? In this paper, we study the problem of uncertainty quantification in LLMs. We propose a novel Random-Set Large Language Model (RSLLM) approach which predicts finite random sets (belief functions) over the token space, rather than probability vectors as in classical LLMs. In order to allow so efficiently, we also present a methodology based on hierarchical clustering to extract and use a budget of \"focal\" subsets of tokens upon which the belief 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":"2504.18085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T05:25:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e162dbc33d88b379573d5d972558a06541785bfd10a37fa8a6b03b4be6963830","abstract_canon_sha256":"602e885f9740a0161f0e29baecca0f476409687289a36a08fc1bf50c29772b0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:01.438247Z","signature_b64":"UKNTQf+nefU3i8OmYRdZkGLNp3Aa8/Z46ulJEoBGU29vEzyOPAoAXcbR8eUzALv4MrmxR9wkP7UA01aO3OzlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d8ac53fbf6361ef4c903cdafb23c6baf4ede26f52bc12bc868085893aa43a50","last_reissued_at":"2026-07-05T10:54:01.437794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:01.437794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random-Set Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fabio Cuzzolin, Muhammad Mubashar, Shireen Kudukkil Manchingal","submitted_at":"2025-04-25T05:25:27Z","abstract_excerpt":"Large Language Models (LLMs) are known to produce very high-quality tests and responses to our queries. But how much can we trust this generated text? In this paper, we study the problem of uncertainty quantification in LLMs. We propose a novel Random-Set Large Language Model (RSLLM) approach which predicts finite random sets (belief functions) over the token space, rather than probability vectors as in classical LLMs. In order to allow so efficiently, we also present a methodology based on hierarchical clustering to extract and use a budget of \"focal\" subsets of tokens upon which the belief p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18085","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/2504.18085/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":"2504.18085","created_at":"2026-07-05T10:54:01.437845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18085v1","created_at":"2026-07-05T10:54:01.437845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18085","created_at":"2026-07-05T10:54:01.437845+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWFMKP57MNQ6","created_at":"2026-07-05T10:54:01.437845+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWFMKP57MNQ66TEQ","created_at":"2026-07-05T10:54:01.437845+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWFMKP57","created_at":"2026-07-05T10:54:01.437845+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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL","json":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL.json","graph_json":"https://pith.science/api/pith-number/PWFMKP57MNQ66TEQHTNPWI6GXL/graph.json","events_json":"https://pith.science/api/pith-number/PWFMKP57MNQ66TEQHTNPWI6GXL/events.json","paper":"https://pith.science/paper/PWFMKP57"},"agent_actions":{"view_html":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL","download_json":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL.json","view_paper":"https://pith.science/paper/PWFMKP57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18085&json=true","fetch_graph":"https://pith.science/api/pith-number/PWFMKP57MNQ66TEQHTNPWI6GXL/graph.json","fetch_events":"https://pith.science/api/pith-number/PWFMKP57MNQ66TEQHTNPWI6GXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL/action/storage_attestation","attest_author":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL/action/author_attestation","sign_citation":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL/action/citation_signature","submit_replication":"https://pith.science/pith/PWFMKP57MNQ66TEQHTNPWI6GXL/action/replication_record"}},"created_at":"2026-07-05T10:54:01.437845+00:00","updated_at":"2026-07-05T10:54:01.437845+00:00"}