{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VRFUUGWUFVP2HDBLGDE477E5AX","short_pith_number":"pith:VRFUUGWU","schema_version":"1.0","canonical_sha256":"ac4b4a1ad42d5fa38c2b30c9cffc9d05dca8c93e484cfff02e54a3f3d8363756","source":{"kind":"arxiv","id":"2403.16527","version":2},"attestation_state":"computed","paper":{"title":"Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.AI","authors_text":"Katherine Driggs-Campbell, Melkior Ornik, Neeloy Chakraborty","submitted_at":"2024-03-25T08:11:02Z","abstract_excerpt":"Autonomous systems are soon to be ubiquitous, spanning manufacturing, agriculture, healthcare, entertainment, and other industries. Most of these systems are developed with modular sub-components for decision-making, planning, and control that may be hand-engineered or learning-based. While these approaches perform well under the situations they were specifically designed for, they can perform especially poorly in out-of-distribution scenarios that will undoubtedly arise at test-time. The rise of foundation models trained on multiple tasks with impressively large datasets has led researchers t"},"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":"2403.16527","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-25T08:11:02Z","cross_cats_sorted":["cs.CL","cs.RO"],"title_canon_sha256":"880fd85ba06ad83db7f6d660ab0f7588ce48005f03113f8ac372b2a477c93dd0","abstract_canon_sha256":"2688dd06b37301243cbce13e35efeddacf3bb42986b3bf357e436d3e3ac0bfd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:47.432108Z","signature_b64":"3YFNziEDYVI8VUNB6KAAKf1O8eEyHJ9BtQ24cxLkSMMcUKFqWadWj/XJd4rfjQZ7MoD7O9YAHrQIpDyURjphAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac4b4a1ad42d5fa38c2b30c9cffc9d05dca8c93e484cfff02e54a3f3d8363756","last_reissued_at":"2026-07-05T10:12:47.431552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:47.431552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.AI","authors_text":"Katherine Driggs-Campbell, Melkior Ornik, Neeloy Chakraborty","submitted_at":"2024-03-25T08:11:02Z","abstract_excerpt":"Autonomous systems are soon to be ubiquitous, spanning manufacturing, agriculture, healthcare, entertainment, and other industries. Most of these systems are developed with modular sub-components for decision-making, planning, and control that may be hand-engineered or learning-based. While these approaches perform well under the situations they were specifically designed for, they can perform especially poorly in out-of-distribution scenarios that will undoubtedly arise at test-time. The rise of foundation models trained on multiple tasks with impressively large datasets has led researchers t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16527","kind":"arxiv","version":2},"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/2403.16527/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":"2403.16527","created_at":"2026-07-05T10:12:47.431611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16527v2","created_at":"2026-07-05T10:12:47.431611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16527","created_at":"2026-07-05T10:12:47.431611+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRFUUGWUFVP2","created_at":"2026-07-05T10:12:47.431611+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRFUUGWUFVP2HDBL","created_at":"2026-07-05T10:12:47.431611+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRFUUGWU","created_at":"2026-07-05T10:12:47.431611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05504","citing_title":"Semantic Communication with an LLM-enabled Knowledge Base","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX","json":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX.json","graph_json":"https://pith.science/api/pith-number/VRFUUGWUFVP2HDBLGDE477E5AX/graph.json","events_json":"https://pith.science/api/pith-number/VRFUUGWUFVP2HDBLGDE477E5AX/events.json","paper":"https://pith.science/paper/VRFUUGWU"},"agent_actions":{"view_html":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX","download_json":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX.json","view_paper":"https://pith.science/paper/VRFUUGWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16527&json=true","fetch_graph":"https://pith.science/api/pith-number/VRFUUGWUFVP2HDBLGDE477E5AX/graph.json","fetch_events":"https://pith.science/api/pith-number/VRFUUGWUFVP2HDBLGDE477E5AX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX/action/storage_attestation","attest_author":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX/action/author_attestation","sign_citation":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX/action/citation_signature","submit_replication":"https://pith.science/pith/VRFUUGWUFVP2HDBLGDE477E5AX/action/replication_record"}},"created_at":"2026-07-05T10:12:47.431611+00:00","updated_at":"2026-07-05T10:12:47.431611+00:00"}