{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZM6GKSC2SC4UXWNGT3SNEYAON5","short_pith_number":"pith:ZM6GKSC2","schema_version":"1.0","canonical_sha256":"cb3c65485a90b94bd9a69ee4d2600e6f61bbe187e53dbb38433cff0c5406bec1","source":{"kind":"arxiv","id":"2404.05904","version":2},"attestation_state":"computed","paper":{"title":"The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aryo Pradipta Gema, Cl\\'ementine Fourrier, Giwon Hong, Laura Perez-Beltrachini, Max Ryabinin, Pasquale Minervini, Ping Nie, Rohit Saxena, Xiaotang Du, Xuanli He, Yu Zhao","submitted_at":"2024-04-08T23:16:22Z","abstract_excerpt":"Large Language Models (LLMs) have transformed the Natural Language Processing (NLP) landscape with their remarkable ability to understand and generate human-like text. However, these models are prone to ``hallucinations'' -- outputs that do not align with factual reality or the input context. This paper introduces the Hallucinations Leaderboard, an open initiative to quantitatively measure and compare the tendency of each model to produce hallucinations. The leaderboard uses a comprehensive set of benchmarks focusing on different aspects of hallucinations, such as factuality and faithfulness, "},"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":"2404.05904","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T23:16:22Z","cross_cats_sorted":[],"title_canon_sha256":"1bb9612e9fe75236c40f8ce6aea7349dcf72760335d382edc83a146b3e280074","abstract_canon_sha256":"0c7fb30c000a73bccb3d10fc1eb2bf912ecd4c7b59ac9b263145ab7ebfc0b565"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:57.178894Z","signature_b64":"/R1ZtZhk5MxODJkT9Xwk6teiQsvgj7nix6lYLqMzoR0/rqgjlKB2dEZJxM9XwoZEoqGcULUR+JCtZBP0F8J0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb3c65485a90b94bd9a69ee4d2600e6f61bbe187e53dbb38433cff0c5406bec1","last_reissued_at":"2026-07-05T08:08:57.178427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:57.178427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Hallucinations Leaderboard -- An Open Effort to Measure Hallucinations in Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aryo Pradipta Gema, Cl\\'ementine Fourrier, Giwon Hong, Laura Perez-Beltrachini, Max Ryabinin, Pasquale Minervini, Ping Nie, Rohit Saxena, Xiaotang Du, Xuanli He, Yu Zhao","submitted_at":"2024-04-08T23:16:22Z","abstract_excerpt":"Large Language Models (LLMs) have transformed the Natural Language Processing (NLP) landscape with their remarkable ability to understand and generate human-like text. However, these models are prone to ``hallucinations'' -- outputs that do not align with factual reality or the input context. This paper introduces the Hallucinations Leaderboard, an open initiative to quantitatively measure and compare the tendency of each model to produce hallucinations. The leaderboard uses a comprehensive set of benchmarks focusing on different aspects of hallucinations, such as factuality and faithfulness, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05904","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/2404.05904/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":"2404.05904","created_at":"2026-07-05T08:08:57.178480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05904v2","created_at":"2026-07-05T08:08:57.178480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05904","created_at":"2026-07-05T08:08:57.178480+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZM6GKSC2SC4U","created_at":"2026-07-05T08:08:57.178480+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZM6GKSC2SC4UXWNG","created_at":"2026-07-05T08:08:57.178480+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZM6GKSC2","created_at":"2026-07-05T08:08:57.178480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11330","citing_title":"Rethinking Evaluation for LLM Hallucination Detection: A Desiderata, A New RAG-based Benchmark, New Insights","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5","json":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5.json","graph_json":"https://pith.science/api/pith-number/ZM6GKSC2SC4UXWNGT3SNEYAON5/graph.json","events_json":"https://pith.science/api/pith-number/ZM6GKSC2SC4UXWNGT3SNEYAON5/events.json","paper":"https://pith.science/paper/ZM6GKSC2"},"agent_actions":{"view_html":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5","download_json":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5.json","view_paper":"https://pith.science/paper/ZM6GKSC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05904&json=true","fetch_graph":"https://pith.science/api/pith-number/ZM6GKSC2SC4UXWNGT3SNEYAON5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZM6GKSC2SC4UXWNGT3SNEYAON5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5/action/storage_attestation","attest_author":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5/action/author_attestation","sign_citation":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5/action/citation_signature","submit_replication":"https://pith.science/pith/ZM6GKSC2SC4UXWNGT3SNEYAON5/action/replication_record"}},"created_at":"2026-07-05T08:08:57.178480+00:00","updated_at":"2026-07-05T08:08:57.178480+00:00"}