{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O2LPJLFZJTIW376XUVH2PKGS2R","short_pith_number":"pith:O2LPJLFZ","schema_version":"1.0","canonical_sha256":"7696f4acb94cd16dffd7a54fa7a8d2d45cff4cd4fe5bca8eedb4d09bfdebbc6b","source":{"kind":"arxiv","id":"2505.20880","version":1},"attestation_state":"computed","paper":{"title":"MSA at SemEval-2025 Task 3: High Quality Weak Labeling and LLM Ensemble Verification for Multilingual Hallucination Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Nasreldin, Ali Hamdi, Baraa Hikal","submitted_at":"2025-05-27T08:26:17Z","abstract_excerpt":"This paper describes our submission for SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. The task involves detecting hallucinated spans in text generated by instruction-tuned Large Language Models (LLMs) across multiple languages. Our approach combines task-specific prompt engineering with an LLM ensemble verification mechanism, where a primary model extracts hallucination spans and three independent LLMs adjudicate their validity through probability-based voting. This framework simulates the human annotation workflo"},"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":"2505.20880","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T08:26:17Z","cross_cats_sorted":[],"title_canon_sha256":"ce7cca8cdd522fbcccf198dc3348eb4e59d0ea5e173eaed892c0014a87dfd9ff","abstract_canon_sha256":"41ed147f48b82fbdb0a951578972356aa1a5cfa07b339c84eb07773297e9894a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:20.365430Z","signature_b64":"Y/bQF/ImojuJoWUrouU3ohqa9sjE4JX/AsZ8J1LIIGzfd4SRianR2S1BerJj37YZq2zIHc9+hi97ojxgb8VvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7696f4acb94cd16dffd7a54fa7a8d2d45cff4cd4fe5bca8eedb4d09bfdebbc6b","last_reissued_at":"2026-07-05T11:10:20.364932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:20.364932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSA at SemEval-2025 Task 3: High Quality Weak Labeling and LLM Ensemble Verification for Multilingual Hallucination Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Nasreldin, Ali Hamdi, Baraa Hikal","submitted_at":"2025-05-27T08:26:17Z","abstract_excerpt":"This paper describes our submission for SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes. The task involves detecting hallucinated spans in text generated by instruction-tuned Large Language Models (LLMs) across multiple languages. Our approach combines task-specific prompt engineering with an LLM ensemble verification mechanism, where a primary model extracts hallucination spans and three independent LLMs adjudicate their validity through probability-based voting. This framework simulates the human annotation workflo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20880","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/2505.20880/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":"2505.20880","created_at":"2026-07-05T11:10:20.364984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20880v1","created_at":"2026-07-05T11:10:20.364984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20880","created_at":"2026-07-05T11:10:20.364984+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2LPJLFZJTIW","created_at":"2026-07-05T11:10:20.364984+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2LPJLFZJTIW376X","created_at":"2026-07-05T11:10:20.364984+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2LPJLFZ","created_at":"2026-07-05T11:10:20.364984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R","json":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R.json","graph_json":"https://pith.science/api/pith-number/O2LPJLFZJTIW376XUVH2PKGS2R/graph.json","events_json":"https://pith.science/api/pith-number/O2LPJLFZJTIW376XUVH2PKGS2R/events.json","paper":"https://pith.science/paper/O2LPJLFZ"},"agent_actions":{"view_html":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R","download_json":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R.json","view_paper":"https://pith.science/paper/O2LPJLFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20880&json=true","fetch_graph":"https://pith.science/api/pith-number/O2LPJLFZJTIW376XUVH2PKGS2R/graph.json","fetch_events":"https://pith.science/api/pith-number/O2LPJLFZJTIW376XUVH2PKGS2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R/action/storage_attestation","attest_author":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R/action/author_attestation","sign_citation":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R/action/citation_signature","submit_replication":"https://pith.science/pith/O2LPJLFZJTIW376XUVH2PKGS2R/action/replication_record"}},"created_at":"2026-07-05T11:10:20.364984+00:00","updated_at":"2026-07-05T11:10:20.364984+00:00"}