{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3WG5YZXJBIT4CD4KGT33YPI6AI","short_pith_number":"pith:3WG5YZXJ","schema_version":"1.0","canonical_sha256":"dd8ddc66e90a27c10f8a34f7bc3d1e020b6985069c8ee9a448150deb7220774d","source":{"kind":"arxiv","id":"2505.17485","version":1},"attestation_state":"computed","paper":{"title":"keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Parameswari Krishnamurthy, Saketh Reddy Vemula","submitted_at":"2025-05-23T05:25:14Z","abstract_excerpt":"Identification of hallucination spans in black-box language model generated text is essential for applications in the real world. A recent attempt at this direction is SemEval-2025 Task 3, Mu-SHROOM-a Multilingual Shared Task on Hallucinations and Related Observable Over-generation Errors. In this work, we present our solution to this problem, which capitalizes on the variability of stochastically-sampled responses in order to identify hallucinated spans. Our hypothesis is that if a language model is certain of a fact, its sampled responses will be uniform, while hallucinated facts will yield "},"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":"2505.17485","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T05:25:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f11f4b625a486a281cf16b947c728116c44ee231e7c0b57f61fa4aaef46e242b","abstract_canon_sha256":"e431b283f1aae7ca257f3e4993e995145413d36d3fd172d009f6daec920bb8b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:26.815071Z","signature_b64":"cVQeIVFF2ngcTIAC4aRZfKKO14SIZt62Qd0jEHehVj8kuuRrzQxtPEcLYPgpJIC74+v5YeG34Anxd4NXMNtmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd8ddc66e90a27c10f8a34f7bc3d1e020b6985069c8ee9a448150deb7220774d","last_reissued_at":"2026-07-05T11:08:26.814627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:26.814627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Parameswari Krishnamurthy, Saketh Reddy Vemula","submitted_at":"2025-05-23T05:25:14Z","abstract_excerpt":"Identification of hallucination spans in black-box language model generated text is essential for applications in the real world. A recent attempt at this direction is SemEval-2025 Task 3, Mu-SHROOM-a Multilingual Shared Task on Hallucinations and Related Observable Over-generation Errors. In this work, we present our solution to this problem, which capitalizes on the variability of stochastically-sampled responses in order to identify hallucinated spans. Our hypothesis is that if a language model is certain of a fact, its sampled responses will be uniform, while hallucinated facts will yield "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17485","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/2505.17485/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":"2505.17485","created_at":"2026-07-05T11:08:26.814676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17485v1","created_at":"2026-07-05T11:08:26.814676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17485","created_at":"2026-07-05T11:08:26.814676+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WG5YZXJBIT4","created_at":"2026-07-05T11:08:26.814676+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WG5YZXJBIT4CD4K","created_at":"2026-07-05T11:08:26.814676+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WG5YZXJ","created_at":"2026-07-05T11:08:26.814676+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/3WG5YZXJBIT4CD4KGT33YPI6AI","json":"https://pith.science/pith/3WG5YZXJBIT4CD4KGT33YPI6AI.json","graph_json":"https://pith.science/api/pith-number/3WG5YZXJBIT4CD4KGT33YPI6AI/graph.json","events_json":"https://pith.science/api/pith-number/3WG5YZXJBIT4CD4KGT33YPI6AI/events.json","paper":"https://pith.science/paper/3WG5YZXJ"},"agent_actions":{"view_html":"https://pith.science/pith/3WG5YZXJBIT4CD4KGT33YPI6AI","download_json":"https://pith.science/pith/3WG5YZXJBIT4CD4KGT33YPI6AI.json","view_paper":"https://pith.science/paper/3WG5YZXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17485&json=true","fetch_graph":"https://pith.science/api/pith-number/3WG5YZXJBIT4CD4KGT33YPI6AI/graph.json","fetch_events":"https://pith.science/api/pith-number/3WG5YZXJBIT4CD4KGT33YPI6AI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WG5YZXJBIT4CD4KGT33YPI6AI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WG5YZXJBIT4CD4KGT33YPI6AI/action/storage_attestation","attest_author":"https://pith.science/pith/3WG5YZXJBIT4CD4KGT33YPI6AI/action/author_attestation","sign_citation":"https://pith.science/pith/3WG5YZXJBIT4CD4KGT33YPI6AI/action/citation_signature","submit_replication":"https://pith.science/pith/3WG5YZXJBIT4CD4KGT33YPI6AI/action/replication_record"}},"created_at":"2026-07-05T11:08:26.814676+00:00","updated_at":"2026-07-05T11:08:26.814676+00:00"}