{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:N6VT3RH2YFPPYOTGMZM2VLF3AC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dd7364a8c6dbb2a9e72325e51ffa141829d67df2f2272c9433522d72bca21101","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T16:07:33Z","title_canon_sha256":"840351b06eac8c5b7e88d230f0fd765a7d402c3804cbb9d557675273c467e4f9"},"schema_version":"1.0","source":{"id":"2605.31483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31483","created_at":"2026-06-01T02:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31483v1","created_at":"2026-06-01T02:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31483","created_at":"2026-06-01T02:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"N6VT3RH2YFPP","created_at":"2026-06-01T02:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"N6VT3RH2YFPPYOTG","created_at":"2026-06-01T02:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"N6VT3RH2","created_at":"2026-06-01T02:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:7327c311a340315c3cf870ccd27e14ffd2536cba029829b8ebe16ce688bb8e35","target":"graph","created_at":"2026-06-01T02:04:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.31483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite Bengali being the sixth most spoken language in the world, no prior work has systematically evaluated hallucination in large language models (LLMs) for Bengali. We introduce BenHalluEval, a fine-grained hallucination evaluation framework for Bengali covering four tasks: Generative Question Answering (GQA), Bangla-English Code-Mixed QA, Summarization, and Reasoning. We construct 12,000 hallucinated candidates using GPT-5.4 across twelve task-specific hallucination types, drawn from three existing Bengali datasets, and evaluate seven LLMs spanning reasoning-oriented, multilingual, and Be","authors_text":"Ahmed Alfey Sani, Ajwad Abrar, Ekramul Alam Esham, Ishmam Tashdeed, Md Taukir Azam Chowdhury, Shefayat E Shams Adib","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T16:07:33Z","title":"BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31483","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0c222ab6de694dc5ed551efcca653472813619d6692096a824d3bc6a0b39f8e9","target":"record","created_at":"2026-06-01T02:04:08Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dd7364a8c6dbb2a9e72325e51ffa141829d67df2f2272c9433522d72bca21101","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T16:07:33Z","title_canon_sha256":"840351b06eac8c5b7e88d230f0fd765a7d402c3804cbb9d557675273c467e4f9"},"schema_version":"1.0","source":{"id":"2605.31483","kind":"arxiv","version":1}},"canonical_sha256":"6fab3dc4fac15efc3a666659aaacbb00937c1f4eabc9d144276d0114c4a90676","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fab3dc4fac15efc3a666659aaacbb00937c1f4eabc9d144276d0114c4a90676","first_computed_at":"2026-06-01T02:04:08.448669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:04:08.448669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xg9F0yJ6P4JCgCbYJSk3pzLT0Lic8Oz1m+AIbGNknz4OiqrMRUJU15DodUcsYF8ynjnLOKKgxWvsqWI2v7yCBw==","signature_status":"signed_v1","signed_at":"2026-06-01T02:04:08.449559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c222ab6de694dc5ed551efcca653472813619d6692096a824d3bc6a0b39f8e9","sha256:7327c311a340315c3cf870ccd27e14ffd2536cba029829b8ebe16ce688bb8e35"],"state_sha256":"0e447e23df54138a04ce5e3bed33dcc84b07d54ec98ecf2385d8f04052eda164"}