{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FSJFSWCVCJWUCUBD76XJTUC75P","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":"c751fb9619dd771ea0c65695e940bb02e57571e30435b2d2b918d5536f8970dc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T17:11:48Z","title_canon_sha256":"0fc9743a4c795a47268dcb572f16a558a02781bd46779696b9846932966eda39"},"schema_version":"1.0","source":{"id":"2412.11988","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11988","created_at":"2026-07-05T09:49:54Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11988v1","created_at":"2026-07-05T09:49:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11988","created_at":"2026-07-05T09:49:54Z"},{"alias_kind":"pith_short_12","alias_value":"FSJFSWCVCJWU","created_at":"2026-07-05T09:49:54Z"},{"alias_kind":"pith_short_16","alias_value":"FSJFSWCVCJWUCUBD","created_at":"2026-07-05T09:49:54Z"},{"alias_kind":"pith_short_8","alias_value":"FSJFSWCV","created_at":"2026-07-05T09:49:54Z"}],"graph_snapshots":[{"event_id":"sha256:d1842405de20c10e6cc5349337ea0e7fa209ded2222e066f7d7c73fd6f150d5b","target":"graph","created_at":"2026-07-05T09:49:54Z","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/2412.11988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consider the problem: ``If one man and one woman can produce one child in one year, how many children will be produced by one woman and three men in 0.5 years?\" Current large language models (LLMs) such as GPT-4o, GPT-o1-preview, and Gemini Flash frequently answer \"0.5,\" which does not make sense. While these models sometimes acknowledge the unrealistic nature of the question, in many cases (8 out of 10 trials), they provide the nonsensical answer of \"0.5 child.\" Additionally, temporal variation has been observed: if an LLM answers correctly once (by recognizing the faulty nature of the questi","authors_text":"Debarshi Kundu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T17:11:48Z","title":"SciFaultyQA: Benchmarking LLMs on Faulty Science Question Detection with a GAN-Inspired Approach to Synthetic Dataset Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11988","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":"sha256:2f5939c63cdf1ee78a4e89a49f17ac57045f8c5f2a4c872d4b1659cfcd6ab74a","target":"record","created_at":"2026-07-05T09:49:54Z","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":"c751fb9619dd771ea0c65695e940bb02e57571e30435b2d2b918d5536f8970dc","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T17:11:48Z","title_canon_sha256":"0fc9743a4c795a47268dcb572f16a558a02781bd46779696b9846932966eda39"},"schema_version":"1.0","source":{"id":"2412.11988","kind":"arxiv","version":1}},"canonical_sha256":"2c92595855126d415023ffae99d05febc3de874792e7f5400604c58f68db8c37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c92595855126d415023ffae99d05febc3de874792e7f5400604c58f68db8c37","first_computed_at":"2026-07-05T09:49:54.949209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:54.949209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DrRxZGYB1dBf2UB5xxS05xixjCige7fuffn57vnJxhyMYRwxJZbdEscGU6B4Liqh8+J2qN0OP3xlhQSVkcZcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:54.949770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11988","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f5939c63cdf1ee78a4e89a49f17ac57045f8c5f2a4c872d4b1659cfcd6ab74a","sha256:d1842405de20c10e6cc5349337ea0e7fa209ded2222e066f7d7c73fd6f150d5b"],"state_sha256":"b09c14da77b20e9fd3b88266ad0737f638c234558a2f8579492e69010ad8e814"}