{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OQZIFQMWEV454P6AFY3OWEC7WX","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":"3a1764a926cefbdbc157f5f9d3ccdee0973f6d9e7cadeb64fb7ac541509ace75","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T10:11:42Z","title_canon_sha256":"77bbbfd77821aa9ef9188909f7f6f0bedf237816f6bcff7988f798b7c127c67d"},"schema_version":"1.0","source":{"id":"2605.29712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29712","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29712v1","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29712","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"OQZIFQMWEV45","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"OQZIFQMWEV454P6A","created_at":"2026-05-29T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"OQZIFQMW","created_at":"2026-05-29T01:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:395b4127177542174930ae5db70c2117bd0eb8879508c8e0413c363ad0b2f9ff","target":"graph","created_at":"2026-05-29T01:05:56Z","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/2605.29712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Grounded claim factuality checking is important for large language model (LLM) applications such as retrieval-augmented generation, as it helps users assess the correctness of generated outputs. Existing metrics using entailment classifiers require dataset-specific threshold tuning, while LLM-based approaches often use direct prompting, which underutilises the reasoning capabilities of LLMs. We address this by formulating grounded claim factuality checking as a true/false reading comprehension task and prompting LLMs with explicit test-taking strategies for efficient reasoning. Our method redu","authors_text":"Edwin Simpson, Raul Santos-Rodriguez, Yuxuan Ye","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T10:11:42Z","title":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29712","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":"sha256:52da6ddb6554023e9f3cecc7e05ccc228ff66735057cae1a7d1a15a0c6f50180","target":"record","created_at":"2026-05-29T01:05:56Z","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":"3a1764a926cefbdbc157f5f9d3ccdee0973f6d9e7cadeb64fb7ac541509ace75","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T10:11:42Z","title_canon_sha256":"77bbbfd77821aa9ef9188909f7f6f0bedf237816f6bcff7988f798b7c127c67d"},"schema_version":"1.0","source":{"id":"2605.29712","kind":"arxiv","version":1}},"canonical_sha256":"743282c1962579de3fc02e36eb105fb5d04e7cd66e7817930d085e956d38a72e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"743282c1962579de3fc02e36eb105fb5d04e7cd66e7817930d085e956d38a72e","first_computed_at":"2026-05-29T01:05:56.641067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:56.641067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jn2eTLLC0/y8hYRbC7uSqnOf+Dn3UqkQVtmGY7+JSKgnfLXlyEaH54rVuETCuhMrY/L+syL4cRwPQQlb06TnBw==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:56.641575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52da6ddb6554023e9f3cecc7e05ccc228ff66735057cae1a7d1a15a0c6f50180","sha256:395b4127177542174930ae5db70c2117bd0eb8879508c8e0413c363ad0b2f9ff"],"state_sha256":"2638532439d2f0a748b4df455de971cee276f9938d19d3cd8a8d45d565950c37"}