{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OQZIFQMWEV454P6AFY3OWEC7WX","short_pith_number":"pith:OQZIFQMW","schema_version":"1.0","canonical_sha256":"743282c1962579de3fc02e36eb105fb5d04e7cd66e7817930d085e956d38a72e","source":{"kind":"arxiv","id":"2605.29712","version":1},"attestation_state":"computed","paper":{"title":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Edwin Simpson, Raul Santos-Rodriguez, Yuxuan Ye","submitted_at":"2026-05-28T10:11:42Z","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"},"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":"2605.29712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T10:11:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77bbbfd77821aa9ef9188909f7f6f0bedf237816f6bcff7988f798b7c127c67d","abstract_canon_sha256":"3a1764a926cefbdbc157f5f9d3ccdee0973f6d9e7cadeb64fb7ac541509ace75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:56.641575Z","signature_b64":"jn2eTLLC0/y8hYRbC7uSqnOf+Dn3UqkQVtmGY7+JSKgnfLXlyEaH54rVuETCuhMrY/L+syL4cRwPQQlb06TnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"743282c1962579de3fc02e36eb105fb5d04e7cd66e7817930d085e956d38a72e","last_reissued_at":"2026-05-29T01:05:56.641067Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:56.641067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Edwin Simpson, Raul Santos-Rodriguez, Yuxuan Ye","submitted_at":"2026-05-28T10:11:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29712","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/2605.29712/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":"2605.29712","created_at":"2026-05-29T01:05:56.641146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29712v1","created_at":"2026-05-29T01:05:56.641146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29712","created_at":"2026-05-29T01:05:56.641146+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQZIFQMWEV45","created_at":"2026-05-29T01:05:56.641146+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQZIFQMWEV454P6A","created_at":"2026-05-29T01:05:56.641146+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQZIFQMW","created_at":"2026-05-29T01:05:56.641146+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/OQZIFQMWEV454P6AFY3OWEC7WX","json":"https://pith.science/pith/OQZIFQMWEV454P6AFY3OWEC7WX.json","graph_json":"https://pith.science/api/pith-number/OQZIFQMWEV454P6AFY3OWEC7WX/graph.json","events_json":"https://pith.science/api/pith-number/OQZIFQMWEV454P6AFY3OWEC7WX/events.json","paper":"https://pith.science/paper/OQZIFQMW"},"agent_actions":{"view_html":"https://pith.science/pith/OQZIFQMWEV454P6AFY3OWEC7WX","download_json":"https://pith.science/pith/OQZIFQMWEV454P6AFY3OWEC7WX.json","view_paper":"https://pith.science/paper/OQZIFQMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29712&json=true","fetch_graph":"https://pith.science/api/pith-number/OQZIFQMWEV454P6AFY3OWEC7WX/graph.json","fetch_events":"https://pith.science/api/pith-number/OQZIFQMWEV454P6AFY3OWEC7WX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQZIFQMWEV454P6AFY3OWEC7WX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQZIFQMWEV454P6AFY3OWEC7WX/action/storage_attestation","attest_author":"https://pith.science/pith/OQZIFQMWEV454P6AFY3OWEC7WX/action/author_attestation","sign_citation":"https://pith.science/pith/OQZIFQMWEV454P6AFY3OWEC7WX/action/citation_signature","submit_replication":"https://pith.science/pith/OQZIFQMWEV454P6AFY3OWEC7WX/action/replication_record"}},"created_at":"2026-05-29T01:05:56.641146+00:00","updated_at":"2026-05-29T01:05:56.641146+00:00"}