{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SDRGKB7ZGN6K4UGL5WP5T4DS56","short_pith_number":"pith:SDRGKB7Z","schema_version":"1.0","canonical_sha256":"90e26507f9337cae50cbed9fd9f072ef9f74af275792baabfa6e857b14a83877","source":{"kind":"arxiv","id":"2405.08760","version":2},"attestation_state":"computed","paper":{"title":"Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akhila Yerukola, Daniel Fried, Maarten Sap, Saujas Vaduguru","submitted_at":"2024-05-14T16:48:56Z","abstract_excerpt":"Humans often express their communicative intents indirectly or non-literally, which requires their interlocutors -- human or AI -- to understand beyond the literal meaning of words. While most existing work has focused on discriminative evaluations, we present a new approach to generatively evaluate large language models' (LLMs') intention understanding by examining their responses to non-literal utterances. Ideally, an LLM should respond in line with the true intention of a non-literal utterance, not its literal interpretation. Our findings show that LLMs struggle to generate pragmatically re"},"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":"2405.08760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T16:48:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"97d8819bc384706b4c548bce18c43656900f362f45c6ac96ec5b90b5fdeb0be8","abstract_canon_sha256":"94eb933e70c4d5f10dbaa6183819669947074879052480ea922ff7e202d65d16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:18.859340Z","signature_b64":"nCNCO0PrY7ROtggXfC2t9a0cSI7Zbte+woMxR7lgmi9x1uTQVNaMIQ0Lt/3xwQQTm6/4JcaPqLFC66cfE88DDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90e26507f9337cae50cbed9fd9f072ef9f74af275792baabfa6e857b14a83877","last_reissued_at":"2026-07-05T08:34:18.858936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:18.858936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akhila Yerukola, Daniel Fried, Maarten Sap, Saujas Vaduguru","submitted_at":"2024-05-14T16:48:56Z","abstract_excerpt":"Humans often express their communicative intents indirectly or non-literally, which requires their interlocutors -- human or AI -- to understand beyond the literal meaning of words. While most existing work has focused on discriminative evaluations, we present a new approach to generatively evaluate large language models' (LLMs') intention understanding by examining their responses to non-literal utterances. Ideally, an LLM should respond in line with the true intention of a non-literal utterance, not its literal interpretation. Our findings show that LLMs struggle to generate pragmatically re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08760","kind":"arxiv","version":2},"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/2405.08760/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":"2405.08760","created_at":"2026-07-05T08:34:18.858992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08760v2","created_at":"2026-07-05T08:34:18.858992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08760","created_at":"2026-07-05T08:34:18.858992+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDRGKB7ZGN6K","created_at":"2026-07-05T08:34:18.858992+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDRGKB7ZGN6K4UGL","created_at":"2026-07-05T08:34:18.858992+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDRGKB7Z","created_at":"2026-07-05T08:34:18.858992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09551","citing_title":"Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56","json":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56.json","graph_json":"https://pith.science/api/pith-number/SDRGKB7ZGN6K4UGL5WP5T4DS56/graph.json","events_json":"https://pith.science/api/pith-number/SDRGKB7ZGN6K4UGL5WP5T4DS56/events.json","paper":"https://pith.science/paper/SDRGKB7Z"},"agent_actions":{"view_html":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56","download_json":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56.json","view_paper":"https://pith.science/paper/SDRGKB7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08760&json=true","fetch_graph":"https://pith.science/api/pith-number/SDRGKB7ZGN6K4UGL5WP5T4DS56/graph.json","fetch_events":"https://pith.science/api/pith-number/SDRGKB7ZGN6K4UGL5WP5T4DS56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56/action/storage_attestation","attest_author":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56/action/author_attestation","sign_citation":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56/action/citation_signature","submit_replication":"https://pith.science/pith/SDRGKB7ZGN6K4UGL5WP5T4DS56/action/replication_record"}},"created_at":"2026-07-05T08:34:18.858992+00:00","updated_at":"2026-07-05T08:34:18.858992+00:00"}