{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SDRGKB7ZGN6K4UGL5WP5T4DS56","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":"94eb933e70c4d5f10dbaa6183819669947074879052480ea922ff7e202d65d16","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T16:48:56Z","title_canon_sha256":"97d8819bc384706b4c548bce18c43656900f362f45c6ac96ec5b90b5fdeb0be8"},"schema_version":"1.0","source":{"id":"2405.08760","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08760","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08760v2","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08760","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"pith_short_12","alias_value":"SDRGKB7ZGN6K","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"pith_short_16","alias_value":"SDRGKB7ZGN6K4UGL","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"pith_short_8","alias_value":"SDRGKB7Z","created_at":"2026-07-05T08:34:18Z"}],"graph_snapshots":[{"event_id":"sha256:124845c07af74c0e28076b26a0a59ef45074a481f4e12edaf7a6013450b46f49","target":"graph","created_at":"2026-07-05T08:34:18Z","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/2405.08760/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akhila Yerukola, Daniel Fried, Maarten Sap, Saujas Vaduguru","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T16:48:56Z","title":"Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08760","kind":"arxiv","version":2},"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:f2886601d8a29b982f61c94345eca8fbb5fa385b80ec22ac7481734e02777ba8","target":"record","created_at":"2026-07-05T08:34:18Z","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":"94eb933e70c4d5f10dbaa6183819669947074879052480ea922ff7e202d65d16","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-14T16:48:56Z","title_canon_sha256":"97d8819bc384706b4c548bce18c43656900f362f45c6ac96ec5b90b5fdeb0be8"},"schema_version":"1.0","source":{"id":"2405.08760","kind":"arxiv","version":2}},"canonical_sha256":"90e26507f9337cae50cbed9fd9f072ef9f74af275792baabfa6e857b14a83877","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90e26507f9337cae50cbed9fd9f072ef9f74af275792baabfa6e857b14a83877","first_computed_at":"2026-07-05T08:34:18.858936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:18.858936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nCNCO0PrY7ROtggXfC2t9a0cSI7Zbte+woMxR7lgmi9x1uTQVNaMIQ0Lt/3xwQQTm6/4JcaPqLFC66cfE88DDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:18.859340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08760","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2886601d8a29b982f61c94345eca8fbb5fa385b80ec22ac7481734e02777ba8","sha256:124845c07af74c0e28076b26a0a59ef45074a481f4e12edaf7a6013450b46f49"],"state_sha256":"cc633f5e0a8ac1222fb4856fa3c2bd919e11d74a0b5eed36ed0efdb8e2037a60"}