{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2KDDEJFIWW25DL3EAD7ND6XF45","short_pith_number":"pith:2KDDEJFI","schema_version":"1.0","canonical_sha256":"d2863224a8b5b5d1af6400fed1fae5e7504be374f57742dea428bc7df93279ba","source":{"kind":"arxiv","id":"2305.01020","version":1},"attestation_state":"computed","paper":{"title":"Evaluating statistical language models as pragmatic reasoners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Lipkin, Gabriel Grand, Joshua B Tenenbaum, Lionel Wong","submitted_at":"2023-05-01T18:22:10Z","abstract_excerpt":"The relationship between communicated language and intended meaning is often probabilistic and sensitive to context. Numerous strategies attempt to estimate such a mapping, often leveraging recursive Bayesian models of communication. In parallel, large language models (LLMs) have been increasingly applied to semantic parsing applications, tasked with inferring logical representations from natural language. While existing LLM explorations have been largely restricted to literal language use, in this work, we evaluate the capacity of LLMs to infer the meanings of pragmatic utterances. Specifical"},"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":"2305.01020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-01T18:22:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"63f147556fa44461a72ba517ebf3b14d10a42165f37a30c867cb25675b74c1fe","abstract_canon_sha256":"c22e7de58793c626652d8b52d6adc40cb238d0be8d11a3babfbec767886707f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:20.488526Z","signature_b64":"+iHulYLm6z3ldS4zsfBKOgRMp2pdW5y3c0yzIp/ikCS/rdnGpL/NK4QGAfMj+aqhD+YKi1yNQHbM5aEm1z7RDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2863224a8b5b5d1af6400fed1fae5e7504be374f57742dea428bc7df93279ba","last_reissued_at":"2026-07-05T06:06:20.488049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:20.488049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating statistical language models as pragmatic reasoners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin Lipkin, Gabriel Grand, Joshua B Tenenbaum, Lionel Wong","submitted_at":"2023-05-01T18:22:10Z","abstract_excerpt":"The relationship between communicated language and intended meaning is often probabilistic and sensitive to context. Numerous strategies attempt to estimate such a mapping, often leveraging recursive Bayesian models of communication. In parallel, large language models (LLMs) have been increasingly applied to semantic parsing applications, tasked with inferring logical representations from natural language. While existing LLM explorations have been largely restricted to literal language use, in this work, we evaluate the capacity of LLMs to infer the meanings of pragmatic utterances. Specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01020","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/2305.01020/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":"2305.01020","created_at":"2026-07-05T06:06:20.488108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01020v1","created_at":"2026-07-05T06:06:20.488108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01020","created_at":"2026-07-05T06:06:20.488108+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KDDEJFIWW25","created_at":"2026-07-05T06:06:20.488108+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KDDEJFIWW25DL3E","created_at":"2026-07-05T06:06:20.488108+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KDDEJFI","created_at":"2026-07-05T06:06:20.488108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09120","citing_title":"Can Vision-Language Models Infer Speaker's Ignorance? The Role of Visual and Linguistic Cues","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45","json":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45.json","graph_json":"https://pith.science/api/pith-number/2KDDEJFIWW25DL3EAD7ND6XF45/graph.json","events_json":"https://pith.science/api/pith-number/2KDDEJFIWW25DL3EAD7ND6XF45/events.json","paper":"https://pith.science/paper/2KDDEJFI"},"agent_actions":{"view_html":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45","download_json":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45.json","view_paper":"https://pith.science/paper/2KDDEJFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01020&json=true","fetch_graph":"https://pith.science/api/pith-number/2KDDEJFIWW25DL3EAD7ND6XF45/graph.json","fetch_events":"https://pith.science/api/pith-number/2KDDEJFIWW25DL3EAD7ND6XF45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45/action/storage_attestation","attest_author":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45/action/author_attestation","sign_citation":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45/action/citation_signature","submit_replication":"https://pith.science/pith/2KDDEJFIWW25DL3EAD7ND6XF45/action/replication_record"}},"created_at":"2026-07-05T06:06:20.488108+00:00","updated_at":"2026-07-05T06:06:20.488108+00:00"}