{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ISSAN3HVAGV5DNZW32AWZO2LJV","short_pith_number":"pith:ISSAN3HV","schema_version":"1.0","canonical_sha256":"44a406ecf501abd1b736de816cbb4b4d5c2f4e8253f76f934dab3f90803fa841","source":{"kind":"arxiv","id":"2212.06801","version":2},"attestation_state":"computed","paper":{"title":"A fine-grained comparison of pragmatic language understanding in humans and language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Edward Gibson, Evelina Fedorenko, Jennifer Hu, Olessia Jouravlev, Sammy Floyd","submitted_at":"2022-12-13T18:34:59Z","abstract_excerpt":"Pragmatics and non-literal language understanding are essential to human communication, and present a long-standing challenge for artificial language models. We perform a fine-grained comparison of language models and humans on seven pragmatic phenomena, using zero-shot prompting on an expert-curated set of English materials. We ask whether models (1) select pragmatic interpretations of speaker utterances, (2) make similar error patterns as humans, and (3) use similar linguistic cues as humans to solve the tasks. We find that the largest models achieve high accuracy and match human error patte"},"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":"2212.06801","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-13T18:34:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a534dbdcce821e84c15e24a60898e334085fbf25e9359723352016a3767d220e","abstract_canon_sha256":"6637536d5406d2a7c8fd801a70b0539830f837618dcc58e068c1080477a601fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:18.101630Z","signature_b64":"E3pJQVVZjrJEXj9GUoG2PqQ+HVAGoeUustiUGtrjjSawbxHmhtD8m+Gs9UBnc6IVhL8SRAaPa5L6lES2R7vACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44a406ecf501abd1b736de816cbb4b4d5c2f4e8253f76f934dab3f90803fa841","last_reissued_at":"2026-07-05T06:13:18.101078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:18.101078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A fine-grained comparison of pragmatic language understanding in humans and language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Edward Gibson, Evelina Fedorenko, Jennifer Hu, Olessia Jouravlev, Sammy Floyd","submitted_at":"2022-12-13T18:34:59Z","abstract_excerpt":"Pragmatics and non-literal language understanding are essential to human communication, and present a long-standing challenge for artificial language models. We perform a fine-grained comparison of language models and humans on seven pragmatic phenomena, using zero-shot prompting on an expert-curated set of English materials. We ask whether models (1) select pragmatic interpretations of speaker utterances, (2) make similar error patterns as humans, and (3) use similar linguistic cues as humans to solve the tasks. We find that the largest models achieve high accuracy and match human error patte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06801","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/2212.06801/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":"2212.06801","created_at":"2026-07-05T06:13:18.101138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.06801v2","created_at":"2026-07-05T06:13:18.101138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06801","created_at":"2026-07-05T06:13:18.101138+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISSAN3HVAGV5","created_at":"2026-07-05T06:13:18.101138+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISSAN3HVAGV5DNZW","created_at":"2026-07-05T06:13:18.101138+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISSAN3HV","created_at":"2026-07-05T06:13:18.101138+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/ISSAN3HVAGV5DNZW32AWZO2LJV","json":"https://pith.science/pith/ISSAN3HVAGV5DNZW32AWZO2LJV.json","graph_json":"https://pith.science/api/pith-number/ISSAN3HVAGV5DNZW32AWZO2LJV/graph.json","events_json":"https://pith.science/api/pith-number/ISSAN3HVAGV5DNZW32AWZO2LJV/events.json","paper":"https://pith.science/paper/ISSAN3HV"},"agent_actions":{"view_html":"https://pith.science/pith/ISSAN3HVAGV5DNZW32AWZO2LJV","download_json":"https://pith.science/pith/ISSAN3HVAGV5DNZW32AWZO2LJV.json","view_paper":"https://pith.science/paper/ISSAN3HV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.06801&json=true","fetch_graph":"https://pith.science/api/pith-number/ISSAN3HVAGV5DNZW32AWZO2LJV/graph.json","fetch_events":"https://pith.science/api/pith-number/ISSAN3HVAGV5DNZW32AWZO2LJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISSAN3HVAGV5DNZW32AWZO2LJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISSAN3HVAGV5DNZW32AWZO2LJV/action/storage_attestation","attest_author":"https://pith.science/pith/ISSAN3HVAGV5DNZW32AWZO2LJV/action/author_attestation","sign_citation":"https://pith.science/pith/ISSAN3HVAGV5DNZW32AWZO2LJV/action/citation_signature","submit_replication":"https://pith.science/pith/ISSAN3HVAGV5DNZW32AWZO2LJV/action/replication_record"}},"created_at":"2026-07-05T06:13:18.101138+00:00","updated_at":"2026-07-05T06:13:18.101138+00:00"}