{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VJRZ7HONW6F2R2GSA554TIIQTE","short_pith_number":"pith:VJRZ7HON","schema_version":"1.0","canonical_sha256":"aa639f9dcdb78ba8e8d2077bc9a1109926b7b0df64f65ae65b540f241c201e4e","source":{"kind":"arxiv","id":"2401.07078","version":1},"attestation_state":"computed","paper":{"title":"PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Meet Doshi, Pushpak Bhattacharyya, Raj Dabre, Rudra Murthy, Settaluri Lakshmi Sravanthi, Tankala Pavan Kalyan","submitted_at":"2024-01-13T13:46:14Z","abstract_excerpt":"LLMs have demonstrated remarkable capability for understanding semantics, but they often struggle with understanding pragmatics. To demonstrate this fact, we release a Pragmatics Understanding Benchmark (PUB) dataset consisting of fourteen tasks in four pragmatics phenomena, namely, Implicature, Presupposition, Reference, and Deixis. We curated high-quality test sets for each task, consisting of Multiple Choice Question Answers (MCQA). PUB includes a total of 28k data points, 6.1k of which have been created by us, and the rest are adapted from existing datasets. We evaluated nine models varyin"},"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":"2401.07078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T13:46:14Z","cross_cats_sorted":[],"title_canon_sha256":"560c304af7930d9e7929dbdf22dddf0e2dcd244b0ef95a8bf0d5b8ba76af61c5","abstract_canon_sha256":"d2354459d42900032cfce557d8da6583ef5b30d47cf299729d427d91e861caaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:31.543376Z","signature_b64":"Vf1KFX0LKZhuRMP9Swii6aWFpWmRYskMxwrp3qLIS7SftWthuCXr48OasWiEyeE+4jYSYg4CfQqigvb/2N1HAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa639f9dcdb78ba8e8d2077bc9a1109926b7b0df64f65ae65b540f241c201e4e","last_reissued_at":"2026-07-05T07:33:31.542895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:31.542895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Meet Doshi, Pushpak Bhattacharyya, Raj Dabre, Rudra Murthy, Settaluri Lakshmi Sravanthi, Tankala Pavan Kalyan","submitted_at":"2024-01-13T13:46:14Z","abstract_excerpt":"LLMs have demonstrated remarkable capability for understanding semantics, but they often struggle with understanding pragmatics. To demonstrate this fact, we release a Pragmatics Understanding Benchmark (PUB) dataset consisting of fourteen tasks in four pragmatics phenomena, namely, Implicature, Presupposition, Reference, and Deixis. We curated high-quality test sets for each task, consisting of Multiple Choice Question Answers (MCQA). PUB includes a total of 28k data points, 6.1k of which have been created by us, and the rest are adapted from existing datasets. We evaluated nine models varyin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07078","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/2401.07078/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":"2401.07078","created_at":"2026-07-05T07:33:31.542953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07078v1","created_at":"2026-07-05T07:33:31.542953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07078","created_at":"2026-07-05T07:33:31.542953+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJRZ7HONW6F2","created_at":"2026-07-05T07:33:31.542953+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJRZ7HONW6F2R2GS","created_at":"2026-07-05T07:33:31.542953+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJRZ7HON","created_at":"2026-07-05T07:33:31.542953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28782","citing_title":"Can Large Language Models Handle Discourse Particles? A Case Study of Colloquial Malay","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25426","citing_title":"Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE","json":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE.json","graph_json":"https://pith.science/api/pith-number/VJRZ7HONW6F2R2GSA554TIIQTE/graph.json","events_json":"https://pith.science/api/pith-number/VJRZ7HONW6F2R2GSA554TIIQTE/events.json","paper":"https://pith.science/paper/VJRZ7HON"},"agent_actions":{"view_html":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE","download_json":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE.json","view_paper":"https://pith.science/paper/VJRZ7HON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07078&json=true","fetch_graph":"https://pith.science/api/pith-number/VJRZ7HONW6F2R2GSA554TIIQTE/graph.json","fetch_events":"https://pith.science/api/pith-number/VJRZ7HONW6F2R2GSA554TIIQTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE/action/storage_attestation","attest_author":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE/action/author_attestation","sign_citation":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE/action/citation_signature","submit_replication":"https://pith.science/pith/VJRZ7HONW6F2R2GSA554TIIQTE/action/replication_record"}},"created_at":"2026-07-05T07:33:31.542953+00:00","updated_at":"2026-07-05T07:33:31.542953+00:00"}