{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VJRZ7HONW6F2R2GSA554TIIQTE","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":"d2354459d42900032cfce557d8da6583ef5b30d47cf299729d427d91e861caaa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T13:46:14Z","title_canon_sha256":"560c304af7930d9e7929dbdf22dddf0e2dcd244b0ef95a8bf0d5b8ba76af61c5"},"schema_version":"1.0","source":{"id":"2401.07078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07078","created_at":"2026-07-05T07:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07078v1","created_at":"2026-07-05T07:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07078","created_at":"2026-07-05T07:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"VJRZ7HONW6F2","created_at":"2026-07-05T07:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"VJRZ7HONW6F2R2GS","created_at":"2026-07-05T07:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"VJRZ7HON","created_at":"2026-07-05T07:33:31Z"}],"graph_snapshots":[{"event_id":"sha256:af61f62a41b13eb910570de81aa762a2b247b335171640567916fda73aecb955","target":"graph","created_at":"2026-07-05T07:33:31Z","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/2401.07078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Meet Doshi, Pushpak Bhattacharyya, Raj Dabre, Rudra Murthy, Settaluri Lakshmi Sravanthi, Tankala Pavan Kalyan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T13:46:14Z","title":"PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07078","kind":"arxiv","version":1},"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":"sha256:76856595f1564c9149bcdc58eecafd933b8fe5a0a6bfa8e5ff22c05fc799097b","target":"record","created_at":"2026-07-05T07:33:31Z","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":"d2354459d42900032cfce557d8da6583ef5b30d47cf299729d427d91e861caaa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-13T13:46:14Z","title_canon_sha256":"560c304af7930d9e7929dbdf22dddf0e2dcd244b0ef95a8bf0d5b8ba76af61c5"},"schema_version":"1.0","source":{"id":"2401.07078","kind":"arxiv","version":1}},"canonical_sha256":"aa639f9dcdb78ba8e8d2077bc9a1109926b7b0df64f65ae65b540f241c201e4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa639f9dcdb78ba8e8d2077bc9a1109926b7b0df64f65ae65b540f241c201e4e","first_computed_at":"2026-07-05T07:33:31.542895Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:31.542895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vf1KFX0LKZhuRMP9Swii6aWFpWmRYskMxwrp3qLIS7SftWthuCXr48OasWiEyeE+4jYSYg4CfQqigvb/2N1HAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:31.543376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76856595f1564c9149bcdc58eecafd933b8fe5a0a6bfa8e5ff22c05fc799097b","sha256:af61f62a41b13eb910570de81aa762a2b247b335171640567916fda73aecb955"],"state_sha256":"31dea8b7366958473a0423abdf842afda0020cf52932a4ce1cb8ca3571bc1061"}