{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TVSJ2QJQDAR4WJN7T2BDJMSFEA","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":"4ca42d097436eedddd510063efc21e03417035a2815a24d37c912f0c9584ebd1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T06:41:09Z","title_canon_sha256":"49d8d08801a32c3d6b16d9d0ac6f90cf9ced0b3bd3a280df12ebb65c7ba688a2"},"schema_version":"1.0","source":{"id":"2305.14785","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14785","created_at":"2026-07-05T08:06:41Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14785v2","created_at":"2026-07-05T08:06:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14785","created_at":"2026-07-05T08:06:41Z"},{"alias_kind":"pith_short_12","alias_value":"TVSJ2QJQDAR4","created_at":"2026-07-05T08:06:41Z"},{"alias_kind":"pith_short_16","alias_value":"TVSJ2QJQDAR4WJN7","created_at":"2026-07-05T08:06:41Z"},{"alias_kind":"pith_short_8","alias_value":"TVSJ2QJQ","created_at":"2026-07-05T08:06:41Z"}],"graph_snapshots":[{"event_id":"sha256:9568fe50c3625b0d9985a8e16c7dffccb3bdc6b26c284548758fb9abf5f618f3","target":"graph","created_at":"2026-07-05T08:06:41Z","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/2305.14785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate LLMs' language understanding capacities on simple inference tasks that most humans find trivial. Specifically, we target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. We design evaluation sets for these tasks and conduct experiments in both zero-shot and chain-of-thought setups, and with multiple prompts and LLMs. The models exhibit moderate to low performance on these evaluation sets. Subsequent experiments show that embedding the premise in syntactic constructions that should preserve the entailm","authors_text":"Reut Tsarfaty, Victoria Basmov, Yoav Goldberg","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T06:41:09Z","title":"Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14785","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":"sha256:924f9b1ac2292999ae4a1cd01c951e03fd00308825b77503eee3718d0c40374f","target":"record","created_at":"2026-07-05T08:06:41Z","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":"4ca42d097436eedddd510063efc21e03417035a2815a24d37c912f0c9584ebd1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T06:41:09Z","title_canon_sha256":"49d8d08801a32c3d6b16d9d0ac6f90cf9ced0b3bd3a280df12ebb65c7ba688a2"},"schema_version":"1.0","source":{"id":"2305.14785","kind":"arxiv","version":2}},"canonical_sha256":"9d649d41301823cb25bf9e8234b245203179b0356d4b559d56e5afdd4427fa01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d649d41301823cb25bf9e8234b245203179b0356d4b559d56e5afdd4427fa01","first_computed_at":"2026-07-05T08:06:41.003363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:41.003363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AhTqkolymjQjfjRXJdYeXmDPBZ5ZB71PZVMpFQPkuuzoAbxBHuOo6yBiztMBJ+PUq6SAQDsEWTLny/8joAXAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:41.003873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14785","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:924f9b1ac2292999ae4a1cd01c951e03fd00308825b77503eee3718d0c40374f","sha256:9568fe50c3625b0d9985a8e16c7dffccb3bdc6b26c284548758fb9abf5f618f3"],"state_sha256":"af2036466f6b37dd3982c165e66643334f7d693f1ecd3f2b192022b75dcd03c6"}