{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N5TXT3BW3HJZAQMNA7IPQKQSL5","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":"5a19e63b8837c416e8e986f461ad0820c68a4fdb838f40182a428d775cf2442e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T17:46:05Z","title_canon_sha256":"747abaefef75ac4dd64ec9f3c8c6b11bb7f9ad1e4ccbf980d7b1eb9db5a2a138"},"schema_version":"1.0","source":{"id":"2210.07993","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07993","created_at":"2026-07-05T05:06:43Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07993v1","created_at":"2026-07-05T05:06:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07993","created_at":"2026-07-05T05:06:43Z"},{"alias_kind":"pith_short_12","alias_value":"N5TXT3BW3HJZ","created_at":"2026-07-05T05:06:43Z"},{"alias_kind":"pith_short_16","alias_value":"N5TXT3BW3HJZAQMN","created_at":"2026-07-05T05:06:43Z"},{"alias_kind":"pith_short_8","alias_value":"N5TXT3BW","created_at":"2026-07-05T05:06:43Z"}],"graph_snapshots":[{"event_id":"sha256:6a5c76f79aec59bb429b143e9f52f713b2bb618dedc27fa0c9c1474344a868e0","target":"graph","created_at":"2026-07-05T05:06:43Z","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/2210.07993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a benchmark to assess the capability of large language models to reason with conventional metaphors. Our benchmark combines the previously isolated topics of metaphor detection and commonsense reasoning into a single task that requires a model to make inferences by accurately selecting between the literal and metaphorical register. We examine the performance of state-of-the-art pre-trained models on binary-choice tasks and find a large discrepancy between the performance of small and very large models, going from chance to near-human level. We also analyse the largest model in a gen","authors_text":"Iulia-Maria Comsa, Julian Martin Eisenschlos, Srini Narayanan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T17:46:05Z","title":"MiQA: A Benchmark for Inference on Metaphorical Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07993","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:a870e82303322033fadb461eedb3423527e7d9671747b30c3430dee9f8ef3c79","target":"record","created_at":"2026-07-05T05:06:43Z","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":"5a19e63b8837c416e8e986f461ad0820c68a4fdb838f40182a428d775cf2442e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T17:46:05Z","title_canon_sha256":"747abaefef75ac4dd64ec9f3c8c6b11bb7f9ad1e4ccbf980d7b1eb9db5a2a138"},"schema_version":"1.0","source":{"id":"2210.07993","kind":"arxiv","version":1}},"canonical_sha256":"6f6779ec36d9d390418d07d0f82a125f40033abecbcf53e4afde88431b659ff3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f6779ec36d9d390418d07d0f82a125f40033abecbcf53e4afde88431b659ff3","first_computed_at":"2026-07-05T05:06:43.251215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:43.251215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aO8rk+Z7dNLcu+BAa2ZzmH/nNjwd0VxXOgh6MyO5+o+zxIKuHzz13t56ATWBOJPXabMUPFu0VqO9n+UD6ZPYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:43.251563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07993","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a870e82303322033fadb461eedb3423527e7d9671747b30c3430dee9f8ef3c79","sha256:6a5c76f79aec59bb429b143e9f52f713b2bb618dedc27fa0c9c1474344a868e0"],"state_sha256":"f7dcedc069b4b206a5788a79937d97b07a0563a41346023096e9126b1cafc14b"}