{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:N5TXT3BW3HJZAQMNA7IPQKQSL5","short_pith_number":"pith:N5TXT3BW","canonical_record":{"source":{"id":"2210.07993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T17:46:05Z","cross_cats_sorted":[],"title_canon_sha256":"747abaefef75ac4dd64ec9f3c8c6b11bb7f9ad1e4ccbf980d7b1eb9db5a2a138","abstract_canon_sha256":"5a19e63b8837c416e8e986f461ad0820c68a4fdb838f40182a428d775cf2442e"},"schema_version":"1.0"},"canonical_sha256":"6f6779ec36d9d390418d07d0f82a125f40033abecbcf53e4afde88431b659ff3","source":{"kind":"arxiv","id":"2210.07993","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:N5TXT3BW3HJZAQMNA7IPQKQSL5","target":"record","payload":{"canonical_record":{"source":{"id":"2210.07993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T17:46:05Z","cross_cats_sorted":[],"title_canon_sha256":"747abaefef75ac4dd64ec9f3c8c6b11bb7f9ad1e4ccbf980d7b1eb9db5a2a138","abstract_canon_sha256":"5a19e63b8837c416e8e986f461ad0820c68a4fdb838f40182a428d775cf2442e"},"schema_version":"1.0"},"canonical_sha256":"6f6779ec36d9d390418d07d0f82a125f40033abecbcf53e4afde88431b659ff3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:43.251563Z","signature_b64":"aO8rk+Z7dNLcu+BAa2ZzmH/nNjwd0VxXOgh6MyO5+o+zxIKuHzz13t56ATWBOJPXabMUPFu0VqO9n+UD6ZPYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f6779ec36d9d390418d07d0f82a125f40033abecbcf53e4afde88431b659ff3","last_reissued_at":"2026-07-05T05:06:43.251215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:43.251215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.07993","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:06:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aMyhoNqKgUBnuXQfQhTRZQpBGHKMDX/PzJB5dHCkDuBOEP19b4Eqadx6gGzank6R2DFvqeBuiXCUWc6GdRSrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:58:44.601854Z"},"content_sha256":"a870e82303322033fadb461eedb3423527e7d9671747b30c3430dee9f8ef3c79","schema_version":"1.0","event_id":"sha256:a870e82303322033fadb461eedb3423527e7d9671747b30c3430dee9f8ef3c79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:N5TXT3BW3HJZAQMNA7IPQKQSL5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MiQA: A Benchmark for Inference on Metaphorical Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iulia-Maria Comsa, Julian Martin Eisenschlos, Srini Narayanan","submitted_at":"2022-10-14T17:46:05Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07993","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/2210.07993/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:06:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"joyqNajfInK8hhtGZ8LBBj4zCw3kRmv8h9rxMS+MtSRe1iWfnD/1bk3wj00Ji3hYspY3Q6ZqiH0FF84o8WQPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:58:44.602354Z"},"content_sha256":"6a5c76f79aec59bb429b143e9f52f713b2bb618dedc27fa0c9c1474344a868e0","schema_version":"1.0","event_id":"sha256:6a5c76f79aec59bb429b143e9f52f713b2bb618dedc27fa0c9c1474344a868e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5TXT3BW3HJZAQMNA7IPQKQSL5/bundle.json","state_url":"https://pith.science/pith/N5TXT3BW3HJZAQMNA7IPQKQSL5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5TXT3BW3HJZAQMNA7IPQKQSL5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T22:58:44Z","links":{"resolver":"https://pith.science/pith/N5TXT3BW3HJZAQMNA7IPQKQSL5","bundle":"https://pith.science/pith/N5TXT3BW3HJZAQMNA7IPQKQSL5/bundle.json","state":"https://pith.science/pith/N5TXT3BW3HJZAQMNA7IPQKQSL5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5TXT3BW3HJZAQMNA7IPQKQSL5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1/Em76/HcuRPabi/tNjhUC6iEH23Y75bDwwl3d0eiE1YDbNf1vCmAL9NhYw35w0Eu+EeV6AqR5Mt3BLzgBoQAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:58:44.606249Z","bundle_sha256":"e62dbad0ecfadee19975efa8cf1a9563f4fa3f7878b2616f901127d1694f814f"}}