{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:727RCSC4WITGF5RZQALEJ2CLJO","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":"ed55ca1ddd01c6ed43b0721395e5563ccd9844946f4529d7461eb08146e065a2","cross_cats_sorted":["cs.CL","cs.SC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T03:06:52Z","title_canon_sha256":"7fa8b8acfd5e6adc9c8349e78588e850ae8fddebfdc28c69beadb1421a04dd94"},"schema_version":"1.0","source":{"id":"2411.17066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.17066","created_at":"2026-07-05T09:40:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.17066v1","created_at":"2026-07-05T09:40:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17066","created_at":"2026-07-05T09:40:26Z"},{"alias_kind":"pith_short_12","alias_value":"727RCSC4WITG","created_at":"2026-07-05T09:40:26Z"},{"alias_kind":"pith_short_16","alias_value":"727RCSC4WITGF5RZ","created_at":"2026-07-05T09:40:26Z"},{"alias_kind":"pith_short_8","alias_value":"727RCSC4","created_at":"2026-07-05T09:40:26Z"}],"graph_snapshots":[{"event_id":"sha256:3e9734e37928b284f228278fcf7984bace0f363570c816d5d1e5d52fbf5143bf","target":"graph","created_at":"2026-07-05T09:40:26Z","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/2411.17066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite remarkable progress in multi-modal AI research, there is a salient domain in which modern AI continues to lag considerably behind even human children: the reliable deployment of logical operators. Here, we examine three forms of logical operators: relations, negations, and discrete numbers. We asked human respondents (N=178 in total) to evaluate images generated by a state-of-the-art image-generating AI (DALL-E 3) prompted with these `logical probes', and find that none reliably produce human agreement scores greater than 50\\%. The negation probes and numbers (beyond 3) fail most frequ","authors_text":"Colin Conwell, Rupert Tawiah-Quashie, Tomer Ullman","cross_cats":["cs.CL","cs.SC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T03:06:52Z","title":"Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17066","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:b0f10e5838558d56da1302c9a4ab56d8f5448a8f9964bda9eb1ebc9da876b286","target":"record","created_at":"2026-07-05T09:40:26Z","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":"ed55ca1ddd01c6ed43b0721395e5563ccd9844946f4529d7461eb08146e065a2","cross_cats_sorted":["cs.CL","cs.SC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-26T03:06:52Z","title_canon_sha256":"7fa8b8acfd5e6adc9c8349e78588e850ae8fddebfdc28c69beadb1421a04dd94"},"schema_version":"1.0","source":{"id":"2411.17066","kind":"arxiv","version":1}},"canonical_sha256":"febf11485cb22662f639801644e84b4bb2d13373968eb8d71872a7064768093a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"febf11485cb22662f639801644e84b4bb2d13373968eb8d71872a7064768093a","first_computed_at":"2026-07-05T09:40:26.940358Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:26.940358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SV11BV9r1GNIHIew1wQpK5O4PWaR8ADs2GvL4ZWE93qPqeJcwJt3hDi/HaMunsw40YdPItzwLEoEKrK+O9A1Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:26.941113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.17066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0f10e5838558d56da1302c9a4ab56d8f5448a8f9964bda9eb1ebc9da876b286","sha256:3e9734e37928b284f228278fcf7984bace0f363570c816d5d1e5d52fbf5143bf"],"state_sha256":"3c16f64860ea9a9c3812931a1aaa2a12a033d746b3d200f80eadfde5652dde03"}