{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZIZ6C6VSW35QZJHXG2223M6EVP","short_pith_number":"pith:ZIZ6C6VS","schema_version":"1.0","canonical_sha256":"ca33e17ab2b6fb0ca4f736b5adb3c4abef7143f6bede9a938599c7f5fcd7f138","source":{"kind":"arxiv","id":"2208.00005","version":1},"attestation_state":"computed","paper":{"title":"Testing Relational Understanding in Text-Guided Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Colin Conwell, Tomer Ullman","submitted_at":"2022-07-29T02:59:38Z","abstract_excerpt":"Relations are basic building blocks of human cognition. Classic and recent work suggests that many relations are early developing, and quickly perceived. Machine models that aspire to human-level perception and reasoning should reflect the ability to recognize and reason generatively about relations. We report a systematic empirical examination of a recent text-guided image generation model (DALL-E 2), using a set of 15 basic physical and social relations studied or proposed in the literature, and judgements from human participants (N = 169). Overall, we find that only ~22% of images matched b"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2208.00005","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-29T02:59:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d0924e78bfa656e3ff0f0c71aad7380d37fe17d8f302fa89762f0ba2bdf068bf","abstract_canon_sha256":"16ce1b9ad85bf1f94f48389bb0a633d80e74d32ea80eaab82287a66db4f5c1cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:46.775912Z","signature_b64":"fxHzuorAG45TeGkj6AhjgKsNALiabxqy1R1qM1hWXohPXGSTYOCJMWNDlKVhjYdNrORJP9cpTENdYVpINGT9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca33e17ab2b6fb0ca4f736b5adb3c4abef7143f6bede9a938599c7f5fcd7f138","last_reissued_at":"2026-07-05T04:44:46.775372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:46.775372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Testing Relational Understanding in Text-Guided Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Colin Conwell, Tomer Ullman","submitted_at":"2022-07-29T02:59:38Z","abstract_excerpt":"Relations are basic building blocks of human cognition. Classic and recent work suggests that many relations are early developing, and quickly perceived. Machine models that aspire to human-level perception and reasoning should reflect the ability to recognize and reason generatively about relations. We report a systematic empirical examination of a recent text-guided image generation model (DALL-E 2), using a set of 15 basic physical and social relations studied or proposed in the literature, and judgements from human participants (N = 169). Overall, we find that only ~22% of images matched b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00005","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/2208.00005/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2208.00005","created_at":"2026-07-05T04:44:46.775434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.00005v1","created_at":"2026-07-05T04:44:46.775434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00005","created_at":"2026-07-05T04:44:46.775434+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZIZ6C6VSW35Q","created_at":"2026-07-05T04:44:46.775434+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZIZ6C6VSW35QZJHX","created_at":"2026-07-05T04:44:46.775434+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZIZ6C6VS","created_at":"2026-07-05T04:44:46.775434+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19941","citing_title":"Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2505.03530","citing_title":"A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10019","citing_title":"The two clocks and the innovation window: When and how generative models learn rules","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP","json":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP.json","graph_json":"https://pith.science/api/pith-number/ZIZ6C6VSW35QZJHXG2223M6EVP/graph.json","events_json":"https://pith.science/api/pith-number/ZIZ6C6VSW35QZJHXG2223M6EVP/events.json","paper":"https://pith.science/paper/ZIZ6C6VS"},"agent_actions":{"view_html":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP","download_json":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP.json","view_paper":"https://pith.science/paper/ZIZ6C6VS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.00005&json=true","fetch_graph":"https://pith.science/api/pith-number/ZIZ6C6VSW35QZJHXG2223M6EVP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZIZ6C6VSW35QZJHXG2223M6EVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP/action/storage_attestation","attest_author":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP/action/author_attestation","sign_citation":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP/action/citation_signature","submit_replication":"https://pith.science/pith/ZIZ6C6VSW35QZJHXG2223M6EVP/action/replication_record"}},"created_at":"2026-07-05T04:44:46.775434+00:00","updated_at":"2026-07-05T04:44:46.775434+00:00"}