{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:24SNICU2GXRD7J6SIAFV6GNC3P","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":"96c11ed930c77f4fc98313423786acaa8f66cf866c53dc867484d520bed60de5","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T16:05:13Z","title_canon_sha256":"1f057c9396ae54c9b5af43691250b0c5935f78c50a6d1fad4e24c8d4b4b483ec"},"schema_version":"1.0","source":{"id":"2310.15061","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15061","created_at":"2026-07-05T07:35:22Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15061v1","created_at":"2026-07-05T07:35:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15061","created_at":"2026-07-05T07:35:22Z"},{"alias_kind":"pith_short_12","alias_value":"24SNICU2GXRD","created_at":"2026-07-05T07:35:22Z"},{"alias_kind":"pith_short_16","alias_value":"24SNICU2GXRD7J6S","created_at":"2026-07-05T07:35:22Z"},{"alias_kind":"pith_short_8","alias_value":"24SNICU2","created_at":"2026-07-05T07:35:22Z"}],"graph_snapshots":[{"event_id":"sha256:f5d3fa15d025c5c1f33fb3eeb140ef6d1c06584119f3326f7b2048943305d5ec","target":"graph","created_at":"2026-07-05T07:35:22Z","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/2310.15061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the impressive performance achieved by pre-trained language-and-vision models in downstream tasks, it remains an open question whether this reflects a proper understanding of image-text interaction. In this work, we explore to what extent they handle basic linguistic constructions -- active-passive voice, coordination, and relative clauses -- that even preschool children can typically master. We present BLA, a novel, automatically constructed benchmark to evaluate multimodal models on these Basic Language Abilities. We show that different types of Transformer-based systems, such as CLI","authors_text":"Raquel Fern\\'andez, Sandro Pezzelle, Xinyi Chen","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T16:05:13Z","title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15061","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:d5dee0e2b20a6a78a71f6f36b2304611a3fa7250cca18686dc80b48b55172511","target":"record","created_at":"2026-07-05T07:35:22Z","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":"96c11ed930c77f4fc98313423786acaa8f66cf866c53dc867484d520bed60de5","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T16:05:13Z","title_canon_sha256":"1f057c9396ae54c9b5af43691250b0c5935f78c50a6d1fad4e24c8d4b4b483ec"},"schema_version":"1.0","source":{"id":"2310.15061","kind":"arxiv","version":1}},"canonical_sha256":"d724d40a9a35e23fa7d2400b5f19a2dbf8e474752ce6fbce914cf2977dcbf476","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d724d40a9a35e23fa7d2400b5f19a2dbf8e474752ce6fbce914cf2977dcbf476","first_computed_at":"2026-07-05T07:35:22.189560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:22.189560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oHTf2jFDpUI/v7QxKLYSXVE2aLe5LH8Ao2v+7slQ6JG6QpbU81+p4BYvS5BAsKg5Ds7JMWljRm+PqsDju3cqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:22.189999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15061","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5dee0e2b20a6a78a71f6f36b2304611a3fa7250cca18686dc80b48b55172511","sha256:f5d3fa15d025c5c1f33fb3eeb140ef6d1c06584119f3326f7b2048943305d5ec"],"state_sha256":"a9be45f9b73202b0ff2acd12be78eaa5b9d135209fcd0e0917e0b59314ea4590"}