{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:24SNICU2GXRD7J6SIAFV6GNC3P","short_pith_number":"pith:24SNICU2","schema_version":"1.0","canonical_sha256":"d724d40a9a35e23fa7d2400b5f19a2dbf8e474752ce6fbce914cf2977dcbf476","source":{"kind":"arxiv","id":"2310.15061","version":1},"attestation_state":"computed","paper":{"title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Raquel Fern\\'andez, Sandro Pezzelle, Xinyi Chen","submitted_at":"2023-10-23T16:05:13Z","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"},"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":"2310.15061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T16:05:13Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"1f057c9396ae54c9b5af43691250b0c5935f78c50a6d1fad4e24c8d4b4b483ec","abstract_canon_sha256":"96c11ed930c77f4fc98313423786acaa8f66cf866c53dc867484d520bed60de5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:22.189999Z","signature_b64":"oHTf2jFDpUI/v7QxKLYSXVE2aLe5LH8Ao2v+7slQ6JG6QpbU81+p4BYvS5BAsKg5Ds7JMWljRm+PqsDju3cqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d724d40a9a35e23fa7d2400b5f19a2dbf8e474752ce6fbce914cf2977dcbf476","last_reissued_at":"2026-07-05T07:35:22.189560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:22.189560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Raquel Fern\\'andez, Sandro Pezzelle, Xinyi Chen","submitted_at":"2023-10-23T16:05:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15061","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/2310.15061/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":"2310.15061","created_at":"2026-07-05T07:35:22.189617+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15061v1","created_at":"2026-07-05T07:35:22.189617+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15061","created_at":"2026-07-05T07:35:22.189617+00:00"},{"alias_kind":"pith_short_12","alias_value":"24SNICU2GXRD","created_at":"2026-07-05T07:35:22.189617+00:00"},{"alias_kind":"pith_short_16","alias_value":"24SNICU2GXRD7J6S","created_at":"2026-07-05T07:35:22.189617+00:00"},{"alias_kind":"pith_short_8","alias_value":"24SNICU2","created_at":"2026-07-05T07:35:22.189617+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08227","citing_title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P","json":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P.json","graph_json":"https://pith.science/api/pith-number/24SNICU2GXRD7J6SIAFV6GNC3P/graph.json","events_json":"https://pith.science/api/pith-number/24SNICU2GXRD7J6SIAFV6GNC3P/events.json","paper":"https://pith.science/paper/24SNICU2"},"agent_actions":{"view_html":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P","download_json":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P.json","view_paper":"https://pith.science/paper/24SNICU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15061&json=true","fetch_graph":"https://pith.science/api/pith-number/24SNICU2GXRD7J6SIAFV6GNC3P/graph.json","fetch_events":"https://pith.science/api/pith-number/24SNICU2GXRD7J6SIAFV6GNC3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P/action/storage_attestation","attest_author":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P/action/author_attestation","sign_citation":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P/action/citation_signature","submit_replication":"https://pith.science/pith/24SNICU2GXRD7J6SIAFV6GNC3P/action/replication_record"}},"created_at":"2026-07-05T07:35:22.189617+00:00","updated_at":"2026-07-05T07:35:22.189617+00:00"}