{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7DFX62YXUM7TSBLMKX35XF6PB3","short_pith_number":"pith:7DFX62YX","schema_version":"1.0","canonical_sha256":"f8cb7f6b17a33f39056c55f7db97cf0ef95d69db4a9a5b8617b1bf3aa7a07b89","source":{"kind":"arxiv","id":"2606.05497","version":1},"attestation_state":"computed","paper":{"title":"LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, \"Is Your VLM Smarter Than a 5th Grader?\")","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alvin Wei Ming Tan, David Cardinal, Laura Bravo-Sanchez, Michael C. Frank, Sunny Yu, Tania Lorido-Botran","submitted_at":"2026-06-03T22:41:11Z","abstract_excerpt":"Given the inherently multimodal nature of human experience, vision-language models (VLMs) hold substantial promise for modeling human cognition as it grows and develops with experience. Realizing their potential requires tools for comparing VLMs with human cognitive development across tasks, ages, and populations. We present LEVANTE-bench, a benchmark based on tasks and data from the Learning Variability Network (LEVANTE), which distributes open-source tasks and data measuring children's cognition across languages and cultures. In LEVANTE-bench, we systematically assess VLMs on six tasks, comp"},"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":"2606.05497","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T22:41:11Z","cross_cats_sorted":[],"title_canon_sha256":"87b403daa34765e6b6656e311fa66a37153e1aa3169de4278a8770e8bd952ad9","abstract_canon_sha256":"e19d0e3addb3301f21aa0bda456962719f08b94c61ec334048a273bfea19941d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:52.972645Z","signature_b64":"Y5m5AaPdZGGZsEj68/GYq/zGp4BEhWe11//yvoipCdFkzOQNNy0N8UaRlx2YuZ2R4dpilcSme4mGv8iqWZ5YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8cb7f6b17a33f39056c55f7db97cf0ef95d69db4a9a5b8617b1bf3aa7a07b89","last_reissued_at":"2026-06-05T01:14:52.971976Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:52.971976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEVANTE-bench: Multi-Scale Comparison of VLMs to Children Using Cognitive Tasks (or, \"Is Your VLM Smarter Than a 5th Grader?\")","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alvin Wei Ming Tan, David Cardinal, Laura Bravo-Sanchez, Michael C. Frank, Sunny Yu, Tania Lorido-Botran","submitted_at":"2026-06-03T22:41:11Z","abstract_excerpt":"Given the inherently multimodal nature of human experience, vision-language models (VLMs) hold substantial promise for modeling human cognition as it grows and develops with experience. Realizing their potential requires tools for comparing VLMs with human cognitive development across tasks, ages, and populations. We present LEVANTE-bench, a benchmark based on tasks and data from the Learning Variability Network (LEVANTE), which distributes open-source tasks and data measuring children's cognition across languages and cultures. In LEVANTE-bench, we systematically assess VLMs on six tasks, comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05497","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/2606.05497/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":"2606.05497","created_at":"2026-06-05T01:14:52.972097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05497v1","created_at":"2026-06-05T01:14:52.972097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05497","created_at":"2026-06-05T01:14:52.972097+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DFX62YXUM7T","created_at":"2026-06-05T01:14:52.972097+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DFX62YXUM7TSBLM","created_at":"2026-06-05T01:14:52.972097+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DFX62YX","created_at":"2026-06-05T01:14:52.972097+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3","json":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3.json","graph_json":"https://pith.science/api/pith-number/7DFX62YXUM7TSBLMKX35XF6PB3/graph.json","events_json":"https://pith.science/api/pith-number/7DFX62YXUM7TSBLMKX35XF6PB3/events.json","paper":"https://pith.science/paper/7DFX62YX"},"agent_actions":{"view_html":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3","download_json":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3.json","view_paper":"https://pith.science/paper/7DFX62YX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05497&json=true","fetch_graph":"https://pith.science/api/pith-number/7DFX62YXUM7TSBLMKX35XF6PB3/graph.json","fetch_events":"https://pith.science/api/pith-number/7DFX62YXUM7TSBLMKX35XF6PB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3/action/storage_attestation","attest_author":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3/action/author_attestation","sign_citation":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3/action/citation_signature","submit_replication":"https://pith.science/pith/7DFX62YXUM7TSBLMKX35XF6PB3/action/replication_record"}},"created_at":"2026-06-05T01:14:52.972097+00:00","updated_at":"2026-06-05T01:14:52.972097+00:00"}