{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3EH2NPPAYZ2CZPCPBKOKOHA34E","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":"e27e275e1025be98b1c1568a637ff681df85bb1d2fa36a109b40f09adede4fc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T14:26:11Z","title_canon_sha256":"4e0cad2155293d0ffe3a14615d7966187212538da3d80e628cb79fc5140c102d"},"schema_version":"1.0","source":{"id":"2304.03659","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03659","created_at":"2026-07-05T08:12:25Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03659v3","created_at":"2026-07-05T08:12:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03659","created_at":"2026-07-05T08:12:25Z"},{"alias_kind":"pith_short_12","alias_value":"3EH2NPPAYZ2C","created_at":"2026-07-05T08:12:25Z"},{"alias_kind":"pith_short_16","alias_value":"3EH2NPPAYZ2CZPCP","created_at":"2026-07-05T08:12:25Z"},{"alias_kind":"pith_short_8","alias_value":"3EH2NPPA","created_at":"2026-07-05T08:12:25Z"}],"graph_snapshots":[{"event_id":"sha256:0576b2b2391304ce5458b6ad0a8af8a911c69523c758b417122cffd0820cdb9c","target":"graph","created_at":"2026-07-05T08:12:25Z","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/2304.03659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years large visual-language (V+L) models have achieved great success in various downstream tasks. However, it is not well studied whether these models have a conceptual grasp of the visual content. In this work we focus on conceptual understanding of these large V+L models. To facilitate this study, we propose novel benchmarking datasets for probing three different aspects of content understanding, 1) \\textit{relations}, 2) \\textit{composition}, and 3) \\textit{context}. Our probes are grounded in cognitive science and help determine if a V+L model can, for example, determine if snow ","authors_text":"Ajay Divakaran, Jared Claypoole, Madeline Schiappa, Michael Cogswell, Raiyaan Abdullah, Shehreen Azad, Yogesh Rawat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T14:26:11Z","title":"Probing Conceptual Understanding of Large Visual-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03659","kind":"arxiv","version":3},"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":"sha256:75f905601d75b5c6b316c931095772cc7059face4aa574820ccce7ff74eb45ba","target":"record","created_at":"2026-07-05T08:12:25Z","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":"e27e275e1025be98b1c1568a637ff681df85bb1d2fa36a109b40f09adede4fc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T14:26:11Z","title_canon_sha256":"4e0cad2155293d0ffe3a14615d7966187212538da3d80e628cb79fc5140c102d"},"schema_version":"1.0","source":{"id":"2304.03659","kind":"arxiv","version":3}},"canonical_sha256":"d90fa6bde0c6742cbc4f0a9ca71c1be12a6042a8b9449c0b028ed50cf6ef6405","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d90fa6bde0c6742cbc4f0a9ca71c1be12a6042a8b9449c0b028ed50cf6ef6405","first_computed_at":"2026-07-05T08:12:25.634703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:25.634703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FvkKkAdXdwFGt8DijlcNlU621gIe2sTsQmjcsd8WVdTKwXZ1hCjWL8HAG0QEqRbjK3EPQC8RJHtpR7/9h+UkAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:25.635127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03659","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75f905601d75b5c6b316c931095772cc7059face4aa574820ccce7ff74eb45ba","sha256:0576b2b2391304ce5458b6ad0a8af8a911c69523c758b417122cffd0820cdb9c"],"state_sha256":"ec2cb8e1452aefccc09e50895da3352f386e122f882a1da89e10e20c2e7e805e"}