{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FQRFPEYRAWQA5BNBOMIJRYTKAO","short_pith_number":"pith:FQRFPEYR","schema_version":"1.0","canonical_sha256":"2c2257931105a00e85a1731098e26a03ad6f7012ecd1badf2fddb5ae155e0dc3","source":{"kind":"arxiv","id":"2403.13315","version":3},"attestation_state":"computed","paper":{"title":"PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deepanway Ghosal, Lidong Bing, Soujanya Poria, Vernon Toh Yan Han, Yew Ken Chia","submitted_at":"2024-03-20T05:37:24Z","abstract_excerpt":"Large multimodal models extend the impressive capabilities of large language models by integrating multimodal understanding abilities. However, it is not clear how they can emulate the general intelligence and reasoning ability of humans. As recognizing patterns and abstracting concepts are key to general intelligence, we introduce PuzzleVQA, a collection of 2000 puzzle instances based on abstract patterns. With this dataset, we evaluate large multimodal models with abstract patterns based on fundamental concepts, including colors, numbers, sizes, and shapes. Through our experiments on state-o"},"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":"2403.13315","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T05:37:24Z","cross_cats_sorted":[],"title_canon_sha256":"74077fe9eee614a75e5601ca3dd51335c5b42dba7920008fbef8ace0c86e596f","abstract_canon_sha256":"eaae869c7e2b99e92e71873bf9030aaaa98b775ad11b6d077ea575a3990e99c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:17.983041Z","signature_b64":"Sq0rpeGbsnVV8CHeJtatu3vbEGIk15CLotTrcmVvpXSt45gh6tY4lORIyqdkb3pydliG9hniDfzDqjPNtEOiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c2257931105a00e85a1731098e26a03ad6f7012ecd1badf2fddb5ae155e0dc3","last_reissued_at":"2026-07-05T08:56:17.982599Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:17.982599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deepanway Ghosal, Lidong Bing, Soujanya Poria, Vernon Toh Yan Han, Yew Ken Chia","submitted_at":"2024-03-20T05:37:24Z","abstract_excerpt":"Large multimodal models extend the impressive capabilities of large language models by integrating multimodal understanding abilities. However, it is not clear how they can emulate the general intelligence and reasoning ability of humans. As recognizing patterns and abstracting concepts are key to general intelligence, we introduce PuzzleVQA, a collection of 2000 puzzle instances based on abstract patterns. With this dataset, we evaluate large multimodal models with abstract patterns based on fundamental concepts, including colors, numbers, sizes, and shapes. Through our experiments on state-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13315","kind":"arxiv","version":3},"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/2403.13315/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":"2403.13315","created_at":"2026-07-05T08:56:17.982664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13315v3","created_at":"2026-07-05T08:56:17.982664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13315","created_at":"2026-07-05T08:56:17.982664+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQRFPEYRAWQA","created_at":"2026-07-05T08:56:17.982664+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQRFPEYRAWQA5BNB","created_at":"2026-07-05T08:56:17.982664+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQRFPEYR","created_at":"2026-07-05T08:56:17.982664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09092","citing_title":"From Shortcuts to Reasoning: Robust Post-Training of Theory of Mind with Reinforcement Learning","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05769","citing_title":"Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01599","citing_title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06211","citing_title":"PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2511.04570","citing_title":"Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2505.07062","citing_title":"Seed1.5-VL Technical Report","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2408.03326","citing_title":"LLaVA-OneVision: Easy Visual Task Transfer","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO","json":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO.json","graph_json":"https://pith.science/api/pith-number/FQRFPEYRAWQA5BNBOMIJRYTKAO/graph.json","events_json":"https://pith.science/api/pith-number/FQRFPEYRAWQA5BNBOMIJRYTKAO/events.json","paper":"https://pith.science/paper/FQRFPEYR"},"agent_actions":{"view_html":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO","download_json":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO.json","view_paper":"https://pith.science/paper/FQRFPEYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13315&json=true","fetch_graph":"https://pith.science/api/pith-number/FQRFPEYRAWQA5BNBOMIJRYTKAO/graph.json","fetch_events":"https://pith.science/api/pith-number/FQRFPEYRAWQA5BNBOMIJRYTKAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO/action/storage_attestation","attest_author":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO/action/author_attestation","sign_citation":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO/action/citation_signature","submit_replication":"https://pith.science/pith/FQRFPEYRAWQA5BNBOMIJRYTKAO/action/replication_record"}},"created_at":"2026-07-05T08:56:17.982664+00:00","updated_at":"2026-07-05T08:56:17.982664+00:00"}