{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KV5DX2GJAVCG6HDIWQGZORET7X","short_pith_number":"pith:KV5DX2GJ","schema_version":"1.0","canonical_sha256":"557a3be8c905446f1c68b40d974493fdd039275f01c32731a21cb820a46e15bf","source":{"kind":"arxiv","id":"2411.01173","version":2},"attestation_state":"computed","paper":{"title":"Reasoning Limitations of Multimodal Large Language Models. A Case Study of Bongard Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jacek Ma\\'ndziuk, Miko{\\l}aj Ma{\\l}ki\\'nski, Szymon Pawlonka","submitted_at":"2024-11-02T08:06:30Z","abstract_excerpt":"Abstract visual reasoning (AVR) involves discovering shared concepts across images through analogy, akin to solving IQ test problems. Bongard Problems (BPs) remain a key challenge in AVR, requiring both visual reasoning and verbal description. We investigate whether multimodal large language models (MLLMs) can solve BPs by formulating a set of diverse MLLM-suited solution strategies and testing $4$ proprietary and $4$ open-access models on $3$ BP datasets featuring synthetic (classic BPs) and real-world (Bongard HOI and Bongard-OpenWorld) images. Despite some successes on real-world datasets, "},"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":"2411.01173","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-02T08:06:30Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"1d6d9f40b0f42ae6e9f64d5929fb3af69696e173becbe00628cfdca3ca3e2ea9","abstract_canon_sha256":"2f3265dd5e6a7736baceb5e870c7eb9b6d2018d4b6097bbd3c51646490a812d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:40.192423Z","signature_b64":"Cj8JkmB4g5okdrfDXCVpzZ9oZFPvz7z2cw6oF3hDJxjNyOfm+f/rYfvJdWJBOhZDt2IR5cd6Z8uHcUulV1lvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"557a3be8c905446f1c68b40d974493fdd039275f01c32731a21cb820a46e15bf","last_reissued_at":"2026-07-05T11:25:40.191994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:40.191994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Limitations of Multimodal Large Language Models. A Case Study of Bongard Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jacek Ma\\'ndziuk, Miko{\\l}aj Ma{\\l}ki\\'nski, Szymon Pawlonka","submitted_at":"2024-11-02T08:06:30Z","abstract_excerpt":"Abstract visual reasoning (AVR) involves discovering shared concepts across images through analogy, akin to solving IQ test problems. Bongard Problems (BPs) remain a key challenge in AVR, requiring both visual reasoning and verbal description. We investigate whether multimodal large language models (MLLMs) can solve BPs by formulating a set of diverse MLLM-suited solution strategies and testing $4$ proprietary and $4$ open-access models on $3$ BP datasets featuring synthetic (classic BPs) and real-world (Bongard HOI and Bongard-OpenWorld) images. Despite some successes on real-world datasets, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01173","kind":"arxiv","version":2},"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/2411.01173/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":"2411.01173","created_at":"2026-07-05T11:25:40.192051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01173v2","created_at":"2026-07-05T11:25:40.192051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01173","created_at":"2026-07-05T11:25:40.192051+00:00"},{"alias_kind":"pith_short_12","alias_value":"KV5DX2GJAVCG","created_at":"2026-07-05T11:25:40.192051+00:00"},{"alias_kind":"pith_short_16","alias_value":"KV5DX2GJAVCG6HDI","created_at":"2026-07-05T11:25:40.192051+00:00"},{"alias_kind":"pith_short_8","alias_value":"KV5DX2GJ","created_at":"2026-07-05T11:25:40.192051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20814","citing_title":"SPHINX: A Synthetic Environment for Visual Perception and Reasoning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X","json":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X.json","graph_json":"https://pith.science/api/pith-number/KV5DX2GJAVCG6HDIWQGZORET7X/graph.json","events_json":"https://pith.science/api/pith-number/KV5DX2GJAVCG6HDIWQGZORET7X/events.json","paper":"https://pith.science/paper/KV5DX2GJ"},"agent_actions":{"view_html":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X","download_json":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X.json","view_paper":"https://pith.science/paper/KV5DX2GJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01173&json=true","fetch_graph":"https://pith.science/api/pith-number/KV5DX2GJAVCG6HDIWQGZORET7X/graph.json","fetch_events":"https://pith.science/api/pith-number/KV5DX2GJAVCG6HDIWQGZORET7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X/action/storage_attestation","attest_author":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X/action/author_attestation","sign_citation":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X/action/citation_signature","submit_replication":"https://pith.science/pith/KV5DX2GJAVCG6HDIWQGZORET7X/action/replication_record"}},"created_at":"2026-07-05T11:25:40.192051+00:00","updated_at":"2026-07-05T11:25:40.192051+00:00"}