{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KV5DX2GJAVCG6HDIWQGZORET7X","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":"2f3265dd5e6a7736baceb5e870c7eb9b6d2018d4b6097bbd3c51646490a812d7","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-02T08:06:30Z","title_canon_sha256":"1d6d9f40b0f42ae6e9f64d5929fb3af69696e173becbe00628cfdca3ca3e2ea9"},"schema_version":"1.0","source":{"id":"2411.01173","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01173","created_at":"2026-07-05T11:25:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01173v2","created_at":"2026-07-05T11:25:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01173","created_at":"2026-07-05T11:25:40Z"},{"alias_kind":"pith_short_12","alias_value":"KV5DX2GJAVCG","created_at":"2026-07-05T11:25:40Z"},{"alias_kind":"pith_short_16","alias_value":"KV5DX2GJAVCG6HDI","created_at":"2026-07-05T11:25:40Z"},{"alias_kind":"pith_short_8","alias_value":"KV5DX2GJ","created_at":"2026-07-05T11:25:40Z"}],"graph_snapshots":[{"event_id":"sha256:26f55cf790fae006429f5fc67c7d889a14a205042f2b2a72948934aa5f42516c","target":"graph","created_at":"2026-07-05T11:25:40Z","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/2411.01173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Jacek Ma\\'ndziuk, Miko{\\l}aj Ma{\\l}ki\\'nski, Szymon Pawlonka","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-02T08:06:30Z","title":"Reasoning Limitations of Multimodal Large Language Models. A Case Study of Bongard Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01173","kind":"arxiv","version":2},"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":"sha256:2d76ff15a88f4bde07ac112f33855bbe328cda45b3702074c1e4528a5c3620aa","target":"record","created_at":"2026-07-05T11:25:40Z","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":"2f3265dd5e6a7736baceb5e870c7eb9b6d2018d4b6097bbd3c51646490a812d7","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-02T08:06:30Z","title_canon_sha256":"1d6d9f40b0f42ae6e9f64d5929fb3af69696e173becbe00628cfdca3ca3e2ea9"},"schema_version":"1.0","source":{"id":"2411.01173","kind":"arxiv","version":2}},"canonical_sha256":"557a3be8c905446f1c68b40d974493fdd039275f01c32731a21cb820a46e15bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"557a3be8c905446f1c68b40d974493fdd039275f01c32731a21cb820a46e15bf","first_computed_at":"2026-07-05T11:25:40.191994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:40.191994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cj8JkmB4g5okdrfDXCVpzZ9oZFPvz7z2cw6oF3hDJxjNyOfm+f/rYfvJdWJBOhZDt2IR5cd6Z8uHcUulV1lvAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:40.192423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01173","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d76ff15a88f4bde07ac112f33855bbe328cda45b3702074c1e4528a5c3620aa","sha256:26f55cf790fae006429f5fc67c7d889a14a205042f2b2a72948934aa5f42516c"],"state_sha256":"658067c242bf3224a41e77196122d71e61e7da74590340e8911ae4a2969ab4c0"}