{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RA6IRTQF4EHGDCTX7KIIXZYAXV","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":"b8d7b71ff4fdd02e8868e3ff3904f458f0860e3b9f129e0e8533a764ce9c15ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-25T18:21:07Z","title_canon_sha256":"08b9fa440c21f5aa9aaafecb094f5138390c5412791bff9bb0db47ef42c0f191"},"schema_version":"1.0","source":{"id":"2503.19990","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19990","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19990v3","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19990","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"pith_short_12","alias_value":"RA6IRTQF4EHG","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"pith_short_16","alias_value":"RA6IRTQF4EHGDCTX","created_at":"2026-07-05T11:24:17Z"},{"alias_kind":"pith_short_8","alias_value":"RA6IRTQF","created_at":"2026-07-05T11:24:17Z"}],"graph_snapshots":[{"event_id":"sha256:bcb83399f520b3922e6c5964b265e9d65a6620a6506b455cf23f83051f36d565","target":"graph","created_at":"2026-07-05T11:24:17Z","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/2503.19990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-step spatial reasoning entails understanding and reasoning about spatial relationships across multiple sequential steps, which is crucial for tackling complex real-world applications, such as robotic manipulation, autonomous navigation, and automated assembly. To assess how well current Multimodal Large Language Models (MLLMs) have acquired this fundamental capability, we introduce LEGO-Puzzles, a scalable benchmark designed to evaluate both spatial understanding and sequential reasoning in MLLMs through LEGO-based tasks. LEGO-Puzzles consists of 1,100 carefully curated visual question-a","authors_text":"Haodong Duan, Junyao Gao, Kai Chen, Kaifeng Lyu, Kexian Tang, Wenran Liu, Yanan Sun, Yanhong Zeng, Zhening Xing","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-25T18:21:07Z","title":"LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19990","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":"sha256:9511a5832c5404e6126257afdf62e0a9efc874cb08d480227b2f0c8a5b822853","target":"record","created_at":"2026-07-05T11:24:17Z","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":"b8d7b71ff4fdd02e8868e3ff3904f458f0860e3b9f129e0e8533a764ce9c15ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-25T18:21:07Z","title_canon_sha256":"08b9fa440c21f5aa9aaafecb094f5138390c5412791bff9bb0db47ef42c0f191"},"schema_version":"1.0","source":{"id":"2503.19990","kind":"arxiv","version":3}},"canonical_sha256":"883c88ce05e10e618a77fa908be700bd69f7ecfd89fb7488546e6752c9cefdd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"883c88ce05e10e618a77fa908be700bd69f7ecfd89fb7488546e6752c9cefdd2","first_computed_at":"2026-07-05T11:24:17.006458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:17.006458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Px4My3rBV7MksD3Nnb67KYrS3STLX+ek6vHhSrSuHc9ohniShdMI/2EtzXnRks0r7AFVtmkxWL+X54ArrPG4CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:17.006974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19990","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9511a5832c5404e6126257afdf62e0a9efc874cb08d480227b2f0c8a5b822853","sha256:bcb83399f520b3922e6c5964b265e9d65a6620a6506b455cf23f83051f36d565"],"state_sha256":"ad58a2ea4727268cf5547dc3c51d739c518a6efadb11f19d070a30dc92d8bfcb"}