{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4J3HJ2TJOUTLQIVDQNCHLWYMVZ","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":"2245d6722b8507892d6450a94ae7a31d764e363b394cd3f446b7393bac630050","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T05:17:41Z","title_canon_sha256":"1e6941d0182401df08bfdf4c08f77713c066683d9568e09092ce2ec8a7f4a33f"},"schema_version":"1.0","source":{"id":"2505.20728","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20728","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20728v4","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20728","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"4J3HJ2TJOUTL","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"pith_short_16","alias_value":"4J3HJ2TJOUTLQIVD","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"pith_short_8","alias_value":"4J3HJ2TJ","created_at":"2026-07-05T11:59:14Z"}],"graph_snapshots":[{"event_id":"sha256:4d10a241b528bf193ca1e3f36b1bfbd95e919e76952fc17afc7e6dfec4993519","target":"graph","created_at":"2026-07-05T11:59:14Z","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/2505.20728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial reasoning is a core component of human cognition, enabling individuals to perceive, comprehend, and interact with the physical world. It relies on a nuanced understanding of spatial structures and inter-object relationships, serving as the foundation for complex reasoning and decision-making. To investigate whether current vision-language models (VLMs) exhibit similar capability, we introduce Jigsaw-Puzzles, a novel benchmark consisting of 1,100 carefully curated real-world images with high spatial complexity. Based on this dataset, we design five tasks to rigorously evaluate VLMs' spa","authors_text":"Dandan Zhang, Fangdi Li, Wei Ye, Yao Yang, Zesen Lyu, Zhihang Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T05:17:41Z","title":"Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20728","kind":"arxiv","version":4},"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:a7662017d416d72f9d9ce74747e912139addfce3a24e8c57297f8a6cdcc85138","target":"record","created_at":"2026-07-05T11:59:14Z","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":"2245d6722b8507892d6450a94ae7a31d764e363b394cd3f446b7393bac630050","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T05:17:41Z","title_canon_sha256":"1e6941d0182401df08bfdf4c08f77713c066683d9568e09092ce2ec8a7f4a33f"},"schema_version":"1.0","source":{"id":"2505.20728","kind":"arxiv","version":4}},"canonical_sha256":"e27674ea697526b822a3834475db0cae4c4a1db39265157ed91457fe840d2e60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e27674ea697526b822a3834475db0cae4c4a1db39265157ed91457fe840d2e60","first_computed_at":"2026-07-05T11:59:14.952664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:14.952664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ayXnHnMwxKJ1pu14RW28G1m0tNnvdqAIzZAB8sP81dr7RiObcWSjksmXww2Gv7tfnVNL1uyJEW32xln7LV6WAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:14.953079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20728","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7662017d416d72f9d9ce74747e912139addfce3a24e8c57297f8a6cdcc85138","sha256:4d10a241b528bf193ca1e3f36b1bfbd95e919e76952fc17afc7e6dfec4993519"],"state_sha256":"f0986f3516bd20683c59860ce28d2458751332b421013d085b9698130e925353"}