{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:335BGFGFEHBUHB3XTGTKJQQGJH","short_pith_number":"pith:335BGFGF","schema_version":"1.0","canonical_sha256":"defa1314c521c343877799a6a4c20649c4c60b39d7c3ab91741f8ca9fd25a1c1","source":{"kind":"arxiv","id":"2607.27670","version":1},"attestation_state":"computed","paper":{"title":"JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Franck Dernoncourt, Jiate Li, Jiawei Yang, Jike Zhong, Mohit Bansal, Roger Zimmermann, Ryan Rossi, Shawn Li, Vicente Ordonez, Wei Yang, You Qin, Yue Wang, Yue Zhao, Zhengzhong Tu","submitted_at":"2026-07-30T04:34:27Z","abstract_excerpt":"Jigsaw puzzle solving requires jointly reasoning about visual content and geometric constraints, yet existing benchmarks use rectangular cuts that create ambiguous ground truth in texture-repeated regions. We introduce \\textit{\\ours{}}, a benchmark with tab-and-blank interlocking pieces where geometric constraints provide strong local compatibility requirements that, combined with visual content, yield unambiguous ground truth. Across 95K instances at four grid densities (4$\\times$4 to 16$\\times$16), we find that \\textbf{zero-shot VLMs largely lack geometric reasoning}: only one of five fronti"},"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":"2607.27670","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T04:34:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"945c1d6abd5c0d92e83b1e064db57e1d08fa65d50ab0f5c2fae83fb077628ce5","abstract_canon_sha256":"e78fbb09dee8dbbbc236d39c83fa55f6cef1d6d952dfa0c7606985311271508e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"defa1314c521c343877799a6a4c20649c4c60b39d7c3ab91741f8ca9fd25a1c1","last_reissued_at":"2026-07-31T01:29:41.866752Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:29:41.866752Z"},"graph_snapshot":{"paper":{"title":"JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Franck Dernoncourt, Jiate Li, Jiawei Yang, Jike Zhong, Mohit Bansal, Roger Zimmermann, Ryan Rossi, Shawn Li, Vicente Ordonez, Wei Yang, You Qin, Yue Wang, Yue Zhao, Zhengzhong Tu","submitted_at":"2026-07-30T04:34:27Z","abstract_excerpt":"Jigsaw puzzle solving requires jointly reasoning about visual content and geometric constraints, yet existing benchmarks use rectangular cuts that create ambiguous ground truth in texture-repeated regions. We introduce \\textit{\\ours{}}, a benchmark with tab-and-blank interlocking pieces where geometric constraints provide strong local compatibility requirements that, combined with visual content, yield unambiguous ground truth. Across 95K instances at four grid densities (4$\\times$4 to 16$\\times$16), we find that \\textbf{zero-shot VLMs largely lack geometric reasoning}: only one of five fronti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27670","kind":"arxiv","version":1},"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/2607.27670/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":"2607.27670","created_at":"2026-07-31T01:29:41.869892+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27670v1","created_at":"2026-07-31T01:29:41.869892+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27670","created_at":"2026-07-31T01:29:41.869892+00:00"},{"alias_kind":"pith_short_12","alias_value":"335BGFGFEHBU","created_at":"2026-07-31T01:29:41.869892+00:00"},{"alias_kind":"pith_short_16","alias_value":"335BGFGFEHBUHB3X","created_at":"2026-07-31T01:29:41.869892+00:00"},{"alias_kind":"pith_short_8","alias_value":"335BGFGF","created_at":"2026-07-31T01:29:41.869892+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH","json":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH.json","graph_json":"https://pith.science/api/pith-number/335BGFGFEHBUHB3XTGTKJQQGJH/graph.json","events_json":"https://pith.science/api/pith-number/335BGFGFEHBUHB3XTGTKJQQGJH/events.json","paper":"https://pith.science/paper/335BGFGF"},"agent_actions":{"view_html":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH","download_json":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH.json","view_paper":"https://pith.science/paper/335BGFGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27670&json=true","fetch_graph":"https://pith.science/api/pith-number/335BGFGFEHBUHB3XTGTKJQQGJH/graph.json","fetch_events":"https://pith.science/api/pith-number/335BGFGFEHBUHB3XTGTKJQQGJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH/action/storage_attestation","attest_author":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH/action/author_attestation","sign_citation":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH/action/citation_signature","submit_replication":"https://pith.science/pith/335BGFGFEHBUHB3XTGTKJQQGJH/action/replication_record"}},"created_at":"2026-07-31T01:29:41.869892+00:00","updated_at":"2026-07-31T01:29:41.869892+00:00"}