{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:77QQMSS5FRQYDV327AZ7TPRXLF","short_pith_number":"pith:77QQMSS5","schema_version":"1.0","canonical_sha256":"ffe1064a5d2c6181d77af833f9be37595a3cdbf863f1560ede0ee44873e030f0","source":{"kind":"arxiv","id":"2605.13167","version":1},"attestation_state":"computed","paper":{"title":"GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Current multimodal models often produce geometry diagrams with hallucinations, missing objects, and violated constraints from natural language problems.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huishuai Zhang, Jinwoong Kim, Rui Yang","submitted_at":"2026-05-13T08:30:12Z","abstract_excerpt":"We introduce GeoBuildBench, a benchmark designed to evaluate whether large language models and multimodal agents can ground informal natural-language plane geometry problems into executable geometric constructions. Unlike existing geometry benchmarks that focus on answer correctness or static diagram interpretation, GeoBuildBench treats geometry diagram as an interactive construction task: given a textual problem, an agent must generate a domain-specific language (DSL) program to produce a diagram satisfying explicitly specified geometric objects and verifiable constraints. The benchmark featu"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T08:30:12Z","cross_cats_sorted":[],"title_canon_sha256":"7804e664a040037fee66e7b338add73f19f91fd4e634549dd42f0e595308920d","abstract_canon_sha256":"8410ba2e2f49ddb32a3ad7c2f86c3c449830c77be08fe23d70ff257fbc11e2ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:56.700208Z","signature_b64":"zvSP1r/dEgIRAVwXQOeDpAMw+nN+qXm1UHcIsNBOwjsoUUC7Tt3k6hPbJUmlYN4X1ijzT3KF5or7yVGGhRmRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffe1064a5d2c6181d77af833f9be37595a3cdbf863f1560ede0ee44873e030f0","last_reissued_at":"2026-05-18T03:08:56.699362Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:56.699362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Current multimodal models often produce geometry diagrams with hallucinations, missing objects, and violated constraints from natural language problems.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huishuai Zhang, Jinwoong Kim, Rui Yang","submitted_at":"2026-05-13T08:30:12Z","abstract_excerpt":"We introduce GeoBuildBench, a benchmark designed to evaluate whether large language models and multimodal agents can ground informal natural-language plane geometry problems into executable geometric constructions. Unlike existing geometry benchmarks that focus on answer correctness or static diagram interpretation, GeoBuildBench treats geometry diagram as an interactive construction task: given a textual problem, an agent must generate a domain-specific language (DSL) program to produce a diagram satisfying explicitly specified geometric objects and verifiable constraints. The benchmark featu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"despite reasonable success rates, models frequently exhibit structural hallucinations, missing objects, and failures to satisfy geometric constraints, with limited ability to exploit visual and constraint-based feedback for self-correction","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 489 problems are text-complete and constructible after automated filtering and human validation, and the chosen DSL accurately represents valid geometric constructions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GeoBuildBench is a new benchmark requiring LLMs to generate executable geometry constructions from text, revealing frequent hallucinations, missing objects, and constraint failures in state-of-the-art models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Current multimodal models often produce geometry diagrams with hallucinations, missing objects, and violated constraints from natural language problems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7700514e8b32e1fa170da2b41b42d4bcbb6ce3e57bbf280c7dc20c094e4bdfac"},"source":{"id":"2605.13167","kind":"arxiv","version":1},"verdict":{"id":"2db43c02-abd6-48cb-8cbe-5ff76b0b110f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:17:00.021261Z","strongest_claim":"despite reasonable success rates, models frequently exhibit structural hallucinations, missing objects, and failures to satisfy geometric constraints, with limited ability to exploit visual and constraint-based feedback for self-correction","one_line_summary":"GeoBuildBench is a new benchmark requiring LLMs to generate executable geometry constructions from text, revealing frequent hallucinations, missing objects, and constraint failures in state-of-the-art models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 489 problems are text-complete and constructible after automated filtering and human validation, and the chosen DSL accurately represents valid geometric constructions.","pith_extraction_headline":"Current multimodal models often produce geometry diagrams with hallucinations, missing objects, and violated constraints from natural language problems."},"references":{"count":12,"sample":[{"doi":"","year":2021,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","ref_index":1,"cited_arxiv_id":"2511.21631","is_internal_anchor":true},{"doi":"","year":null,"title":"One definition per label","work_id":"65c86816-fcc8-4cc5-8fce-057339080c40","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Construct, don't assert","work_id":"7d863cb8-fce3-4358-9c98-afe4a8cad918","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"These prompts define the construction suitability criteria and the formal extraction of geometric objects and verifica- tion conditions","work_id":"d40e34e9-4394-48d5-b994-6b0e6692437e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Determine whether this problem is suitable for geometric figure construction","work_id":"40f491f4-77ea-48ae-b724-05e0380c7495","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":12,"snapshot_sha256":"eb2354cb310d94239aa3c1c1790363cda58565c67dd64946d2598d9d3058403c","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f33771f89a64f5d72cbd7ec57900d483471b62b6220cbc15eb76bf15efeb6c21"},"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":"2605.13167","created_at":"2026-05-18T03:08:56.699501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13167v1","created_at":"2026-05-18T03:08:56.699501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13167","created_at":"2026-05-18T03:08:56.699501+00:00"},{"alias_kind":"pith_short_12","alias_value":"77QQMSS5FRQY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"77QQMSS5FRQYDV32","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"77QQMSS5","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20743","citing_title":"Draw2Think: Harnessing Geometry Reasoning through Constraint Engine Interaction","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF","json":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF.json","graph_json":"https://pith.science/api/pith-number/77QQMSS5FRQYDV327AZ7TPRXLF/graph.json","events_json":"https://pith.science/api/pith-number/77QQMSS5FRQYDV327AZ7TPRXLF/events.json","paper":"https://pith.science/paper/77QQMSS5"},"agent_actions":{"view_html":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF","download_json":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF.json","view_paper":"https://pith.science/paper/77QQMSS5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13167&json=true","fetch_graph":"https://pith.science/api/pith-number/77QQMSS5FRQYDV327AZ7TPRXLF/graph.json","fetch_events":"https://pith.science/api/pith-number/77QQMSS5FRQYDV327AZ7TPRXLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/action/storage_attestation","attest_author":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/action/author_attestation","sign_citation":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/action/citation_signature","submit_replication":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/action/replication_record"}},"created_at":"2026-05-18T03:08:56.699501+00:00","updated_at":"2026-05-18T03:08:56.699501+00:00"}