{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:77QQMSS5FRQYDV327AZ7TPRXLF","short_pith_number":"pith:77QQMSS5","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"},"canonical_sha256":"ffe1064a5d2c6181d77af833f9be37595a3cdbf863f1560ede0ee44873e030f0","source":{"kind":"arxiv","id":"2605.13167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13167","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13167v1","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13167","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"77QQMSS5FRQY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"77QQMSS5FRQYDV32","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"77QQMSS5","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:77QQMSS5FRQYDV327AZ7TPRXLF","target":"record","payload":{"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"},"canonical_sha256":"ffe1064a5d2c6181d77af833f9be37595a3cdbf863f1560ede0ee44873e030f0","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"},"source_kind":"arxiv","source_id":"2605.13167","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+rishg/tVE5X9yFG1hjudq8PbcTt9JziSGaIoROJPQ+uG2762pW+Cq5WqDnCJujNLXmPf5nfKrHJldCxL7cAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T22:26:03.796430Z"},"content_sha256":"2856c870b51cce2305c75dc0e4a1998ebdb3b0bec8a508acf3390198f31000ca","schema_version":"1.0","event_id":"sha256:2856c870b51cce2305c75dc0e4a1998ebdb3b0bec8a508acf3390198f31000ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:77QQMSS5FRQYDV327AZ7TPRXLF","target":"graph","payload":{"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"},"verdict_id":"2db43c02-abd6-48cb-8cbe-5ff76b0b110f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdTNDwQZMv6oK0IwrrufOT+LuqbJ/7To6b302ba2GFlLKgCr4JAhl8oOHiIlh8hDnAjRaUqczsTChPU5lTGNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T22:26:03.797423Z"},"content_sha256":"036d22a48f14ec252db249d5b7661340e08c87d06d6ae2bb90552edc5f8acc47","schema_version":"1.0","event_id":"sha256:036d22a48f14ec252db249d5b7661340e08c87d06d6ae2bb90552edc5f8acc47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/bundle.json","state_url":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77QQMSS5FRQYDV327AZ7TPRXLF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-22T22:26:03Z","links":{"resolver":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF","bundle":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/bundle.json","state":"https://pith.science/pith/77QQMSS5FRQYDV327AZ7TPRXLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77QQMSS5FRQYDV327AZ7TPRXLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:77QQMSS5FRQYDV327AZ7TPRXLF","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":"8410ba2e2f49ddb32a3ad7c2f86c3c449830c77be08fe23d70ff257fbc11e2ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T08:30:12Z","title_canon_sha256":"7804e664a040037fee66e7b338add73f19f91fd4e634549dd42f0e595308920d"},"schema_version":"1.0","source":{"id":"2605.13167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13167","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13167v1","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13167","created_at":"2026-05-18T03:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"77QQMSS5FRQY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"77QQMSS5FRQYDV32","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"77QQMSS5","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:036d22a48f14ec252db249d5b7661340e08c87d06d6ae2bb90552edc5f8acc47","target":"graph","created_at":"2026-05-18T03:08:56Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The 489 problems are text-complete and constructible after automated filtering and human validation, and the chosen DSL accurately represents valid geometric constructions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Current multimodal models often produce geometry diagrams with hallucinations, missing objects, and violated constraints from natural language problems."}],"snapshot_sha256":"7700514e8b32e1fa170da2b41b42d4bcbb6ce3e57bbf280c7dc20c094e4bdfac"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f33771f89a64f5d72cbd7ec57900d483471b62b6220cbc15eb76bf15efeb6c21"},"paper":{"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","authors_text":"Huishuai Zhang, Jinwoong Kim, Rui Yang","cross_cats":[],"headline":"Current multimodal models often produce geometry diagrams with hallucinations, missing objects, and violated constraints from natural language problems.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T08:30:12Z","title":"GeoBuildBench: A Benchmark for Interactive and Executable Geometry Construction from Natural Language"},"references":{"count":12,"internal_anchors":1,"resolved_work":12,"sample":[{"cited_arxiv_id":"2511.21631","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"One definition per label","work_id":"65c86816-fcc8-4cc5-8fce-057339080c40","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Construct, don't assert","work_id":"7d863cb8-fce3-4358-9c98-afe4a8cad918","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"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","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Determine whether this problem is suitable for geometric figure construction","work_id":"40f491f4-77ea-48ae-b724-05e0380c7495","year":null}],"snapshot_sha256":"eb2354cb310d94239aa3c1c1790363cda58565c67dd64946d2598d9d3058403c"},"source":{"id":"2605.13167","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:17:00.021261Z","id":"2db43c02-abd6-48cb-8cbe-5ff76b0b110f","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Current multimodal models often produce geometry diagrams with hallucinations, missing objects, and violated constraints from natural language problems.","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","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."}},"verdict_id":"2db43c02-abd6-48cb-8cbe-5ff76b0b110f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2856c870b51cce2305c75dc0e4a1998ebdb3b0bec8a508acf3390198f31000ca","target":"record","created_at":"2026-05-18T03:08:56Z","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":"8410ba2e2f49ddb32a3ad7c2f86c3c449830c77be08fe23d70ff257fbc11e2ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T08:30:12Z","title_canon_sha256":"7804e664a040037fee66e7b338add73f19f91fd4e634549dd42f0e595308920d"},"schema_version":"1.0","source":{"id":"2605.13167","kind":"arxiv","version":1}},"canonical_sha256":"ffe1064a5d2c6181d77af833f9be37595a3cdbf863f1560ede0ee44873e030f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffe1064a5d2c6181d77af833f9be37595a3cdbf863f1560ede0ee44873e030f0","first_computed_at":"2026-05-18T03:08:56.699362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:56.699362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zvSP1r/dEgIRAVwXQOeDpAMw+nN+qXm1UHcIsNBOwjsoUUC7Tt3k6hPbJUmlYN4X1ijzT3KF5or7yVGGhRmRCg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:56.700208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2856c870b51cce2305c75dc0e4a1998ebdb3b0bec8a508acf3390198f31000ca","sha256:036d22a48f14ec252db249d5b7661340e08c87d06d6ae2bb90552edc5f8acc47"],"state_sha256":"de1f2aeb68036c5f726f410844ac5681973a93a2b6d1620aff3b21d7bef6bd5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNweZNtAB9gLK7E3u2y+hSo/oaiYaGevQr7OzqIIgbdssVIhelt5ls2hBixRmsew0q3Uxkn4hKCZYtjVyOG7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T22:26:03.801827Z","bundle_sha256":"b6b067ea52d89b26ac05f79dedacd4fa1e599010f742ee2212d5c4a388c727c6"}}