{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H5VOCR2KU2AAE6US7JQ5QKBRKG","short_pith_number":"pith:H5VOCR2K","schema_version":"1.0","canonical_sha256":"3f6ae1474aa680027a92fa61d82831519b001026098ceabe3815249b1e8cf042","source":{"kind":"arxiv","id":"2411.00264","version":2},"attestation_state":"computed","paper":{"title":"TurtleBench: A Visual Programming Benchmark in Turtle Geometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Sameer Singh, Shayan Doroudi, Sina Rismanchian, Yasaman Razeghi","submitted_at":"2024-10-31T23:52:06Z","abstract_excerpt":"Humans have the ability to reason about geometric patterns in images and scenes from a young age. However, developing large multimodal models (LMMs) capable of similar reasoning remains a challenge, highlighting the need for robust evaluation methods to assess these capabilities. We introduce \\Turtle, a benchmark designed to evaluate LMMs' capacity to interpret geometric patterns -- given visual examples, textual instructions, or both -- and generate precise code outputs. Inspired by turtle geometry, a notion used to teach children foundational coding and geometric concepts, TurtleBench featur"},"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":"2411.00264","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-31T23:52:06Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ecbabbc25616abd6e1b1987993173fef8e0d3dc5cc9320792c5cdc95479e4224","abstract_canon_sha256":"f54225b6d9870aaabfcc4941a911a6ba75a46d3b741391494bdfdb8553ac8d33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:56.017815Z","signature_b64":"hL7+UcZBaVJca1UpamHMQbsa7cPemsWbL+5RVz4eX69vUwkUTQER+1MWzQa9nIJ7qNlNvPd9GzQAXkRTDo8GBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f6ae1474aa680027a92fa61d82831519b001026098ceabe3815249b1e8cf042","last_reissued_at":"2026-07-05T10:47:56.017311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:56.017311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TurtleBench: A Visual Programming Benchmark in Turtle Geometry","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Sameer Singh, Shayan Doroudi, Sina Rismanchian, Yasaman Razeghi","submitted_at":"2024-10-31T23:52:06Z","abstract_excerpt":"Humans have the ability to reason about geometric patterns in images and scenes from a young age. However, developing large multimodal models (LMMs) capable of similar reasoning remains a challenge, highlighting the need for robust evaluation methods to assess these capabilities. We introduce \\Turtle, a benchmark designed to evaluate LMMs' capacity to interpret geometric patterns -- given visual examples, textual instructions, or both -- and generate precise code outputs. Inspired by turtle geometry, a notion used to teach children foundational coding and geometric concepts, TurtleBench featur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00264","kind":"arxiv","version":2},"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/2411.00264/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":"2411.00264","created_at":"2026-07-05T10:47:56.017377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00264v2","created_at":"2026-07-05T10:47:56.017377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00264","created_at":"2026-07-05T10:47:56.017377+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5VOCR2KU2AA","created_at":"2026-07-05T10:47:56.017377+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5VOCR2KU2AAE6US","created_at":"2026-07-05T10:47:56.017377+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5VOCR2K","created_at":"2026-07-05T10:47:56.017377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11680","citing_title":"ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG","json":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG.json","graph_json":"https://pith.science/api/pith-number/H5VOCR2KU2AAE6US7JQ5QKBRKG/graph.json","events_json":"https://pith.science/api/pith-number/H5VOCR2KU2AAE6US7JQ5QKBRKG/events.json","paper":"https://pith.science/paper/H5VOCR2K"},"agent_actions":{"view_html":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG","download_json":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG.json","view_paper":"https://pith.science/paper/H5VOCR2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00264&json=true","fetch_graph":"https://pith.science/api/pith-number/H5VOCR2KU2AAE6US7JQ5QKBRKG/graph.json","fetch_events":"https://pith.science/api/pith-number/H5VOCR2KU2AAE6US7JQ5QKBRKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG/action/storage_attestation","attest_author":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG/action/author_attestation","sign_citation":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG/action/citation_signature","submit_replication":"https://pith.science/pith/H5VOCR2KU2AAE6US7JQ5QKBRKG/action/replication_record"}},"created_at":"2026-07-05T10:47:56.017377+00:00","updated_at":"2026-07-05T10:47:56.017377+00:00"}