{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TTFD45QSJ6UE2UXAAODNFOTNPE","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":"6eeb04a513f6d82799ee79c4328b406a39a317bdd8972e9e996966481d2b4164","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T13:25:05Z","title_canon_sha256":"a19d3ba0d753e4af45e1a5e003376233350290fc9e1be1ba0b404de9e134841f"},"schema_version":"1.0","source":{"id":"2606.03626","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03626","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03626v1","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03626","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_12","alias_value":"TTFD45QSJ6UE","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_16","alias_value":"TTFD45QSJ6UE2UXA","created_at":"2026-06-03T01:06:02Z"},{"alias_kind":"pith_short_8","alias_value":"TTFD45QS","created_at":"2026-06-03T01:06:02Z"}],"graph_snapshots":[{"event_id":"sha256:37db0c9e8ca154925ee3edda11641442931df66df88b4ffb68d7fe7581a86cb4","target":"graph","created_at":"2026-06-03T01:06:02Z","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/2606.03626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have been explored for visual programming, where they generate code to solve visual tasks. However, most prior work focuses on visual programming for productivity; it remains unclear how well current VLMs perform on education-oriented visual programming and what factors limit their performance. To bridge this gap, we introduce TurtleAI, a benchmark containing 823 tasks curated based on real-world visual programming tasks in the Turtle Graphics domain. Solving these tasks requires models to perceive geometric patterns, reason about spatial relationships, and synthe","authors_text":"Adish Singla, Chao Wen, Jacqueline Staub","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T13:25:05Z","title":"TurtleAI: Benchmarking Multimodal Models for Visual Programming in Turtle Graphics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03626","kind":"arxiv","version":1},"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":"sha256:4594a7d75e33a3bdacc807e2b659ff36a1a6da09cbcd3cc804694bc9ad0930bb","target":"record","created_at":"2026-06-03T01:06:02Z","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":"6eeb04a513f6d82799ee79c4328b406a39a317bdd8972e9e996966481d2b4164","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T13:25:05Z","title_canon_sha256":"a19d3ba0d753e4af45e1a5e003376233350290fc9e1be1ba0b404de9e134841f"},"schema_version":"1.0","source":{"id":"2606.03626","kind":"arxiv","version":1}},"canonical_sha256":"9cca3e76124fa84d52e00386d2ba6d792e83cbbd0a671ba917f043566cb553d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cca3e76124fa84d52e00386d2ba6d792e83cbbd0a671ba917f043566cb553d6","first_computed_at":"2026-06-03T01:06:02.705677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:06:02.705677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ys+g6wHUXpR4xD3G9D+3Sgu85eXbvXgKI53/owVJv/rPE6TWbv+wkxTdFa9VBOn8g5UBWppuRkgWikQ9159FBA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:06:02.706134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03626","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4594a7d75e33a3bdacc807e2b659ff36a1a6da09cbcd3cc804694bc9ad0930bb","sha256:37db0c9e8ca154925ee3edda11641442931df66df88b4ffb68d7fe7581a86cb4"],"state_sha256":"73e927002acb70f96db4213cdffade5430c52e9b48049aee8d10ad80eddb5a01"}