{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FPKQ4GTM57XQBF7MR4I7JH3IE6","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":"f2bca53d46f4340c6c6545c75bf8a59f9e591571a0d699263df09bff6da8eceb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:31Z","title_canon_sha256":"367f0b688db05eaaf7daeefad1b50fbe00d4c01824faccf123e9a88a015936fd"},"schema_version":"1.0","source":{"id":"2406.09403","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09403","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09403v3","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09403","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_12","alias_value":"FPKQ4GTM57XQ","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FPKQ4GTM57XQBF7M","created_at":"2026-07-05T09:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FPKQ4GTM","created_at":"2026-07-05T09:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:203000b0f2fdfc267a20b90c4e5ea297319c2d33e5f5a3aac62179853a543189","target":"graph","created_at":"2026-07-05T09:33:33Z","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/2406.09403/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans draw to facilitate reasoning: we draw auxiliary lines when solving geometry problems; we mark and circle when reasoning on maps; we use sketches to amplify our ideas and relieve our limited-capacity working memory. However, such actions are missing in current multimodal language models (LMs). Current chain-of-thought and tool-use paradigms only use text as intermediate reasoning steps. In this work, we introduce Sketchpad, a framework that gives multimodal LMs a visual sketchpad and tools to draw on the sketchpad. The LM conducts planning and reasoning according to the visual artifacts ","authors_text":"Dan Roth, Luke Zettlemoyer, Mari Ostendorf, Noah A Smith, Ranjay Krishna, Weijia Shi, Xingyu Fu, Yushi Hu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:31Z","title":"Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09403","kind":"arxiv","version":3},"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":"sha256:1cbd178a6c9d0d74e904ef7f7f22c2e1351785b486dfac383f0598462611e148","target":"record","created_at":"2026-07-05T09:33:33Z","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":"f2bca53d46f4340c6c6545c75bf8a59f9e591571a0d699263df09bff6da8eceb","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:31Z","title_canon_sha256":"367f0b688db05eaaf7daeefad1b50fbe00d4c01824faccf123e9a88a015936fd"},"schema_version":"1.0","source":{"id":"2406.09403","kind":"arxiv","version":3}},"canonical_sha256":"2bd50e1a6cefef0097ec8f11f49f6827831c213dd41f2e84942b9cb9fa54fcb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bd50e1a6cefef0097ec8f11f49f6827831c213dd41f2e84942b9cb9fa54fcb6","first_computed_at":"2026-07-05T09:33:33.260493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:33.260493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w5I0werXPfYpUAor0fcY2o9ZvfZnAJmMmHxfVUjPWFVulZyrkNS7cCMojWJ2hNuKhIoQDmAWLxji9kcgp0XYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:33.261039Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09403","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cbd178a6c9d0d74e904ef7f7f22c2e1351785b486dfac383f0598462611e148","sha256:203000b0f2fdfc267a20b90c4e5ea297319c2d33e5f5a3aac62179853a543189"],"state_sha256":"35759c16920235e83d9a996691b00e8430ae5bae82571b80a1e9bd45cc848d75"}