{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DMNDIYZ6LD3KV44VFERAOOUZQY","short_pith_number":"pith:DMNDIYZ6","schema_version":"1.0","canonical_sha256":"1b1a34633e58f6aaf3952922073a99861b264bfad4e1494fc56067e07e3f0740","source":{"kind":"arxiv","id":"2603.26839","version":2},"attestation_state":"computed","paper":{"title":"From Pixels to BFS: High Maze Accuracy Does Not Imply Visual Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multimodal models solve maze images by converting them to text grids and enumerating paths token by token rather than through visual planning.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alberto G. Rodriguez Salgado","submitted_at":"2026-03-27T08:10:05Z","abstract_excerpt":"How do multimodal models solve visual spatial tasks -- through genuine planning, or through brute-force search in token space? We introduce \\textsc{MazeBench}, a benchmark of 110 procedurally generated maze images across nine controlled groups, and evaluate 16 model configurations from OpenAI, Anthropic, Google, and Alibaba. GPT-5.4 solves 91\\% and Gemini 3.1 Pro 79\\%, but these scores are misleading: models typically translate images into text grids and then enumerate paths step by step, consuming 1,710--22,818 tokens per solve for a task humans do quickly. Without added reasoning budgets, al"},"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":true},"canonical_record":{"source":{"id":"2603.26839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-27T08:10:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"643eafe4d72694bb367d0827179831d9525fd75bafb8ce520b2208c13252d20c","abstract_canon_sha256":"7111c05fde22dd9f75c971e49ca175237b4901d279b78cd95c37ba1faa83da92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:22.499994Z","signature_b64":"TDW5+AcfaGAmLsOzz8ScRSejGV6ZXtzKgX++IpIGjHRU5+yQ02jKDiQDY1F5DMRbH4AZ0j4u2UyUD3bVocGUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b1a34633e58f6aaf3952922073a99861b264bfad4e1494fc56067e07e3f0740","last_reissued_at":"2026-05-18T03:09:22.499408Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:22.499408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Pixels to BFS: High Maze Accuracy Does Not Imply Visual Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multimodal models solve maze images by converting them to text grids and enumerating paths token by token rather than through visual planning.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alberto G. Rodriguez Salgado","submitted_at":"2026-03-27T08:10:05Z","abstract_excerpt":"How do multimodal models solve visual spatial tasks -- through genuine planning, or through brute-force search in token space? We introduce \\textsc{MazeBench}, a benchmark of 110 procedurally generated maze images across nine controlled groups, and evaluate 16 model configurations from OpenAI, Anthropic, Google, and Alibaba. GPT-5.4 solves 91\\% and Gemini 3.1 Pro 79\\%, but these scores are misleading: models typically translate images into text grids and then enumerate paths step by step, consuming 1,710--22,818 tokens per solve for a task humans do quickly. Without added reasoning budgets, al"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MazeBench therefore shows that high accuracy on visual planning tasks does not imply human-like spatial understanding.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the two-stage image-to-grid plus token enumeration strategy observed in traces is the dominant mechanism driving performance rather than an artifact of the specific prompting or model configurations tested.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Multimodal models achieve high maze accuracy by translating images to text grids and performing token-level BFS search, not through visual planning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multimodal models solve maze images by converting them to text grids and enumerating paths token by token rather than through visual planning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d976b97cdf972bb6cafa6e406e76c79ea9bf3feaa696102766660ef5b8dbfcb3"},"source":{"id":"2603.26839","kind":"arxiv","version":2},"verdict":{"id":"bf6d08d8-4812-4267-97ea-c988b94b243a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T00:05:18.200340Z","strongest_claim":"MazeBench therefore shows that high accuracy on visual planning tasks does not imply human-like spatial understanding.","one_line_summary":"Multimodal models achieve high maze accuracy by translating images to text grids and performing token-level BFS search, not through visual planning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the two-stage image-to-grid plus token enumeration strategy observed in traces is the dominant mechanism driving performance rather than an artifact of the specific prompting or model configurations tested.","pith_extraction_headline":"Multimodal models solve maze images by converting them to text grids and enumerating paths token by token rather than through visual planning."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2fe155cd7c9677a14573ccbf4acbc8106e30e888fad95d92065dbff341312706"},"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":"2603.26839","created_at":"2026-05-18T03:09:22.499518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.26839v2","created_at":"2026-05-18T03:09:22.499518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.26839","created_at":"2026-05-18T03:09:22.499518+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMNDIYZ6LD3K","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMNDIYZ6LD3KV44V","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMNDIYZ6","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY","json":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY.json","graph_json":"https://pith.science/api/pith-number/DMNDIYZ6LD3KV44VFERAOOUZQY/graph.json","events_json":"https://pith.science/api/pith-number/DMNDIYZ6LD3KV44VFERAOOUZQY/events.json","paper":"https://pith.science/paper/DMNDIYZ6"},"agent_actions":{"view_html":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY","download_json":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY.json","view_paper":"https://pith.science/paper/DMNDIYZ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.26839&json=true","fetch_graph":"https://pith.science/api/pith-number/DMNDIYZ6LD3KV44VFERAOOUZQY/graph.json","fetch_events":"https://pith.science/api/pith-number/DMNDIYZ6LD3KV44VFERAOOUZQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY/action/storage_attestation","attest_author":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY/action/author_attestation","sign_citation":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY/action/citation_signature","submit_replication":"https://pith.science/pith/DMNDIYZ6LD3KV44VFERAOOUZQY/action/replication_record"}},"created_at":"2026-05-18T03:09:22.499518+00:00","updated_at":"2026-05-18T03:09:22.499518+00:00"}