bcN12UkftY / logbook.json
Yashp2003's picture
Update logbook: Repro - FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations
8394209 verified
Raw
History Blame Contribute Delete
2.41 kB
{
"schema_version": 1,
"title": "Repro - FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations",
"emoji": "🎯",
"space_id": "Yashp2003/bcN12UkftY",
"paper": {
"arxiv_id": "2507.07644",
"openreview_id": "bcN12UkftY",
"title": "FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations"
},
"tags": [
"icml2026-repro",
"paper-bcN12UkftY"
],
"updated_at": "2026-07-18T07:58:56+00:00",
"root": {
"slug": "index",
"title": "Repro - FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations",
"file": "pages/index.md",
"children": [
{
"slug": "claim-1-benchmark-scale-taxonomy-sec-3-1-table-1",
"title": "Claim 1: Benchmark scale & taxonomy (Sec 3.1, Table 1)",
"file": "pages/claim-1-benchmark-scale-taxonomy-sec-3-1-table-1/page.md",
"children": []
},
{
"slug": "claim-2-95-metric-vs-50-topology-rule-figure-2",
"title": "Claim 2: >95% metric vs <50% topology/rule (Figure 2)",
"file": "pages/claim-2-95-metric-vs-50-topology-rule-figure-2/page.md",
"children": []
},
{
"slug": "claim-3-accuracy-plateau-30b-params-figure-3",
"title": "Claim 3: Accuracy plateau ~30B params (Figure 3)",
"file": "pages/claim-3-accuracy-plateau-30b-params-figure-3/page.md",
"children": []
},
{
"slug": "claim-4-json-vs-xml-format-invariance-table-5",
"title": "Claim 4: JSON vs XML format invariance (Table 5)",
"file": "pages/claim-4-json-vs-xml-format-invariance-table-5/page.md",
"children": []
},
{
"slug": "claim-5-robustness-to-spatial-jitter-table-10",
"title": "Claim 5: Robustness to spatial jitter (Table 10)",
"file": "pages/claim-5-robustness-to-spatial-jitter-table-10/page.md",
"children": []
},
{
"slug": "claim-6-accuracy-by-room-type-figure-4",
"title": "Claim 6: Accuracy by room type (Figure 4)",
"file": "pages/claim-6-accuracy-by-room-type-figure-4/page.md",
"children": []
},
{
"slug": "conclusion",
"title": "Conclusion",
"file": "pages/conclusion/page.md",
"children": []
}
]
},
"agent_view_tokens": 5683,
"revision": "1784361536014135388"
}