{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/spatial-reasoning","name":"Spatial Reasoning","slug":"spatial-reasoning","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":453,"papers_with_code":198,"benchmarks":2,"benchmark_tables_in_archive":16,"benchmark_tables_shown":16,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/spatial-reasoning-on-6-dof-spatialbench","slug":"spatial-reasoning-on-6-dof-spatialbench","dataset":"6-DoF SpatialBench","dataset_url":null,"rows_in_archive":7,"metrics":["Total","Position-rel","Position-abs","Orientation-rel","Orientation-abs"],"first_row_in_archive_order":{"model":"SoFar","paper_title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","paper_url":"/paper/sofar-language-grounded-orientation-bridges","paper_date":"2025-02-18","arxiv_id":"2502.13143","code_links":[{"title":"qizekun/SoFar","url":"https://github.com/qizekun/SoFar"},{"title":"zhangwenyao1/open6dor_v2_execution","url":"https://github.com/zhangwenyao1/open6dor_v2_execution"}],"syntology":null}},{"leaderboard":"/sota/spatial-reasoning-on-embspatial-bench","slug":"spatial-reasoning-on-embspatial-bench","dataset":"EmbSpatial-Bench","dataset_url":"/dataset/embspatial-bench","rows_in_archive":5,"metrics":["Generation"],"first_row_in_archive_order":{"model":"SoFar","paper_title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","paper_url":"/paper/sofar-language-grounded-orientation-bridges","paper_date":"2025-02-18","arxiv_id":"2502.13143","code_links":[{"title":"qizekun/SoFar","url":"https://github.com/qizekun/SoFar"},{"title":"zhangwenyao1/open6dor_v2_execution","url":"https://github.com/zhangwenyao1/open6dor_v2_execution"}],"syntology":null}},{"leaderboard":null,"slug":"spatial-reasoning-on-3dsrbench","dataset":"3DSRBench","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-blink","dataset":"BlINK","dataset_url":"/dataset/blink","rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-cvbench","dataset":"cvbench","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-mmiu","dataset":"MMIU","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-mmvp","dataset":"MMVP","dataset_url":"/dataset/musicqa-dataset","rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-q-spatial-bench","dataset":"Q-Spatial-Bench","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-qspatialbench-plus","dataset":"QSpatialBench-Plus","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-qspatialbench-scannet","dataset":"QSpatialBench-ScanNet","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-realworldqa","dataset":"RealWorldQA","dataset_url":"/dataset/realworldqa","rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-spatialbench","dataset":"SpatialBench","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-spatialsense","dataset":"SpatialSense","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-vgbench","dataset":"VGBench","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-vsi-bench-8","dataset":"VSI-Bench_8","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null},{"leaderboard":null,"slug":"spatial-reasoning-on-vsr-zeroshot","dataset":"VSR-ZeroShot","dataset_url":null,"rows_in_archive":0,"metrics":["Overall Success Rate"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/blink","name":"BlINK","full_name":"","num_papers_in_archive":58},{"url":"/dataset/musicqa-dataset","name":"MMVP","full_name":"","num_papers_in_archive":53},{"url":"/dataset/embspatial-bench","name":"EmbSpatial-Bench","full_name":"EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models","num_papers_in_archive":6},{"url":"/dataset/repair","name":"RePAIR Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/realworldqa","name":"RealWorldQA","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-question-answering-1","name":"Visual Question Answering"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":5,"rows_per_page":100,"shown":100,"of":453,"of_with_code":198,"tagged_in_all":453,"counts":{"archive_papers_tagged":453,"with_a_code_link":198,"where_syntology_ran_a_sample":70,"not_listed_spam_title":0,"listed":453,"listed_where_code_ran":70,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":56,"every_run_a_failure_of_syntologys_instrument":14,"listed_with_a_run_with_no_instrument_failure":56,"listed_every_run_a_failure_of_syntologys_instrument":14,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/spatial-memory-for-context-reasoning-in","slug":"spatial-memory-for-context-reasoning-in","title":"Spatial Memory for Context Reasoning in Object Detection","date":"2017-04-13","arxiv_id":"1704.04224","repositories_listed":35,"syntology":null},{"url":"/paper/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_constructed":6,"n_ran_checked":8,"n_instrument":8,"n_unverified":35,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]}}},{"url":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}},"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improved-baselines-with-visual-instruction","slug":"improved-baselines-with-visual-instruction","title":"Improved Baselines with Visual Instruction Tuning","date":"2023-10-05","arxiv_id":"2310.03744","repositories_listed":9,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/improved-baselines-with-visual-instruction#ran","syntology_url":"https://syntology.ai/paper/2310.03744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03744"}},"official":null}},{"url":"/paper/minigpt-4-enhancing-vision-language","slug":"minigpt-4-enhancing-vision-language","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","date":"2023-04-20","arxiv_id":"2304.10592","repositories_listed":6,"syntology":null},{"url":"/paper/long-range-arena-a-benchmark-for-efficient-1","slug":"long-range-arena-a-benchmark-for-efficient-1","title":"Long Range Arena: A Benchmark for Efficient Transformers","date":"2020-11-08","arxiv_id":"2011.04006","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/long-range-arena-a-benchmark-for-efficient-1#ran","syntology_url":"https://syntology.ai/paper/2011.04006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.04006"}},"official":{"repos":["google-research/long-range-arena"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/visual-spatial-reasoning","slug":"visual-spatial-reasoning","title":"Visual Spatial Reasoning","date":"2022-04-30","arxiv_id":"2205.00363","repositories_listed":4,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/visual-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2205.00363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.00363"}},"official":{"repos":["cambridgeltl/visual-spatial-reasoning","sohojoe/clip_visual-spatial-reasoning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/touchdown-natural-language-navigation-and","slug":"touchdown-natural-language-navigation-and","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","date":"2018-11-29","arxiv_id":"1811.12354","repositories_listed":4,"syntology":null},{"url":"/paper/guesswhat-visual-object-discovery-through","slug":"guesswhat-visual-object-discovery-through","title":"GuessWhat?! Visual object discovery through multi-modal dialogue","date":"2016-11-23","arxiv_id":"1611.08481","repositories_listed":4,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/guesswhat-visual-object-discovery-through#ran","syntology_url":"https://syntology.ai/paper/1611.08481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08481"}},"official":null}},{"url":"/paper/mapeval-a-map-based-evaluation-of-geo-spatial","slug":"mapeval-a-map-based-evaluation-of-geo-spatial","title":"MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models","date":"2024-12-31","arxiv_id":"2501.00316","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mapeval-a-map-based-evaluation-of-geo-spatial#ran","syntology_url":"https://syntology.ai/paper/2501.00316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00316"}},"official":{"repos":["MapEval/MapEval-API","MapEval/MapEval-Textual","MapEval/MapEval-Visual"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/probing-the-limitations-of-multimodal","slug":"probing-the-limitations-of-multimodal","title":"Probing the limitations of multimodal language models for chemistry and materials research","date":"2024-11-25","arxiv_id":"2411.16955","repositories_listed":3,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/probing-the-limitations-of-multimodal#ran","syntology_url":"https://syntology.ai/paper/2411.16955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16955"}},"official":{"repos":["lamalab-org/mac-bench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/no-blind-spots-full-surround-multi-object","slug":"no-blind-spots-full-surround-multi-object","title":"No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles using Cameras & LiDARs","date":"2018-02-23","arxiv_id":"1802.08755","repositories_listed":3,"syntology":null},{"url":"/paper/infigui-r1-advancing-multimodal-gui-agents","slug":"infigui-r1-advancing-multimodal-gui-agents","title":"InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners","date":"2025-04-19","arxiv_id":"2504.14239","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/infigui-r1-advancing-multimodal-gui-agents#ran","syntology_url":"https://syntology.ai/paper/2504.14239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14239"}},"official":{"repos":["reallm-labs/infigui-r1"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spatial-r1-enhancing-mllms-in-video-spatial","slug":"spatial-r1-enhancing-mllms-in-video-spatial","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","date":"2025-04-02","arxiv_id":"2504.01805","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatial-r1-enhancing-mllms-in-video-spatial#ran","syntology_url":"https://syntology.ai/paper/2504.01805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01805"}},"official":{"repos":["ouyangkun10/spacer","ouyangkun10/spatial-r1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/iref-vla-a-benchmark-for-interactive","slug":"iref-vla-a-benchmark-for-interactive","title":"IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes","date":"2025-03-20","arxiv_id":"2503.17406","repositories_listed":2,"syntology":null},{"url":"/paper/sonata-self-supervised-learning-of-reliable","slug":"sonata-self-supervised-learning-of-reliable","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","date":"2025-03-20","arxiv_id":"2503.16429","repositories_listed":2,"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/sonata-self-supervised-learning-of-reliable#ran","syntology_url":"https://syntology.ai/paper/2503.16429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16429"}},"official":{"repos":["Pointcept/Pointcept","facebookresearch/sonata"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/cityeqa-a-hierarchical-llm-agent-on-embodied","slug":"cityeqa-a-hierarchical-llm-agent-on-embodied","title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","date":"2025-02-18","arxiv_id":"2502.12532","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/cityeqa-a-hierarchical-llm-agent-on-embodied#ran","syntology_url":"https://syntology.ai/paper/2502.12532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12532"}},"official":{"repos":["biluyong/cityeqa","tsinghua-fib-lab/CityEQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sofar-language-grounded-orientation-bridges","slug":"sofar-language-grounded-orientation-bridges","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","date":"2025-02-18","arxiv_id":"2502.13143","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-planning-abilities-of-openai-s-o1","slug":"on-the-planning-abilities-of-openai-s-o1","title":"On The Planning Abilities of OpenAI's o1 Models: Feasibility, Optimality, and Generalizability","date":"2024-09-30","arxiv_id":"2409.19924","repositories_listed":2,"syntology":null},{"url":"/paper/reframing-spatial-reasoning-evaluation-in","slug":"reframing-spatial-reasoning-evaluation-in","title":"Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning","date":"2024-05-23","arxiv_id":"2405.15064","repositories_listed":2,"syntology":null},{"url":"/paper/seeing-the-roads-through-the-trees-a","slug":"seeing-the-roads-through-the-trees-a","title":"Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery","date":"2024-01-12","arxiv_id":"2401.06762","repositories_listed":2,"syntology":null},{"url":"/paper/what-s-up-with-vision-language-models","slug":"what-s-up-with-vision-language-models","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","date":"2023-10-30","arxiv_id":"2310.19785","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/what-s-up-with-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2310.19785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19785"}},"official":{"repos":["amitakamath/whatsup_vlms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/qwen-vl-a-frontier-large-vision-language","slug":"qwen-vl-a-frontier-large-vision-language","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","date":"2023-08-24","arxiv_id":"2308.12966","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/qwen-vl-a-frontier-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12966"}},"official":{"repos":["qwenlm/qwen-vl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/chat-3d-data-efficiently-tuning-large","slug":"chat-3d-data-efficiently-tuning-large","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","date":"2023-08-17","arxiv_id":"2308.08769","repositories_listed":2,"syntology":null},{"url":"/paper/act3d-infinite-resolution-action-detection","slug":"act3d-infinite-resolution-action-detection","title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","date":"2023-06-30","arxiv_id":"2306.17817","repositories_listed":2,"syntology":null},{"url":"/paper/llm-grounded-diffusion-enhancing-prompt","slug":"llm-grounded-diffusion-enhancing-prompt","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","date":"2023-05-23","arxiv_id":"2305.13655","repositories_listed":2,"syntology":null},{"url":"/paper/reclip-a-strong-zero-shot-baseline-for-1","slug":"reclip-a-strong-zero-shot-baseline-for-1","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","date":"2022-04-12","arxiv_id":"2204.05991","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/reclip-a-strong-zero-shot-baseline-for-1#ran","syntology_url":"https://syntology.ai/paper/2204.05991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.05991"}},"official":{"repos":["allenai/reclip"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-agents-how-to-map-spatial-reasoning","slug":"teaching-agents-how-to-map-spatial-reasoning","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","date":"2021-07-13","arxiv_id":"2107.06011","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/teaching-agents-how-to-map-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2107.06011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06011"}},"official":{"repos":["PierreMarza/teaching_agents_how_to_map"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/spartqa-a-textual-question-answering-1","slug":"spartqa-a-textual-question-answering-1","title":"SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning","date":"2021-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-egospheric-spatial-memory","slug":"end-to-end-egospheric-spatial-memory","title":"End-to-End Egospheric Spatial Memory","date":"2021-02-15","arxiv_id":"2102.07764","repositories_listed":2,"syntology":null},{"url":"/paper/learning-and-reasoning-with-the-graph","slug":"learning-and-reasoning-with-the-graph","title":"Learning and Reasoning with the Graph Structure Representation in Robotic Surgery","date":"2020-07-07","arxiv_id":"2007.03357","repositories_listed":2,"syntology":{"n":8,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/learning-and-reasoning-with-the-graph#ran","syntology_url":"https://syntology.ai/paper/2007.03357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03357"}},"official":{"repos":["mobarakol/Surgical_SceneGraph_Generation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"url":"/paper/vsgnet-spatial-attention-network-for","slug":"vsgnet-spatial-attention-network-for","title":"VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions","date":"2020-03-11","arxiv_id":"2003.05541","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vsgnet-spatial-attention-network-for#ran","syntology_url":"https://syntology.ai/paper/2003.05541","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05541"}},"official":{"repos":["ASMIftekhar/VSGNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/floornet-a-unified-framework-for-floorplan","slug":"floornet-a-unified-framework-for-floorplan","title":"FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans","date":"2018-03-31","arxiv_id":"1804.00090","repositories_listed":2,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/floornet-a-unified-framework-for-floorplan#ran","syntology_url":"https://syntology.ai/paper/1804.00090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00090"}},"official":{"repos":["art-programmer/FloorNet"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/warehouse-spatial-question-answering-with-llm","slug":"warehouse-spatial-question-answering-with-llm","title":"Warehouse Spatial Question Answering with LLM Agent","date":"2025-07-14","arxiv_id":"2507.10778","repositories_listed":1,"syntology":null},{"url":"/paper/ost-bench-evaluating-the-capabilities-of","slug":"ost-bench-evaluating-the-capabilities-of","title":"OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding","date":"2025-07-10","arxiv_id":"2507.07984","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-rl-to-long-videos","slug":"scaling-rl-to-long-videos","title":"Scaling RL to Long Videos","date":"2025-07-10","arxiv_id":"2507.07966","repositories_listed":1,"syntology":{"n":24,"n_ran":18,"n_constructed":1,"n_ran_checked":7,"n_instrument":11,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 11 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/scaling-rl-to-long-videos#ran","syntology_url":"https://syntology.ai/paper/2507.07966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.07966"}},"official":{"repos":["hiyouga/easyr1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/implicitqa-going-beyond-frames-towards","slug":"implicitqa-going-beyond-frames-towards","title":"ImplicitQA: Going beyond frames towards Implicit Video Reasoning","date":"2025-06-26","arxiv_id":"2506.21742","repositories_listed":1,"syntology":null},{"url":"/paper/3d-aware-vision-language-models-fine-tuning","slug":"3d-aware-vision-language-models-fine-tuning","title":"3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation","date":"2025-06-11","arxiv_id":"2506.09883","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcing-spatial-reasoning-in-vision","slug":"reinforcing-spatial-reasoning-in-vision","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","date":"2025-06-11","arxiv_id":"2506.09965","repositories_listed":1,"syntology":null},{"url":"/paper/unfolding-spatial-cognition-evaluating","slug":"unfolding-spatial-cognition-evaluating","title":"Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations","date":"2025-06-05","arxiv_id":"2506.04633","repositories_listed":1,"syntology":null},{"url":"/paper/in-the-wild-audio-spatialization-with","slug":"in-the-wild-audio-spatialization-with","title":"In-the-wild Audio Spatialization with Flexible Text-guided Localization","date":"2025-06-01","arxiv_id":"2506.00927","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-videos-for-3d-world-enhancing","slug":"learning-from-videos-for-3d-world-enhancing","title":"Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors","date":"2025-05-30","arxiv_id":"2505.24625","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/learning-from-videos-for-3d-world-enhancing#ran","syntology_url":"https://syntology.ai/paper/2505.24625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24625"}},"official":null}},{"url":"/paper/seeing-is-not-reasoning-mvpbench-for-graph","slug":"seeing-is-not-reasoning-mvpbench-for-graph","title":"Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT","date":"2025-05-30","arxiv_id":"2505.24182","repositories_listed":1,"syntology":null},{"url":"/paper/videocad-a-large-scale-video-dataset-for","slug":"videocad-a-large-scale-video-dataset-for","title":"VideoCAD: A Large-Scale Video Dataset for Learning UI Interactions and 3D Reasoning from CAD Software","date":"2025-05-30","arxiv_id":"2505.24838","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-reinforcement-learning-for-visual","slug":"grounded-reinforcement-learning-for-visual","title":"Grounded Reinforcement Learning for Visual Reasoning","date":"2025-05-29","arxiv_id":"2505.23678","repositories_listed":1,"syntology":null},{"url":"/paper/thinkgeo-evaluating-tool-augmented-agents-for","slug":"thinkgeo-evaluating-tool-augmented-agents-for","title":"ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks","date":"2025-05-29","arxiv_id":"2505.23752","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/thinkgeo-evaluating-tool-augmented-agents-for#ran","syntology_url":"https://syntology.ai/paper/2505.23752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23752"}},"official":{"repos":["mbzuai-oryx/thinkgeo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/uni-mumer-unified-multi-task-fine-tuning-of","slug":"uni-mumer-unified-multi-task-fine-tuning-of","title":"Uni-MuMER: Unified Multi-Task Fine-Tuning of Vision-Language Model for Handwritten Mathematical Expression Recognition","date":"2025-05-29","arxiv_id":"2505.23566","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":1,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uni-mumer-unified-multi-task-fine-tuning-of#ran","syntology_url":"https://syntology.ai/paper/2505.23566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23566"}},"official":{"repos":["bflameswift/uni-mumer"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-action-model-with-open-world","slug":"vision-language-action-model-with-open-world","title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","date":"2025-05-28","arxiv_id":"2505.21906","repositories_listed":1,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vision-language-action-model-with-open-world#ran","syntology_url":"https://syntology.ai/paper/2505.21906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21906"}},"official":null}},{"url":"/paper/mineanybuild-benchmarking-spatial-planning","slug":"mineanybuild-benchmarking-spatial-planning","title":"MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents","date":"2025-05-26","arxiv_id":"2505.20148","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mineanybuild-benchmarking-spatial-planning#ran","syntology_url":"https://syntology.ai/paper/2505.20148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20148"}},"official":{"repos":["mineanybuild/mineanybuild"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/vlm-3r-vision-language-models-augmented-with","slug":"vlm-3r-vision-language-models-augmented-with","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","date":"2025-05-26","arxiv_id":"2505.20279","repositories_listed":1,"syntology":null},{"url":"/paper/knot-so-simple-a-minimalistic-environment-for","slug":"knot-so-simple-a-minimalistic-environment-for","title":"Knot So Simple: A Minimalistic Environment for Spatial Reasoning","date":"2025-05-23","arxiv_id":"2505.18028","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-the-dynamic-perception-gap-training","slug":"bridging-the-dynamic-perception-gap-training","title":"Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning","date":"2025-05-22","arxiv_id":"2505.16579","repositories_listed":1,"syntology":null},{"url":"/paper/conav-collaborative-cross-modal-reasoning-for","slug":"conav-collaborative-cross-modal-reasoning-for","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","date":"2025-05-22","arxiv_id":"2505.16663","repositories_listed":1,"syntology":null},{"url":"/paper/detailmaster-can-your-text-to-image-model","slug":"detailmaster-can-your-text-to-image-model","title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","date":"2025-05-22","arxiv_id":"2505.16915","repositories_listed":1,"syntology":null},{"url":"/paper/got-r1-unleashing-reasoning-capability-of","slug":"got-r1-unleashing-reasoning-capability-of","title":"GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.17022","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":6,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/got-r1-unleashing-reasoning-capability-of#ran","syntology_url":"https://syntology.ai/paper/2505.17022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17022"}},"official":{"repos":["gogoduan/got-r1"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sparc-a-spatial-pathfinding-reasoning","slug":"sparc-a-spatial-pathfinding-reasoning","title":"SPaRC: A Spatial Pathfinding Reasoning Challenge","date":"2025-05-22","arxiv_id":"2505.16686","repositories_listed":1,"syntology":null},{"url":"/paper/spatialscore-towards-unified-evaluation-for","slug":"spatialscore-towards-unified-evaluation-for","title":"SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding","date":"2025-05-22","arxiv_id":"2505.17012","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatialscore-towards-unified-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/2505.17012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17012"}},"official":{"repos":["haoningwu3639/SpatialScore"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sphyr-spatial-physical-reasoning-benchmark-on","slug":"sphyr-spatial-physical-reasoning-benchmark-on","title":"SPhyR: Spatial-Physical Reasoning Benchmark on Material Distribution","date":"2025-05-21","arxiv_id":"2505.16048","repositories_listed":1,"syntology":null},{"url":"/paper/towards-visuospatial-cognition-via","slug":"towards-visuospatial-cognition-via","title":"Towards Visuospatial Cognition via Hierarchical Fusion of Visual Experts","date":"2025-05-18","arxiv_id":"2505.12363","repositories_listed":1,"syntology":null},{"url":"/paper/visuospatial-cognitive-assistant","slug":"visuospatial-cognitive-assistant","title":"Visuospatial Cognitive Assistant","date":"2025-05-18","arxiv_id":"2505.12312","repositories_listed":1,"syntology":null},{"url":"/paper/from-seeing-to-doing-bridging-reasoning-and","slug":"from-seeing-to-doing-bridging-reasoning-and","title":"From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation","date":"2025-05-13","arxiv_id":"2505.08548","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/from-seeing-to-doing-bridging-reasoning-and#ran","syntology_url":"https://syntology.ai/paper/2505.08548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.08548"}},"official":{"repos":["pickxiguapi/embodied-fsd"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/text-to-cadquery-a-new-paradigm-for-cad","slug":"text-to-cadquery-a-new-paradigm-for-cad","title":"Text-to-CadQuery: A New Paradigm for CAD Generation with Scalable Large Model Capabilities","date":"2025-05-10","arxiv_id":"2505.06507","repositories_listed":1,"syntology":null},{"url":"/paper/citynavagent-aerial-vision-and-language","slug":"citynavagent-aerial-vision-and-language","title":"CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory","date":"2025-05-08","arxiv_id":"2505.05622","repositories_listed":1,"syntology":null},{"url":"/paper/geospatial-mechanistic-interpretability-of","slug":"geospatial-mechanistic-interpretability-of","title":"Geospatial Mechanistic Interpretability of Large Language Models","date":"2025-05-06","arxiv_id":"2505.03368","repositories_listed":1,"syntology":null},{"url":"/paper/sort3d-spatial-object-centric-reasoning","slug":"sort3d-spatial-object-centric-reasoning","title":"SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models","date":"2025-04-25","arxiv_id":"2504.18684","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-visual-chain-of-thought","slug":"unsupervised-visual-chain-of-thought","title":"Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization","date":"2025-04-25","arxiv_id":"2504.18397","repositories_listed":1,"syntology":{"n":30,"n_ran":25,"n_constructed":3,"n_ran_checked":7,"n_instrument":18,"n_unverified":5,"n_honours":1,"n_violates":3,"n_no_contract":3,"n_pointer_only":30,"phrase":"25 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 3 violated, 3 with no contract checked; 18 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/unsupervised-visual-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2504.18397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.18397"}},"official":{"repos":["kesenzhao/uv-cot"],"state":"official (archive's flag): 24 ran","n_ran":24,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/embodied-r-collaborative-framework-for","slug":"embodied-r-collaborative-framework-for","title":"Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning","date":"2025-04-17","arxiv_id":"2504.12680","repositories_listed":1,"syntology":null},{"url":"/paper/smartfreeedit-mask-free-spatial-aware-image","slug":"smartfreeedit-mask-free-spatial-aware-image","title":"SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding","date":"2025-04-17","arxiv_id":"2504.12704","repositories_listed":1,"syntology":null},{"url":"/paper/3d-coca-contrastive-learners-are-3d","slug":"3d-coca-contrastive-learners-are-3d","title":"3D CoCa: Contrastive Learners are 3D Captioners","date":"2025-04-13","arxiv_id":"2504.09518","repositories_listed":1,"syntology":null},{"url":"/paper/enabling-systematic-generalization-in","slug":"enabling-systematic-generalization-in","title":"Enabling Systematic Generalization in Abstract Spatial Reasoning through Meta-Learning for Compositionality","date":"2025-04-02","arxiv_id":"2504.01445","repositories_listed":1,"syntology":null},{"url":"/paper/improved-visual-spatial-reasoning-via-r1-zero","slug":"improved-visual-spatial-reasoning-via-r1-zero","title":"Improved Visual-Spatial Reasoning via R1-Zero-Like Training","date":"2025-04-01","arxiv_id":"2504.00883","repositories_listed":1,"syntology":null},{"url":"/paper/inference-time-scaling-for-complex-tasks","slug":"inference-time-scaling-for-complex-tasks","title":"Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead","date":"2025-03-31","arxiv_id":"2504.00294","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inference-time-scaling-for-complex-tasks#ran","syntology_url":"https://syntology.ai/paper/2504.00294","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.00294"}},"official":null}},{"url":"/paper/from-flatland-to-space-teaching-vision","slug":"from-flatland-to-space-teaching-vision","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D","date":"2025-03-29","arxiv_id":"2503.22976","repositories_listed":1,"syntology":null},{"url":"/paper/embodied-reasoner-synergizing-visual-search","slug":"embodied-reasoner-synergizing-visual-search","title":"Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks","date":"2025-03-27","arxiv_id":"2503.21696","repositories_listed":1,"syntology":null},{"url":"/paper/video-r1-reinforcing-video-reasoning-in-mllms","slug":"video-r1-reinforcing-video-reasoning-in-mllms","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","date":"2025-03-27","arxiv_id":"2503.21776","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-r1-reinforcing-video-reasoning-in-mllms#ran","syntology_url":"https://syntology.ai/paper/2503.21776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21776"}},"official":{"repos":["tulerfeng/video-r1"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/mind-the-gap-benchmarking-spatial-reasoning","slug":"mind-the-gap-benchmarking-spatial-reasoning","title":"Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models","date":"2025-03-25","arxiv_id":"2503.19707","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mind-the-gap-benchmarking-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19707"}},"official":{"repos":["stogiannidis/srbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/metaspatial-reinforcing-3d-spatial-reasoning","slug":"metaspatial-reinforcing-3d-spatial-reasoning","title":"MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse","date":"2025-03-24","arxiv_id":"2503.18470","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/metaspatial-reinforcing-3d-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.18470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18470"}},"official":{"repos":["pzyseere/metaspatial"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cospace-benchmarking-continuous-space","slug":"cospace-benchmarking-continuous-space","title":"CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models","date":"2025-03-18","arxiv_id":"2503.14161","repositories_listed":1,"syntology":null},{"url":"/paper/free-form-language-based-robotic-reasoning","slug":"free-form-language-based-robotic-reasoning","title":"Free-form language-based robotic reasoning and grasping","date":"2025-03-17","arxiv_id":"2503.13082","repositories_listed":1,"syntology":null},{"url":"/paper/grounded-chain-of-thought-for-multimodal","slug":"grounded-chain-of-thought-for-multimodal","title":"Grounded Chain-of-Thought for Multimodal Large Language Models","date":"2025-03-17","arxiv_id":"2503.12799","repositories_listed":1,"syntology":null},{"url":"/paper/nuplanqa-a-large-scale-dataset-and-benchmark","slug":"nuplanqa-a-large-scale-dataset-and-benchmark","title":"NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models","date":"2025-03-17","arxiv_id":"2503.12772","repositories_listed":1,"syntology":null},{"url":"/paper/logic-rag-augmenting-large-multimodal-models","slug":"logic-rag-augmenting-large-multimodal-models","title":"Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding","date":"2025-03-16","arxiv_id":"2503.12663","repositories_listed":1,"syntology":null},{"url":"/paper/viso-grasp-vision-language-informed-spatial","slug":"viso-grasp-vision-language-informed-spatial","title":"VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility","date":"2025-03-16","arxiv_id":"2503.12609","repositories_listed":1,"syntology":null},{"url":"/paper/open3dvqa-a-benchmark-for-comprehensive","slug":"open3dvqa-a-benchmark-for-comprehensive","title":"Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space","date":"2025-03-14","arxiv_id":"2503.11094","repositories_listed":1,"syntology":null},{"url":"/paper/pointvla-injecting-the-3d-world-into-vision","slug":"pointvla-injecting-the-3d-world-into-vision","title":"PointVLA: Injecting the 3D World into Vision-Language-Action Models","date":"2025-03-10","arxiv_id":"2503.07511","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pointvla-injecting-the-3d-world-into-vision#ran","syntology_url":"https://syntology.ai/paper/2503.07511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07511"}},"official":null}},{"url":"/paper/towards-ambiguity-free-spatial-foundation","slug":"towards-ambiguity-free-spatial-foundation","title":"Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity","date":"2025-03-08","arxiv_id":"2503.06014","repositories_listed":1,"syntology":null},{"url":"/paper/factorio-learning-environment","slug":"factorio-learning-environment","title":"Factorio Learning Environment","date":"2025-03-06","arxiv_id":"2503.09617","repositories_listed":1,"syntology":null},{"url":"/paper/why-is-spatial-reasoning-hard-for-vlms-an","slug":"why-is-spatial-reasoning-hard-for-vlms-an","title":"Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas","date":"2025-03-03","arxiv_id":"2503.01773","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":4,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/why-is-spatial-reasoning-hard-for-vlms-an#ran","syntology_url":"https://syntology.ai/paper/2503.01773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01773"}},"official":{"repos":["shiqichen17/adaptvis"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/forest-frame-of-reference-evaluation-in","slug":"forest-frame-of-reference-evaluation-in","title":"FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks","date":"2025-02-25","arxiv_id":"2502.17775","repositories_listed":1,"syntology":null},{"url":"/paper/introducing-visual-perception-token-into","slug":"introducing-visual-perception-token-into","title":"Introducing Visual Perception Token into Multimodal Large Language Model","date":"2025-02-24","arxiv_id":"2502.17425","repositories_listed":1,"syntology":null},{"url":"/paper/from-text-to-space-mapping-abstract-spatial","slug":"from-text-to-space-mapping-abstract-spatial","title":"From Text to Space: Mapping Abstract Spatial Models in LLMs during a Grid-World Navigation Task","date":"2025-02-23","arxiv_id":"2502.16690","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-text-to-space-mapping-abstract-spatial#ran","syntology_url":"https://syntology.ai/paper/2502.16690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16690"}},"official":{"repos":["mneuronico/griw-world-spatial-orientation-task"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/alphamaze-enhancing-large-language-models","slug":"alphamaze-enhancing-large-language-models","title":"AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO","date":"2025-02-20","arxiv_id":"2502.14669","repositories_listed":1,"syntology":null},{"url":"/paper/pulsecheck457-a-diagnostic-benchmark-for-6d","slug":"pulsecheck457-a-diagnostic-benchmark-for-6d","title":"Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models","date":"2025-02-12","arxiv_id":"2502.08636","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-reasoning-to-adapt-large-language","slug":"enhancing-reasoning-to-adapt-large-language","title":"Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications","date":"2025-02-05","arxiv_id":"2502.04384","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/enhancing-reasoning-to-adapt-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.04384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04384"}},"official":{"repos":["wenboown/generative-ai-for-semiconductor-physical-design"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ivispar-an-interactive-visual-spatial","slug":"ivispar-an-interactive-visual-spatial","title":"iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs","date":"2025-02-05","arxiv_id":"2502.03214","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ivispar-an-interactive-visual-spatial#ran","syntology_url":"https://syntology.ai/paper/2502.03214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03214"}},"official":{"repos":["SharkyBamboozle/iVISPAR"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hspformer-hierarchical-spatial-perception","slug":"hspformer-hierarchical-spatial-perception","title":"HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation","date":"2025-01-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/imagine-while-reasoning-in-space-multimodal","slug":"imagine-while-reasoning-in-space-multimodal","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","date":"2025-01-13","arxiv_id":"2501.07542","repositories_listed":1,"syntology":null},{"url":"/paper/mm-gen-enhancing-task-performance-through","slug":"mm-gen-enhancing-task-performance-through","title":"MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation","date":"2025-01-07","arxiv_id":"2501.04155","repositories_listed":1,"syntology":null},{"url":"/paper/expand-vsr-benchmark-for-vllm-to-expertize-in","slug":"expand-vsr-benchmark-for-vllm-to-expertize-in","title":"Expand VSR Benchmark for VLLM to Expertize in Spatial Rules","date":"2024-12-24","arxiv_id":"2412.18224","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-relational-state-abstraction-in","slug":"investigating-relational-state-abstraction-in","title":"Investigating Relational State Abstraction in Collaborative MARL","date":"2024-12-19","arxiv_id":"2412.15388","repositories_listed":1,"syntology":null}],"syntology_records":38,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":70,"papers_where_code_ran_first_page":"/task/spatial-reasoning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":5,"url":"/task/spatial-reasoning/papers/2","json":"/task/spatial-reasoning/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/spatial-reasoning/papers/3","json":"/task/spatial-reasoning/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/spatial-reasoning/papers/4","json":"/task/spatial-reasoning/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/spatial-reasoning/papers/5","json":"/task/spatial-reasoning/papers/5.json","rows":53},{"order":"ran","page":1,"of":1,"url":"/task/spatial-reasoning/papers/ran/1","json":"/task/spatial-reasoning/papers/ran/1.json","rows":70}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"e1a221b4e05c36cba4223c521e5b06098d0b5e8beeebefa8730f182b54a1ea67","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}