{"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/3d-question-answering-3d-qa","name":"3D Question Answering (3D-QA)","slug":"3d-question-answering-3d-qa","description_markdown":"A 3D-QA task requires models to answer a question when given all the information of a 3D scene. Here, models use the 3D spatial information, such as RGB-D scans or point cloud data. We also require models to specify the 3D-bounding boxes of objects that are related to this question answering. This prevents models from answering questions by relying on the textual priors of the trained questions without examining the scene. However, unlike 3D dense captioning, we do not require models to target one described object for each question. This is because multiple objects can be used to answer certain questions. For example, the question “What color is the chairs around the table?” is related to multiple objects. This question is also answerable as long as the chairs around the unique table in the scene have the same color. In such scenarios, we require models to answer the question addressing multiple 3D-bounding boxes.","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":22,"papers_with_code":17,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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/3d-question-answering-3d-qa-on-scanqa-test-w","slug":"3d-question-answering-3d-qa-on-scanqa-test-w","dataset":"ScanQA Test w/ objects","dataset_url":"/dataset/scanqa","rows_in_archive":18,"metrics":["Exact Match","BLEU-1","BLEU-4","ROUGE","METEOR","CIDEr"],"first_row_in_archive_order":{"model":"BridgeQA","paper_title":"Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA","paper_url":"/paper/bridging-the-gap-between-2d-and-3d-visual","paper_date":"2024-02-24","arxiv_id":"2402.15933","code_links":[{"title":"matthewdm0816/bridgeqa","url":"https://github.com/matthewdm0816/bridgeqa"}],"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":1,"n_honours":4,"n_violates":1,"n_no_contract":0,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-the-gap-between-2d-and-3d-visual#ran","syntology_url":"https://syntology.ai/paper/2402.15933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15933"}},"official":{"repos":["matthewdm0816/bridgeqa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/3d-question-answering-3d-qa-on-sqa3d","slug":"3d-question-answering-3d-qa-on-sqa3d","dataset":"SQA3D","dataset_url":"/dataset/sqa3d","rows_in_archive":13,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"LLaVA-3D","paper_title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","paper_url":"/paper/llava-3d-a-simple-yet-effective-pathway-to","paper_date":"2024-09-26","arxiv_id":"2409.18125","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-question-answering-3d-qa-on-3d-mm-vet","slug":"3d-question-answering-3d-qa-on-3d-mm-vet","dataset":"3D MM-Vet","dataset_url":"/dataset/3d-mm-vet","rows_in_archive":5,"metrics":["Overall Accuracy"],"first_row_in_archive_order":{"model":"ShapeLLM-13B","paper_title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","paper_url":"/paper/shapellm-universal-3d-object-understanding","paper_date":"2024-02-27","arxiv_id":"2402.17766","code_links":[{"title":"qizekun/ShapeLLM","url":"https://github.com/qizekun/ShapeLLM"},{"title":"qizekun/ReCon","url":"https://github.com/qizekun/ReCon"},{"title":"runpeidong/act","url":"https://github.com/runpeidong/act"}],"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":6,"n_instrument":8,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/shapellm-universal-3d-object-understanding#ran","syntology_url":"https://syntology.ai/paper/2402.17766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17766"}},"official":{"repos":["qizekun/ShapeLLM"],"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"]}}}}],"datasets":[{"url":"/dataset/scanqa","name":"ScanQA","full_name":"ScanQA: 3D Question Answering for Spatial Scene Understanding","num_papers_in_archive":70},{"url":"/dataset/sqa3d","name":"SQA3D","full_name":"Situated Question Answering in 3D Scenes","num_papers_in_archive":58},{"url":"/dataset/3d-mm-vet","name":"3D MM-Vet","full_name":"","num_papers_in_archive":4},{"url":"/dataset/beacon3d","name":"Beacon3D","full_name":"","num_papers_in_archive":2},{"url":"/dataset/msqa","name":"MSQA","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-question-answering","name":"Visual Question Answering (VQA)"}],"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":1,"rows_per_page":100,"shown":22,"of":22,"of_with_code":17,"tagged_in_all":22,"counts":{"archive_papers_tagged":22,"with_a_code_link":17,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":13,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/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/point-bind-point-llm-aligning-point-cloud","slug":"point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","arxiv_id":"2309.00615","repositories_listed":5,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":9,"n_instrument":6,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":5,"n_pointer_only":15,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/point-bind-point-llm-aligning-point-cloud#ran","syntology_url":"https://syntology.ai/paper/2309.00615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.00615"}},"official":{"repos":["ziyuguo99/point-bind_point-llm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/3d-llm-injecting-the-3d-world-into-large","slug":"3d-llm-injecting-the-3d-world-into-large","title":"3D-LLM: Injecting the 3D World into Large Language Models","date":"2023-07-24","arxiv_id":"2307.12981","repositories_listed":5,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/3d-llm-injecting-the-3d-world-into-large#ran","syntology_url":"https://syntology.ai/paper/2307.12981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12981"}},"official":null}},{"url":"/paper/shapellm-universal-3d-object-understanding","slug":"shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","date":"2024-02-27","arxiv_id":"2402.17766","repositories_listed":3,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":6,"n_instrument":8,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/shapellm-universal-3d-object-understanding#ran","syntology_url":"https://syntology.ai/paper/2402.17766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17766"}},"official":{"repos":["qizekun/ShapeLLM"],"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/mvbench-a-comprehensive-multi-modal-video","slug":"mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mvbench-a-comprehensive-multi-modal-video#ran","syntology_url":"https://syntology.ai/paper/2311.17005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17005"}},"official":{"repos":["opengvlab/ask-anything"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pointllm-empowering-large-language-models-to","slug":"pointllm-empowering-large-language-models-to","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","date":"2023-08-31","arxiv_id":"2308.16911","repositories_listed":3,"syntology":null},{"url":"/paper/llava-onevision-easy-visual-task-transfer","slug":"llava-onevision-easy-visual-task-transfer","title":"LLaVA-OneVision: Easy Visual Task Transfer","date":"2024-08-06","arxiv_id":"2408.03326","repositories_listed":2,"syntology":null},{"url":"/paper/chat-3d-v2-bridging-3d-scene-and-large","slug":"chat-3d-v2-bridging-3d-scene-and-large","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","date":"2023-12-13","arxiv_id":"2312.08168","repositories_listed":2,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":5,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"11 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/chat-3d-v2-bridging-3d-scene-and-large#ran","syntology_url":"https://syntology.ai/paper/2312.08168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08168"}},"official":{"repos":["chat-3d/chat-3d-v2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-learning-a-generalist-model-for","slug":"towards-learning-a-generalist-model-for","title":"Towards Learning a Generalist Model for Embodied Navigation","date":"2023-12-04","arxiv_id":"2312.02010","repositories_listed":2,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/towards-learning-a-generalist-model-for#ran","syntology_url":"https://syntology.ai/paper/2312.02010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02010"}},"official":{"repos":["lavi-lab/navillm","zd11024/NaviLLM"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-the-mist-over-3d-vision-language","slug":"unveiling-the-mist-over-3d-vision-language","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","date":"2025-03-28","arxiv_id":"2503.22420","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":1,"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; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unveiling-the-mist-over-3d-vision-language#ran","syntology_url":"https://syntology.ai/paper/2503.22420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.22420"}},"official":{"repos":["beacon-3d/beacon-3d"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dspnet-dual-vision-scene-perception-for","slug":"dspnet-dual-vision-scene-perception-for","title":"DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering","date":"2025-03-05","arxiv_id":"2503.03190","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/dspnet-dual-vision-scene-perception-for#ran","syntology_url":"https://syntology.ai/paper/2503.03190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.03190"}},"official":{"repos":["LZ-CH/DSPNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-3d-llm-learning-position-aware-video","slug":"video-3d-llm-learning-position-aware-video","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","date":"2024-11-30","arxiv_id":"2412.00493","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-situated-reasoning-in-3d-scenes","slug":"multi-modal-situated-reasoning-in-3d-scenes","title":"Multi-modal Situated Reasoning in 3D Scenes","date":"2024-09-04","arxiv_id":"2409.02389","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-modal-situated-reasoning-in-3d-scenes#ran","syntology_url":"https://syntology.ai/paper/2409.02389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02389"}},"official":{"repos":["MSR3D/MSR3D"],"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","unlocated"]}}},{"url":"/paper/bridging-the-gap-between-2d-and-3d-visual","slug":"bridging-the-gap-between-2d-and-3d-visual","title":"Bridging the Gap between 2D and 3D Visual Question Answering: A Fusion Approach for 3D VQA","date":"2024-02-24","arxiv_id":"2402.15933","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":1,"n_honours":4,"n_violates":1,"n_no_contract":0,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-the-gap-between-2d-and-3d-visual#ran","syntology_url":"https://syntology.ai/paper/2402.15933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15933"}},"official":{"repos":["matthewdm0816/bridgeqa"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/an-embodied-generalist-agent-in-3d-world","slug":"an-embodied-generalist-agent-in-3d-world","title":"An Embodied Generalist Agent in 3D World","date":"2023-11-18","arxiv_id":"2311.12871","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":9,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/an-embodied-generalist-agent-in-3d-world#ran","syntology_url":"https://syntology.ai/paper/2311.12871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12871"}},"official":{"repos":["embodied-generalist/embodied-generalist"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/3d-vista-pre-trained-transformer-for-3d","slug":"3d-vista-pre-trained-transformer-for-3d","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","date":"2023-08-08","arxiv_id":"2308.04352","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/3d-vista-pre-trained-transformer-for-3d#ran","syntology_url":"https://syntology.ai/paper/2308.04352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04352"}},"official":null}},{"url":"/paper/scanqa-3d-question-answering-for-spatial","slug":"scanqa-3d-question-answering-for-spatial","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","date":"2021-12-20","arxiv_id":"2112.10482","repositories_listed":1,"syntology":null},{"url":"/paper/video-instruction-tuning-with-synthetic-data","slug":"video-instruction-tuning-with-synthetic-data","title":"Video Instruction Tuning With Synthetic Data","date":"2024-10-03","arxiv_id":"2410.02713","repositories_listed":0,"syntology":null},{"url":"/paper/llava-3d-a-simple-yet-effective-pathway-to","slug":"llava-3d-a-simple-yet-effective-pathway-to","title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","date":"2024-09-26","arxiv_id":"2409.18125","repositories_listed":0,"syntology":null},{"url":"/paper/unifying-3d-vision-language-understanding-via","slug":"unifying-3d-vision-language-understanding-via","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","date":"2024-05-19","arxiv_id":"2405.11442","repositories_listed":0,"syntology":null},{"url":"/paper/scene-llm-extending-language-model-for-3d","slug":"scene-llm-extending-language-model-for-3d","title":"Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning","date":"2024-03-18","arxiv_id":"2403.11401","repositories_listed":0,"syntology":null},{"url":"/paper/scan2cap-context-aware-dense-captioning-in","slug":"scan2cap-context-aware-dense-captioning-in","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","date":"2020-12-03","arxiv_id":"2012.02206","repositories_listed":0,"syntology":null}],"syntology_records":13,"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":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/3d-question-answering-3d-qa-on-sqa3d","since_archive":"/sota/3d-question-answering-3d-qa-on-sqa3d#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/task/3d-question-answering-3d-qa/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":"ran","page":1,"of":1,"url":"/task/3d-question-answering-3d-qa/papers/ran/1","json":"/task/3d-question-answering-3d-qa/papers/ran/1.json","rows":13}],"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":"841d41a0183097d3ebff4b3b00755b51d6ca27cc3b70c67da6908b348c995240","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}