{"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":"/dataset/next-qa/papers/ran/1","list_of":"/dataset/next-qa","dataset":"NExT-QA","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","key_notes":{"samples_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'","samples_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)"},"order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,35],"of":35,"counts":{"papers_with_a_benchmark_row":64,"with_a_code_link":52,"where_syntology_ran_a_sample":35,"not_listed_spam_title":0,"listed":64,"listed_where_code_ran":35,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":5,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/dataset/next-qa/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/agentic-keyframe-search-for-video-question","slug":"agentic-keyframe-search-for-video-question","title":"Agentic Keyframe Search for Video Question Answering","date":"2025-03-20","arxiv_id":"2503.16032","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["fansunqi/akeys"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/agentic-keyframe-search-for-video-question#ran","syntology_url":"https://syntology.ai/paper/2503.16032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16032"}}}},{"paper":"/paper/videollama-3-frontier-multimodal-foundation","slug":"videollama-3-frontier-multimodal-foundation","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","date":"2025-01-22","arxiv_id":"2501.13106","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":14,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":5,"samples_unverified":6,"pointer_only_for_licence":2,"official":{"repos":["damo-nlp-sg/videollama3"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videollama-3-frontier-multimodal-foundation#ran","syntology_url":"https://syntology.ai/paper/2501.13106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13106"}}}},{"paper":"/paper/linvt-empower-your-image-level-large-language","slug":"linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","date":"2024-12-06","arxiv_id":"2412.05185","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":12,"official":{"repos":["gls0425/linvt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linvt-empower-your-image-level-large-language#ran","syntology_url":"https://syntology.ai/paper/2412.05185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05185"}}}},{"paper":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":8,"pointer_only_for_licence":0,"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}}}},{"paper":"/paper/ts-llava-constructing-visual-tokens-through","slug":"ts-llava-constructing-visual-tokens-through","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","date":"2024-11-17","arxiv_id":"2411.11066","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["tingyu215/ts-llava"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/ts-llava-constructing-visual-tokens-through#ran","syntology_url":"https://syntology.ai/paper/2411.11066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11066"}}}},{"paper":"/paper/oryx-mllm-on-demand-spatial-temporal","slug":"oryx-mllm-on-demand-spatial-temporal","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","date":"2024-09-19","arxiv_id":"2409.12961","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["oryx-mllm/oryx"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/oryx-mllm-on-demand-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2409.12961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12961"}}}},{"paper":"/paper/qwen2-vl-enhancing-vision-language-model-s","slug":"qwen2-vl-enhancing-vision-language-model-s","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","date":"2024-09-18","arxiv_id":"2409.12191","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":12,"samples_ran":12,"samples_constructed":1,"samples_ran_checked":10,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["qwenlm/qwen2-vl"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/qwen2-vl-enhancing-vision-language-model-s#ran","syntology_url":"https://syntology.ai/paper/2409.12191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12191"}}}},{"paper":"/paper/slowfast-llava-a-strong-training-free","slug":"slowfast-llava-a-strong-training-free","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","date":"2024-07-22","arxiv_id":"2407.15841","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":6,"official":{"repos":["apple/ml-slowfast-llava"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/slowfast-llava-a-strong-training-free#ran","syntology_url":"https://syntology.ai/paper/2407.15841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15841"}}}},{"paper":"/paper/llava-next-interleave-tackling-multi-image","slug":"llava-next-interleave-tackling-multi-image","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","date":"2024-07-10","arxiv_id":"2407.07895","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":4,"official":{"repos":["LLaVA-VL/LLaVA-NeXT"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llava-next-interleave-tackling-multi-image#ran","syntology_url":"https://syntology.ai/paper/2407.07895","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07895"}}}},{"paper":"/paper/tarsier-recipes-for-training-and-evaluating-1","slug":"tarsier-recipes-for-training-and-evaluating-1","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","date":"2024-06-30","arxiv_id":"2407.00634","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["bytedance/tarsier"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/tarsier-recipes-for-training-and-evaluating-1#ran","syntology_url":"https://syntology.ai/paper/2407.00634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00634"}}}},{"paper":"/paper/long-context-transfer-from-language-to-vision","slug":"long-context-transfer-from-language-to-vision","title":"Long Context Transfer from Language to Vision","date":"2024-06-24","arxiv_id":"2406.16852","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["evolvinglmms-lab/longva"],"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":["listed","official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/long-context-transfer-from-language-to-vision#ran","syntology_url":"https://syntology.ai/paper/2406.16852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16852"}}}},{"paper":"/paper/too-many-frames-not-all-useful-efficient","slug":"too-many-frames-not-all-useful-efficient","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","date":"2024-06-13","arxiv_id":"2406.09396","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["jongwoopark7978/LVNet"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/too-many-frames-not-all-useful-efficient#ran","syntology_url":"https://syntology.ai/paper/2406.09396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09396"}}}},{"paper":"/paper/videollama-2-advancing-spatial-temporal","slug":"videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","arxiv_id":"2406.07476","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":17,"samples_ran":12,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":5,"samples_unverified":5,"pointer_only_for_licence":8,"official":{"repos":["damo-nlp-sg/videollama2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videollama-2-advancing-spatial-temporal#ran","syntology_url":"https://syntology.ai/paper/2406.07476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07476"}}}},{"paper":"/paper/videotree-adaptive-tree-based-video","slug":"videotree-adaptive-tree-based-video","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","date":"2024-05-29","arxiv_id":"2405.19209","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Ziyang412/VideoTree"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/videotree-adaptive-tree-based-video#ran","syntology_url":"https://syntology.ai/paper/2405.19209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19209"}}}},{"paper":"/paper/an-image-grid-can-be-worth-a-video-zero-shot","slug":"an-image-grid-can-be-worth-a-video-zero-shot","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","date":"2024-03-27","arxiv_id":"2403.18406","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["imagegridworth/IG-VLM"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-image-grid-can-be-worth-a-video-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2403.18406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18406"}}}},{"paper":"/paper/understanding-long-videos-in-one-multimodal","slug":"understanding-long-videos-in-one-multimodal","title":"Understanding Long Videos with Multimodal Language Models","date":"2024-03-25","arxiv_id":"2403.16998","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["kahnchana/mvu"],"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":["found_in_text","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understanding-long-videos-in-one-multimodal#ran","syntology_url":"https://syntology.ai/paper/2403.16998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16998"}}}},{"paper":"/paper/language-repository-for-long-video","slug":"language-repository-for-long-video","title":"Language Repository for Long Video Understanding","date":"2024-03-21","arxiv_id":"2403.14622","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["kkahatapitiya/langrepo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-repository-for-long-video#ran","syntology_url":"https://syntology.ai/paper/2403.14622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14622"}}}},{"paper":"/paper/lstp-language-guided-spatial-temporal-prompt","slug":"lstp-language-guided-spatial-temporal-prompt","title":"Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge","date":"2024-02-25","arxiv_id":"2402.16050","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":4,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["bigai-nlco/lstp-chat","bigai-nlco/videotgb"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lstp-language-guided-spatial-temporal-prompt#ran","syntology_url":"https://syntology.ai/paper/2402.16050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16050"}}}},{"paper":"/paper/crema-multimodal-compositional-video","slug":"crema-multimodal-compositional-video","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","date":"2024-02-08","arxiv_id":"2402.05889","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":5,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["Yui010206/CREMA"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/crema-multimodal-compositional-video#ran","syntology_url":"https://syntology.ai/paper/2402.05889","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05889"}}}},{"paper":"/paper/glance-and-focus-memory-prompting-for-multi-1","slug":"glance-and-focus-memory-prompting-for-multi-1","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","date":"2024-01-03","arxiv_id":"2401.01529","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":18,"samples_ran":14,"samples_constructed":2,"samples_ran_checked":14,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":7,"official":{"repos":["byz0e/glance-focus"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":2,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glance-and-focus-memory-prompting-for-multi-1#ran","syntology_url":"https://syntology.ai/paper/2401.01529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01529"}}}},{"paper":"/paper/a-simple-llm-framework-for-long-range-video","slug":"a-simple-llm-framework-for-long-range-video","title":"A Simple LLM Framework for Long-Range Video Question-Answering","date":"2023-12-28","arxiv_id":"2312.17235","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ceezh/llovi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/a-simple-llm-framework-for-long-range-video#ran","syntology_url":"https://syntology.ai/paper/2312.17235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17235"}}}},{"paper":"/paper/vlap-efficient-video-language-alignment-via","slug":"vlap-efficient-video-language-alignment-via","title":"ViLA: Efficient Video-Language Alignment for Video Question Answering","date":"2023-12-13","arxiv_id":"2312.08367","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["xijun-cs/vila"],"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":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vlap-efficient-video-language-alignment-via#ran","syntology_url":"https://syntology.ai/paper/2312.08367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08367"}}}},{"paper":"/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","rows_on_this_dataset":4,"code_links":3,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":10,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":2,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/vamos-versatile-action-models-for-video","slug":"vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","arxiv_id":"2311.13627","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":8,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":5,"official":{"repos":["brown-palm/Vamos"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vamos-versatile-action-models-for-video#ran","syntology_url":"https://syntology.ai/paper/2311.13627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13627"}}}},{"paper":"/paper/pali-3-vision-language-models-smaller-faster","slug":"pali-3-vision-language-models-smaller-faster","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","date":"2023-10-13","arxiv_id":"2310.09199","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pali-3-vision-language-models-smaller-faster#ran","syntology_url":"https://syntology.ai/paper/2310.09199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09199"}}}},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"paper":"/paper/pali-x-on-scaling-up-a-multilingual-vision","slug":"pali-x-on-scaling-up-a-multilingual-vision","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","date":"2023-05-29","arxiv_id":"2305.18565","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pali-x-on-scaling-up-a-multilingual-vision#ran","syntology_url":"https://syntology.ai/paper/2305.18565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18565"}}}},{"paper":"/paper/paxion-patching-action-knowledge-in-video-1","slug":"paxion-patching-action-knowledge-in-video-1","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","date":"2023-05-18","arxiv_id":"2305.10683","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":2,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["mikewangwzhl/paxion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/paxion-patching-action-knowledge-in-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.10683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10683"}}}},{"paper":"/paper/self-chained-image-language-model-for-video-1","slug":"self-chained-image-language-model-for-video-1","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","date":"2023-05-11","arxiv_id":"2305.06988","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":7,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":7,"official":{"repos":["yui010206/sevila"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/self-chained-image-language-model-for-video-1#ran","syntology_url":"https://syntology.ai/paper/2305.06988","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06988"}}}},{"paper":"/paper/verbs-in-action-improving-verb-understanding","slug":"verbs-in-action-improving-verb-understanding","title":"Verbs in Action: Improving verb understanding in video-language models","date":"2023-04-13","arxiv_id":"2304.06708","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/scenic"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/verbs-in-action-improving-verb-understanding#ran","syntology_url":"https://syntology.ai/paper/2304.06708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06708"}}}},{"paper":"/paper/contrastive-video-question-answering-via","slug":"contrastive-video-question-answering-via","title":"Contrastive Video Question Answering via Video Graph Transformer","date":"2023-02-27","arxiv_id":"2302.13668","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["doc-doc/covgt"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/contrastive-video-question-answering-via#ran","syntology_url":"https://syntology.ai/paper/2302.13668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13668"}}}},{"paper":"/paper/video-graph-transformer-for-video-question","slug":"video-graph-transformer-for-video-question","title":"Video Graph Transformer for Video Question Answering","date":"2022-07-12","arxiv_id":"2207.05342","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":14,"samples_ran":9,"samples_constructed":5,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":5,"pointer_only_for_licence":0,"official":{"repos":["sail-sg/vgt"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":5,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-graph-transformer-for-video-question#ran","syntology_url":"https://syntology.ai/paper/2207.05342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.05342"}}}},{"paper":"/paper/revisiting-the-video-in-video-language","slug":"revisiting-the-video-in-video-language","title":"Revisiting the \"Video\" in Video-Language Understanding","date":"2022-06-03","arxiv_id":"2206.01720","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":2,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/revisiting-the-video-in-video-language#ran","syntology_url":"https://syntology.ai/paper/2206.01720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01720"}}}},{"paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","slug":"flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":24,"samples_ran":18,"samples_constructed":6,"samples_ran_checked":12,"samples_ran_instrument_failed":6,"samples_unverified":6,"pointer_only_for_licence":8,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flamingo-a-visual-language-model-for-few-shot-1#ran","syntology_url":"https://syntology.ai/paper/2204.14198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14198"}}}},{"paper":"/paper/video-as-conditional-graph-hierarchy-for","slug":"video-as-conditional-graph-hierarchy-for","title":"Video as Conditional Graph Hierarchy for Multi-Granular Question Answering","date":"2021-12-12","arxiv_id":"2112.06197","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-28T10:30:06+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["doc-doc/hqga"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/video-as-conditional-graph-hierarchy-for#ran","syntology_url":"https://syntology.ai/paper/2112.06197","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.06197"}}}}],"record_sha256":"8547fbd3ca73d04301c06cb5321a6c884239cf86ce13320de942e68d308c1326","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}