{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/do-nms","entry":"do_nms","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":12,"n_papers_ran":12,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.27311","paper":"/paper/arxiv-2605-27311","title":"CHARTOGRAPHER: Counterfactual Chart Generation for Evaluating Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"vis-nlp/ChartQA","path":"Models/VL-T5/inference/modeling_frcnn.py","file_url":"https://github.com/vis-nlp/ChartQA/blob/HEAD/Models/VL-T5/inference/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2402.07742","paper":"/paper/asking-multimodal-clarifying-questions-in","title":"Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search","date":"2024-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yfyuan01/mqc","path":"VL-T5/VL-T5/inference/modeling_frcnn.py","file_url":"https://github.com/yfyuan01/mqc/blob/HEAD/VL-T5/VL-T5/inference/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2307.05182","paper":"/paper/co-attention-gated-vision-language-embedding","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","date":"2023-07-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"longbai1006/cat-vil","path":"dataset/feature_extraction/visual_bert/modeling_frcnn.py","file_url":"https://github.com/longbai1006/cat-vil/blob/HEAD/dataset/feature_extraction/visual_bert/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2306.16713","paper":"/paper/answer-mining-from-a-pool-of-images-towards","title":"Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answering","date":"2023-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Abhiram4572/mi_bart","path":"mi_bart/inference/modeling_frcnn.py","file_url":"https://github.com/Abhiram4572/mi_bart/blob/HEAD/mi_bart/inference/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2305.11692","paper":"/paper/surgical-vqla-transformer-with-gated-vision","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","date":"2023-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"longbai1006/surgical-vqla","path":"dataset/feature_extraction/visual_bert/modeling_frcnn.py","file_url":"https://github.com/longbai1006/surgical-vqla/blob/HEAD/dataset/feature_extraction/visual_bert/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2207.00056","paper":"/paper/multiviz-an-analysis-benchmark-for","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","date":"2022-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pliang279/MultiViz","path":"demos/lxmert/modeling_frcnn.py","file_url":"https://github.com/pliang279/MultiViz/blob/HEAD/demos/lxmert/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2206.06522","paper":"/paper/lst-ladder-side-tuning-for-parameter-and","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","date":"2022-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ylsung/ladder-side-tuning","path":"VL-T5/inference/modeling_frcnn.py","file_url":"https://github.com/ylsung/ladder-side-tuning/blob/HEAD/VL-T5/inference/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2205.00363","paper":"/paper/visual-spatial-reasoning","title":"Visual Spatial Reasoning","date":"2022-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/visual-spatial-reasoning","path":"feature_extraction/lxmert/modeling_frcnn.py","file_url":"https://github.com/cambridgeltl/visual-spatial-reasoning/blob/HEAD/feature_extraction/lxmert/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2204.03162","paper":"/paper/winoground-probing-vision-and-language-models","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","date":"2022-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"juletx/spatial-reasoning","path":"visual-spatial-reasoning/feature_extraction/lxmert/modeling_frcnn.py","file_url":"https://github.com/juletx/spatial-reasoning/blob/HEAD/visual-spatial-reasoning/feature_extraction/lxmert/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2203.02013","paper":"/paper/dime-fine-grained-interpretations-of","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","date":"2022-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lvyiwei1/dime","path":"lxmert/modeling_frcnn.py","file_url":"https://github.com/lvyiwei1/dime/blob/HEAD/lxmert/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"2112.07566","paper":"/paper/valse-a-task-independent-benchmark-for-vision-1","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","date":"2021-12-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heidelberg-nlp/valse","path":"modeling_frcnn.py","file_url":"https://github.com/heidelberg-nlp/valse/blob/HEAD/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}},{"arxiv_id":"Zhang_VQACL_A_Novel_Visual_Question_Answering_Continual_Learning_Setting_CVPR_2023_paper","paper":null,"title":"arXiv:Zhang_VQACL_A_Novel_Visual_Question_Answering_Continual_Learning_Setting_CVPR_2023_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zhangxi1997/VQACL","path":"VL-T5/inference/modeling_frcnn.py","file_url":"https://github.com/zhangxi1997/VQACL/blob/HEAD/VL-T5/inference/modeling_frcnn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e21bb85b8e1b4836","mcp_get_code":{"code_sha256":"e21bb85b8e1b4836"}}]}