{"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/load-metadata","entry":"load_metadata","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":23,"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":19,"n_samples_ran":9,"n_samples_fingerprinted":0,"n_places":25,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"ran":5,"unverified":10},"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":"2609.14722","paper":"/paper/arxiv-2609-14722","title":"PC 2 -AD: Point Cloud Upsampling to Safeguard 3D Anomaly Detection with Resolution-constrained Edge Devices","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"gyutong406-commits/PC2-AD","path":"approach/data_preparation/common/audit_core.py","file_url":"https://github.com/gyutong406-commits/PC2-AD/blob/HEAD/approach/data_preparation/common/audit_core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"795221c9231146f1","mcp_get_code":{"code_sha256":"795221c9231146f1"}},{"arxiv_id":"2608.21075","paper":"/paper/arxiv-2608-21075","title":"AudioWorldSim: Realistic Binaural Audio Datasets For World Models","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Luizerko/AudioWorldSim","path":"soundspaces/utils.py","file_url":"https://github.com/Luizerko/AudioWorldSim/blob/HEAD/soundspaces/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c585ab6ae045ebd0","mcp_get_code":{"code_sha256":"c585ab6ae045ebd0"}},{"arxiv_id":"2606.23881","paper":"/paper/arxiv-2606-23881","title":"Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"VAN-QIAN/ACL26-IBA","path":"src/io.py","file_url":"https://github.com/VAN-QIAN/ACL26-IBA/blob/HEAD/src/io.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"010caf3fb5a3f3d9","mcp_get_code":{"code_sha256":"010caf3fb5a3f3d9"}},{"arxiv_id":"2606.22692","paper":"/paper/arxiv-2606-22692","title":"VISTA Architect: A graph database-oriented health AI system demonstrated in multidisciplinary tumor boards","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"VISTA-Stanford/meds2text","path":"src/meds2text/textify.py","file_url":"https://github.com/VISTA-Stanford/meds2text/blob/HEAD/src/meds2text/textify.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4dc52f703b8c3a0a","mcp_get_code":{"code_sha256":"4dc52f703b8c3a0a"}},{"arxiv_id":"2603.13431","paper":"/paper/arxiv-2603-13431","title":"Chimera-Bench: A Benchmark Dataset for Epitope-Specific Antibody Design","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"mansoor181/chimera-bench","path":"chimera_bench/data.py","file_url":"https://github.com/mansoor181/chimera-bench/blob/HEAD/chimera_bench/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61cec02d26468459","mcp_get_code":{"code_sha256":"61cec02d26468459"}},{"arxiv_id":"2506.20879","paper":"/paper/multihuman-testbench-benchmarking-image","title":"MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Qualcomm-AI-research/MultiHuman-Testbench","path":"inference/generate_omnigen_images.py","file_url":"https://github.com/Qualcomm-AI-research/MultiHuman-Testbench/blob/HEAD/inference/generate_omnigen_images.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"code_sha256_prefix":"b6a6189df614c4c0","mcp_get_code":{"code_sha256":"b6a6189df614c4c0"}},{"arxiv_id":"2505.23281","paper":"/paper/matharena-evaluating-llms-on-uncontaminated","title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/matharena","path":"src/matharena/arxivbench_utils.py","file_url":"https://github.com/eth-sri/matharena/blob/HEAD/src/matharena/arxivbench_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2318c1b39c8b47e","mcp_get_code":{"code_sha256":"d2318c1b39c8b47e"}},{"arxiv_id":"2411.05338","paper":"/paper/scidqa-a-deep-reading-comprehension-dataset","title":"SciDQA: A Deep Reading Comprehension Dataset over Scientific Papers","date":"2024-11-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yale-nlp/scidqa","path":"src/llm_generation/gpt_ans_generation.py","file_url":"https://github.com/yale-nlp/scidqa/blob/HEAD/src/llm_generation/gpt_ans_generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bccefed5eb5ec57f","mcp_get_code":{"code_sha256":"bccefed5eb5ec57f"}},{"arxiv_id":"2410.09421","paper":"/paper/vlfeedback-a-large-scale-ai-feedback-dataset","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuweihao/MM-Vet","path":"mm-vet_evaluator.py","file_url":"https://github.com/yuweihao/MM-Vet/blob/HEAD/mm-vet_evaluator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"969f70cdb9e7b42d","mcp_get_code":{"code_sha256":"969f70cdb9e7b42d"}},{"arxiv_id":"2410.09421","paper":"/paper/vlfeedback-a-large-scale-ai-feedback-dataset","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuweihao/MM-Vet","path":"v2/mm-vet-v2_evaluator.py","file_url":"https://github.com/yuweihao/MM-Vet/blob/HEAD/v2/mm-vet-v2_evaluator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9385df01fd8cdfee","mcp_get_code":{"code_sha256":"9385df01fd8cdfee"}},{"arxiv_id":"2408.00765","paper":"/paper/2408-00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"969f70cdb9e7b42d","mcp_get_code":{"code_sha256":"969f70cdb9e7b42d"}},{"arxiv_id":"2408.00765","paper":"/paper/2408-00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuweihao/mm-vet","path":"v2/mm-vet-v2_evaluator.py","file_url":"https://github.com/yuweihao/mm-vet/blob/HEAD/v2/mm-vet-v2_evaluator.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9385df01fd8cdfee","mcp_get_code":{"code_sha256":"9385df01fd8cdfee"}},{"arxiv_id":"2405.19716","paper":"/paper/enhancing-large-vision-language-models-with","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihedeng9/stic","path":"llava/eval/eval_mm_vet.py","file_url":"https://github.com/yihedeng9/stic/blob/HEAD/llava/eval/eval_mm_vet.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"969f70cdb9e7b42d","mcp_get_code":{"code_sha256":"969f70cdb9e7b42d"}},{"arxiv_id":"2405.00740","paper":"/paper/modeling-caption-diversity-in-contrastive","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/llip","path":"llip/clipeval/eval_zeroshot.py","file_url":"https://github.com/facebookresearch/llip/blob/HEAD/llip/clipeval/eval_zeroshot.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"520cc1220abd0e5f","mcp_get_code":{"code_sha256":"520cc1220abd0e5f"}},{"arxiv_id":"2310.18652","paper":"/paper/ehrxqa-a-multi-modal-question-answering-1","title":"EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images","date":"2023-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baeseongsu/mimic-cxr-vqa","path":"dataset_builder/generate_answer.py","file_url":"https://github.com/baeseongsu/mimic-cxr-vqa/blob/HEAD/dataset_builder/generate_answer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b97ea8675949406d","mcp_get_code":{"code_sha256":"b97ea8675949406d"}},{"arxiv_id":"2310.07931","paper":"/paper/d2-pruning-message-passing-for-balancing","title":"D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adymaharana/d2pruning","path":"select_d2_datacomp.py","file_url":"https://github.com/adymaharana/d2pruning/blob/HEAD/select_d2_datacomp.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f44f975b8f160a3","mcp_get_code":{"code_sha256":"2f44f975b8f160a3"}},{"arxiv_id":"2308.02490","paper":"/paper/mm-vet-evaluating-large-multimodal-models-for","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"969f70cdb9e7b42d","mcp_get_code":{"code_sha256":"969f70cdb9e7b42d"}},{"arxiv_id":"2210.16822","paper":"/paper/towards-versatile-embodied-navigation","title":"Towards Versatile Embodied Navigation","date":"2022-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanqingwangai/vxn","path":"habitat_extensions/audionav_sensor.py","file_url":"https://github.com/hanqingwangai/vxn/blob/HEAD/habitat_extensions/audionav_sensor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"deea512d3e44113c","mcp_get_code":{"code_sha256":"deea512d3e44113c"}},{"arxiv_id":"2202.10910","paper":"/paper/sound-adversarial-audio-visual-navigation-1","title":"Sound Adversarial Audio-Visual Navigation","date":"2022-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yyf17/saavn","path":"soundspaces/utils.py","file_url":"https://github.com/yyf17/saavn/blob/HEAD/soundspaces/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c585ab6ae045ebd0","mcp_get_code":{"code_sha256":"c585ab6ae045ebd0"}},{"arxiv_id":"2009.05005","paper":"/paper/uncovering-edge-plasma-dynamics-via-deep","title":"Uncovering turbulent plasma dynamics via deep learning from partial observations","date":null,"month_inferred_from_arxiv_id":"2020-09","title_source":"archive","repo":"abhilashmathews/plasmapinns","path":"plot_results.py","file_url":"https://github.com/abhilashmathews/plasmapinns/blob/HEAD/plot_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"665f7ef195a17686","mcp_get_code":{"code_sha256":"665f7ef195a17686"}},{"arxiv_id":"2006.04727","paper":"/paper/theoretical-guarantees-for-learning","title":"Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HerreraKrachTeichmann/ControlledODERNN","path":"NJODE/data_utils.py","file_url":"https://github.com/HerreraKrachTeichmann/ControlledODERNN/blob/HEAD/NJODE/data_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a809ed2bcb40ac31","mcp_get_code":{"code_sha256":"a809ed2bcb40ac31"}},{"arxiv_id":"2004.05477","paper":"/paper/learned-discretizations-for-passive-scalar","title":"Learned discretizations for passive scalar advection in a 2-D turbulent flow","date":null,"month_inferred_from_arxiv_id":"2020-04","title_source":"archive","repo":"google-research/data-driven-pdes","path":"datadrivenpdes/core/readers.py","file_url":"https://github.com/google-research/data-driven-pdes/blob/HEAD/datadrivenpdes/core/readers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1438b8637b3b0933","mcp_get_code":{"code_sha256":"1438b8637b3b0933"}},{"arxiv_id":"1909.05803","paper":"/paper/self-assembling-modular-networks-for","title":"Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning","date":"2019-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiangycTarheel/NMN-MultiHopQA","path":"basic/read_data.py","file_url":"https://github.com/jiangycTarheel/NMN-MultiHopQA/blob/HEAD/basic/read_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51367733c0620cb7","mcp_get_code":{"code_sha256":"51367733c0620cb7"}},{"arxiv_id":"1906.05210","paper":"/paper/explore-propose-and-assemble-an-interpretable","title":"Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension","date":"2019-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiangycTarheel/EPAr","path":"basic/read_data.py","file_url":"https://github.com/jiangycTarheel/EPAr/blob/HEAD/basic/read_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51367733c0620cb7","mcp_get_code":{"code_sha256":"51367733c0620cb7"}},{"arxiv_id":"2025.emnlp-main.353","paper":null,"title":"arXiv:2025.emnlp-main.353","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nju-websoft/GraDaSE","path":"code/utils/data_preprocess.py","file_url":"https://github.com/nju-websoft/GraDaSE/blob/HEAD/code/utils/data_preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b09c1e493d0e3664","mcp_get_code":{"code_sha256":"b09c1e493d0e3664"}}]}