{"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/local-image-to-data-url","entry":"local_image_to_data_url","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":9,"n_papers_ran":6,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":3},"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":"2505.18079","paper":"/paper/deep-video-discovery-agentic-search-with-tool","title":"Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/DeepVideoDiscovery","path":"dvd/utils.py","file_url":"https://github.com/microsoft/DeepVideoDiscovery/blob/HEAD/dvd/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"31bb18c44ed2df47","mcp_get_code":{"code_sha256":"31bb18c44ed2df47"}},{"arxiv_id":"2411.02937","paper":"/paper/benchmarking-multimodal-retrieval-augmented","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba-nlp/omnisearch","path":"src/Omnisearch_gpt/search_api.py","file_url":"https://github.com/alibaba-nlp/omnisearch/blob/HEAD/src/Omnisearch_gpt/search_api.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"30b736781f36ff56","mcp_get_code":{"code_sha256":"30b736781f36ff56"}},{"arxiv_id":"2409.14818","paper":"/paper/mobilevlm-a-vision-language-model-for-better","title":"MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding","date":"2024-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaomi/mobilevlm","path":"test_515/gpt.py","file_url":"https://github.com/xiaomi/mobilevlm/blob/HEAD/test_515/gpt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"829b3a29017bf6be","mcp_get_code":{"code_sha256":"829b3a29017bf6be"}},{"arxiv_id":"2408.08054","paper":"/paper/text2bim-generating-building-models-using-a","title":"Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dcy0577/Text2BIM","path":"tool_agent/utils.py","file_url":"https://github.com/dcy0577/Text2BIM/blob/HEAD/tool_agent/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd830bd5206c5822","mcp_get_code":{"code_sha256":"dd830bd5206c5822"}},{"arxiv_id":"2407.07053","paper":"/paper/multimodal-self-instruct-synthetic-abstract","title":"Multimodal Self-Instruct: Synthetic Abstract Image and Visual Reasoning Instruction Using Language Model","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwq2018/multi-modal-self-instruct","path":"scripts/eval_model.py","file_url":"https://github.com/zwq2018/multi-modal-self-instruct/blob/HEAD/scripts/eval_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd830bd5206c5822","mcp_get_code":{"code_sha256":"dd830bd5206c5822"}},{"arxiv_id":"2406.19643","paper":"/paper/unlocking-varied-perspectives-a-persona-based","title":"Debate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument Generation","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"derekkk/llm4arggen","path":"openai_generation.py","file_url":"https://github.com/derekkk/llm4arggen/blob/HEAD/openai_generation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd830bd5206c5822","mcp_get_code":{"code_sha256":"dd830bd5206c5822"}},{"arxiv_id":"2405.01483","paper":"/paper/mantis-interleaved-multi-image-instruction","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TIGER-AI-Lab/Mantis","path":"mantis/easy_openai/openai_utils.py","file_url":"https://github.com/TIGER-AI-Lab/Mantis/blob/HEAD/mantis/easy_openai/openai_utils.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":"3b97d96aa93fe3ee","mcp_get_code":{"code_sha256":"3b97d96aa93fe3ee"}},{"arxiv_id":"2311.16502","paper":"/paper/mmmu-a-massive-multi-discipline-multimodal","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-ai-lab/probmed","path":"eval/inference/GPT-4V/gpt4v.py","file_url":"https://github.com/eric-ai-lab/probmed/blob/HEAD/eval/inference/GPT-4V/gpt4v.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"829b3a29017bf6be","mcp_get_code":{"code_sha256":"829b3a29017bf6be"}},{"arxiv_id":"Lin_From_Elements_to_Design_A_Layered_Approach_for_Automatic_Graphic_CVPR_2025_paper","paper":null,"title":"arXiv:Lin_From_Elements_to_Design_A_Layered_Approach_for_Automatic_Graphic_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"CyberAgentAILab/OpenCOLE","path":"src/opencole/evaluation/eval_gpt4v.py","file_url":"https://github.com/CyberAgentAILab/OpenCOLE/blob/HEAD/src/opencole/evaluation/eval_gpt4v.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":"f3f31bd41c3d39db","mcp_get_code":{"code_sha256":"f3f31bd41c3d39db"}}]}