{"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/get-api-key","entry":"get_api_key","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":10,"n_papers_ran":4,"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":10,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":10,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"unverified":6},"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":"2609.00845","paper":"/paper/arxiv-2609-00845","title":"Towards Generalizable Visually Grounded Exploration of Household Devices","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"BITHLP/VGEBench","path":"models/api_model_infer.py","file_url":"https://github.com/BITHLP/VGEBench/blob/HEAD/models/api_model_infer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"204272a1b007b246","mcp_get_code":{"code_sha256":"204272a1b007b246"}},{"arxiv_id":"2608.21252","paper":"/paper/arxiv-2608-21252","title":"EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"RamonMeng/EnSI-RAG","path":"ensi-rag-financebench-eval/ensi_financebench/config.py","file_url":"https://github.com/RamonMeng/EnSI-RAG/blob/HEAD/ensi-rag-financebench-eval/ensi_financebench/config.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"78b1285843d93b6e","mcp_get_code":{"code_sha256":"78b1285843d93b6e"}},{"arxiv_id":"2605.17041","paper":"/paper/arxiv-2605-17041","title":"Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"chuckmy/agentic-translator","path":"api.py","file_url":"https://github.com/chuckmy/agentic-translator/blob/HEAD/api.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8501ce77e915517b","mcp_get_code":{"code_sha256":"8501ce77e915517b"}},{"arxiv_id":"2603.01990","paper":"/paper/arxiv-2603-01990","title":"According to Me: Long-Term Personalized Referential Memory QA","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"JingbiaoMei/ATM-Bench","path":"memqa/global_config.py","file_url":"https://github.com/JingbiaoMei/ATM-Bench/blob/HEAD/memqa/global_config.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"159e7f0ea5b4e0b2","mcp_get_code":{"code_sha256":"159e7f0ea5b4e0b2"}},{"arxiv_id":"2510.26937","paper":"/paper/arxiv-2510-26937","title":"MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"MM-OPERA-Bench/MM-OPERA","path":"evaluation/config_loader.py","file_url":"https://github.com/MM-OPERA-Bench/MM-OPERA/blob/HEAD/evaluation/config_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e9d7ce78723ebd69","mcp_get_code":{"code_sha256":"e9d7ce78723ebd69"}},{"arxiv_id":"2408.13986","paper":"/paper/agentmove-predicting-human-mobility-anywhere","title":"AgentMove: Predicting Human Mobility Anywhere Using Large Language Model based Agentic Framework","date":"2024-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsinghua-fib-lab/agentmove","path":"models/llm_api.py","file_url":"https://github.com/tsinghua-fib-lab/agentmove/blob/HEAD/models/llm_api.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"360642acb964d417","mcp_get_code":{"code_sha256":"360642acb964d417"}},{"arxiv_id":"2312.14867","paper":"/paper/viescore-towards-explainable-metrics-for","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","date":"2023-12-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TIGER-AI-Lab/VIEScore","path":"viescore/mllm_tools/openai.py","file_url":"https://github.com/TIGER-AI-Lab/VIEScore/blob/HEAD/viescore/mllm_tools/openai.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e71f0a1840318cb9","mcp_get_code":{"code_sha256":"e71f0a1840318cb9"}},{"arxiv_id":"2310.08419","paper":"/paper/jailbreaking-black-box-large-language-models","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"patrickrchao/jailbreakingllms","path":"conversers.py","file_url":"https://github.com/patrickrchao/jailbreakingllms/blob/HEAD/conversers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c87fc7d15c6dc917","mcp_get_code":{"code_sha256":"c87fc7d15c6dc917"}},{"arxiv_id":"2310.04793","paper":"/paper/fingpt-instruction-tuning-benchmark-for-open","title":"FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets","date":"2023-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI4Finance-Foundation/FinGPT","path":"fingpt/FinGPT_Forecaster/market_sentiment.py","file_url":"https://github.com/AI4Finance-Foundation/FinGPT/blob/HEAD/fingpt/FinGPT_Forecaster/market_sentiment.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"761e6e67888a33d2","mcp_get_code":{"code_sha256":"761e6e67888a33d2"}},{"arxiv_id":"2305.12474","paper":"/paper/evaluating-the-performance-of-large-language","title":"Evaluating the Performance of Large Language Models on GAOKAO Benchmark","date":"2023-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openlmlab/gaokao-bench","path":"Bench/bench_function.py","file_url":"https://github.com/openlmlab/gaokao-bench/blob/HEAD/Bench/bench_function.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":"caf642f8691c44c5","mcp_get_code":{"code_sha256":"caf642f8691c44c5"}}]}