{"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-json-data","entry":"load_json_data","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":16,"n_papers_ran":8,"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":20,"n_samples_ran":8,"n_samples_fingerprinted":0,"n_places":20,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":7,"unverified":12},"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":"2605.03460","paper":"/paper/arxiv-2605-03460","title":"FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"seunghan96/FinSTaR","path":"src/training/data_utils.py","file_url":"https://github.com/seunghan96/FinSTaR/blob/HEAD/src/training/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c0c06b4bc4756314","mcp_get_code":{"code_sha256":"c0c06b4bc4756314"}},{"arxiv_id":"2604.18566","paper":"/paper/arxiv-2604-18566","title":"Benchmarking System Dynamics AI Assistants: Cloud Versus Local Large Language Models on CLD Extraction and Discussion","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"UB-IAD/sd-ai","path":"third-party/time-series-behavior-analysis/classify_behavior.py","file_url":"https://github.com/UB-IAD/sd-ai/blob/HEAD/third-party/time-series-behavior-analysis/classify_behavior.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"48a884dfccfdcbd2","mcp_get_code":{"code_sha256":"48a884dfccfdcbd2"}},{"arxiv_id":"2604.11841","paper":"/paper/arxiv-2604-11841","title":"Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"zhangwenhao6/PERA","path":"dataset/dataset_hg.py","file_url":"https://github.com/zhangwenhao6/PERA/blob/HEAD/dataset/dataset_hg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7a97754032b6353c","mcp_get_code":{"code_sha256":"7a97754032b6353c"}},{"arxiv_id":"2512.14395","paper":"/paper/arxiv-2512-14395","title":"Massive Editing for Large Language Models Based on Dynamic Weight Generation","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"RodeWayne/MeG-for-Knowledge-Editing","path":"merge_results.py","file_url":"https://github.com/RodeWayne/MeG-for-Knowledge-Editing/blob/HEAD/merge_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0c46563c5bb7d9e3","mcp_get_code":{"code_sha256":"0c46563c5bb7d9e3"}},{"arxiv_id":"2502.17166","paper":"/paper/jurex-4e-juridical-expert-annotated-four","title":"JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THUlawtech/JUREX","path":"SCD_experiment/preprocess_scd_data.py","file_url":"https://github.com/THUlawtech/JUREX/blob/HEAD/SCD_experiment/preprocess_scd_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b08067637ffe4055","mcp_get_code":{"code_sha256":"b08067637ffe4055"}},{"arxiv_id":"2406.07529","paper":"/paper/map-low-compute-model-merging-with-amortized","title":"MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luli-git/MAP","path":"utils.py","file_url":"https://github.com/luli-git/MAP/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b4926d98ff6bbaa3","mcp_get_code":{"code_sha256":"b4926d98ff6bbaa3"}},{"arxiv_id":"2406.05673","paper":"/paper/flow-of-reasoning-efficient-training-of-llm","title":"Flow of Reasoning:Training LLMs for Divergent Problem Solving with Minimal Examples","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yu-Fangxu/FoR","path":"1D-ARC/lightning_data.py","file_url":"https://github.com/Yu-Fangxu/FoR/blob/HEAD/1D-ARC/lightning_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8f6dea1ad179b459","mcp_get_code":{"code_sha256":"8f6dea1ad179b459"}},{"arxiv_id":"2404.00599","paper":"/paper/evocodebench-an-evolving-code-generation","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seketeam/evocodebench","path":"utils.py","file_url":"https://github.com/seketeam/evocodebench/blob/HEAD/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":"dbc6dc84387eb165","mcp_get_code":{"code_sha256":"dbc6dc84387eb165"}},{"arxiv_id":"2403.06833","paper":"/paper/can-llms-separate-instructions-from-data-and","title":"Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"egozverev/Shold-It-Be-Executed-Or-Processed","path":"SEP_dataset/utils.py","file_url":"https://github.com/egozverev/Shold-It-Be-Executed-Or-Processed/blob/HEAD/SEP_dataset/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c822a8f32726ba36","mcp_get_code":{"code_sha256":"c822a8f32726ba36"}},{"arxiv_id":"2402.11893","paper":"/paper/discerning-and-resolving-knowledge-conflicts","title":"Discerning and Resolving Knowledge Conflicts through Adaptive Decoding with Contextual Information-Entropy Constraint","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stacy027/coiecd","path":"decoding.py","file_url":"https://github.com/stacy027/coiecd/blob/HEAD/decoding.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":"1e67969d221f571f","mcp_get_code":{"code_sha256":"1e67969d221f571f"}},{"arxiv_id":"2401.03408","paper":"/paper/escalation-risks-from-language-models-in","title":"Escalation Risks from Language Models in Military and Diplomatic Decision-Making","date":"2024-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jprivera44/EscalAItion","path":"charts/escalation_scores.py","file_url":"https://github.com/jprivera44/EscalAItion/blob/HEAD/charts/escalation_scores.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ee9268ca5491513","mcp_get_code":{"code_sha256":"1ee9268ca5491513"}},{"arxiv_id":"2310.01880","paper":"/paper/autocast-enhancing-world-event-prediction","title":"AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"borealisai/autocast-plus-plus","path":"autocast_experiments/data/process.py","file_url":"https://github.com/borealisai/autocast-plus-plus/blob/HEAD/autocast_experiments/data/process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"6fb1488fa816f0cc","mcp_get_code":{"code_sha256":"6fb1488fa816f0cc"}},{"arxiv_id":"2307.11984","paper":"/paper/learning-vision-and-language-navigation-from","title":"Learning Vision-and-Language Navigation from YouTube Videos","date":"2023-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeremylinky/youtube-vln","path":"utils/dataset/common.py","file_url":"https://github.com/jeremylinky/youtube-vln/blob/HEAD/utils/dataset/common.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6369d66e36fc6a2f","mcp_get_code":{"code_sha256":"6369d66e36fc6a2f"}},{"arxiv_id":"2306.05212","paper":"/paper/reta-llm-a-retrieval-augmented-large-language","title":"RETA-LLM: A Retrieval-Augmented Large Language Model Toolkit","date":"2023-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruc-gsai/yulan-ir","path":"RETA-LLM/indexer/index_pipeline.py","file_url":"https://github.com/ruc-gsai/yulan-ir/blob/HEAD/RETA-LLM/indexer/index_pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"879f374a0414d8c3","mcp_get_code":{"code_sha256":"879f374a0414d8c3"}},{"arxiv_id":"openreview_9DfcvXahRb","paper":null,"title":"arXiv:openreview_9DfcvXahRb","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"xuwang0117/EIG-LLM-Eval","path":"calculate_human_consistency.py","file_url":"https://github.com/xuwang0117/EIG-LLM-Eval/blob/HEAD/calculate_human_consistency.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5984a4b574086826","mcp_get_code":{"code_sha256":"5984a4b574086826"}},{"arxiv_id":"2025.findings-emnlp.1002","paper":null,"title":"arXiv:2025.findings-emnlp.1002","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"pranav-ust/glitter","path":"prompting_experiments/contrastive_few_shot.py","file_url":"https://github.com/pranav-ust/glitter/blob/HEAD/prompting_experiments/contrastive_few_shot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f2069b0ef21f9c86","mcp_get_code":{"code_sha256":"f2069b0ef21f9c86"}},{"arxiv_id":"2025.findings-emnlp.1002","paper":null,"title":"arXiv:2025.findings-emnlp.1002","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"pranav-ust/glitter","path":"prompting_experiments/cot.py","file_url":"https://github.com/pranav-ust/glitter/blob/HEAD/prompting_experiments/cot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"74344ed0f8e46ea2","mcp_get_code":{"code_sha256":"74344ed0f8e46ea2"}},{"arxiv_id":"2025.findings-emnlp.1002","paper":null,"title":"arXiv:2025.findings-emnlp.1002","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"pranav-ust/glitter","path":"prompting_experiments/few_shot.py","file_url":"https://github.com/pranav-ust/glitter/blob/HEAD/prompting_experiments/few_shot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1977f9faaf31e6a3","mcp_get_code":{"code_sha256":"1977f9faaf31e6a3"}},{"arxiv_id":"2025.findings-emnlp.1002","paper":null,"title":"arXiv:2025.findings-emnlp.1002","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"pranav-ust/glitter","path":"prompting_experiments/iterative.py","file_url":"https://github.com/pranav-ust/glitter/blob/HEAD/prompting_experiments/iterative.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c10ab04862e48fa7","mcp_get_code":{"code_sha256":"c10ab04862e48fa7"}},{"arxiv_id":"2025.findings-emnlp.1002","paper":null,"title":"arXiv:2025.findings-emnlp.1002","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"pranav-ust/glitter","path":"prompting_experiments/zero_shot.py","file_url":"https://github.com/pranav-ust/glitter/blob/HEAD/prompting_experiments/zero_shot.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf7eb545fb24ea19","mcp_get_code":{"code_sha256":"cf7eb545fb24ea19"}}]}