{"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/process-results","entry":"process_results","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":11,"n_papers_ran":3,"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":11,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":8},"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":"2607.28319","paper":"/paper/arxiv-2607-28319","title":"Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"peremartra/fairness-pruning","path":"custom_tasks/esbbq/esbbq_utils.py","file_url":"https://github.com/peremartra/fairness-pruning/blob/HEAD/custom_tasks/esbbq/esbbq_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0361b34a9385c607","mcp_get_code":{"code_sha256":"0361b34a9385c607"}},{"arxiv_id":"2602.01479","paper":"/paper/arxiv-2602-01479","title":"EBISU: Benchmarking Large Language Models in Japanese Finance","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"The-FinAI/Ebisu","path":"tasks/jp/jp_utils.py","file_url":"https://github.com/The-FinAI/Ebisu/blob/HEAD/tasks/jp/jp_utils.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":"196afa6c732d8a12","mcp_get_code":{"code_sha256":"196afa6c732d8a12"}},{"arxiv_id":"2506.09659","paper":"/paper/intent-factored-generation-unleashing-the","title":"Intent Factored Generation: Unleashing the Diversity in Your Language Model","date":"2025-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"flairox/ifg","path":"hendrycks_math/math_eval.py","file_url":"https://github.com/flairox/ifg/blob/HEAD/hendrycks_math/math_eval.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":"90f8729aba04c979","mcp_get_code":{"code_sha256":"90f8729aba04c979"}},{"arxiv_id":"2505.13379","paper":"/paper/thinkless-llm-learns-when-to-think","title":"Thinkless: LLM Learns When to Think","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vainf/thinkless","path":"eval_configs/deepseek/minerva/utils.py","file_url":"https://github.com/vainf/thinkless/blob/HEAD/eval_configs/deepseek/minerva/utils.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":"23c431ee9b6a079a","mcp_get_code":{"code_sha256":"23c431ee9b6a079a"}},{"arxiv_id":"2504.04022","paper":"/paper/rethinking-reflection-in-pre-training","title":"Rethinking Reflection in Pre-Training","date":"2025-04-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Essential-AI/reflection","path":"tasks/triviaqa_adv/preprocess.py","file_url":"https://github.com/Essential-AI/reflection/blob/HEAD/tasks/triviaqa_adv/preprocess.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a7350c092246e7e","mcp_get_code":{"code_sha256":"1a7350c092246e7e"}},{"arxiv_id":"2502.07154","paper":"/paper/rethinking-fine-tuning-when-scaling-test-time","title":"Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning","date":"2025-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allanraventos/refine","path":"refine/training/filter_samples.py","file_url":"https://github.com/allanraventos/refine/blob/HEAD/refine/training/filter_samples.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"30b50c454a1ff5a6","mcp_get_code":{"code_sha256":"30b50c454a1ff5a6"}},{"arxiv_id":"2406.03503","paper":"/paper/position-rethinking-post-hoc-search-based","title":"Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems","date":"2024-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xyfffff/rethink_mcts_for_tsp","path":"utsp/Search/summarize.py","file_url":"https://github.com/xyfffff/rethink_mcts_for_tsp/blob/HEAD/utsp/Search/summarize.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c511696d8a36eef","mcp_get_code":{"code_sha256":"2c511696d8a36eef"}},{"arxiv_id":"2403.11901","paper":"/paper/larimar-large-language-models-with-episodic","title":"Larimar: Large Language Models with Episodic Memory Control","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/larimar","path":"larimar_base/counterfact_eval.py","file_url":"https://github.com/IBM/larimar/blob/HEAD/larimar_base/counterfact_eval.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":"be354c92aa1305df","mcp_get_code":{"code_sha256":"be354c92aa1305df"}},{"arxiv_id":"2201.05773","paper":"/paper/automated-causal-inference-in-application-to","title":"Automated causal inference in application to randomized controlled clinical trials","date":"2022-01-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ctplab/autoci","path":"src/evaluation.py","file_url":"https://github.com/ctplab/autoci/blob/HEAD/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23947e4fdf54d3ca","mcp_get_code":{"code_sha256":"23947e4fdf54d3ca"}},{"arxiv_id":"2006.01969","paper":"/paper/rel-an-entity-linker-standing-on-the","title":"REL: An Entity Linker Standing on the Shoulders of Giants","date":"2020-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"informagi/REL","path":"src/REL/utils.py","file_url":"https://github.com/informagi/REL/blob/HEAD/src/REL/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d35d743722eb4e7e","mcp_get_code":{"code_sha256":"d35d743722eb4e7e"}},{"arxiv_id":"1903.09588","paper":"/paper/utilizing-bert-for-aspect-based-sentiment","title":"Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence","date":"2019-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"recommeddit/labs","path":"AnmolStuff/gsearch.py","file_url":"https://github.com/recommeddit/labs/blob/HEAD/AnmolStuff/gsearch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56f00d998b03da1b","mcp_get_code":{"code_sha256":"56f00d998b03da1b"}}]}