{"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/format-input","entry":"format_input","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":8,"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":7,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":4},"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":"2603.03915","paper":"/paper/arxiv-2603-03915","title":"Rethinking Role-Playing Evaluation: Anonymous Benchmarking and A Systematic Study of Personality Effects","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"MiuLab/RolePlayBench","path":"CharacterEval/run_char_rm.py","file_url":"https://github.com/MiuLab/RolePlayBench/blob/HEAD/CharacterEval/run_char_rm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8f301aa7c29f9221","mcp_get_code":{"code_sha256":"8f301aa7c29f9221"}},{"arxiv_id":"2403.01304","paper":"/paper/improving-the-validity-of-automatically","title":"Improving the Validity of Automatically Generated Feedback via Reinforcement Learning","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"umass-ml4ed/feedback-gen-dpo","path":"reward_model_dataset.py","file_url":"https://github.com/umass-ml4ed/feedback-gen-dpo/blob/HEAD/reward_model_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fca5d04c2f6ba6c9","mcp_get_code":{"code_sha256":"fca5d04c2f6ba6c9"}},{"arxiv_id":"2402.11863","paper":"/paper/how-interpretable-are-reasoning-explanations","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wj210/cot_interpretability","path":"utils/data_collator_pinto.py","file_url":"https://github.com/wj210/cot_interpretability/blob/HEAD/utils/data_collator_pinto.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9bac83066a04172a","mcp_get_code":{"code_sha256":"9bac83066a04172a"}},{"arxiv_id":"2402.03293","paper":"/paper/flora-low-rank-adapters-are-secretly-gradient","title":"Flora: Low-Rank Adapters Are Secretly Gradient Compressors","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"borealisai/flora-opt","path":"examples/flax/decoder_seq2seq.py","file_url":"https://github.com/borealisai/flora-opt/blob/HEAD/examples/flax/decoder_seq2seq.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"LGPL-3.0","inline_ok":false,"code_sha256_prefix":"79df288fccf351fa","mcp_get_code":{"code_sha256":"79df288fccf351fa"}},{"arxiv_id":"2401.01275","paper":"/paper/charactereval-a-chinese-benchmark-for-role","title":"CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation","date":"2024-01-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"morecry/charactereval","path":"run_char_rm.py","file_url":"https://github.com/morecry/charactereval/blob/HEAD/run_char_rm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8f301aa7c29f9221","mcp_get_code":{"code_sha256":"8f301aa7c29f9221"}},{"arxiv_id":"2311.17154","paper":"/paper/pragmatic-radiology-report-generation","title":"Pragmatic Radiology Report Generation","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chicagohai/llm_radiology","path":"format_llama_input.py","file_url":"https://github.com/chicagohai/llm_radiology/blob/HEAD/format_llama_input.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"94711428e0791fe9","mcp_get_code":{"code_sha256":"94711428e0791fe9"}},{"arxiv_id":"2010.15750","paper":"/paper/gaussian-process-bandit-optimization-of","title":"Gaussian Process Bandit Optimization of the Thermodynamic Variational Objective","date":"2020-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ntienvu/tvo_gp_bandit","path":"src/gp_bandit.py","file_url":"https://github.com/ntienvu/tvo_gp_bandit/blob/HEAD/src/gp_bandit.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"64c88c97da2c1b4f","mcp_get_code":{"code_sha256":"64c88c97da2c1b4f"}},{"arxiv_id":"1910.14424","paper":"/paper/multi-stage-document-ranking-with-bert","title":"Multi-Stage Document Ranking with BERT","date":"2019-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"philipphager/baidu-bert-model","path":"src/data.py","file_url":"https://github.com/philipphager/baidu-bert-model/blob/HEAD/src/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e3d14a4472327aa7","mcp_get_code":{"code_sha256":"e3d14a4472327aa7"}}]}