{"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/read-prompt-list","entry":"read_prompt_list","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":7,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"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":"2604.02795","paper":"/paper/arxiv-2604-02795","title":"Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"TURLEing/Rubrics-To-Tokens","path":"Benchmark/IFBench/evaluation_lib.py","file_url":"https://github.com/TURLEing/Rubrics-To-Tokens/blob/HEAD/Benchmark/IFBench/evaluation_lib.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":"688320f8e08335ac","mcp_get_code":{"code_sha256":"688320f8e08335ac"}},{"arxiv_id":"2506.00329","paper":null,"title":"arXiv:2506.00329","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"STAR-Laboratory/foresight","path":"eval/foresight/experiments/utils.py","file_url":"https://github.com/STAR-Laboratory/foresight/blob/HEAD/eval/foresight/experiments/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":"48adac316c7f38aa","mcp_get_code":{"code_sha256":"48adac316c7f38aa"}},{"arxiv_id":"2505.19037","paper":"/paper/speech-ifeval-evaluating-instruction","title":"Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kehanlu/speech-ifeval","path":"instruction_following_eval/evaluation_main.py","file_url":"https://github.com/kehanlu/speech-ifeval/blob/HEAD/instruction_following_eval/evaluation_main.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":"5434c331e19c4198","mcp_get_code":{"code_sha256":"5434c331e19c4198"}},{"arxiv_id":"2410.17196","paper":"/paper/voicebench-benchmarking-llm-based-voice","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","date":"2024-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"matthewcym/voicebench","path":"src/evaluator/ifeval.py","file_url":"https://github.com/matthewcym/voicebench/blob/HEAD/src/evaluator/ifeval.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":"5bc9a1b5b02a8f64","mcp_get_code":{"code_sha256":"5bc9a1b5b02a8f64"}},{"arxiv_id":"2404.15846","paper":"/paper/from-complex-to-simple-enhancing-multi","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meowpass/followcomplexinstruction","path":"get_data/check.py","file_url":"https://github.com/meowpass/followcomplexinstruction/blob/HEAD/get_data/check.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ef1aee592402546","mcp_get_code":{"code_sha256":"6ef1aee592402546"}},{"arxiv_id":"2311.07911","paper":"/paper/instruction-following-evaluation-for-large","title":"Instruction-Following Evaluation for Large Language Models","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lightblue-tech/M-IFEval","path":"evaluation_main.py","file_url":"https://github.com/lightblue-tech/M-IFEval/blob/HEAD/evaluation_main.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1c91fdb27a21c14a","mcp_get_code":{"code_sha256":"1c91fdb27a21c14a"}},{"arxiv_id":"2025.emnlp-main.1010","paper":null,"title":"arXiv:2025.emnlp-main.1010","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"joaopfonseca/SafeNudge","path":"ctg/evaluation_main.py","file_url":"https://github.com/joaopfonseca/SafeNudge/blob/HEAD/ctg/evaluation_main.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"688320f8e08335ac","mcp_get_code":{"code_sha256":"688320f8e08335ac"}}]}