{"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-json-list","entry":"get_json_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":11,"n_papers_ran":9,"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":5,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":4,"unverified":2},"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":"2604.14463","paper":"/paper/arxiv-2604-14463","title":"Psychological Steering of Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"kaistAI/FLASK","path":"gpt_review/gpt4_eval.py","file_url":"https://github.com/kaistAI/FLASK/blob/HEAD/gpt_review/gpt4_eval.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":"7a847088a718d3dd","mcp_get_code":{"code_sha256":"7a847088a718d3dd"}},{"arxiv_id":"2412.20888","paper":"/paper/navigating-chemical-linguistic-sharing-space","title":"Navigating Chemical-Linguistic Sharing Space with Heterogeneous Molecular Encoding","date":null,"month_inferred_from_arxiv_id":"2024-12","title_source":"archive","repo":"Lyu6PosHao/HME","path":"src/hme/preprocess_mol.py","file_url":"https://github.com/Lyu6PosHao/HME/blob/HEAD/src/hme/preprocess_mol.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"271e7e74e265eaf2","mcp_get_code":{"code_sha256":"271e7e74e265eaf2"}},{"arxiv_id":"2408.07471","paper":"/paper/bridging-and-modeling-correlations-in","title":"Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization","date":"2024-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YJiangcm/BMC","path":"eval/alpacaeval2/alpaca_eval_inference.py","file_url":"https://github.com/YJiangcm/BMC/blob/HEAD/eval/alpacaeval2/alpaca_eval_inference.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":"7dfbedc27279839f","mcp_get_code":{"code_sha256":"7dfbedc27279839f"}},{"arxiv_id":"2406.04371","paper":"/paper/phased-instruction-fine-tuning-for-large","title":"Phased Instruction Fine-Tuning for Large Language Models","date":"2024-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xubuvd/phasedsft","path":"evaluation/win_tie_loss_stat.py","file_url":"https://github.com/xubuvd/phasedsft/blob/HEAD/evaluation/win_tie_loss_stat.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":"5d17b604c968b41d","mcp_get_code":{"code_sha256":"5d17b604c968b41d"}},{"arxiv_id":"2401.10768","paper":"/paper/mitigating-hallucinations-of-large-language","title":"Knowledge Verification to Nip Hallucination in the Bud","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanqiwan/KCA","path":"eval/gpt_judge/gpt_judge.py","file_url":"https://github.com/fanqiwan/KCA/blob/HEAD/eval/gpt_judge/gpt_judge.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":"5d17b604c968b41d","mcp_get_code":{"code_sha256":"5d17b604c968b41d"}},{"arxiv_id":"2310.20410","paper":"/paper/followbench-a-multi-level-fine-grained","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yjiangcm/followbench","path":"code/llm_eval.py","file_url":"https://github.com/yjiangcm/followbench/blob/HEAD/code/llm_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":"5d17b604c968b41d","mcp_get_code":{"code_sha256":"5d17b604c968b41d"}},{"arxiv_id":"2310.09168","paper":"/paper/explore-instruct-enhancing-domain-specific","title":"Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanqiwan/Explore-Instruct","path":"eval/chatgpt_score.py","file_url":"https://github.com/fanqiwan/Explore-Instruct/blob/HEAD/eval/chatgpt_score.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":"5d17b604c968b41d","mcp_get_code":{"code_sha256":"5d17b604c968b41d"}},{"arxiv_id":"2310.09168","paper":"/paper/explore-instruct-enhancing-domain-specific","title":"Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fanqiwan/Explore-Instruct","path":"eval/chatgpt_generate.py","file_url":"https://github.com/fanqiwan/Explore-Instruct/blob/HEAD/eval/chatgpt_generate.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":"76f57c5b5180ce60","mcp_get_code":{"code_sha256":"76f57c5b5180ce60"}},{"arxiv_id":"2307.10928","paper":"/paper/flask-fine-grained-language-model-evaluation","title":"FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets","date":"2023-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaistai/flask","path":"gpt_review/gpt4_eval.py","file_url":"https://github.com/kaistai/flask/blob/HEAD/gpt_review/gpt4_eval.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":"7a847088a718d3dd","mcp_get_code":{"code_sha256":"7a847088a718d3dd"}},{"arxiv_id":"2307.02762","paper":"/paper/prd-peer-rank-and-discussion-improve-large","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","date":"2023-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bcdnlp/prd","path":"human_annotation/generate_mturk_input.py","file_url":"https://github.com/bcdnlp/prd/blob/HEAD/human_annotation/generate_mturk_input.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e5264b01e60f3d3d","mcp_get_code":{"code_sha256":"e5264b01e60f3d3d"}},{"arxiv_id":"2305.12870","paper":"/paper/lion-adversarial-distillation-of-closed","title":"Lion: Adversarial Distillation of Proprietary Large Language Models","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yjiangcm/lion","path":"src/utils.py","file_url":"https://github.com/yjiangcm/lion/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e74ea48e46988286","mcp_get_code":{"code_sha256":"e74ea48e46988286"}},{"arxiv_id":"2024.findings-acl.341","paper":null,"title":"arXiv:2024.findings-acl.341","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"xubuvd/PhasedSFT","path":"evaluation/win_tie_loss_stat.py","file_url":"https://github.com/xubuvd/PhasedSFT/blob/HEAD/evaluation/win_tie_loss_stat.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":"5d17b604c968b41d","mcp_get_code":{"code_sha256":"5d17b604c968b41d"}}]}