{"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-prompt-template","entry":"load_prompt_template","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":10,"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":12,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":12,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":9},"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":"2609.03370","paper":"/paper/arxiv-2609-03370","title":"FrameBench:A Language Understanding Benchmark Based on Frame Semantics","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"SasanoLab/FrameBench","path":"src/evaluation/eval_utils.py","file_url":"https://github.com/SasanoLab/FrameBench/blob/HEAD/src/evaluation/eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc2b050f0d6840e7","mcp_get_code":{"code_sha256":"dc2b050f0d6840e7"}},{"arxiv_id":"2607.13433","paper":"/paper/arxiv-2607-13433","title":"When Rubrics Change: Cross-Rubric Generalization for Critical Thinking Essay Scoring","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"umass-ml4ed/generalization-in-essay-scoring","path":"infer_traits.py","file_url":"https://github.com/umass-ml4ed/generalization-in-essay-scoring/blob/HEAD/infer_traits.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"c78179a9cf42084f","mcp_get_code":{"code_sha256":"c78179a9cf42084f"}},{"arxiv_id":"2605.18352","paper":"/paper/arxiv-2605-18352","title":"Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"proviso-bench/Presupposition-and-Reasoning-in-Conditionals","path":"inference/llm_as_judge.py","file_url":"https://github.com/proviso-bench/Presupposition-and-Reasoning-in-Conditionals/blob/HEAD/inference/llm_as_judge.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"beb0ac741afb6044","mcp_get_code":{"code_sha256":"beb0ac741afb6044"}},{"arxiv_id":"2605.18352","paper":"/paper/arxiv-2605-18352","title":"Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"proviso-bench/Presupposition-and-Reasoning-in-Conditionals","path":"inference/closedsource/inference_closedsource.py","file_url":"https://github.com/proviso-bench/Presupposition-and-Reasoning-in-Conditionals/blob/HEAD/inference/closedsource/inference_closedsource.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a906644faf2ca29","mcp_get_code":{"code_sha256":"6a906644faf2ca29"}},{"arxiv_id":"2604.19459","paper":"/paper/arxiv-2604-19459","title":"Do LLMs Game Formalization? Evaluating Faithfulness in Logical Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"koreankiwi99/formalization-gaming","path":"src/analysis/analyze_errors.py","file_url":"https://github.com/koreankiwi99/formalization-gaming/blob/HEAD/src/analysis/analyze_errors.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f1c89036844e212","mcp_get_code":{"code_sha256":"0f1c89036844e212"}},{"arxiv_id":"2604.00536","paper":"/paper/arxiv-2604-00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"FanZT6/OptimSyn","path":"data_synthesis/generate_qa.py","file_url":"https://github.com/FanZT6/OptimSyn/blob/HEAD/data_synthesis/generate_qa.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"870b252c8dbfcaba","mcp_get_code":{"code_sha256":"870b252c8dbfcaba"}},{"arxiv_id":"2604.00536","paper":"/paper/arxiv-2604-00536","title":"Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"FanZT6/OptimSyn","path":"data_synthesis/generate_qa_eval.py","file_url":"https://github.com/FanZT6/OptimSyn/blob/HEAD/data_synthesis/generate_qa_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"acc9101b33043248","mcp_get_code":{"code_sha256":"acc9101b33043248"}},{"arxiv_id":"2602.07422","paper":"/paper/arxiv-2602-07422","title":"Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"AndrewWTY/SecCoderX","path":"vul_induce_prompt_pipeline/inference_instructions_with_vllm.py","file_url":"https://github.com/AndrewWTY/SecCoderX/blob/HEAD/vul_induce_prompt_pipeline/inference_instructions_with_vllm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"95e7a771b99223f2","mcp_get_code":{"code_sha256":"95e7a771b99223f2"}},{"arxiv_id":"2512.15674","paper":"/paper/arxiv-2512-15674","title":"Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"cywinski/eliciting-secret-knowledge","path":"utils/guess_secret_word.py","file_url":"https://github.com/cywinski/eliciting-secret-knowledge/blob/HEAD/utils/guess_secret_word.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7b71485921e1d112","mcp_get_code":{"code_sha256":"7b71485921e1d112"}},{"arxiv_id":"2407.04842","paper":"/paper/mj-bench-is-your-multimodal-reward-model","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MJ-Bench/MJ-Bench","path":"inference.py","file_url":"https://github.com/MJ-Bench/MJ-Bench/blob/HEAD/inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4fb4a653fefe74ee","mcp_get_code":{"code_sha256":"4fb4a653fefe74ee"}},{"arxiv_id":"2402.14016","paper":"/paper/is-llm-as-a-judge-robust-investigating","title":"Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rainavyas/attack-comparative-assessment","path":"src/attacker/greedy.py","file_url":"https://github.com/rainavyas/attack-comparative-assessment/blob/HEAD/src/attacker/greedy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"42ad8d850594ddc0","mcp_get_code":{"code_sha256":"42ad8d850594ddc0"}},{"arxiv_id":"2312.16682","paper":"/paper/some-things-are-more-cringe-than-others","title":"Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss","date":"2023-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/RAM","path":"ram/data.py","file_url":"https://github.com/facebookresearch/RAM/blob/HEAD/ram/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"712ef575ecebd0ef","mcp_get_code":{"code_sha256":"712ef575ecebd0ef"}}]}