{"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","entry":"read_prompt","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":4,"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":8,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"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":"2608.12836","paper":"/paper/arxiv-2608-12836","title":"From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"obedjunias19/structured-compositional-reasoning","path":"utils/prompting.py","file_url":"https://github.com/obedjunias19/structured-compositional-reasoning/blob/HEAD/utils/prompting.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfd6f1e61da0bede","mcp_get_code":{"code_sha256":"dfd6f1e61da0bede"}},{"arxiv_id":"2602.03548","paper":"/paper/arxiv-2602-03548","title":"SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Da1yuqin/SEAD","path":"utils/create_prompt_data.py","file_url":"https://github.com/Da1yuqin/SEAD/blob/HEAD/utils/create_prompt_data.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":"18b5ff46b3ab5402","mcp_get_code":{"code_sha256":"18b5ff46b3ab5402"}},{"arxiv_id":"2412.11716","paper":"/paper/llms-can-simulate-standardized-patients-via","title":"LLMs Can Simulate Standardized Patients via Agent Coevolution","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjumai/evopatient","path":"utils.py","file_url":"https://github.com/zjumai/evopatient/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0c2b1e68e05635fc","mcp_get_code":{"code_sha256":"0c2b1e68e05635fc"}},{"arxiv_id":"2411.07132","paper":"/paper/token-merging-for-training-free-semantic","title":"Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hutaihang/tome","path":"run_demo.py","file_url":"https://github.com/hutaihang/tome/blob/HEAD/run_demo.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":"b4ba9e438f266d33","mcp_get_code":{"code_sha256":"b4ba9e438f266d33"}},{"arxiv_id":"2311.08089","paper":"/paper/align-after-pre-train-improving-multilingual","title":"Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chongli17/crosslingualalignment","path":"src/paws_x_prompt.py","file_url":"https://github.com/chongli17/crosslingualalignment/blob/HEAD/src/paws_x_prompt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b1e6bd407417bb8","mcp_get_code":{"code_sha256":"3b1e6bd407417bb8"}},{"arxiv_id":"2307.13528","paper":"/paper/factool-factuality-detection-in-generative-ai","title":"FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios","date":"2023-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"freedomintelligence/sdak","path":"code/src/gpt4_eval.py","file_url":"https://github.com/freedomintelligence/sdak/blob/HEAD/code/src/gpt4_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":"75a67db826a48255","mcp_get_code":{"code_sha256":"75a67db826a48255"}},{"arxiv_id":"2305.17878","paper":"/paper/ask-an-expert-leveraging-language-models-to","title":"Ask an Expert: Leveraging Language Models to Improve Strategic Reasoning in Goal-Oriented Dialogue Models","date":"2023-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qzx7/bbmhreasoning","path":"bbmhr/pipeline/prompting.py","file_url":"https://github.com/qzx7/bbmhreasoning/blob/HEAD/bbmhr/pipeline/prompting.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2065e1a55aa14adf","mcp_get_code":{"code_sha256":"2065e1a55aa14adf"}},{"arxiv_id":"2210.07128","paper":"/paper/language-models-of-code-are-few-shot","title":"Language Models of Code are Few-Shot Commonsense Learners","date":"2022-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reasoning-machines/cocogen","path":"src/api/query_openai_over_tasks.py","file_url":"https://github.com/reasoning-machines/cocogen/blob/HEAD/src/api/query_openai_over_tasks.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":"f1c9971fa0b6bc31","mcp_get_code":{"code_sha256":"f1c9971fa0b6bc31"}}]}