{"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-question-text","entry":"get_question_text","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":5,"n_papers_ran":5,"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":2,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":0},"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":"2411.19500","paper":"/paper/cold-causal-reasoning-in-closed-daily","title":"COLD: Causal reasOning in cLosed Daily activities","date":"2024-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Exploration-Lab/COLD","path":"prompt-based-evaluation/evaluation_templates/mcqa.py","file_url":"https://github.com/Exploration-Lab/COLD/blob/HEAD/prompt-based-evaluation/evaluation_templates/mcqa.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e74f77b7ab07422d","mcp_get_code":{"code_sha256":"e74f77b7ab07422d"}},{"arxiv_id":"2405.05615","paper":"/paper/memory-space-visual-prompting-for-efficient","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","date":"2024-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jieshibo/memvp","path":"util/base_prompt.py","file_url":"https://github.com/jieshibo/memvp/blob/HEAD/util/base_prompt.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":"c86a79e229253816","mcp_get_code":{"code_sha256":"c86a79e229253816"}},{"arxiv_id":"2307.12626","paper":"/paper/enhancing-human-like-multi-modal-reasoning-a","title":"Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weijingxuan/COCO-MMR","path":"utils_prompt.py","file_url":"https://github.com/weijingxuan/COCO-MMR/blob/HEAD/utils_prompt.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":"c86a79e229253816","mcp_get_code":{"code_sha256":"c86a79e229253816"}},{"arxiv_id":"2302.00923","paper":"/paper/multimodal-chain-of-thought-reasoning-in","title":"Multimodal Chain-of-Thought Reasoning in Language Models","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/mm-cot","path":"utils_prompt.py","file_url":"https://github.com/amazon-science/mm-cot/blob/HEAD/utils_prompt.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":"c86a79e229253816","mcp_get_code":{"code_sha256":"c86a79e229253816"}},{"arxiv_id":"2209.09513","paper":"/paper/learn-to-explain-multimodal-reasoning-via","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","date":"2022-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lupantech/ScienceQA","path":"models/base_prompt.py","file_url":"https://github.com/lupantech/ScienceQA/blob/HEAD/models/base_prompt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c86a79e229253816","mcp_get_code":{"code_sha256":"c86a79e229253816"}}]}