{"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/create-question","entry":"create_question","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":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":5,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"unverified":1},"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":"2406.09396","paper":"/paper/too-many-frames-not-all-useful-efficient","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","date":"2024-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jongwoopark7978/LVNet","path":"fineKeyframeDetector.py","file_url":"https://github.com/jongwoopark7978/LVNet/blob/HEAD/fineKeyframeDetector.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":"3069205356329c82","mcp_get_code":{"code_sha256":"3069205356329c82"}},{"arxiv_id":"2403.13315","paper":"/paper/puzzlevqa-diagnosing-multimodal-reasoning","title":"PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns","date":"2024-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"declare-lab/llm-puzzletest","path":"AlgoPuzzleVQA/generation/board_tile.py","file_url":"https://github.com/declare-lab/llm-puzzletest/blob/HEAD/AlgoPuzzleVQA/generation/board_tile.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"459d2e0c665b8b99","mcp_get_code":{"code_sha256":"459d2e0c665b8b99"}},{"arxiv_id":"2402.15300","paper":"/paper/seeing-is-believing-mitigating-hallucination","title":"Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"d-ailin/clip-guided-decoding","path":"lib/data_utils.py","file_url":"https://github.com/d-ailin/clip-guided-decoding/blob/HEAD/lib/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"928cc991142557ee","mcp_get_code":{"code_sha256":"928cc991142557ee"}},{"arxiv_id":"2305.10355","paper":"/paper/evaluating-object-hallucination-in-large","title":"Evaluating Object Hallucination in Large Vision-Language Models","date":"2023-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mengchuang123/vasparse-github","path":"eval/opope_eval.py","file_url":"https://github.com/mengchuang123/vasparse-github/blob/HEAD/eval/opope_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f48c9c176418803","mcp_get_code":{"code_sha256":"9f48c9c176418803"}},{"arxiv_id":"2305.10355","paper":"/paper/evaluating-object-hallucination-in-large","title":"Evaluating Object Hallucination in Large Vision-Language Models","date":"2023-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/pope","path":"utils.py","file_url":"https://github.com/rucaibox/pope/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2715c0290945600d","mcp_get_code":{"code_sha256":"2715c0290945600d"}},{"arxiv_id":"2025.emnlp-main.534","paper":null,"title":"arXiv:2025.emnlp-main.534","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RUCAIBox/POPE","path":"utils.py","file_url":"https://github.com/RUCAIBox/POPE/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2715c0290945600d","mcp_get_code":{"code_sha256":"2715c0290945600d"}}]}