{"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/process-single-sample","entry":"process_single_sample","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":4,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2605.03465","paper":"/paper/arxiv-2605-03465","title":"FINER-SQL: Boosting Small Language Models for Text-to-SQL","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"thanhdath/finer-sql","path":"build_gt_cache.py","file_url":"https://github.com/thanhdath/finer-sql/blob/HEAD/build_gt_cache.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"80a58884b0c0aded","mcp_get_code":{"code_sha256":"80a58884b0c0aded"}},{"arxiv_id":"2502.06884","paper":"/paper/learning-conformal-abstention-policies-for","title":"Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language Models","date":"2025-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sinatayebati/vlm-uncertainty","path":"data_utils/mmmu.py","file_url":"https://github.com/sinatayebati/vlm-uncertainty/blob/HEAD/data_utils/mmmu.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1b3610ee2583172","mcp_get_code":{"code_sha256":"c1b3610ee2583172"}},{"arxiv_id":"2502.00698","paper":"/paper/mm-iq-benchmarking-human-like-abstraction-and-1","title":"MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models","date":"2025-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AceCHQ/MMIQ","path":"mmiq/utils/data_utils.py","file_url":"https://github.com/AceCHQ/MMIQ/blob/HEAD/mmiq/utils/data_utils.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":"09fe27c6ee70aa9b","mcp_get_code":{"code_sha256":"09fe27c6ee70aa9b"}},{"arxiv_id":"2405.05949","paper":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shi-labs/cumo","path":"cumo/eval/model_vqa_mathvista.py","file_url":"https://github.com/shi-labs/cumo/blob/HEAD/cumo/eval/model_vqa_mathvista.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":"d6888be4b2989f1f","mcp_get_code":{"code_sha256":"d6888be4b2989f1f"}},{"arxiv_id":"2402.14418","paper":"/paper/uncertainty-aware-evaluation-for-vision","title":"Uncertainty-Aware Evaluation for Vision-Language Models","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ensec-ai/vlm-uncertainty-bench","path":"data_utils/mmmu.py","file_url":"https://github.com/ensec-ai/vlm-uncertainty-bench/blob/HEAD/data_utils/mmmu.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c1b3610ee2583172","mcp_get_code":{"code_sha256":"c1b3610ee2583172"}}]}