{"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/judge","entry":"judge","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":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":8,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":5},"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":"2601.16644","paper":"/paper/arxiv-2601-16644","title":"Sycophancy Hides Linearly in the Attention Heads","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"rifoagenadi/sycophancy","path":"extension/judge.py","file_url":"https://github.com/rifoagenadi/sycophancy/blob/HEAD/extension/judge.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14f95d42884c5248","mcp_get_code":{"code_sha256":"14f95d42884c5248"}},{"arxiv_id":"2503.14021","paper":"/paper/mp-gui-modality-perception-with-mllms-for-gui","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","date":"2025-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BigTaige/MP-GUI","path":"data_tools/XML_format_get_spatial_relationship_prediction_data.py","file_url":"https://github.com/BigTaige/MP-GUI/blob/HEAD/data_tools/XML_format_get_spatial_relationship_prediction_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"63bbe0118077916d","mcp_get_code":{"code_sha256":"63bbe0118077916d"}},{"arxiv_id":"2502.16971","paper":"/paper/longsafety-evaluating-long-context-safety-of","title":"LongSafety: Evaluating Long-Context Safety of Large Language Models","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/LongSafety","path":"src/multi_agent_eval.py","file_url":"https://github.com/thu-coai/LongSafety/blob/HEAD/src/multi_agent_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"962e634cb87af48b","mcp_get_code":{"code_sha256":"962e634cb87af48b"}},{"arxiv_id":"2406.14129","paper":"/paper/towards-event-oriented-long-video","title":"Towards Event-oriented Long Video Understanding","date":"2024-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/event-bench","path":"evaluation/evaluate_gpt.py","file_url":"https://github.com/rucaibox/event-bench/blob/HEAD/evaluation/evaluate_gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d6240c90c840d77","mcp_get_code":{"code_sha256":"7d6240c90c840d77"}},{"arxiv_id":"2401.07128","paper":"/paper/ehragent-code-empowers-large-language-models","title":"EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records","date":"2024-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wshi83/EhrAgent","path":"ehragent/evaluate.py","file_url":"https://github.com/wshi83/EhrAgent/blob/HEAD/ehragent/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bcc19e0a980e5fb7","mcp_get_code":{"code_sha256":"bcc19e0a980e5fb7"}},{"arxiv_id":"2212.10305","paper":"/paper/which-pixel-to-annotate-a-label-efficient","title":"Which Pixel to Annotate: a Label-Efficient Nuclei Segmentation Framework","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lhaof/nuseg","path":"CSinGAN/mask_synthesis.py","file_url":"https://github.com/lhaof/nuseg/blob/HEAD/CSinGAN/mask_synthesis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f78c053a21aa75f9","mcp_get_code":{"code_sha256":"f78c053a21aa75f9"}},{"arxiv_id":"2001.03360","paper":"/paper/nwpu-crowd-a-large-scale-benchmark-for-crowd","title":"NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization","date":"2020-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gjy3035/NWPU-Crowd-Sample-Code","path":"misc/evaluation_code.py","file_url":"https://github.com/gjy3035/NWPU-Crowd-Sample-Code/blob/HEAD/misc/evaluation_code.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":"7f332d3b08e57871","mcp_get_code":{"code_sha256":"7f332d3b08e57871"}},{"arxiv_id":"aaai_16595","paper":null,"title":"arXiv:aaai_16595","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"BGT-M/AugSplicing","path":"codes/CalTopkBlocks.py","file_url":"https://github.com/BGT-M/AugSplicing/blob/HEAD/codes/CalTopkBlocks.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"cd5c0dff42005400","mcp_get_code":{"code_sha256":"cd5c0dff42005400"}}]}