{"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/find-json-files","entry":"find_json_files","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":6,"n_papers_ran":2,"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":6,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"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":"2606.31394","paper":"/paper/arxiv-2606-31394","title":"Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jijihihi/Bio_superposition","path":"cell_death/plot_knn_std_trend.py","file_url":"https://github.com/jijihihi/Bio_superposition/blob/HEAD/cell_death/plot_knn_std_trend.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"43a21f97fd3ed76f","mcp_get_code":{"code_sha256":"43a21f97fd3ed76f"}},{"arxiv_id":"2602.09662","paper":"/paper/arxiv-2602-09662","title":"TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"UITron-hub/TreeCUA","path":"exploration/traj_score_agent.py","file_url":"https://github.com/UITron-hub/TreeCUA/blob/HEAD/exploration/traj_score_agent.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":"0b4e6c094f970221","mcp_get_code":{"code_sha256":"0b4e6c094f970221"}},{"arxiv_id":"2601.09449","paper":"/paper/arxiv-2601-09449","title":"PrivLEX: Detecting legal concepts in images through Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"idiap/privlex","path":"pipeline/explainability/generate_explanations_for_images.py","file_url":"https://github.com/idiap/privlex/blob/HEAD/pipeline/explainability/generate_explanations_for_images.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"33379081645a792b","mcp_get_code":{"code_sha256":"33379081645a792b"}},{"arxiv_id":"2505.03570","paper":"/paper/osuniverse-benchmark-for-multimodal-gui","title":"OSUniverse: Benchmark for Multimodal GUI-navigation AI Agents","date":"2025-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentsea/osuniverse","path":"osuniverse/utils.py","file_url":"https://github.com/agentsea/osuniverse/blob/HEAD/osuniverse/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7400fda119d2d3fc","mcp_get_code":{"code_sha256":"7400fda119d2d3fc"}},{"arxiv_id":"2410.09893","paper":"/paper/rmb-comprehensively-benchmarking-reward","title":"RMB: Comprehensively Benchmarking Reward Models in LLM Alignment","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhou-zoey/rmb-reward-model-benchmark","path":"eval/scripts/my_run_rm.py","file_url":"https://github.com/zhou-zoey/rmb-reward-model-benchmark/blob/HEAD/eval/scripts/my_run_rm.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e95b318087b7ce83","mcp_get_code":{"code_sha256":"e95b318087b7ce83"}},{"arxiv_id":"2006.04884","paper":"/paper/on-the-stability-of-fine-tuning-bert","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruanchaves/eplm","path":"leaderboard/extract_portuguese_leaderboard.py","file_url":"https://github.com/ruanchaves/eplm/blob/HEAD/leaderboard/extract_portuguese_leaderboard.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6e1f4e02403886e3","mcp_get_code":{"code_sha256":"6e1f4e02403886e3"}}]}