{"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/run-test","entry":"run_test","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":11,"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":12,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":10},"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":"2606.02231","paper":"/paper/arxiv-2606-02231","title":"Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"roelhulsman/flowmsm","path":"src/flowmsm/causal_discovery/pcmci_plus.py","file_url":"https://github.com/roelhulsman/flowmsm/blob/HEAD/src/flowmsm/causal_discovery/pcmci_plus.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"df5eb7d86a1051c1","mcp_get_code":{"code_sha256":"df5eb7d86a1051c1"}},{"arxiv_id":"2604.01170","paper":"/paper/arxiv-2604-01170","title":"Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"wzekai/ORCA","path":"code/calibrate.py","file_url":"https://github.com/wzekai/ORCA/blob/HEAD/code/calibrate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"84570830f93e1e84","mcp_get_code":{"code_sha256":"84570830f93e1e84"}},{"arxiv_id":"2603.26469","paper":"/paper/arxiv-2603-26469","title":"UNIFERENCE: A Discrete Event Simulation Framework for Developing Distributed AI Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Dogacel/Uniference","path":"run_sanity_tests.py","file_url":"https://github.com/Dogacel/Uniference/blob/HEAD/run_sanity_tests.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5f3a741c1b9f987b","mcp_get_code":{"code_sha256":"5f3a741c1b9f987b"}},{"arxiv_id":"2509.26404","paper":"/paper/arxiv-2509-26404","title":"SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"YnezT0311/SeedPrints","path":"seedprint.py","file_url":"https://github.com/YnezT0311/SeedPrints/blob/HEAD/seedprint.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"47feeb169b931d7d","mcp_get_code":{"code_sha256":"47feeb169b931d7d"}},{"arxiv_id":"2506.08184","paper":"/paper/2506-08184","title":"Unable to Forget: Proactive lnterference Reveals Working Memory Limits in LLMs Beyond Context Length","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhuangziGiantfish/Unable-to-Forget","path":"run_pi_benchmark.py","file_url":"https://github.com/zhuangziGiantfish/Unable-to-Forget/blob/HEAD/run_pi_benchmark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96b02e69075ec726","mcp_get_code":{"code_sha256":"96b02e69075ec726"}},{"arxiv_id":"2502.08166","paper":"/paper/from-individual-experience-to-collective","title":"From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms","date":"2025-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jessica-dai/reporting","path":"algorithms.py","file_url":"https://github.com/jessica-dai/reporting/blob/HEAD/algorithms.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f8226b3b8cef816a","mcp_get_code":{"code_sha256":"f8226b3b8cef816a"}},{"arxiv_id":"2408.01417","paper":"/paper/2408-01417","title":"Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs","date":"2024-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lil-lab/icca","path":"src/run_icca.py","file_url":"https://github.com/lil-lab/icca/blob/HEAD/src/run_icca.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f4801dced0b1a674","mcp_get_code":{"code_sha256":"f4801dced0b1a674"}},{"arxiv_id":"2405.07344","paper":"/paper/tkan-temporal-kolmogorov-arnold-networks","title":"TKAN: Temporal Kolmogorov-Arnold Networks","date":"2024-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"remigenet/tkan","path":"run_tests.py","file_url":"https://github.com/remigenet/tkan/blob/HEAD/run_tests.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1d4060eeb28f365a","mcp_get_code":{"code_sha256":"1d4060eeb28f365a"}},{"arxiv_id":"2404.09486","paper":"/paper/mmcode-evaluating-multi-modal-code-large","title":"MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems","date":"2024-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"happylkx/mmcode","path":"testing_utils.py","file_url":"https://github.com/happylkx/mmcode/blob/HEAD/testing_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f968344aa35117c","mcp_get_code":{"code_sha256":"6f968344aa35117c"}},{"arxiv_id":"2210.17041","paper":"/paper/gps-genetic-prompt-search-for-efficient-few","title":"GPS: Genetic Prompt Search for Efficient Few-shot Learning","date":"2022-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hwxu20/gps","path":"ga_processer_t0.py","file_url":"https://github.com/hwxu20/gps/blob/HEAD/ga_processer_t0.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ef8c9c9ac454d25","mcp_get_code":{"code_sha256":"9ef8c9c9ac454d25"}},{"arxiv_id":"1905.09591","paper":"/paper/a-direct-approach-to-robust-deep-learning-1","title":"A Direct Approach to Robust Deep Learning Using Adversarial Networks","date":"2019-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whxbergkamp/RobustDL_GAN","path":"cifar10/adversarial_networks/train_gan_cifar10.py","file_url":"https://github.com/whxbergkamp/RobustDL_GAN/blob/HEAD/cifar10/adversarial_networks/train_gan_cifar10.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"afb91a2794a82aa9","mcp_get_code":{"code_sha256":"afb91a2794a82aa9"}},{"arxiv_id":"1905.09591","paper":"/paper/a-direct-approach-to-robust-deep-learning-1","title":"A Direct Approach to Robust Deep Learning Using Adversarial Networks","date":"2019-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"whxbergkamp/RobustDL_GAN","path":"svhn/adversarial_networks/train_gan_svhn.py","file_url":"https://github.com/whxbergkamp/RobustDL_GAN/blob/HEAD/svhn/adversarial_networks/train_gan_svhn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e45c8e8b0a36a79e","mcp_get_code":{"code_sha256":"e45c8e8b0a36a79e"}}]}