{"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/compute-metric","entry":"compute_metric","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":18,"n_papers_ran":8,"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":18,"n_samples_ran":8,"n_samples_fingerprinted":0,"n_places":20,"n_places_pointer_only":9,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":1,"ran":3,"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":"2608.31058","paper":"/paper/arxiv-2608-31058","title":"Improving Information Extraction with Learned Queries","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"ZhaoyueSun/PHEE","path":"evaluate/phee_metric.py","file_url":"https://github.com/ZhaoyueSun/PHEE/blob/HEAD/evaluate/phee_metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"65ffc8abe1a9b4eb","mcp_get_code":{"code_sha256":"65ffc8abe1a9b4eb"}},{"arxiv_id":"2603.20263","paper":"/paper/arxiv-2603-20263","title":"MiSiSUn: Minimum Simplex Semisupervised Unmixing","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"BehnoodRasti/HySUPP","path":"src/utils/metrics.py","file_url":"https://github.com/BehnoodRasti/HySUPP/blob/HEAD/src/utils/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9d143ca2c58f98ec","mcp_get_code":{"code_sha256":"9d143ca2c58f98ec"}},{"arxiv_id":"2506.01262","paper":"/paper/exploring-the-potential-of-llms-as","title":"Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis","date":"2025-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"12kimih/HiCUPID","path":"src/bleu_rouge.py","file_url":"https://github.com/12kimih/HiCUPID/blob/HEAD/src/bleu_rouge.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":"0bbec0695520ec07","mcp_get_code":{"code_sha256":"0bbec0695520ec07"}},{"arxiv_id":"2408.10284","paper":"/paper/adapmoe-adaptive-sensitivity-based-expert","title":"AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference","date":"2024-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-sec-lab/adapmoe","path":"benchmarks/chain-of-thought-hub/run_mmlu.py","file_url":"https://github.com/pku-sec-lab/adapmoe/blob/HEAD/benchmarks/chain-of-thought-hub/run_mmlu.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f01688d0434b6835","mcp_get_code":{"code_sha256":"f01688d0434b6835"}},{"arxiv_id":"2403.14598","paper":"/paper/psalm-pixelwise-segmentation-with-large-multi","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zamling/PSALM","path":"psalm/eval/eval_davis.py","file_url":"https://github.com/zamling/PSALM/blob/HEAD/psalm/eval/eval_davis.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":"6cf5142ee7139417","mcp_get_code":{"code_sha256":"6cf5142ee7139417"}},{"arxiv_id":"2401.06469","paper":"/paper/batch-icl-effective-efficient-and-order","title":"Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cardinalere/batch-icl","path":"Batch-ICL-multi_epoch.py","file_url":"https://github.com/cardinalere/batch-icl/blob/HEAD/Batch-ICL-multi_epoch.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f01688d0434b6835","mcp_get_code":{"code_sha256":"f01688d0434b6835"}},{"arxiv_id":"2401.06469","paper":"/paper/batch-icl-effective-efficient-and-order","title":"Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cardinalere/batch-icl","path":"BatchICL_generation.py","file_url":"https://github.com/cardinalere/batch-icl/blob/HEAD/BatchICL_generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ccd8b3dbcb91ca8","mcp_get_code":{"code_sha256":"6ccd8b3dbcb91ca8"}},{"arxiv_id":"2312.04604","paper":"/paper/transferable-candidate-proposal-with-bounded","title":"Transferable Candidate Proposal with Bounded Uncertainty","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gokyeongryeol/tbu","path":"active/models/train_utils.py","file_url":"https://github.com/gokyeongryeol/tbu/blob/HEAD/active/models/train_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"92b61b67ddcc3a83","mcp_get_code":{"code_sha256":"92b61b67ddcc3a83"}},{"arxiv_id":"2311.07468","paper":"/paper/are-we-falling-in-a-middle-intelligence-trap","title":"An Analysis and Mitigation of the Reversal Curse","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trestad/mitigating-reversal-curse","path":"generate.py","file_url":"https://github.com/trestad/mitigating-reversal-curse/blob/HEAD/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"33553b56020f3138","mcp_get_code":{"code_sha256":"33553b56020f3138"}},{"arxiv_id":"2310.01468","paper":"/paper/the-entity-deduction-arena-a-playground-for","title":"Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Games","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-entity-deduction-arena","path":"eval_result.py","file_url":"https://github.com/apple/ml-entity-deduction-arena/blob/HEAD/eval_result.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"a35529b0a2a29c54","mcp_get_code":{"code_sha256":"a35529b0a2a29c54"}},{"arxiv_id":"2309.06365","paper":"/paper/2309-06365","title":"Cited Text Spans for Citation Text Generation","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jacklxc/cts4citationtextgeneration","path":"code/CTS_LED_no_trainer.py","file_url":"https://github.com/jacklxc/cts4citationtextgeneration/blob/HEAD/code/CTS_LED_no_trainer.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":"9e24746ae8703804","mcp_get_code":{"code_sha256":"9e24746ae8703804"}},{"arxiv_id":"2306.03580","paper":"/paper/l-c2st-local-diagnostics-for-posterior","title":"L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference","date":"2023-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"julialinhart/lc2st","path":"lc2st/lc2st.py","file_url":"https://github.com/julialinhart/lc2st/blob/HEAD/lc2st/lc2st.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7eb3d41af29f7521","mcp_get_code":{"code_sha256":"7eb3d41af29f7521"}},{"arxiv_id":"2303.09989","paper":"/paper/finding-competence-regions-in-domain","title":"Finding Competence Regions in Domain Generalization","date":"2023-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xarwinm/competence_estimation","path":"competence_estimation/metrics.py","file_url":"https://github.com/xarwinm/competence_estimation/blob/HEAD/competence_estimation/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51bfa38a289b0fb8","mcp_get_code":{"code_sha256":"51bfa38a289b0fb8"}},{"arxiv_id":"2203.10681","paper":"/paper/online-continual-learning-for-embedded","title":"Online Continual Learning for Embedded Devices","date":"2022-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tyler-hayes/embedded-cl","path":"analyze_results_openloris.py","file_url":"https://github.com/tyler-hayes/embedded-cl/blob/HEAD/analyze_results_openloris.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b77c1e7de919038c","mcp_get_code":{"code_sha256":"b77c1e7de919038c"}},{"arxiv_id":"2106.00948","paper":"/paper/unsupervised-out-of-domain-detection-via-pre","title":"Unsupervised Out-of-Domain Detection via Pre-trained Transformers","date":"2021-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rivercold/BERT-unsupervised-OOD","path":"calculate_log.py","file_url":"https://github.com/rivercold/BERT-unsupervised-OOD/blob/HEAD/calculate_log.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"160824dee7076cd5","mcp_get_code":{"code_sha256":"160824dee7076cd5"}},{"arxiv_id":"1912.12510","paper":"/paper/detecting-out-of-distribution-examples-with","title":"Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices","date":"2019-12-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VectorInstitute/gram-ood-detection","path":"calculate_log.py","file_url":"https://github.com/VectorInstitute/gram-ood-detection/blob/HEAD/calculate_log.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"160824dee7076cd5","mcp_get_code":{"code_sha256":"160824dee7076cd5"}},{"arxiv_id":"1904.06991","paper":"/paper/improved-precision-and-recall-metric-for","title":"Improved Precision and Recall Metric for Assessing Generative Models","date":"2019-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlexVerine/PrecisionRecallGan","path":"precision_recall_kyn_utils.py","file_url":"https://github.com/AlexVerine/PrecisionRecallGan/blob/HEAD/precision_recall_kyn_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"88c7b603b76960ad","mcp_get_code":{"code_sha256":"88c7b603b76960ad"}},{"arxiv_id":"1904.06991","paper":"/paper/improved-precision-and-recall-metric-for","title":"Improved Precision and Recall Metric for Assessing Generative Models","date":"2019-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"youngjung/improved-precision-and-recall-metric-pytorch","path":"improved_precision_recall.py","file_url":"https://github.com/youngjung/improved-precision-and-recall-metric-pytorch/blob/HEAD/improved_precision_recall.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9f1f8858820c945f","mcp_get_code":{"code_sha256":"9f1f8858820c945f"}},{"arxiv_id":"1608.06993","paper":"/paper/densely-connected-convolutional-networks","title":"Densely Connected Convolutional Networks","date":"2016-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GeoTrouvetout/Vehicle_ReID","path":"vehicle_reid/ranking.py","file_url":"https://github.com/GeoTrouvetout/Vehicle_ReID/blob/HEAD/vehicle_reid/ranking.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f3873bb6bde781e","mcp_get_code":{"code_sha256":"0f3873bb6bde781e"}},{"arxiv_id":"2023.findings-emnlp.698","paper":null,"title":"arXiv:2023.findings-emnlp.698","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"tommytyc/RSVP","path":"util.py","file_url":"https://github.com/tommytyc/RSVP/blob/HEAD/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8440749e93818bb4","mcp_get_code":{"code_sha256":"8440749e93818bb4"}}]}