{"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/evaluator-2","entry":"evaluator","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":7,"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":9,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":2,"unverified":6},"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":"2603.02176","paper":"/paper/arxiv-2603-02176","title":"Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ynulihao/AgentSkillOS","path":"benchmark/AgentSkillOS_bench/registry.py","file_url":"https://github.com/ynulihao/AgentSkillOS/blob/HEAD/benchmark/AgentSkillOS_bench/registry.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bf1d70b73019164a","mcp_get_code":{"code_sha256":"bf1d70b73019164a"}},{"arxiv_id":"2510.16292","paper":"/paper/arxiv-2510-16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"SAI-Lab-NYU/QSVD","path":"fake_quant/eval_utilsdistllava.py","file_url":"https://github.com/SAI-Lab-NYU/QSVD/blob/HEAD/fake_quant/eval_utilsdistllava.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":"c768089cdb0d6d61","mcp_get_code":{"code_sha256":"c768089cdb0d6d61"}},{"arxiv_id":"2510.16292","paper":"/paper/arxiv-2510-16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"SAI-Lab-NYU/QSVD","path":"fake_quant/eval_utilsdistseed.py","file_url":"https://github.com/SAI-Lab-NYU/QSVD/blob/HEAD/fake_quant/eval_utilsdistseed.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":"8854b3767fe1bd32","mcp_get_code":{"code_sha256":"8854b3767fe1bd32"}},{"arxiv_id":"2510.16292","paper":"/paper/arxiv-2510-16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"SAI-Lab-NYU/QSVD","path":"fake_quant/eval_utilsdistsmolvlm.py","file_url":"https://github.com/SAI-Lab-NYU/QSVD/blob/HEAD/fake_quant/eval_utilsdistsmolvlm.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":"0ce6edaafba5a1ca","mcp_get_code":{"code_sha256":"0ce6edaafba5a1ca"}},{"arxiv_id":"2509.04202","paper":"/paper/arxiv-2509-04202","title":"Explicit and Implicit Data Augmentation for Social Event Detection","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"congboma/SED-Aug","path":"code/utils.py","file_url":"https://github.com/congboma/SED-Aug/blob/HEAD/code/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0c947eca966fd8a3","mcp_get_code":{"code_sha256":"0c947eca966fd8a3"}},{"arxiv_id":"2410.12865","paper":"/paper/elf-gym-evaluating-large-language-models","title":"ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Prediction","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lilyzhangyanlin/ELF-Gym","path":"evaluator/base.py","file_url":"https://github.com/Lilyzhangyanlin/ELF-Gym/blob/HEAD/evaluator/base.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0754af0fa72eaf46","mcp_get_code":{"code_sha256":"0754af0fa72eaf46"}},{"arxiv_id":"2307.08430","paper":"/paper/long-range-dependency-based-multi-layer","title":"Long-range Meta-path Search on Large-scale Heterogeneous Graphs","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jhl-hust/ldmlp","path":"hgb/utils.py","file_url":"https://github.com/jhl-hust/ldmlp/blob/HEAD/hgb/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bdd10a0559cd9f67","mcp_get_code":{"code_sha256":"bdd10a0559cd9f67"}},{"arxiv_id":"2203.14291","paper":"/paper/video-polyp-segmentation-a-deep-learning","title":"Video Polyp Segmentation: A Deep Learning Perspective","date":"2022-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gewelsji/vps","path":"eval/vps_evaluator.py","file_url":"https://github.com/gewelsji/vps/blob/HEAD/eval/vps_evaluator.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":"88d6754357faca2d","mcp_get_code":{"code_sha256":"88d6754357faca2d"}},{"arxiv_id":"2106.04530","paper":"/paper/learning-from-multiple-noisy-partial-labelers","title":"Learning from Multiple Noisy Partial Labelers","date":"2021-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"batsresearch/nplm","path":"nplm/plf/exec.py","file_url":"https://github.com/batsresearch/nplm/blob/HEAD/nplm/plf/exec.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"2e0222f1fd6d4471","mcp_get_code":{"code_sha256":"2e0222f1fd6d4471"}}]}