{"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/load-result","entry":"load_result","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":16,"n_papers_ran":7,"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":17,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":18,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"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":"2609.02264","paper":"/paper/arxiv-2609-02264","title":"Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"jinxiy1104/CodebookAgent","path":"experiments/run_gsm8k.py","file_url":"https://github.com/jinxiy1104/CodebookAgent/blob/HEAD/experiments/run_gsm8k.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f56ba650da6274d1","mcp_get_code":{"code_sha256":"f56ba650da6274d1"}},{"arxiv_id":"2609.02264","paper":"/paper/arxiv-2609-02264","title":"Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"jinxiy1104/CodebookAgent","path":"experiments/run_math.py","file_url":"https://github.com/jinxiy1104/CodebookAgent/blob/HEAD/experiments/run_math.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bcde03579f1c0bee","mcp_get_code":{"code_sha256":"bcde03579f1c0bee"}},{"arxiv_id":"2609.02264","paper":"/paper/arxiv-2609-02264","title":"Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"jinxiy1104/CodebookAgent","path":"experiments/run_mmlu.py","file_url":"https://github.com/jinxiy1104/CodebookAgent/blob/HEAD/experiments/run_mmlu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ea6dc23b572af8d8","mcp_get_code":{"code_sha256":"ea6dc23b572af8d8"}},{"arxiv_id":"2607.15176","paper":"/paper/arxiv-2607-15176","title":"Benchmarking Multimodal Large Language Models for Scientific Visualization Literacy","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"patdmp/mllm-scivis-lit-benchmark","path":"src/evaluate.py","file_url":"https://github.com/patdmp/mllm-scivis-lit-benchmark/blob/HEAD/src/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"976e8ac2f2a36a13","mcp_get_code":{"code_sha256":"976e8ac2f2a36a13"}},{"arxiv_id":"2605.25816","paper":"/paper/arxiv-2605-25816","title":"Fine-Tuning Over Architectural Complexity: Broad-Coverage PII Detection on PIIBench with DeBERTa","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"pritesh-2711/pii-bench","path":"analyze_full_test_comparison.py","file_url":"https://github.com/pritesh-2711/pii-bench/blob/HEAD/analyze_full_test_comparison.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"74f51b209e69852e","mcp_get_code":{"code_sha256":"74f51b209e69852e"}},{"arxiv_id":"2602.05134","paper":"/paper/arxiv-2602-05134","title":"SEMPIPES -Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"noahho/CAAFE","path":"caafe/evaluate.py","file_url":"https://github.com/noahho/CAAFE/blob/HEAD/caafe/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"29bb04a164941e13","mcp_get_code":{"code_sha256":"29bb04a164941e13"}},{"arxiv_id":"2502.11133","paper":"/paper/masrouter-learning-to-route-llms-for-multi","title":"MasRouter: Learning to Route LLMs for Multi-Agent Systems","date":"2025-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yanweiyue/masrouter","path":"Experiments/run_gsm8k.py","file_url":"https://github.com/yanweiyue/masrouter/blob/HEAD/Experiments/run_gsm8k.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":"bcde03579f1c0bee","mcp_get_code":{"code_sha256":"bcde03579f1c0bee"}},{"arxiv_id":"2410.12705","paper":"/paper/worldcuisines-a-massive-scale-benchmark-for","title":"WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"worldcuisines/worldcuisines","path":"evaluation/score/score.py","file_url":"https://github.com/worldcuisines/worldcuisines/blob/HEAD/evaluation/score/score.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":"d2fb3f56c8a5c3b4","mcp_get_code":{"code_sha256":"d2fb3f56c8a5c3b4"}},{"arxiv_id":"2410.09870","paper":"/paper/chroknowledge-unveiling-chronological","title":"ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dmis-lab/chroknowledge","path":"sources/process.py","file_url":"https://github.com/dmis-lab/chroknowledge/blob/HEAD/sources/process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8b2d62b047d63fa4","mcp_get_code":{"code_sha256":"8b2d62b047d63fa4"}},{"arxiv_id":"2410.06097","paper":"/paper/decoding-decoded-understanding-hyperparameter","title":"Decoding Decoded: Understanding Hyperparameter Effects in Open-Ended Text Generation","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yecanlee/decoding-decoded","path":"utils/compute_diversity.py","file_url":"https://github.com/yecanlee/decoding-decoded/blob/HEAD/utils/compute_diversity.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":"b38f1bc3e3fa73b1","mcp_get_code":{"code_sha256":"b38f1bc3e3fa73b1"}},{"arxiv_id":"2404.15004","paper":"/paper/taxi-evaluating-categorical-knowledge-editing","title":"TAXI: Evaluating Categorical Knowledge Editing for Language Models","date":"2024-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"derekpowell/taxi","path":"benchmark.py","file_url":"https://github.com/derekpowell/taxi/blob/HEAD/benchmark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"108f10fc0bb72b90","mcp_get_code":{"code_sha256":"108f10fc0bb72b90"}},{"arxiv_id":"2402.16823","paper":"/paper/language-agents-as-optimizable-graphs","title":"Language Agents as Optimizable Graphs","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"metauto-ai/gptswarm","path":"experiments/run_humaneval.py","file_url":"https://github.com/metauto-ai/gptswarm/blob/HEAD/experiments/run_humaneval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2dd39bccea7e9386","mcp_get_code":{"code_sha256":"2dd39bccea7e9386"}},{"arxiv_id":"2402.02175","paper":"/paper/enhancing-complex-question-answering-over","title":"Enhancing Complex Question Answering over Knowledge Graphs through Evidence Pattern Retrieval","date":"2024-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nju-websoft/epr-kgqa","path":"NSM_H/integrate_results.py","file_url":"https://github.com/nju-websoft/epr-kgqa/blob/HEAD/NSM_H/integrate_results.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":"e96dad361f1ffebc","mcp_get_code":{"code_sha256":"e96dad361f1ffebc"}},{"arxiv_id":"2210.14140","paper":"/paper/contrastive-search-is-what-you-need-for","title":"Contrastive Search Is What You Need For Neural Text Generation","date":"2022-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YecanLee/Adaptive-Contrastive-Search","path":"measure_coherence.py","file_url":"https://github.com/YecanLee/Adaptive-Contrastive-Search/blob/HEAD/measure_coherence.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":"65983de78a3eea7d","mcp_get_code":{"code_sha256":"65983de78a3eea7d"}},{"arxiv_id":"2208.10291","paper":"/paper/efficient-planning-in-a-compact-latent-action","title":"Efficient Planning in a Compact Latent Action Space","date":"2022-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengyaoJiang/latentplan","path":"plotting/read_results.py","file_url":"https://github.com/ZhengyaoJiang/latentplan/blob/HEAD/plotting/read_results.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":"9a6f4af7dbd0084d","mcp_get_code":{"code_sha256":"9a6f4af7dbd0084d"}},{"arxiv_id":"2010.06599","paper":"/paper/quantum-autoencoders-with-enhanced-data","title":"Quantum autoencoders with enhanced data encoding","date":null,"month_inferred_from_arxiv_id":"2020-10","title_source":"archive","repo":"Quantum-TII/qibo","path":"src/qibo/result.py","file_url":"https://github.com/Quantum-TII/qibo/blob/HEAD/src/qibo/result.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":"247a0a010ba1ded1","mcp_get_code":{"code_sha256":"247a0a010ba1ded1"}},{"arxiv_id":"2003.06222","paper":"/paper/an-evaluation-of-change-point-detection","title":"An Evaluation of Change Point Detection Algorithms","date":"2020-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alan-turing-institute/TCPD","path":"utils/plot_dataset.py","file_url":"https://github.com/alan-turing-institute/TCPD/blob/HEAD/utils/plot_dataset.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":"e760a298613383f4","mcp_get_code":{"code_sha256":"e760a298613383f4"}},{"arxiv_id":"ijcai2025_0843","paper":null,"title":"arXiv:ijcai2025_0843","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wason981/Frequency-Fingerprinting","path":"utils.py","file_url":"https://github.com/wason981/Frequency-Fingerprinting/blob/HEAD/utils.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":"7ef4c01a7b99198e","mcp_get_code":{"code_sha256":"7ef4c01a7b99198e"}}]}