{"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/normalize-zh-answer","entry":"normalize_zh_answer","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":32,"n_papers_ran":32,"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":2,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":34,"n_places_pointer_only":9,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":0},"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":"2604.10900","paper":"/paper/arxiv-2604-10900","title":"CASK: Core-Aware Selective KV Compression for Reasoning Traces","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"THUDM/LongBench","path":"LongBench/metrics.py","file_url":"https://github.com/THUDM/LongBench/blob/HEAD/LongBench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2603.04759","paper":"/paper/arxiv-2603-04759","title":"Stacked from One: Multi-Scale Self-Injection for Context Window Extension","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Clement25/SharedLLM","path":"LongBenchTest/metrics.py","file_url":"https://github.com/Clement25/SharedLLM/blob/HEAD/LongBenchTest/metrics.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":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2509.19633","paper":"/paper/arxiv-2509-19633","title":"Mamba Modulation On the Length Generalization of Mamba","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"gnepul-ace/mamba_modulation","path":"Mamba/LongBench/metrics.py","file_url":"https://github.com/gnepul-ace/mamba_modulation/blob/HEAD/Mamba/LongBench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2503.10571","paper":"/paper/radar-fast-long-context-decoding-for-any","title":"Radar: Fast Long-Context Decoding for Any Transformer","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"borealisai/radar-decoding","path":"research/longbench/longbench.py","file_url":"https://github.com/borealisai/radar-decoding/blob/HEAD/research/longbench/longbench.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"LGPL-3.0","inline_ok":false,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2411.09688","paper":"/paper/squeezed-attention-accelerating-long-context","title":"Squeezed Attention: Accelerating Long Context Length LLM Inference","date":"2024-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SqueezeAILab/SqueezedAttention","path":"LongBench/metrics.py","file_url":"https://github.com/SqueezeAILab/SqueezedAttention/blob/HEAD/LongBench/metrics.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":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2410.19258","paper":"/paper/not-all-heads-matter-a-head-level-kv-cache","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","date":"2024-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fyyfu/headkv","path":"metrics.py","file_url":"https://github.com/fyyfu/headkv/blob/HEAD/metrics.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":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2410.13846","paper":"/paper/simlayerkv-a-simple-framework-for-layer-level","title":"SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/simlayerkv","path":"LongBench/metrics.py","file_url":"https://github.com/sail-sg/simlayerkv/blob/HEAD/LongBench/metrics.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":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2410.05076","paper":"/paper/tidaldecode-fast-and-accurate-llm-decoding","title":"TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DerrickYLJ/TidalDecode","path":"experiments/LongBench/metrics.py","file_url":"https://github.com/DerrickYLJ/TidalDecode/blob/HEAD/experiments/LongBench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2409.20288","paper":"/paper/lexeval-a-comprehensive-chinese-legal","title":"LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CSHaitao/LexEval","path":"code/evaluation/process.py","file_url":"https://github.com/CSHaitao/LexEval/blob/HEAD/code/evaluation/process.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2409.17422","paper":"/paper/discovering-the-gems-in-early-layers","title":"Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforceairesearch/gemfilter","path":"eval/LongBench/metrics.py","file_url":"https://github.com/salesforceairesearch/gemfilter/blob/HEAD/eval/LongBench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2409.12181","paper":"/paper/a-controlled-study-on-long-context-extension","title":"A Controlled Study on Long Context Extension and Generalization in LLMs","date":"2024-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leooyii/lceg","path":"longbench/metrics.py","file_url":"https://github.com/leooyii/lceg/blob/HEAD/longbench/metrics.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":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2408.11745","paper":"/paper/focusllm-scaling-llm-s-context-by-parallel","title":"FocusLLM: Precise Understanding of Long Context by Dynamic Condensing","date":"2024-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leezythu/focusllm","path":"infbench_src/compute_scores.py","file_url":"https://github.com/leezythu/focusllm/blob/HEAD/infbench_src/compute_scores.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f62b4d2a31aa1081","mcp_get_code":{"code_sha256":"f62b4d2a31aa1081"}},{"arxiv_id":"2408.07092","paper":"/paper/post-training-sparse-attention-with-double","title":"Post-Training Sparse Attention with Double Sparsity","date":"2024-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andy-yang-1/doublesparse","path":"LongBench/metrics.py","file_url":"https://github.com/andy-yang-1/doublesparse/blob/HEAD/LongBench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2407.13803","paper":"/paper/less-is-more-sparse-watermarking-in-llms-with","title":"Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mail-research/sparse-llm-watermarking","path":"metrics.py","file_url":"https://github.com/mail-research/sparse-llm-watermarking/blob/HEAD/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2407.09450","paper":"/paper/human-like-episodic-memory-for-infinite","title":"Human-like Episodic Memory for Infinite Context LLMs","date":"2024-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"em-llm/EM-LLM-model","path":"benchmark/infinitebench_eval.py","file_url":"https://github.com/em-llm/EM-LLM-model/blob/HEAD/benchmark/infinitebench_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f62b4d2a31aa1081","mcp_get_code":{"code_sha256":"f62b4d2a31aa1081"}},{"arxiv_id":"2407.01527","paper":"/paper/kv-cache-compression-but-what-must-we-give-in","title":"KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"henryzhongsc/longctx_bench","path":"eval/longbench_utils/metrics.py","file_url":"https://github.com/henryzhongsc/longctx_bench/blob/HEAD/eval/longbench_utils/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2406.10774","paper":"/paper/quest-query-aware-sparsity-for-efficient-long","title":"Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference","date":"2024-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mit-han-lab/Quest","path":"evaluation/LongBench/metrics.py","file_url":"https://github.com/mit-han-lab/Quest/blob/HEAD/evaluation/LongBench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2406.07528","paper":"/paper/quickllama-query-aware-inference-acceleration","title":"QuickLLaMA: Query-aware Inference Acceleration for Large Language Models","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/q-llm","path":"benchmark/metrics.py","file_url":"https://github.com/dvlab-research/q-llm/blob/HEAD/benchmark/metrics.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":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2406.07528","paper":"/paper/quickllama-query-aware-inference-acceleration","title":"QuickLLaMA: Query-aware Inference Acceleration for Large Language Models","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/q-llm","path":"benchmark/infinitebench_eval.py","file_url":"https://github.com/dvlab-research/q-llm/blob/HEAD/benchmark/infinitebench_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f62b4d2a31aa1081","mcp_get_code":{"code_sha256":"f62b4d2a31aa1081"}},{"arxiv_id":"2406.03482","paper":"/paper/qjl-1-bit-quantized-jl-transform-for-kv-cache","title":"QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amirzandieh/qjl","path":"metrics.py","file_url":"https://github.com/amirzandieh/qjl/blob/HEAD/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2406.02536","paper":"/paper/mitigate-position-bias-in-large-language","title":"Mitigate Position Bias in Large Language Models via Scaling a Single Dimension","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PositionalHidden/PositionalHidden","path":"experiments/run_on_longbench/metrics.py","file_url":"https://github.com/PositionalHidden/PositionalHidden/blob/HEAD/experiments/run_on_longbench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2404.14469","paper":"/paper/snapkv-llm-knows-what-you-are-looking-for","title":"SnapKV: LLM Knows What You are Looking for Before Generation","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fasterdecoding/snapkv","path":"experiments/LongBench/metrics.py","file_url":"https://github.com/fasterdecoding/snapkv/blob/HEAD/experiments/LongBench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2404.04793","paper":"/paper/squeezeattention-2d-management-of-kv-cache-in","title":"SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget","date":"2024-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hetailang/squeezeattention","path":"metrics.py","file_url":"https://github.com/hetailang/squeezeattention/blob/HEAD/metrics.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":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2403.03514","paper":"/paper/clongeval-a-chinese-benchmark-for-evaluating","title":"CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models","date":"2024-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zexuanqiu/clongeval","path":"metrics.py","file_url":"https://github.com/zexuanqiu/clongeval/blob/HEAD/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2402.04617","paper":"/paper/infllm-unveiling-the-intrinsic-capacity-of","title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","date":"2024-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/infllm","path":"benchmark/metrics.py","file_url":"https://github.com/thunlp/infllm/blob/HEAD/benchmark/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2402.04617","paper":"/paper/infllm-unveiling-the-intrinsic-capacity-of","title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","date":"2024-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/infllm","path":"benchmark/infinitebench_eval.py","file_url":"https://github.com/thunlp/infllm/blob/HEAD/benchmark/infinitebench_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f62b4d2a31aa1081","mcp_get_code":{"code_sha256":"f62b4d2a31aa1081"}},{"arxiv_id":"2402.02750","paper":"/paper/kivi-a-tuning-free-asymmetric-2bit","title":"KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jy-yuan/kivi","path":"metrics.py","file_url":"https://github.com/jy-yuan/kivi/blob/HEAD/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2311.09198","paper":"/paper/never-lost-in-the-middle-improving-large","title":"Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hejunqing/never-lost-in-the-middle","path":"LongBench/src/metrics.py","file_url":"https://github.com/hejunqing/never-lost-in-the-middle/blob/HEAD/LongBench/src/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2311.04934","paper":"/paper/prompt-cache-modular-attention-reuse-for-low","title":"Prompt Cache: Modular Attention Reuse for Low-Latency Inference","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yale-sys/prompt-cache","path":"metrics.py","file_url":"https://github.com/yale-sys/prompt-cache/blob/HEAD/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"openreview_trSWJ99WzS","paper":null,"title":"arXiv:openreview_trSWJ99WzS","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"DerrickYLJ/LessIsMore","path":"experiments/LongBench/metrics.py","file_url":"https://github.com/DerrickYLJ/LessIsMore/blob/HEAD/experiments/LongBench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2025.findings-emnlp.429","paper":null,"title":"arXiv:2025.findings-emnlp.429","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zhzihao/QPruningKV","path":"metrics.py","file_url":"https://github.com/zhzihao/QPruningKV/blob/HEAD/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2025.emnlp-main.443","paper":null,"title":"arXiv:2025.emnlp-main.443","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"adlnlp/Gali","path":"longbench/metrics.py","file_url":"https://github.com/adlnlp/Gali/blob/HEAD/longbench/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}},{"arxiv_id":"2025.acl-long.1500","paper":null,"title":"arXiv:2025.acl-long.1500","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"leezythu/FocusLLM","path":"infbench_src/compute_scores.py","file_url":"https://github.com/leezythu/FocusLLM/blob/HEAD/infbench_src/compute_scores.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f62b4d2a31aa1081","mcp_get_code":{"code_sha256":"f62b4d2a31aa1081"}},{"arxiv_id":"2024.findings-emnlp.230","paper":null,"title":"arXiv:2024.findings-emnlp.230","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"zexuanqiu/CLongEval","path":"metrics.py","file_url":"https://github.com/zexuanqiu/CLongEval/blob/HEAD/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c5c581f9264c810","mcp_get_code":{"code_sha256":"8c5c581f9264c810"}}]}