{"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/hash-args","entry":"hash_args","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":46,"n_papers_ran":45,"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":6,"n_samples_ran":2,"n_samples_fingerprinted":2,"n_places":51,"n_places_pointer_only":19,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":4},"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":"2608.26430","paper":"/paper/arxiv-2608-26430","title":"Fine-Tuning of Transformer models with Frames","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"vsingh-group/FrameFT","path":"lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/vsingh-group/FrameFT/blob/HEAD/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2608.10288","paper":"/paper/arxiv-2608-10288","title":"Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2606.05917","paper":"/paper/arxiv-2606-05917","title":"MEMORYCARD: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"NEUIR/MemoryCard","path":"lmms_eval/api/model.py","file_url":"https://github.com/NEUIR/MemoryCard/blob/HEAD/lmms_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2602.01649","paper":"/paper/arxiv-2602-01649","title":"Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"LivingFutureLab/CaCoVID","path":"lmms_eval/lmms_eval/api/model.py","file_url":"https://github.com/LivingFutureLab/CaCoVID/blob/HEAD/lmms_eval/lmms_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2601.22527","paper":"/paper/arxiv-2601-22527","title":"ρ-EOS: Training-free Bidirectional Variable-Length Control for Masked Diffusion LLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yjyddq/rho-EOS","path":"dllm_eval/api/model.py","file_url":"https://github.com/yjyddq/rho-EOS/blob/HEAD/dllm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2601.07645","paper":"/paper/arxiv-2601-07645","title":"PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"wzj1718/PlaM","path":"Vision-Token-Masking/lmms_eval/api/model.py","file_url":"https://github.com/wzj1718/PlaM/blob/HEAD/Vision-Token-Masking/lmms_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2601.02236","paper":"/paper/arxiv-2601-02236","title":"CD 4 LM: Consistency Distillation and aDaptive Decoding for Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"yihao-liang/CDLM","path":"evaluation/dllm_eval/api/model.py","file_url":"https://github.com/yihao-liang/CDLM/blob/HEAD/evaluation/dllm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2512.06866","paper":"/paper/arxiv-2512-06866","title":"Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"yu-lin-li/DyToK","path":"eval/lmms_eval/api/model.py","file_url":"https://github.com/yu-lin-li/DyToK/blob/HEAD/eval/lmms_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2505.13380","paper":"/paper/competesmoe-statistically-guaranteed-mixture","title":"CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2504.08165","paper":"/paper/findings-of-the-babylm-challenge-sample","title":"Findings of the BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"babylm/evaluation-pipeline","path":"lm_eval/api/model.py","file_url":"https://github.com/babylm/evaluation-pipeline/blob/HEAD/lm_eval/api/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de4e47a5e5126171","mcp_get_code":{"code_sha256":"de4e47a5e5126171"}},{"arxiv_id":"2504.06958","paper":"/paper/videochat-r1-enhancing-spatio-temporal","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","date":"2025-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/videochat-r1","path":"Videochat-R1/lmms-eval_videochat/lmms_eval/api/model.py","file_url":"https://github.com/opengvlab/videochat-r1/blob/HEAD/Videochat-R1/lmms-eval_videochat/lmms_eval/api/model.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2504.04715","paper":"/paper/are-you-getting-what-you-pay-for-auditing","title":"Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs","date":"2025-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunblaze-ucb/llm-api-audit","path":"benchmark/lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/sunblaze-ucb/llm-api-audit/blob/HEAD/benchmark/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2503.00555","paper":"/paper/2503-00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","date":"2025-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"git-disl/safety-tax","path":"eval/lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/git-disl/safety-tax/blob/HEAD/eval/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2502.14044","paper":"/paper/enhancing-cognition-and-explainability-of","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","date":"2025-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2502.12143","paper":"/paper/small-models-struggle-to-learn-from-strong","title":"Small Models Struggle to Learn from Strong Reasoners","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Small-Model-Gap/Small-Model-Learnability-Gap","path":"lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/Small-Model-Gap/Small-Model-Learnability-Gap/blob/HEAD/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2502.09992","paper":"/paper/large-language-diffusion-models","title":"Large Language Diffusion Models","date":"2025-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2501.19393","paper":"/paper/s1-simple-test-time-scaling","title":"s1: Simple test-time scaling","date":"2025-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"simplescaling/s1","path":"eval/lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/simplescaling/s1/blob/HEAD/eval/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2412.14171","paper":"/paper/thinking-in-space-how-multimodal-large","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","date":"2024-12-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vision-x-nyu/thinking-in-space","path":"lmms_eval/api/model.py","file_url":"https://github.com/vision-x-nyu/thinking-in-space/blob/HEAD/lmms_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2411.10606","paper":"/paper/amoeballm-constructing-any-shape-large","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","date":"2024-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GATECH-EIC/AmoebaLLM","path":"lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/GATECH-EIC/AmoebaLLM/blob/HEAD/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2411.02688","paper":"/paper/on-the-loss-of-context-awareness-in-general","title":"On the Loss of Context-awareness in General Instruction Fine-tuning","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2410.05357","paper":"/paper/model-glue-democratized-llm-scaling-for-a","title":"Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Model-GLUE/Model-GLUE","path":"lm_eval/api/model.py","file_url":"https://github.com/Model-GLUE/Model-GLUE/blob/HEAD/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2409.14485","paper":"/paper/video-xl-extra-long-vision-language-model-for","title":"Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding","date":"2024-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2409.06851","paper":"/paper/lime-m-less-is-more-for-evaluation-of-mllms","title":"LIME: Less Is More for MLLM Evaluation","date":"2024-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kangreen0210/lime","path":"lmms_eval/api/model.py","file_url":"https://github.com/kangreen0210/lime/blob/HEAD/lmms_eval/api/model.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2408.17267","paper":"/paper/urbench-a-comprehensive-benchmark-for","title":"UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios","date":"2024-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendatalab/urbench","path":"lmms_eval/api/model.py","file_url":"https://github.com/opendatalab/urbench/blob/HEAD/lmms_eval/api/model.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2407.10223","paper":"/paper/practical-unlearning-for-large-language","title":"On Large Language Model Continual Unlearning","date":"2024-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2407.03856","paper":"/paper/q-adapter-training-your-llm-adapter-as-a","title":"Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mansicer/Q-Adapter","path":"lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/mansicer/Q-Adapter/blob/HEAD/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2406.16635","paper":"/paper/shadowllm-predictor-based-contextual-sparsity","title":"ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abdelfattah-lab/shadow_llm","path":"llm-interpret/lm-evaluation-harness/lm_eval/base.py","file_url":"https://github.com/abdelfattah-lab/shadow_llm/blob/HEAD/llm-interpret/lm-evaluation-harness/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2406.11687","paper":"/paper/tokenization-falling-short-the-curse-of","title":"Tokenization Falling Short: On Subword Robustness in Large Language Models","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"floatai/tkeval","path":"evaluation/lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/floatai/tkeval/blob/HEAD/evaluation/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2406.10594","paper":"/paper/blockpruner-fine-grained-pruning-for-large","title":"BlockPruner: Fine-grained Pruning for Large Language Models","date":"2024-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MrGGLS/BlockPruner","path":"lm_eval/lm_eval/api/model.py","file_url":"https://github.com/MrGGLS/BlockPruner/blob/HEAD/lm_eval/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2406.10594","paper":"/paper/blockpruner-fine-grained-pruning-for-large","title":"BlockPruner: Fine-grained Pruning for Large Language Models","date":"2024-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MrGGLS/BlockPruner","path":"lm_eval/lm_eval/base.py","file_url":"https://github.com/MrGGLS/BlockPruner/blob/HEAD/lm_eval/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2405.09055","paper":"/paper/a-safety-realignment-framework-via-subspace","title":"A safety realignment framework via subspace-oriented model fusion for large language models","date":"2024-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinykou/safety_realignment","path":"lm_eval/api/model.py","file_url":"https://github.com/xinykou/safety_realignment/blob/HEAD/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2405.07938","paper":"/paper/econlogicqa-a-question-answering-benchmark","title":"EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yinzhu-quan/lm-evaluation-harness","path":"lm_eval/api/model.py","file_url":"https://github.com/yinzhu-quan/lm-evaluation-harness/blob/HEAD/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2404.01365","paper":"/paper/prompt-prompted-mixture-of-experts-for","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation","date":"2024-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hdong920/griffin","path":"src/lm_eval/base.py","file_url":"https://github.com/hdong920/griffin/blob/HEAD/src/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2402.16775","paper":"/paper/a-comprehensive-evaluation-of-quantization","title":"A Comprehensive Evaluation of Quantization Strategies for Large Language Models","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cordercorder/quant_eval","path":"quant/SpQR/lm-evaluation-harness/lm_eval/base.py","file_url":"https://github.com/cordercorder/quant_eval/blob/HEAD/quant/SpQR/lm-evaluation-harness/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2402.11295","paper":"/paper/onebit-towards-extremely-low-bit-large","title":"OneBit: Towards Extremely Low-bit Large Language Models","date":"2024-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xuyuzhuang11/OneBit","path":"evaluation/lm_eval/base.py","file_url":"https://github.com/xuyuzhuang11/OneBit/blob/HEAD/evaluation/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2402.09398","paper":"/paper/get-more-with-less-synthesizing-recurrence","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hdong920/less","path":"src/lm_eval/base.py","file_url":"https://github.com/hdong920/less/blob/HEAD/src/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2312.15838","paper":"/paper/secqa-a-concise-question-answering-dataset","title":"SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security","date":"2023-12-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zefang-liu/lm-evaluation-harness","path":"lm_eval/api/model.py","file_url":"https://github.com/zefang-liu/lm-evaluation-harness/blob/HEAD/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2310.05620","paper":"/paper/laiw-a-chinese-legal-large-language-models","title":"LAiW: A Chinese Legal Large Language Models Benchmark","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dai-shen/laiw","path":"src/financial-evaluation/lm_eval/base.py","file_url":"https://github.com/dai-shen/laiw/blob/HEAD/src/financial-evaluation/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2305.14493","paper":"/paper/prompt-position-really-matters-in-few-shot","title":"Do prompt positions really matter?","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"milliemaoo/prompt-position","path":"lm_eval/base.py","file_url":"https://github.com/milliemaoo/prompt-position/blob/HEAD/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2304.01089","paper":"/paper/rptq-reorder-based-post-training-quantization","title":"RPTQ: Reorder-based Post-training Quantization for Large Language Models","date":"2023-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hahnyuan/rptq4llm","path":"models/models_utils.py","file_url":"https://github.com/hahnyuan/rptq4llm/blob/HEAD/models/models_utils.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2303.17003","paper":"/paper/evaluating-gpt-3-5-and-gpt-4-models-on","title":"Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams","date":"2023-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"piresramon/gpt-4-enem","path":"lm_eval/base.py","file_url":"https://github.com/piresramon/gpt-4-enem/blob/HEAD/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2110.04374","paper":"/paper/a-few-more-examples-may-be-worth-billions-of","title":"A Few More Examples May Be Worth Billions of Parameters","date":"2021-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuvalkirstain/lm-evaluation-harness","path":"lm_eval/base.py","file_url":"https://github.com/yuvalkirstain/lm-evaluation-harness/blob/HEAD/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2005.14165","paper":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Sypherd/lm-evaluation-harness","path":"lm_eval/api/model.py","file_url":"https://github.com/Sypherd/lm-evaluation-harness/blob/HEAD/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2005.14165","paper":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vilm-ai/viet-llm-eval","path":"lm_eval/api/model.py","file_url":"https://github.com/vilm-ai/viet-llm-eval/blob/HEAD/lm_eval/api/model.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2005.14165","paper":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neuralmagic/lm-evaluation-harness","path":"lm_eval/api/model.py","file_url":"https://github.com/neuralmagic/lm-evaluation-harness/blob/HEAD/lm_eval/api/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26519d22d8af6d48","mcp_get_code":{"code_sha256":"26519d22d8af6d48"}},{"arxiv_id":"2005.14165","paper":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EleutherAI/lm_evaluation_harness","path":"lm_eval/api/model.py","file_url":"https://github.com/EleutherAI/lm_evaluation_harness/blob/HEAD/lm_eval/api/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"72f5b387b64e9d9b","mcp_get_code":{"code_sha256":"72f5b387b64e9d9b"}},{"arxiv_id":"2005.14165","paper":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"juletx/lm-evaluation-harness","path":"lm_eval/api/model.py","file_url":"https://github.com/juletx/lm-evaluation-harness/blob/HEAD/lm_eval/api/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e9d38ecacd03fa7","mcp_get_code":{"code_sha256":"3e9d38ecacd03fa7"}},{"arxiv_id":"openreview_QrC8OgQyOI","paper":null,"title":"arXiv:openreview_QrC8OgQyOI","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"viiika/Prism","path":"LLaDA/LLaDA_Prism/dllm_eval/api/model.py","file_url":"https://github.com/viiika/Prism/blob/HEAD/LLaDA/LLaDA_Prism/dllm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2025.naacl-long.237","paper":null,"title":"arXiv:2025.naacl-long.237","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nbasyl/LLM-FP4","path":"lm_eval/base.py","file_url":"https://github.com/nbasyl/LLM-FP4/blob/HEAD/lm_eval/base.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":"ea06eaae4fc1eaf0","mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}},{"arxiv_id":"2025.findings-acl.744","paper":null,"title":"arXiv:2025.findings-acl.744","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"szu-tera/RankedVotingSC","path":"lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/szu-tera/RankedVotingSC/blob/HEAD/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}},{"arxiv_id":"2024.findings-emnlp.86","paper":null,"title":"arXiv:2024.findings-emnlp.86","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"FloatAI/TKEval","path":"evaluation/lm-evaluation-harness/lm_eval/api/model.py","file_url":"https://github.com/FloatAI/TKEval/blob/HEAD/evaluation/lm-evaluation-harness/lm_eval/api/model.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":"20a7cc804eb22661","mcp_get_code":{"code_sha256":"20a7cc804eb22661"}}]}