{"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-tokenizer","entry":"load_tokenizer","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":66,"n_papers_ran":13,"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":65,"n_samples_ran":12,"n_samples_fingerprinted":0,"n_places":68,"n_places_pointer_only":22,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":12,"unverified":53},"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":"2608.12149","paper":"/paper/arxiv-2608-12149","title":"Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"StartLuxLabs/Massive-Activations-HLA","path":"src/massive_activations_hla/capture/model_loading.py","file_url":"https://github.com/StartLuxLabs/Massive-Activations-HLA/blob/HEAD/src/massive_activations_hla/capture/model_loading.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b04b5f6e4343de9","mcp_get_code":{"code_sha256":"4b04b5f6e4343de9"}},{"arxiv_id":"2607.24688","paper":"/paper/arxiv-2607-24688","title":"Beyond Scale and Generation: Understanding Language Model-based Entity Matching","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"Jantory/llm-trained-matcher","path":"run_cross_dataset.py","file_url":"https://github.com/Jantory/llm-trained-matcher/blob/HEAD/run_cross_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b539874a305789f6","mcp_get_code":{"code_sha256":"b539874a305789f6"}},{"arxiv_id":"2607.19510","paper":"/paper/arxiv-2607-19510","title":"Total Variation Distance Estimation in Autoregressive Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"XunZhiyang/llm-tv-estimation","path":"experiments/tv_estimate.py","file_url":"https://github.com/XunZhiyang/llm-tv-estimation/blob/HEAD/experiments/tv_estimate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6348c83ab01fb9bd","mcp_get_code":{"code_sha256":"6348c83ab01fb9bd"}},{"arxiv_id":"2606.22305","paper":"/paper/arxiv-2606-22305","title":"Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Richard-zrx/ADS","path":"src/model_utils.py","file_url":"https://github.com/Richard-zrx/ADS/blob/HEAD/src/model_utils.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":"a079eb7fd6d1a19a","mcp_get_code":{"code_sha256":"a079eb7fd6d1a19a"}},{"arxiv_id":"2606.08705","paper":"/paper/arxiv-2606-08705","title":"Analyzing the Correlation Between Hallucinations and Knowledge Conflicts in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"llaraspata/HallucinationDetection","path":"src/model/utils.py","file_url":"https://github.com/llaraspata/HallucinationDetection/blob/HEAD/src/model/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f394e98c42552fb","mcp_get_code":{"code_sha256":"6f394e98c42552fb"}},{"arxiv_id":"2605.29796","paper":"/paper/arxiv-2605-29796","title":"SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"XMUDeepLIT/SAAS","path":"search/generate_with_search.py","file_url":"https://github.com/XMUDeepLIT/SAAS/blob/HEAD/search/generate_with_search.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":"39d6a0aa1eaffc16","mcp_get_code":{"code_sha256":"39d6a0aa1eaffc16"}},{"arxiv_id":"2605.26110","paper":"/paper/arxiv-2605-26110","title":"PRISM: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"LAMDA-CL/Prism","path":"backbone/shared/model_loading.py","file_url":"https://github.com/LAMDA-CL/Prism/blob/HEAD/backbone/shared/model_loading.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f0205bc9e1110e2","mcp_get_code":{"code_sha256":"0f0205bc9e1110e2"}},{"arxiv_id":"2605.16339","paper":"/paper/arxiv-2605-16339","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"shunchang-liu/pisa","path":"src/detect_instability.py","file_url":"https://github.com/shunchang-liu/pisa/blob/HEAD/src/detect_instability.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0463d37512d2fda5","mcp_get_code":{"code_sha256":"0463d37512d2fda5"}},{"arxiv_id":"2605.16339","paper":"/paper/arxiv-2605-16339","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"shunchang-liu/pisa","path":"src/evaluate_rb2.py","file_url":"https://github.com/shunchang-liu/pisa/blob/HEAD/src/evaluate_rb2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"472b67e46caa5c7d","mcp_get_code":{"code_sha256":"472b67e46caa5c7d"}},{"arxiv_id":"2605.16339","paper":"/paper/arxiv-2605-16339","title":"Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"shunchang-liu/pisa","path":"src/raw_feature_steering.py","file_url":"https://github.com/shunchang-liu/pisa/blob/HEAD/src/raw_feature_steering.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b155936dd212497a","mcp_get_code":{"code_sha256":"b155936dd212497a"}},{"arxiv_id":"2605.07315","paper":"/paper/arxiv-2605-07315","title":"LaTER: Efficient Test-Time Reasoning via Latent Exploration and Explicit Verification","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"TioeAre/LaTER","path":"later/src/analysis/plot_entropy_reasoning_curves.py","file_url":"https://github.com/TioeAre/LaTER/blob/HEAD/later/src/analysis/plot_entropy_reasoning_curves.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":"0e0355e6f4139423","mcp_get_code":{"code_sha256":"0e0355e6f4139423"}},{"arxiv_id":"2604.27599","paper":"/paper/arxiv-2604-27599","title":"One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ejbito/InvariRank","path":"invarirank/modeling.py","file_url":"https://github.com/ejbito/InvariRank/blob/HEAD/invarirank/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6d2f32351f12ba2b","mcp_get_code":{"code_sha256":"6d2f32351f12ba2b"}},{"arxiv_id":"2602.17653","paper":"/paper/arxiv-2602-17653","title":"Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Iskar-Deng/DAM-learning","path":"evaluation/eval_minpairs_acc.py","file_url":"https://github.com/Iskar-Deng/DAM-learning/blob/HEAD/evaluation/eval_minpairs_acc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4bb1111352e82926","mcp_get_code":{"code_sha256":"4bb1111352e82926"}},{"arxiv_id":"2602.00723","paper":"/paper/arxiv-2602-00723","title":"Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"AI21Labs/in-context-ralm","path":"ralm/model_utils.py","file_url":"https://github.com/AI21Labs/in-context-ralm/blob/HEAD/ralm/model_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":"cdd42d9143f7e2cd","mcp_get_code":{"code_sha256":"cdd42d9143f7e2cd"}},{"arxiv_id":"2601.20357","paper":"/paper/arxiv-2601-20357","title":"TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"furiosa-ai/TABED","path":"tabed/modules/load_pretrained.py","file_url":"https://github.com/furiosa-ai/TABED/blob/HEAD/tabed/modules/load_pretrained.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"433fce01b1f7cb60","mcp_get_code":{"code_sha256":"433fce01b1f7cb60"}},{"arxiv_id":"2601.04537","paper":"/paper/arxiv-2601-04537","title":"Linear Dynamics in the RLVR Training of Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Miaow-Lab/RLVR-Linearity","path":"analysis/token_logprob/plot_token_logprob_linearity.py","file_url":"https://github.com/Miaow-Lab/RLVR-Linearity/blob/HEAD/analysis/token_logprob/plot_token_logprob_linearity.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"974078a91d3ec703","mcp_get_code":{"code_sha256":"974078a91d3ec703"}},{"arxiv_id":"2505.20128","paper":"/paper/iterative-self-incentivization-empowers-large","title":"Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mangopy/searchlm","path":"src/_entropy.py","file_url":"https://github.com/mangopy/searchlm/blob/HEAD/src/_entropy.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":"a3518bfc816435e7","mcp_get_code":{"code_sha256":"a3518bfc816435e7"}},{"arxiv_id":"2505.03912","paper":"/paper/openhelix-a-short-survey-empirical-analysis","title":"OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation","date":"2025-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenHelix-robot/OpenHelix","path":"data_preprocessing/preprocess_calvin_instructions.py","file_url":"https://github.com/OpenHelix-robot/OpenHelix/blob/HEAD/data_preprocessing/preprocess_calvin_instructions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1441fd48c61694c2","mcp_get_code":{"code_sha256":"1441fd48c61694c2"}},{"arxiv_id":"2503.16356","paper":"/paper/cake-circuit-aware-editing-enables","title":"CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners","date":"2025-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zjunlp/CaKE","path":"Analysis/utils.py","file_url":"https://github.com/zjunlp/CaKE/blob/HEAD/Analysis/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"91a41852736ee2f5","mcp_get_code":{"code_sha256":"91a41852736ee2f5"}},{"arxiv_id":"2408.07888","paper":"/paper/fine-tuning-large-language-models-with-human","title":"Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Oxford-AI-for-Society/human-learning-strategies","path":"training/fine_tuning/shared_utils.py","file_url":"https://github.com/Oxford-AI-for-Society/human-learning-strategies/blob/HEAD/training/fine_tuning/shared_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"12071bb621f4cba1","mcp_get_code":{"code_sha256":"12071bb621f4cba1"}},{"arxiv_id":"2406.17746","paper":"/paper/recite-reconstruct-recollect-memorization-in","title":"Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eleutherai/semantic-memorization","path":"inference.py","file_url":"https://github.com/eleutherai/semantic-memorization/blob/HEAD/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a1952e4763d93dba","mcp_get_code":{"code_sha256":"a1952e4763d93dba"}},{"arxiv_id":"2406.12775","paper":"/paper/hopping-too-late-exploring-the-limitations-of","title":"Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"edenbiran/HoppingTooLate","path":"src/utils.py","file_url":"https://github.com/edenbiran/HoppingTooLate/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8164e26307c3a60b","mcp_get_code":{"code_sha256":"8164e26307c3a60b"}},{"arxiv_id":"2406.12329","paper":"/paper/snap-unlearning-selective-knowledge-in-large","title":"Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brightjade/Opt-Out","path":"model.py","file_url":"https://github.com/brightjade/Opt-Out/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e34efa256660441","mcp_get_code":{"code_sha256":"3e34efa256660441"}},{"arxiv_id":"2405.19550","paper":"/paper/stress-testing-capability-elicitation-with","title":"Stress-Testing Capability Elicitation With Password-Locked Models","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FabienRoger/sandbagging","path":"sandbagging/basic_model_info.py","file_url":"https://github.com/FabienRoger/sandbagging/blob/HEAD/sandbagging/basic_model_info.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"009a49e66bf505da","mcp_get_code":{"code_sha256":"009a49e66bf505da"}},{"arxiv_id":"2405.17374","paper":"/paper/navigating-the-safety-landscape-measuring","title":"Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShengYun-Peng/llm-landscape","path":"src/llm/inference.py","file_url":"https://github.com/ShengYun-Peng/llm-landscape/blob/HEAD/src/llm/inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0308de63e8fa3250","mcp_get_code":{"code_sha256":"0308de63e8fa3250"}},{"arxiv_id":"2405.16802","paper":"/paper/autocv-empowering-reasoning-with-automated","title":"AutoPSV: Automated Process-Supervised Verifier","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rookie-joe/autocv","path":"data_annotation.py","file_url":"https://github.com/rookie-joe/autocv/blob/HEAD/data_annotation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"17243183193565ff","mcp_get_code":{"code_sha256":"17243183193565ff"}},{"arxiv_id":"2405.10260","paper":"/paper/keep-it-private-unsupervised-privatization-of","title":"Keep It Private: Unsupervised Privatization of Online Text","date":"2024-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csbao/kip-privatization","path":"src/generate.py","file_url":"https://github.com/csbao/kip-privatization/blob/HEAD/src/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5c7e9c77b1969bc7","mcp_get_code":{"code_sha256":"5c7e9c77b1969bc7"}},{"arxiv_id":"2405.07987","paper":"/paper/the-platonic-representation-hypothesis","title":"The Platonic Representation Hypothesis","date":"2024-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minyoungg/platonic-rep","path":"models.py","file_url":"https://github.com/minyoungg/platonic-rep/blob/HEAD/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c420a7cf0eb5ab96","mcp_get_code":{"code_sha256":"c420a7cf0eb5ab96"}},{"arxiv_id":"2404.16032","paper":"/paper/studying-large-language-model-behaviors-under","title":"Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kortukov/realistic_knowledge_conflicts","path":"src/model_utils.py","file_url":"https://github.com/kortukov/realistic_knowledge_conflicts/blob/HEAD/src/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"676e6dd24fe7e3b5","mcp_get_code":{"code_sha256":"676e6dd24fe7e3b5"}},{"arxiv_id":"2403.13027","paper":"/paper/towards-better-statistical-understanding-of","title":"Towards Better Statistical Understanding of Watermarking LLMs","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhongzecai/dualga","path":"WatermarkAlgorithm/utils/evaluation.py","file_url":"https://github.com/zhongzecai/dualga/blob/HEAD/WatermarkAlgorithm/utils/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ff61ef7b3942bc85","mcp_get_code":{"code_sha256":"ff61ef7b3942bc85"}},{"arxiv_id":"2403.01632","paper":"/paper/improving-llm-code-generation-with-grammar","title":"SynCode: LLM Generation with Grammar Augmentation","date":"2024-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uiuc-focal-lab/syncode","path":"syncode/common.py","file_url":"https://github.com/uiuc-focal-lab/syncode/blob/HEAD/syncode/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba0949d27e98d12e","mcp_get_code":{"code_sha256":"ba0949d27e98d12e"}},{"arxiv_id":"2403.01289","paper":"/paper/greed-is-all-you-need-an-evaluation-of","title":"Greed is All You Need: An Evaluation of Tokenizer Inference Methods","date":"2024-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"melelbgu/tokenizers_intrinsic_benchmark","path":"utils.py","file_url":"https://github.com/melelbgu/tokenizers_intrinsic_benchmark/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"07940de2cf1e2aa0","mcp_get_code":{"code_sha256":"07940de2cf1e2aa0"}},{"arxiv_id":"2403.00742","paper":"/paper/dialect-prejudice-predicts-ai-decisions-about","title":"Dialect prejudice predicts AI decisions about people's character, employability, and criminality","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"valentinhofmann/dialect-prejudice","path":"probing/helpers.py","file_url":"https://github.com/valentinhofmann/dialect-prejudice/blob/HEAD/probing/helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8300552b36c2b281","mcp_get_code":{"code_sha256":"8300552b36c2b281"}},{"arxiv_id":"2403.00815","paper":"/paper/ram-ehr-retrieval-augmentation-meets-clinical","title":"RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ritaranx/RAM-EHR","path":"model_src/utils.py","file_url":"https://github.com/ritaranx/RAM-EHR/blob/HEAD/model_src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd27c40f658addad","mcp_get_code":{"code_sha256":"dd27c40f658addad"}},{"arxiv_id":"2402.16914","paper":"/paper/drattack-prompt-decomposition-and","title":"DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xirui-li/drattack","path":"attack_prompt_data/uncensored_vicuna/uncensor.py","file_url":"https://github.com/xirui-li/drattack/blob/HEAD/attack_prompt_data/uncensored_vicuna/uncensor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f293af98d59df4d0","mcp_get_code":{"code_sha256":"f293af98d59df4d0"}},{"arxiv_id":"2402.16459","paper":"/paper/defending-llms-against-jailbreaking-attacks","title":"Defending LLMs against Jailbreaking Attacks via Backtranslation","date":"2024-02-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihanwang617/llm-jailbreaking-defense","path":"llm_jailbreaking_defense/models.py","file_url":"https://github.com/yihanwang617/llm-jailbreaking-defense/blob/HEAD/llm_jailbreaking_defense/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee5d16865ecd5e2b","mcp_get_code":{"code_sha256":"ee5d16865ecd5e2b"}},{"arxiv_id":"2402.15938","paper":"/paper/generalization-or-memorization-data","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihongdong/cdd-ted4llms","path":"TED.py","file_url":"https://github.com/yihongdong/cdd-ted4llms/blob/HEAD/TED.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1010269bb1357b3","mcp_get_code":{"code_sha256":"a1010269bb1357b3"}},{"arxiv_id":"2402.15131","paper":"/paper/interactive-kbqa-multi-turn-interactions-for","title":"Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models","date":"2024-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jimxionggm/interactive-kbqa","path":"predict/dialog_predictor.py","file_url":"https://github.com/jimxionggm/interactive-kbqa/blob/HEAD/predict/dialog_predictor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e9916eef46c98f37","mcp_get_code":{"code_sha256":"e9916eef46c98f37"}},{"arxiv_id":"2402.12030","paper":"/paper/towards-cross-tokenizer-distillation-the","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicolas-bzrd/llm-recipes","path":"models/models_utils.py","file_url":"https://github.com/nicolas-bzrd/llm-recipes/blob/HEAD/models/models_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15baf103a0b4554f","mcp_get_code":{"code_sha256":"15baf103a0b4554f"}},{"arxiv_id":"2402.10104","paper":"/paper/geoeval-benchmark-for-evaluating-llms-and","title":"GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geoeval/geoeval","path":"tool/tokenized_data.py","file_url":"https://github.com/geoeval/geoeval/blob/HEAD/tool/tokenized_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1c70706ba104f6dc","mcp_get_code":{"code_sha256":"1c70706ba104f6dc"}},{"arxiv_id":"2402.06596","paper":"/paper/understanding-the-weakness-of-large-language","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"androidarenaagent/androidarena","path":"agents/utils.py","file_url":"https://github.com/androidarenaagent/androidarena/blob/HEAD/agents/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ee661fad645d0f0","mcp_get_code":{"code_sha256":"9ee661fad645d0f0"}},{"arxiv_id":"2402.02823","paper":"/paper/evading-data-contamination-detection-for","title":"Evading Data Contamination Detection for Language Models is (too) Easy","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/malicious-contamination","path":"src/contamination/basic_model_loader.py","file_url":"https://github.com/eth-sri/malicious-contamination/blob/HEAD/src/contamination/basic_model_loader.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":"c29c23246ee520ad","mcp_get_code":{"code_sha256":"c29c23246ee520ad"}},{"arxiv_id":"2312.13772","paper":"/paper/on-task-performance-and-model-calibration","title":"On Task Performance and Model Calibration with Supervised and Self-Ensembled In-Context Learning","date":"2023-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/ensembled-sicl","path":"utils/load_model.py","file_url":"https://github.com/cambridgeltl/ensembled-sicl/blob/HEAD/utils/load_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"618ad395c8046ae0","mcp_get_code":{"code_sha256":"618ad395c8046ae0"}},{"arxiv_id":"2311.14479","paper":"/paper/controlled-text-generation-via-language-model","title":"Controlled Text Generation via Language Model Arithmetic","date":"2023-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/language-model-arithmetic","path":"src/model_arithmetic/basic_model_loader.py","file_url":"https://github.com/eth-sri/language-model-arithmetic/blob/HEAD/src/model_arithmetic/basic_model_loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c29c23246ee520ad","mcp_get_code":{"code_sha256":"c29c23246ee520ad"}},{"arxiv_id":"2310.14034","paper":"/paper/tree-prompting-efficient-task-adaptation","title":"Tree Prompting: Efficient Task Adaptation without Fine-Tuning","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csinva/tree-prompt","path":"treeprompt/llm_utils.py","file_url":"https://github.com/csinva/tree-prompt/blob/HEAD/treeprompt/llm_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfcb2eef36f5b7ab","mcp_get_code":{"code_sha256":"cfcb2eef36f5b7ab"}},{"arxiv_id":"2310.02207","paper":"/paper/language-models-represent-space-and-time","title":"Language Models Represent Space and Time","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wesg52/world-models","path":"make_prompt_datasets.py","file_url":"https://github.com/wesg52/world-models/blob/HEAD/make_prompt_datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ec78e0b3d6261ed5","mcp_get_code":{"code_sha256":"ec78e0b3d6261ed5"}},{"arxiv_id":"2309.16119","paper":"/paper/modulora-finetuning-3-bit-llms-on-consumer","title":"ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuleshov-group/llmtools","path":"llmtools/executor.py","file_url":"https://github.com/kuleshov-group/llmtools/blob/HEAD/llmtools/executor.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a2178676d3e7abdd","mcp_get_code":{"code_sha256":"a2178676d3e7abdd"}},{"arxiv_id":"2309.12288","paper":"/paper/the-reversal-curse-llms-trained-on-a-is-b","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","date":"2023-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lukasberglund/reversal_curse","path":"src/models/common.py","file_url":"https://github.com/lukasberglund/reversal_curse/blob/HEAD/src/models/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e18553bc097d701c","mcp_get_code":{"code_sha256":"e18553bc097d701c"}},{"arxiv_id":"2306.15895","paper":"/paper/large-language-model-as-attributed-training-1","title":"Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias","date":"2023-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yueyu1030/attrprompt","path":"train_classifier/plm_model/utils.py","file_url":"https://github.com/yueyu1030/attrprompt/blob/HEAD/train_classifier/plm_model/utils.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":"dd27c40f658addad","mcp_get_code":{"code_sha256":"dd27c40f658addad"}},{"arxiv_id":"2305.13282","paper":"/paper/is-fine-tuning-needed-pre-trained-language","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Uppaal/lm-ood","path":"utils/model_utils.py","file_url":"https://github.com/Uppaal/lm-ood/blob/HEAD/utils/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb9cc88f0bea27c4","mcp_get_code":{"code_sha256":"bb9cc88f0bea27c4"}},{"arxiv_id":"2305.11790","paper":"/paper/prompting-with-pseudo-code-instructions","title":"Prompting with Pseudo-Code Instructions","date":"2023-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mayank31398/pseudo-code-instructions","path":"code_instruct/model.py","file_url":"https://github.com/mayank31398/pseudo-code-instructions/blob/HEAD/code_instruct/model.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":"35ab7eb005ae0a76","mcp_get_code":{"code_sha256":"35ab7eb005ae0a76"}},{"arxiv_id":"2305.07759","paper":"/paper/tinystories-how-small-can-language-models-be","title":"TinyStories: How Small Can Language Models Be and Still Speak Coherent English?","date":"2023-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"danbraunai/simple_stories_train","path":"simple_stories_train/tokenizer.py","file_url":"https://github.com/danbraunai/simple_stories_train/blob/HEAD/simple_stories_train/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c430eca0b62e5574","mcp_get_code":{"code_sha256":"c430eca0b62e5574"}},{"arxiv_id":"2301.03726","paper":"/paper/neighborhood-regularized-self-training-for","title":"Neighborhood-Regularized Self-Training for Learning with Few Labels","date":"2023-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ritaranx/NeST","path":"utils.py","file_url":"https://github.com/ritaranx/NeST/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"661491a0aadeb24e","mcp_get_code":{"code_sha256":"661491a0aadeb24e"}},{"arxiv_id":"2212.10947","paper":"/paper/parallel-context-windows-improve-in-context","title":"Parallel Context Windows for Large Language Models","date":"2022-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI21Labs/Parallel-Context-Windows","path":"model_loaders.py","file_url":"https://github.com/AI21Labs/Parallel-Context-Windows/blob/HEAD/model_loaders.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":"cbb2c50ff3858a3f","mcp_get_code":{"code_sha256":"cbb2c50ff3858a3f"}},{"arxiv_id":"2209.04899","paper":"/paper/instruction-driven-history-aware-policies-for","title":"Instruction-driven history-aware policies for robotic manipulations","date":"2022-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guhur/hiveformer","path":"preprocess_instructions.py","file_url":"https://github.com/guhur/hiveformer/blob/HEAD/preprocess_instructions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1441fd48c61694c2","mcp_get_code":{"code_sha256":"1441fd48c61694c2"}},{"arxiv_id":"2208.07339","paper":"/paper/llm-int8-8-bit-matrix-multiplication-for","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","date":"2022-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/transformers-bloom-inference","path":"inference_server/models/model.py","file_url":"https://github.com/huggingface/transformers-bloom-inference/blob/HEAD/inference_server/models/model.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":"835634e64b6b277d","mcp_get_code":{"code_sha256":"835634e64b6b277d"}},{"arxiv_id":"2111.09453","paper":"/paper/robertuito-a-pre-trained-language-model-for","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","date":"2021-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pysentimiento/robertuito","path":"finetune_vs_scratch/model.py","file_url":"https://github.com/pysentimiento/robertuito/blob/HEAD/finetune_vs_scratch/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6898279b83309763","mcp_get_code":{"code_sha256":"6898279b83309763"}},{"arxiv_id":"2104.00783","paper":"/paper/action-based-conversations-dataset-a-corpus","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","date":"2021-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"asappresearch/abcd","path":"utils/load.py","file_url":"https://github.com/asappresearch/abcd/blob/HEAD/utils/load.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"10442a3755e649e8","mcp_get_code":{"code_sha256":"10442a3755e649e8"}},{"arxiv_id":"2103.14030","paper":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YongWookHa/swin-transformer-ocr","path":"utils.py","file_url":"https://github.com/YongWookHa/swin-transformer-ocr/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f299bd819038020a","mcp_get_code":{"code_sha256":"f299bd819038020a"}},{"arxiv_id":"2006.02419","paper":"/paper/emergent-multi-agent-communication-in-the","title":"Emergent Multi-Agent Communication in the Deep Learning Era","date":"2020-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brendon-boldt/xferbench","path":"xferbench/model/mt.py","file_url":"https://github.com/brendon-boldt/xferbench/blob/HEAD/xferbench/model/mt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"10a49786ffff4dd4","mcp_get_code":{"code_sha256":"10a49786ffff4dd4"}},{"arxiv_id":"1911.12019","paper":"/paper/word2word-a-collection-of-bilingual-lexicons","title":"word2word: A Collection of Bilingual Lexicons for 3,564 Language Pairs","date":"2019-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kyubyong/word2word","path":"word2word/tokenization.py","file_url":"https://github.com/Kyubyong/word2word/blob/HEAD/word2word/tokenization.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":"349ed3bbc388de65","mcp_get_code":{"code_sha256":"349ed3bbc388de65"}},{"arxiv_id":"1905.08284","paper":"/paper/enriching-pre-trained-language-model-with","title":"Enriching Pre-trained Language Model with Entity Information for Relation Classification","date":"2019-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chielingyueh/anaphora_resolution_chemical_patents","path":"utils.py","file_url":"https://github.com/chielingyueh/anaphora_resolution_chemical_patents/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":"057777fc1e9365c2","mcp_get_code":{"code_sha256":"057777fc1e9365c2"}},{"arxiv_id":"1810.05739","paper":"/paper/meansum-a-neural-model-for-unsupervised-multi","title":"MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization","date":"2018-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"megagonlabs/coop","path":"coop/util.py","file_url":"https://github.com/megagonlabs/coop/blob/HEAD/coop/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"bcb4a8a6eebef981","mcp_get_code":{"code_sha256":"bcb4a8a6eebef981"}},{"arxiv_id":"openreview_g9G7qyAzki","paper":null,"title":"arXiv:openreview_g9G7qyAzki","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"The-Inscrutable-X/CalibratedModelAgnosticCorrectness","path":"utils/model_utils.py","file_url":"https://github.com/The-Inscrutable-X/CalibratedModelAgnosticCorrectness/blob/HEAD/utils/model_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":"65b86daaedb4ee28","mcp_get_code":{"code_sha256":"65b86daaedb4ee28"}},{"arxiv_id":"aaai_29784","paper":null,"title":"arXiv:aaai_29784","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HITsz-TMG/Ext-Sub","path":"eval/ngram_rep_eval.py","file_url":"https://github.com/HITsz-TMG/Ext-Sub/blob/HEAD/eval/ngram_rep_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e65a8e07bf87b809","mcp_get_code":{"code_sha256":"e65a8e07bf87b809"}},{"arxiv_id":"2023.findings-ijcnlp.4","paper":null,"title":"arXiv:2023.findings-ijcnlp.4","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"brightjade/PRiSM","path":"models/utils.py","file_url":"https://github.com/brightjade/PRiSM/blob/HEAD/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"59ee54f46b531e61","mcp_get_code":{"code_sha256":"59ee54f46b531e61"}},{"arxiv_id":"2023.acl-long.119","paper":null,"title":"arXiv:2023.acl-long.119","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"lsvih/AtTGen","path":"tokenizer.py","file_url":"https://github.com/lsvih/AtTGen/blob/HEAD/tokenizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7e6ffd70f8da3b41","mcp_get_code":{"code_sha256":"7e6ffd70f8da3b41"}},{"arxiv_id":"2021.findings-acl.173","paper":null,"title":"arXiv:2021.findings-acl.173","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"sysulic/MDGI","path":"models/util.py","file_url":"https://github.com/sysulic/MDGI/blob/HEAD/models/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"70b1c0f23ec51e7a","mcp_get_code":{"code_sha256":"70b1c0f23ec51e7a"}}]}