{"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/generate","entry":"generate","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":143,"n_papers_ran":52,"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":147,"n_samples_ran":46,"n_samples_fingerprinted":2,"n_places":161,"n_places_pointer_only":66,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":12,"ran_fixture":4,"ran":29,"unverified":101},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.00355","paper":"/paper/arxiv-2609-00355","title":"Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"js-lee-AI/GLANCE","path":"glance/decode.py","file_url":"https://github.com/js-lee-AI/GLANCE/blob/HEAD/glance/decode.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dd66ebd76e41bb93","mcp_get_code":{"code_sha256":"dd66ebd76e41bb93"}},{"arxiv_id":"2608.25655","paper":"/paper/arxiv-2608-25655","title":"Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"LordTARN1SHED/SCALE-QA","path":"tsim_reference/src/backends/gemma_local.py","file_url":"https://github.com/LordTARN1SHED/SCALE-QA/blob/HEAD/tsim_reference/src/backends/gemma_local.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e33f0b44b595a82a","mcp_get_code":{"code_sha256":"e33f0b44b595a82a"}},{"arxiv_id":"2608.25655","paper":"/paper/arxiv-2608-25655","title":"Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"LordTARN1SHED/SCALE-QA","path":"tsim_reference/src/backends/openai_compat.py","file_url":"https://github.com/LordTARN1SHED/SCALE-QA/blob/HEAD/tsim_reference/src/backends/openai_compat.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fa8e815443de2ec5","mcp_get_code":{"code_sha256":"fa8e815443de2ec5"}},{"arxiv_id":"2607.26873","paper":"/paper/arxiv-2607-26873","title":"SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"chiefovoavicii/SERPO","path":"eval/eval_gpqa_diamond.py","file_url":"https://github.com/chiefovoavicii/SERPO/blob/HEAD/eval/eval_gpqa_diamond.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":"05b8f187596ad436","mcp_get_code":{"code_sha256":"05b8f187596ad436"}},{"arxiv_id":"2607.18256","paper":"/paper/arxiv-2607-18256","title":"PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"AuroraLHL/PEARL","path":"core/generate_with_code.py","file_url":"https://github.com/AuroraLHL/PEARL/blob/HEAD/core/generate_with_code.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fe6c8218a8e96089","mcp_get_code":{"code_sha256":"fe6c8218a8e96089"}},{"arxiv_id":"2606.10537","paper":"/paper/arxiv-2606-10537","title":"Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"menik1126/Prefilling-dLLM","path":"prefilling_dllm_eval/prefilling_model.py","file_url":"https://github.com/menik1126/Prefilling-dLLM/blob/HEAD/prefilling_dllm_eval/prefilling_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9f95fe726f98f2e","mcp_get_code":{"code_sha256":"f9f95fe726f98f2e"}},{"arxiv_id":"2606.04373","paper":"/paper/arxiv-2606-04373","title":"Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"hfutqian/MaskAQ","path":"MaskAQ/hydra_image_gen_ssim_att_map.py","file_url":"https://github.com/hfutqian/MaskAQ/blob/HEAD/MaskAQ/hydra_image_gen_ssim_att_map.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":"0bbe2df88e08bd7d","mcp_get_code":{"code_sha256":"0bbe2df88e08bd7d"}},{"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":"12cd7a99f12351a7","mcp_get_code":{"code_sha256":"12cd7a99f12351a7"}},{"arxiv_id":"2605.18848","paper":"/paper/arxiv-2605-18848","title":"ELA: Exact Linear Attention with Qualitative Memory and Hyper-Link","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"yauntyour/Exact-Linear-Attention","path":"GPT_input.py","file_url":"https://github.com/yauntyour/Exact-Linear-Attention/blob/HEAD/GPT_input.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"584dfd1b5c011a3c","mcp_get_code":{"code_sha256":"584dfd1b5c011a3c"}},{"arxiv_id":"2605.09536","paper":"/paper/arxiv-2605-09536","title":"TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"BHmingyang/TAD","path":"eval/generate.py","file_url":"https://github.com/BHmingyang/TAD/blob/HEAD/eval/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"419b9da5c8cf99a3","mcp_get_code":{"code_sha256":"419b9da5c8cf99a3"}},{"arxiv_id":"2604.18995","paper":"/paper/arxiv-2604-18995","title":"R 2 -dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"GATECH-EIC/R2-dLLM","path":"llada/generate.py","file_url":"https://github.com/GATECH-EIC/R2-dLLM/blob/HEAD/llada/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c7f043cff0c62f9","mcp_get_code":{"code_sha256":"9c7f043cff0c62f9"}},{"arxiv_id":"2603.22213","paper":"/paper/arxiv-2603-22213","title":"SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Tangkexian/SPA","path":"src/utils_tools/utils.py","file_url":"https://github.com/Tangkexian/SPA/blob/HEAD/src/utils_tools/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ae4b99874db95f6","mcp_get_code":{"code_sha256":"6ae4b99874db95f6"}},{"arxiv_id":"2603.03081","paper":"/paper/arxiv-2603-03081","title":"TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ZevineXu/TAO-Attack","path":"attack.py","file_url":"https://github.com/ZevineXu/TAO-Attack/blob/HEAD/attack.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ced740e66b4569d","mcp_get_code":{"code_sha256":"7ced740e66b4569d"}},{"arxiv_id":"2602.11136","paper":"/paper/arxiv-2602-11136","title":"FORMALJUDGE: A Neuro-Symbolic Paradigm for Agentic Oversight","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"htlou/FormalJudge","path":"AgentSafetyBench/score/eval_with_shield.py","file_url":"https://github.com/htlou/FormalJudge/blob/HEAD/AgentSafetyBench/score/eval_with_shield.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3f49873c783db6b","mcp_get_code":{"code_sha256":"e3f49873c783db6b"}},{"arxiv_id":"2602.06462","paper":"/paper/arxiv-2602-06462","title":"Diffusion-State Policy Optimization for Masked Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"dllm-reasoning/d1","path":"eval/generate.py","file_url":"https://github.com/dllm-reasoning/d1/blob/HEAD/eval/generate.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":"e65421243695657c","mcp_get_code":{"code_sha256":"e65421243695657c"}},{"arxiv_id":"2602.03084","paper":"/paper/arxiv-2602-03084","title":"AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"mira-ai-lab/AERO","path":"synth/inner_loop.py","file_url":"https://github.com/mira-ai-lab/AERO/blob/HEAD/synth/inner_loop.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9554f6df357fa157","mcp_get_code":{"code_sha256":"9554f6df357fa157"}},{"arxiv_id":"2602.02600","paper":"/paper/arxiv-2602-02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","date":"2026-02-01","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"niez233/DiffuGuard","path":"utility/generate_function.py","file_url":"https://github.com/niez233/DiffuGuard/blob/HEAD/utility/generate_function.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"195f48aece3499e6","mcp_get_code":{"code_sha256":"195f48aece3499e6"}},{"arxiv_id":"2602.02600","paper":"/paper/arxiv-2602-02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","date":"2026-02-01","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"shuita2333/PAD-codes","path":"LLaDA-PAD/generate-PAD.py","file_url":"https://github.com/shuita2333/PAD-codes/blob/HEAD/LLaDA-PAD/generate-PAD.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e3a6bc56d604874","mcp_get_code":{"code_sha256":"3e3a6bc56d604874"}},{"arxiv_id":"2602.02600","paper":"/paper/arxiv-2602-02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","date":"2026-02-01","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"shuita2333/PAD-codes","path":"MMaDA-PAD/generate-PAD.py","file_url":"https://github.com/shuita2333/PAD-codes/blob/HEAD/MMaDA-PAD/generate-PAD.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"afd61e748d6c23ce","mcp_get_code":{"code_sha256":"afd61e748d6c23ce"}},{"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":"models/LLaDA_rho_EOS.py","file_url":"https://github.com/yjyddq/rho-EOS/blob/HEAD/models/LLaDA_rho_EOS.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":"f00cde97932a227e","mcp_get_code":{"code_sha256":"f00cde97932a227e"}},{"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":"models/LLaDA_DAEDAL.py","file_url":"https://github.com/yjyddq/rho-EOS/blob/HEAD/models/LLaDA_DAEDAL.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":"2915ef0df5c62d3f","mcp_get_code":{"code_sha256":"2915ef0df5c62d3f"}},{"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/models/LLaDA.py","file_url":"https://github.com/yihao-liang/CDLM/blob/HEAD/evaluation/dllm_eval/models/LLaDA.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":"8cb6e91522671000","mcp_get_code":{"code_sha256":"8cb6e91522671000"}},{"arxiv_id":"2511.02077","paper":"/paper/arxiv-2511-02077","title":"Beyond Static Cutoffs: One-Shot Dynamic Thresholding for Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"jackshen-1215/osdt","path":"osdt/llada_generate_osdt.py","file_url":"https://github.com/jackshen-1215/osdt/blob/HEAD/osdt/llada_generate_osdt.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aac61888dac8e7b2","mcp_get_code":{"code_sha256":"aac61888dac8e7b2"}},{"arxiv_id":"2509.20570","paper":"/paper/arxiv-2509-20570","title":"PIRF: Physics-Informed Reward Fine-Tuning for Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"mingze-yuan/PIRF","path":"evaluate_pirf.py","file_url":"https://github.com/mingze-yuan/PIRF/blob/HEAD/evaluate_pirf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3dcb7d7bb60bc495","mcp_get_code":{"code_sha256":"3dcb7d7bb60bc495"}},{"arxiv_id":"2509.15188","paper":"/paper/arxiv-2509-15188","title":"Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ybseo-ac/Conv","path":"gen1_2_answer_generation_llada.py","file_url":"https://github.com/ybseo-ac/Conv/blob/HEAD/gen1_2_answer_generation_llada.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e8a159c6df1dcb1","mcp_get_code":{"code_sha256":"5e8a159c6df1dcb1"}},{"arxiv_id":"2509.15188","paper":"/paper/arxiv-2509-15188","title":"Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"ybseo-ac/Conv","path":"generate_yb.py","file_url":"https://github.com/ybseo-ac/Conv/blob/HEAD/generate_yb.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6e4c11b91e906864","mcp_get_code":{"code_sha256":"6e4c11b91e906864"}},{"arxiv_id":"2508.20718","paper":"/paper/arxiv-2508-20718","title":"Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-08","title_source":"syntology","repo":"ryehr/Consistency","path":"src/tokenization_consistency/watermark.py","file_url":"https://github.com/ryehr/Consistency/blob/HEAD/src/tokenization_consistency/watermark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4abde2ebde77264f","mcp_get_code":{"code_sha256":"4abde2ebde77264f"}},{"arxiv_id":"2507.11316","paper":null,"title":"arXiv:2507.11316","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"hr-jin/ConVA","path":"src/cav_gen.py","file_url":"https://github.com/hr-jin/ConVA/blob/HEAD/src/cav_gen.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"99b0fdfb4ceaa265","mcp_get_code":{"code_sha256":"99b0fdfb4ceaa265"}},{"arxiv_id":"2507.11097","paper":"/paper/the-devil-behind-the-mask-an-emergent-safety","title":"The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs","date":"2025-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zichenwen1/dija","path":"MMaDA/generate.py","file_url":"https://github.com/zichenwen1/dija/blob/HEAD/MMaDA/generate.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":"bdb7c183d8696b6b","mcp_get_code":{"code_sha256":"bdb7c183d8696b6b"}},{"arxiv_id":"2506.19037","paper":"/paper/plan-for-speed-dilated-scheduling-for-masked","title":"Plan for Speed -- Dilated Scheduling for Masked Diffusion Language Models","date":"2025-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ML-GSAI/LLaDA","path":"generate.py","file_url":"https://github.com/ML-GSAI/LLaDA/blob/HEAD/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6f9738ad733e164b","mcp_get_code":{"code_sha256":"6f9738ad733e164b"}},{"arxiv_id":"2506.15735","paper":null,"title":"arXiv:2506.15735","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"lasr-eliciting-contexts/ContextBench","path":"src/contextbench/llada/generate.py","file_url":"https://github.com/lasr-eliciting-contexts/ContextBench/blob/HEAD/src/contextbench/llada/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73ad213879386d60","mcp_get_code":{"code_sha256":"73ad213879386d60"}},{"arxiv_id":"2505.15809","paper":"/paper/mmada-multimodal-large-diffusion-language","title":"MMaDA: Multimodal Large Diffusion Language Models","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gen-Verse/MMaDA","path":"generate.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bdb7c183d8696b6b","mcp_get_code":{"code_sha256":"bdb7c183d8696b6b"}},{"arxiv_id":"2505.13447","paper":"/paper/mean-flows-for-one-step-generative-modeling","title":"Mean Flows for One-step Generative Modeling","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gsunshine/meanflow","path":"meanflow.py","file_url":"https://github.com/Gsunshine/meanflow/blob/HEAD/meanflow.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"15cb9cb0de4aadad","mcp_get_code":{"code_sha256":"15cb9cb0de4aadad"}},{"arxiv_id":"2503.13538","paper":"/paper/from-demonstrations-to-rewards-alignment","title":"From Demonstrations to Rewards: Alignment Without Explicit Human Preferences","date":"2025-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hong-Lab-UMN-ECE/IRLAlignment","path":"summarize_from_feedback_details/dpo.py","file_url":"https://github.com/Hong-Lab-UMN-ECE/IRLAlignment/blob/HEAD/summarize_from_feedback_details/dpo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51062aca9db3f84c","mcp_get_code":{"code_sha256":"51062aca9db3f84c"}},{"arxiv_id":"2502.16776","paper":"/paper/aisafetylab-a-comprehensive-framework-for-ai","title":"AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement","date":"2025-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/AISafetyLab","path":"aisafetylab/attack/feedback/model_interactions.py","file_url":"https://github.com/thu-coai/AISafetyLab/blob/HEAD/aisafetylab/attack/feedback/model_interactions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d1c9669ced3e8b3","mcp_get_code":{"code_sha256":"2d1c9669ced3e8b3"}},{"arxiv_id":"2502.00657","paper":"/paper/llm-safety-alignment-is-divergence-estimation","title":"LLM Safety Alignment is Divergence Estimation in Disguise","date":"2025-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rhaldarpurdue/kldo","path":"generate.py","file_url":"https://github.com/rhaldarpurdue/kldo/blob/HEAD/generate.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":"762172a898132a82","mcp_get_code":{"code_sha256":"762172a898132a82"}},{"arxiv_id":"2501.01986","paper":"/paper/framefusion-combining-similarity-and","title":"FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models","date":"2024-12-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-nics/framefusion","path":"framefusion/models/internvl/modeling_internvl_chat.py","file_url":"https://github.com/thu-nics/framefusion/blob/HEAD/framefusion/models/internvl/modeling_internvl_chat.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"421deb414feba11c","mcp_get_code":{"code_sha256":"421deb414feba11c"}},{"arxiv_id":"2412.15605","paper":"/paper/don-t-do-rag-when-cache-augmented-generation","title":"Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks","date":"2024-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hhhuang/cag","path":"kvcache.py","file_url":"https://github.com/hhhuang/cag/blob/HEAD/kvcache.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eaefca73f1c36f58","mcp_get_code":{"code_sha256":"eaefca73f1c36f58"}},{"arxiv_id":"2412.12841","paper":"/paper/benchmarking-and-understanding-compositional","title":"Benchmarking and Understanding Compositional Relational Reasoning of LLMs","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caiyun-ai/gar","path":"GAR/code/generate_GAR.py","file_url":"https://github.com/caiyun-ai/gar/blob/HEAD/GAR/code/generate_GAR.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f7bccd2df5ca17cd","mcp_get_code":{"code_sha256":"f7bccd2df5ca17cd"}},{"arxiv_id":"2412.12409","paper":"/paper/improving-cooperation-in-language-games-with","title":"Improving Cooperation in Language Games with Bayesian Inference and the Cognitive Hierarchy","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ganondox/bayesian-codenames","path":"data_objects/associations_creator.py","file_url":"https://github.com/ganondox/bayesian-codenames/blob/HEAD/data_objects/associations_creator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4a0c548d2515833b","mcp_get_code":{"code_sha256":"4a0c548d2515833b"}},{"arxiv_id":"2412.09078","paper":"/paper/forest-of-thought-scaling-test-time-compute","title":"Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iamhankai/Forest-of-Thought","path":"run_with_mcf.py","file_url":"https://github.com/iamhankai/Forest-of-Thought/blob/HEAD/run_with_mcf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8c8ee47126d561c8","mcp_get_code":{"code_sha256":"8c8ee47126d561c8"}},{"arxiv_id":"2412.09078","paper":"/paper/forest-of-thought-scaling-test-time-compute","title":"Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iamhankai/Forest-of-Thought","path":"run_with_mcf_stop_noearly.py","file_url":"https://github.com/iamhankai/Forest-of-Thought/blob/HEAD/run_with_mcf_stop_noearly.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"67301e6cd34829e9","mcp_get_code":{"code_sha256":"67301e6cd34829e9"}},{"arxiv_id":"2411.16955","paper":"/paper/probing-the-limitations-of-multimodal","title":"Probing the limitations of multimodal language models for chemistry and materials research","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lamalab-org/chem-bench","path":"reports/claude3.5-react/run_benchmark.py","file_url":"https://github.com/lamalab-org/chem-bench/blob/HEAD/reports/claude3.5-react/run_benchmark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3d3cc40ac2511b1f","mcp_get_code":{"code_sha256":"3d3cc40ac2511b1f"}},{"arxiv_id":"2411.04282","paper":"/paper/language-models-are-hidden-reasoners","title":"Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforceairesearch/latro","path":"LaTRO/utils/trainer_utils.py","file_url":"https://github.com/salesforceairesearch/latro/blob/HEAD/LaTRO/utils/trainer_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":"5cafb313856b17e6","mcp_get_code":{"code_sha256":"5cafb313856b17e6"}},{"arxiv_id":"2411.03471","paper":"/paper/metrex-a-benchmark-for-verilog-code-metric","title":"MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"scale-lab/MetRex","path":"src/model/model.py","file_url":"https://github.com/scale-lab/MetRex/blob/HEAD/src/model/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b34b7bcd774e5d0","mcp_get_code":{"code_sha256":"7b34b7bcd774e5d0"}},{"arxiv_id":"2411.00566","paper":"/paper/patternboost-constructions-in-mathematics","title":"PatternBoost: Constructions in Mathematics with a Little Help from AI","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zawagner22/transformers_math_experiments","path":"makebettertokens.py","file_url":"https://github.com/zawagner22/transformers_math_experiments/blob/HEAD/makebettertokens.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa1a19150c9003a6","mcp_get_code":{"code_sha256":"fa1a19150c9003a6"}},{"arxiv_id":"2410.16794","paper":"/paper/one-step-diffusion-distillation-through-score","title":"One-Step Diffusion Distillation through Score Implicit Matching","date":"2024-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maple-research-lab/sim","path":"inference.py","file_url":"https://github.com/maple-research-lab/sim/blob/HEAD/inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"AGPL-3.0","inline_ok":false,"code_sha256_prefix":"0023abc199a5c03e","mcp_get_code":{"code_sha256":"0023abc199a5c03e"}},{"arxiv_id":"2410.14516","paper":"/paper/do-llms-know-internally-when-they-follow","title":"Do LLMs \"know\" internally when they follow instructions?","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-internal-llms-instruction-following","path":"run/save_LLMs_activations.py","file_url":"https://github.com/apple/ml-internal-llms-instruction-following/blob/HEAD/run/save_LLMs_activations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2cf4545cbe432d4a","mcp_get_code":{"code_sha256":"2cf4545cbe432d4a"}},{"arxiv_id":"2410.14516","paper":"/paper/do-llms-know-internally-when-they-follow","title":"Do LLMs \"know\" internally when they follow instructions?","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-internal-llms-instruction-following","path":"run/representation_engineering.py","file_url":"https://github.com/apple/ml-internal-llms-instruction-following/blob/HEAD/run/representation_engineering.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"66614882cf7a8fb1","mcp_get_code":{"code_sha256":"66614882cf7a8fb1"}},{"arxiv_id":"2410.12557","paper":"/paper/one-step-diffusion-via-shortcut-models","title":"One Step Diffusion via Shortcut Models","date":"2024-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leffff/FlowModels","path":"flow_models/generation.py","file_url":"https://github.com/leffff/FlowModels/blob/HEAD/flow_models/generation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"950ef8f57521a359","mcp_get_code":{"code_sha256":"950ef8f57521a359"}},{"arxiv_id":"2410.04234","paper":"/paper/functional-homotopy-smoothing-discrete","title":"Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks","date":"2024-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"danshumaan/functional_homotopy","path":"fhautodan/fh-autodan.py","file_url":"https://github.com/danshumaan/functional_homotopy/blob/HEAD/fhautodan/fh-autodan.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"634d43e275317dd4","mcp_get_code":{"code_sha256":"634d43e275317dd4"}},{"arxiv_id":"2410.03489","paper":"/paper/gradient-based-jailbreak-images-for","title":"Gradient-based Jailbreak Images for Multimodal Fusion Models","date":"2024-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/multimodal-fusion-jailbreaks","path":"src/fusion_jailbreaks/eval/evaluation.py","file_url":"https://github.com/facebookresearch/multimodal-fusion-jailbreaks/blob/HEAD/src/fusion_jailbreaks/eval/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8da2df16935a5aa0","mcp_get_code":{"code_sha256":"8da2df16935a5aa0"}},{"arxiv_id":"2410.02992","paper":"/paper/guided-stream-of-search-learning-to-better","title":"Guided Stream of Search: Learning to Better Search with Language Models via Optimal Path Guidance","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"symoon11/guided-stream-of-search","path":"tril/sample.py","file_url":"https://github.com/symoon11/guided-stream-of-search/blob/HEAD/tril/sample.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce288b4b6be413e0","mcp_get_code":{"code_sha256":"ce288b4b6be413e0"}},{"arxiv_id":"2410.02992","paper":"/paper/guided-stream-of-search-learning-to-better","title":"Guided Stream of Search: Learning to Better Search with Language Models via Optimal Path Guidance","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"symoon11/guided-stream-of-search","path":"stream-of-search/src/sample.py","file_url":"https://github.com/symoon11/guided-stream-of-search/blob/HEAD/stream-of-search/src/sample.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b5682ed4efd3768","mcp_get_code":{"code_sha256":"9b5682ed4efd3768"}},{"arxiv_id":"2410.02760","paper":"/paper/erasing-conceptual-knowledge-from-language","title":"Erasing Conceptual Knowledge from Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rohitgandikota/erasing-llm","path":"trainscripts/erase.py","file_url":"https://github.com/rohitgandikota/erasing-llm/blob/HEAD/trainscripts/erase.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a13ff0028dc689e7","mcp_get_code":{"code_sha256":"a13ff0028dc689e7"}},{"arxiv_id":"2410.02760","paper":"/paper/erasing-conceptual-knowledge-from-language","title":"Erasing Conceptual Knowledge from Language Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rohitgandikota/erasing-llm","path":"trainscripts/prepare_consistency_data.py","file_url":"https://github.com/rohitgandikota/erasing-llm/blob/HEAD/trainscripts/prepare_consistency_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"868ded444472e56d","mcp_get_code":{"code_sha256":"868ded444472e56d"}},{"arxiv_id":"2410.01383","paper":"/paper/pairdistill-pairwise-relevance-distillation","title":"PairDistill: Pairwise Relevance Distillation for Dense Retrieval","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MiuLab/PairDistill","path":"pairwise_rerank.py","file_url":"https://github.com/MiuLab/PairDistill/blob/HEAD/pairwise_rerank.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e85c18fbff726802","mcp_get_code":{"code_sha256":"e85c18fbff726802"}},{"arxiv_id":"2408.07978","paper":"/paper/coupling-without-communication-and-drafter","title":"Coupling without Communication and Drafter-Invariant Speculative Decoding","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"majid-daliri/disd","path":"generate_model_distribution.py","file_url":"https://github.com/majid-daliri/disd/blob/HEAD/generate_model_distribution.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d753515a5d74670c","mcp_get_code":{"code_sha256":"d753515a5d74670c"}},{"arxiv_id":"2408.06849","paper":"/paper/causal-agent-based-on-large-language-model","title":"Causal Agent based on Large Language Model","date":"2024-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kairong-han/causal_agent","path":"SCORE-main/demo_SCORE.py","file_url":"https://github.com/kairong-han/causal_agent/blob/HEAD/SCORE-main/demo_SCORE.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1c31ede173ef4356","mcp_get_code":{"code_sha256":"1c31ede173ef4356"}},{"arxiv_id":"2408.03506","paper":"/paper/1-5-pints-technical-report-pretraining-in","title":"1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data","date":"2024-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pints-AI/1.5-Pints","path":"inference/generate.py","file_url":"https://github.com/Pints-AI/1.5-Pints/blob/HEAD/inference/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aee31819bbec4f25","mcp_get_code":{"code_sha256":"aee31819bbec4f25"}},{"arxiv_id":"2407.16222","paper":"/paper/prealign-boosting-cross-lingual-transfer-by","title":"PreAlign: Boosting Cross-Lingual Transfer by Early Establishment of Multilingual Alignment","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saltychtao/prealign","path":"src/utils.py","file_url":"https://github.com/saltychtao/prealign/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"17dae1edb93fa6da","mcp_get_code":{"code_sha256":"17dae1edb93fa6da"}},{"arxiv_id":"2407.04411","paper":"/paper/waterfall-framework-for-robust-and-scalable","title":"Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aoi3142/waterfall","path":"waterfall/group-beam-search/custom_generate/generate.py","file_url":"https://github.com/aoi3142/waterfall/blob/HEAD/waterfall/group-beam-search/custom_generate/generate.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":"e82bfea8b311483b","mcp_get_code":{"code_sha256":"e82bfea8b311483b"}},{"arxiv_id":"2406.19934","paper":"/paper/from-the-least-to-the-most-building-a-plug","title":"From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis","date":"2024-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"steven-ccq/VisualReasoner","path":"utils.py","file_url":"https://github.com/steven-ccq/VisualReasoner/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c626111fb20cdab1","mcp_get_code":{"code_sha256":"c626111fb20cdab1"}},{"arxiv_id":"2406.12128","paper":"/paper/ai-news-content-farms-are-easy-to-make-and","title":"AI \"News\" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpucce/synthetic_llm_data","path":"src/data_generation/data_complete.py","file_url":"https://github.com/gpucce/synthetic_llm_data/blob/HEAD/src/data_generation/data_complete.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e386851e40fd0d0e","mcp_get_code":{"code_sha256":"e386851e40fd0d0e"}},{"arxiv_id":"2406.12128","paper":"/paper/ai-news-content-farms-are-easy-to-make-and","title":"AI \"News\" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpucce/synthetic_llm_data","path":"src/data_generation/data_generate.py","file_url":"https://github.com/gpucce/synthetic_llm_data/blob/HEAD/src/data_generation/data_generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2954c86d261f558","mcp_get_code":{"code_sha256":"e2954c86d261f558"}},{"arxiv_id":"2406.11030","paper":"/paper/foodieqa-a-multimodal-dataset-for-fine","title":"FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture","date":"2024-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyan62/FoodieQA","path":"Yi/finetune/sft/prompt_eval.py","file_url":"https://github.com/lyan62/FoodieQA/blob/HEAD/Yi/finetune/sft/prompt_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c383e2541e15d801","mcp_get_code":{"code_sha256":"c383e2541e15d801"}},{"arxiv_id":"2406.01288","paper":"/paper/improved-few-shot-jailbreaking-can-circumvent","title":"Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/I-FSJ","path":"exps/rs.py","file_url":"https://github.com/sail-sg/I-FSJ/blob/HEAD/exps/rs.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3a80a2bfa48e30bb","mcp_get_code":{"code_sha256":"3a80a2bfa48e30bb"}},{"arxiv_id":"2405.21018","paper":"/paper/improved-techniques-for-optimization-based","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","date":"2024-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaxiaojunQAQ/I-GCG","path":"attack_llm_core_best_update_our_target.py","file_url":"https://github.com/jiaxiaojunQAQ/I-GCG/blob/HEAD/attack_llm_core_best_update_our_target.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ad91f68f0c84d9c","mcp_get_code":{"code_sha256":"6ad91f68f0c84d9c"}},{"arxiv_id":"2405.20340","paper":"/paper/motionllm-understanding-human-behaviors-from","title":"MotionLLM: Understanding Human Behaviors from Human Motions and Videos","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDEA-Research/MotionLLM","path":"generate.py","file_url":"https://github.com/IDEA-Research/MotionLLM/blob/HEAD/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"688ce44db612be08","mcp_get_code":{"code_sha256":"688ce44db612be08"}},{"arxiv_id":"2405.19100","paper":"/paper/enhancing-zero-shot-facial-expression","title":"Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zengqunzhao/exp-clip","path":"models/BLIP2_T5.py","file_url":"https://github.com/zengqunzhao/exp-clip/blob/HEAD/models/BLIP2_T5.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f239483928dcb19e","mcp_get_code":{"code_sha256":"f239483928dcb19e"}},{"arxiv_id":"2405.16455","paper":"/paper/on-the-algorithmic-bias-of-aligning-large","title":"On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JiancongXiao/PM_RLHF","path":"step1_supervised_finetuning/prompt_eval.py","file_url":"https://github.com/JiancongXiao/PM_RLHF/blob/HEAD/step1_supervised_finetuning/prompt_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"451c619b9609c3c0","mcp_get_code":{"code_sha256":"451c619b9609c3c0"}},{"arxiv_id":"2405.03000","paper":"/paper/medadapter-efficient-test-time-adaptation-of","title":"MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning","date":"2024-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wshi83/MedAdapter","path":"reward_model/orm/orm_guide.py","file_url":"https://github.com/wshi83/MedAdapter/blob/HEAD/reward_model/orm/orm_guide.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7fe7aafc5afb6d9b","mcp_get_code":{"code_sha256":"7fe7aafc5afb6d9b"}},{"arxiv_id":"2405.01229","paper":"/paper/boosting-jailbreak-attack-with-momentum","title":"Boosting Jailbreak Attack with Momentum","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weizeming/momentum-attack-llm","path":"gcg.py","file_url":"https://github.com/weizeming/momentum-attack-llm/blob/HEAD/gcg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"30a1818a1dbcef38","mcp_get_code":{"code_sha256":"30a1818a1dbcef38"}},{"arxiv_id":"2404.16767","paper":"/paper/rebel-reinforcement-learning-via-regressing","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaolingao/rebel","path":"src/tldr/sft.py","file_url":"https://github.com/zhaolingao/rebel/blob/HEAD/src/tldr/sft.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":"51062aca9db3f84c","mcp_get_code":{"code_sha256":"51062aca9db3f84c"}},{"arxiv_id":"2404.15846","paper":"/paper/from-complex-to-simple-enhancing-multi","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meowpass/followcomplexinstruction","path":"get_data/do_inference.py","file_url":"https://github.com/meowpass/followcomplexinstruction/blob/HEAD/get_data/do_inference.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"44bfe81032401eb3","mcp_get_code":{"code_sha256":"44bfe81032401eb3"}},{"arxiv_id":"2404.12104","paper":"/paper/ethical-lens-curbing-malicious-usages-of-open","title":"Ethical-Lens: Curbing Malicious Usages of Open-Source Text-to-Image Models","date":"2024-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuzhu-cai/ethical-lens","path":"generate.py","file_url":"https://github.com/yuzhu-cai/ethical-lens/blob/HEAD/generate.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":"1d3fefc527b9ca00","mcp_get_code":{"code_sha256":"1d3fefc527b9ca00"}},{"arxiv_id":"2403.17031","paper":"/paper/the-n-implementation-details-of-rlhf-with-ppo","title":"The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization","date":"2024-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vwxyzjn/summarize_from_feedback_details","path":"summarize_from_feedback_details/dpo.py","file_url":"https://github.com/vwxyzjn/summarize_from_feedback_details/blob/HEAD/summarize_from_feedback_details/dpo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51062aca9db3f84c","mcp_get_code":{"code_sha256":"51062aca9db3f84c"}},{"arxiv_id":"2403.16732","paper":"/paper/enabling-uncertainty-estimation-in-iterative","title":"Enabling Uncertainty Estimation in Iterative Neural Networks","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvlab-epfl/iter_unc","path":"exps/toy_regression.py","file_url":"https://github.com/cvlab-epfl/iter_unc/blob/HEAD/exps/toy_regression.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"626fdad3d8d5da02","mcp_get_code":{"code_sha256":"626fdad3d8d5da02"}},{"arxiv_id":"2403.14112","paper":"/paper/benchmarking-chinese-commonsense-reasoning-of","title":"Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlations","date":"2024-03-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"01-ai/Yi","path":"finetune/sft/prompt_eval.py","file_url":"https://github.com/01-ai/Yi/blob/HEAD/finetune/sft/prompt_eval.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":"c383e2541e15d801","mcp_get_code":{"code_sha256":"c383e2541e15d801"}},{"arxiv_id":"2403.10266","paper":"/paper/dsp-dynamic-sequence-parallelism-for-multi","title":"DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers","date":"2024-03-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nus-hpc-ai-lab/opendit","path":"gradio/cogvideox.py","file_url":"https://github.com/nus-hpc-ai-lab/opendit/blob/HEAD/gradio/cogvideox.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":"be3706734550c9d9","mcp_get_code":{"code_sha256":"be3706734550c9d9"}},{"arxiv_id":"2403.08043","paper":"/paper/authorship-style-transfer-with-policy","title":"Authorship Style Transfer with Policy Optimization","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isi-nlp/astrapop","path":"src/ets/generate.py","file_url":"https://github.com/isi-nlp/astrapop/blob/HEAD/src/ets/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c1788682bf64080","mcp_get_code":{"code_sha256":"6c1788682bf64080"}},{"arxiv_id":"2403.08043","paper":"/paper/authorship-style-transfer-with-policy","title":"Authorship Style Transfer with Policy Optimization","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isi-nlp/astrapop","path":"src/ets/generate_dpo_cpo_data.py","file_url":"https://github.com/isi-nlp/astrapop/blob/HEAD/src/ets/generate_dpo_cpo_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4fef07692ec2e44f","mcp_get_code":{"code_sha256":"4fef07692ec2e44f"}},{"arxiv_id":"2403.07691","paper":"/paper/reference-free-monolithic-preference","title":"ORPO: Monolithic Preference Optimization without Reference Model","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shibing624/medicalgpt","path":"role_play_data/roleplay_data_generate_doubao.py","file_url":"https://github.com/shibing624/medicalgpt/blob/HEAD/role_play_data/roleplay_data_generate_doubao.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":"651d8039d4127f60","mcp_get_code":{"code_sha256":"651d8039d4127f60"}},{"arxiv_id":"2403.07652","paper":"/paper/harder-tasks-need-more-experts-dynamic","title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models","date":"2024-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhenweian/dynamic_moe","path":"infer.py","file_url":"https://github.com/zhenweian/dynamic_moe/blob/HEAD/infer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc7fd354030957b9","mcp_get_code":{"code_sha256":"dc7fd354030957b9"}},{"arxiv_id":"2403.04957","paper":"/paper/automatic-and-universal-prompt-injection","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sheltonliu-n/universal-prompt-injection","path":"universal_prompt_injection.py","file_url":"https://github.com/sheltonliu-n/universal-prompt-injection/blob/HEAD/universal_prompt_injection.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0332de7e8c09ed4","mcp_get_code":{"code_sha256":"c0332de7e8c09ed4"}},{"arxiv_id":"2402.18510","paper":"/paper/rnns-are-not-transformers-yet-the-key","title":"RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dangxingyu/rnn-icrag","path":"rnn/val.py","file_url":"https://github.com/dangxingyu/rnn-icrag/blob/HEAD/rnn/val.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fe384f6380199cb6","mcp_get_code":{"code_sha256":"fe384f6380199cb6"}},{"arxiv_id":"2402.18243","paper":"/paper/learning-or-self-aligning-rethinking","title":"Learning or Self-aligning? Rethinking Instruction Fine-tuning","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"renmengjie7/self-aligning","path":"eval/chat.py","file_url":"https://github.com/renmengjie7/self-aligning/blob/HEAD/eval/chat.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"453c9544fec56390","mcp_get_code":{"code_sha256":"453c9544fec56390"}},{"arxiv_id":"2402.12991","paper":"/paper/trap-targeted-random-adversarial-prompt","title":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"framartin/trap","path":"detect_llm/compute_results.py","file_url":"https://github.com/framartin/trap/blob/HEAD/detect_llm/compute_results.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"58bff4cf03dd8432","mcp_get_code":{"code_sha256":"58bff4cf03dd8432"}},{"arxiv_id":"2402.09154","paper":"/paper/attacking-large-language-models-with","title":"Attacking Large Language Models with Projected Gradient Descent","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sigeisler/reinforce-attacks-llms","path":"baselines/reinforce/generate_utils.py","file_url":"https://github.com/sigeisler/reinforce-attacks-llms/blob/HEAD/baselines/reinforce/generate_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb149efd17214bc3","mcp_get_code":{"code_sha256":"eb149efd17214bc3"}},{"arxiv_id":"2402.09063","paper":"/paper/soft-prompt-threats-attacking-safety","title":"Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"schwinnl/llm_embedding_attack","path":"embedding_attack_toxic.py","file_url":"https://github.com/schwinnl/llm_embedding_attack/blob/HEAD/embedding_attack_toxic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b6b7c037edb3ff3","mcp_get_code":{"code_sha256":"8b6b7c037edb3ff3"}},{"arxiv_id":"2402.05787","paper":"/paper/how-do-transformers-perform-in-context","title":"How do Transformers perform In-Context Autoregressive Learning?","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michaelsdr/ical","path":"validation_token_encoding.py","file_url":"https://github.com/michaelsdr/ical/blob/HEAD/validation_token_encoding.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bebe37bf3ba983c8","mcp_get_code":{"code_sha256":"bebe37bf3ba983c8"}},{"arxiv_id":"2402.00033","paper":"/paper/lf-vit-reducing-spatial-redundancy-in-vision","title":"LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition","date":"2024-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"edgeai1/LF-ViT","path":"deit/models_deit.py","file_url":"https://github.com/edgeai1/LF-ViT/blob/HEAD/deit/models_deit.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd836cf662c768c1","mcp_get_code":{"code_sha256":"dd836cf662c768c1"}},{"arxiv_id":"2401.18018","paper":"/paper/prompt-driven-llm-safeguarding-via-directed","title":"On Prompt-Driven Safeguarding for Large Language Models","date":"2024-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chujiezheng/LLM-Safeguard","path":"code/generate.py","file_url":"https://github.com/chujiezheng/LLM-Safeguard/blob/HEAD/code/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"762172a898132a82","mcp_get_code":{"code_sha256":"762172a898132a82"}},{"arxiv_id":"2401.12973","paper":"/paper/in-context-language-learning-arhitectures-and","title":"In-Context Language Learning: Architectures and Algorithms","date":"2024-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"berlino/seq_icl","path":"generate.py","file_url":"https://github.com/berlino/seq_icl/blob/HEAD/generate.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":"9e64222cc89cf42d","mcp_get_code":{"code_sha256":"9e64222cc89cf42d"}},{"arxiv_id":"2312.03631","paper":"/paper/mocha-multi-objective-reinforcement","title":"Mitigating Open-Vocabulary Caption Hallucinations","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"assafbk/mocha_code","path":"OpenCHAIR/generate_captions.py","file_url":"https://github.com/assafbk/mocha_code/blob/HEAD/OpenCHAIR/generate_captions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"22f204eff2c106a3","mcp_get_code":{"code_sha256":"22f204eff2c106a3"}},{"arxiv_id":"2311.16432","paper":"/paper/text-driven-image-editing-via-learnable","title":"Text-Driven Image Editing via Learnable Regions","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuanze-lin/Learnable_Regions","path":"engine.py","file_url":"https://github.com/yuanze-lin/Learnable_Regions/blob/HEAD/engine.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4c34a449c58f4b7","mcp_get_code":{"code_sha256":"e4c34a449c58f4b7"}},{"arxiv_id":"2311.14632","paper":"/paper/differentially-private-sgd-without-clipping","title":"Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach","date":"2023-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"564612540/DiceSGD","path":"DiceSGD/decoding_utils.py","file_url":"https://github.com/564612540/DiceSGD/blob/HEAD/DiceSGD/decoding_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0dfa7799743daf45","mcp_get_code":{"code_sha256":"0dfa7799743daf45"}},{"arxiv_id":"2311.09060","paper":"/paper/do-localization-methods-actually-localize","title":"Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"terarachang/memdata","path":"utils.py","file_url":"https://github.com/terarachang/memdata/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":"edd9bacc8fb9cfe9","mcp_get_code":{"code_sha256":"edd9bacc8fb9cfe9"}},{"arxiv_id":"2311.04931","paper":"/paper/gpt4all-an-ecosystem-of-open-source","title":"GPT4All: An Ecosystem of Open Source Compressed Language Models","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nomic-ai/gpt4all","path":"gpt4all-training/generate.py","file_url":"https://github.com/nomic-ai/gpt4all/blob/HEAD/gpt4all-training/generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c1b66c904668089","mcp_get_code":{"code_sha256":"7c1b66c904668089"}},{"arxiv_id":"2310.20246","paper":"/paper/breaking-language-barriers-in-multilingual","title":"Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/MathOctopus","path":"step1_supervised_finetuning/prompt_eval.py","file_url":"https://github.com/microsoft/MathOctopus/blob/HEAD/step1_supervised_finetuning/prompt_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"451c619b9609c3c0","mcp_get_code":{"code_sha256":"451c619b9609c3c0"}},{"arxiv_id":"2310.16111","paper":"/paper/locally-differentially-private-document","title":"Locally Differentially Private Document Generation Using Zero Shot Prompting","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saitejautpala/dp_prompt","path":"mechanisms/documentlevel/openai_paraphrase_generation.py","file_url":"https://github.com/saitejautpala/dp_prompt/blob/HEAD/mechanisms/documentlevel/openai_paraphrase_generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b5ebeb9c7fe2859","mcp_get_code":{"code_sha256":"4b5ebeb9c7fe2859"}},{"arxiv_id":"2310.13026","paper":"/paper/weakly-supervised-semantic-segmentation-with-2","title":"Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Models","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaozhengchen/sam_wsss","path":"Tag2Text/batch_inference.py","file_url":"https://github.com/zhaozhengchen/sam_wsss/blob/HEAD/Tag2Text/batch_inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e194cab1dccca09a","mcp_get_code":{"code_sha256":"e194cab1dccca09a"}},{"arxiv_id":"2310.10640","paper":"/paper/llm-blueprint-enabling-text-to-image","title":"LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hananshafi/llmblueprint","path":"models/pipelines.py","file_url":"https://github.com/hananshafi/llmblueprint/blob/HEAD/models/pipelines.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"724401ff948c6e57","mcp_get_code":{"code_sha256":"724401ff948c6e57"}},{"arxiv_id":"2310.10505","paper":"/paper/remax-a-simple-effective-and-efficient-method","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liziniu/ReMax","path":"step1_supervised_finetuning/prompt_eval.py","file_url":"https://github.com/liziniu/ReMax/blob/HEAD/step1_supervised_finetuning/prompt_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"56842aca28dc25b7","mcp_get_code":{"code_sha256":"56842aca28dc25b7"}},{"arxiv_id":"2310.07589","paper":"/paper/goodtriever-adaptive-toxicity-mitigation-with","title":"Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models","date":"2023-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"for-ai/goodtriever","path":"generation/base.py","file_url":"https://github.com/for-ai/goodtriever/blob/HEAD/generation/base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6876cba1d1718afb","mcp_get_code":{"code_sha256":"6876cba1d1718afb"}},{"arxiv_id":"2310.04451","paper":"/paper/autodan-generating-stealthy-jailbreak-prompts","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SheltonLiu-N/AutoDAN","path":"autodan_ga_eval.py","file_url":"https://github.com/SheltonLiu-N/AutoDAN/blob/HEAD/autodan_ga_eval.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0332de7e8c09ed4","mcp_get_code":{"code_sha256":"c0332de7e8c09ed4"}},{"arxiv_id":"2310.04363","paper":"/paper/amortizing-intractable-inference-in-large","title":"Amortizing intractable inference in large language models","date":"2023-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GFNOrg/gfn-lm-tuning","path":"infill_subj_arithmetic/utils.py","file_url":"https://github.com/GFNOrg/gfn-lm-tuning/blob/HEAD/infill_subj_arithmetic/utils.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"086865dae2d16208","mcp_get_code":{"code_sha256":"086865dae2d16208"}},{"arxiv_id":"2310.01753","paper":"/paper/causaltime-realistically-generated-time","title":"CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jarrycyx/unn","path":"CausalTime/generate.py","file_url":"https://github.com/jarrycyx/unn/blob/HEAD/CausalTime/generate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29d0ee7de32d9d14","mcp_get_code":{"code_sha256":"29d0ee7de32d9d14"}},{"arxiv_id":"2310.01717","paper":"/paper/ensemble-distillation-for-unsupervised","title":"Ensemble Distillation for Unsupervised Constituency Parsing","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manga-uofa/ed4ucp","path":"library/ensemble.py","file_url":"https://github.com/manga-uofa/ed4ucp/blob/HEAD/library/ensemble.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b205273797568982","mcp_get_code":{"code_sha256":"b205273797568982"}},{"arxiv_id":"2309.14356","paper":"/paper/coco-counterfactuals-automatically","title":"COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs","date":"2023-09-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"timothybrooks/instruct-pix2pix","path":"dataset_creation/generate_txt_dataset.py","file_url":"https://github.com/timothybrooks/instruct-pix2pix/blob/HEAD/dataset_creation/generate_txt_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"096488ca08edf235","mcp_get_code":{"code_sha256":"096488ca08edf235"}},{"arxiv_id":"2309.06380","paper":"/paper/instaflow-one-step-is-enough-for-high-quality","title":"InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"950ef8f57521a359","mcp_get_code":{"code_sha256":"950ef8f57521a359"}},{"arxiv_id":"2308.02223","paper":"/paper/esrl-efficient-sampling-based-reinforcement","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangclnlp/DeepSpeed-Chat-Extension","path":"rlhf_llama/deepspeed_chat/training/step1_supervised_finetuning/prompt_eval.py","file_url":"https://github.com/wangclnlp/DeepSpeed-Chat-Extension/blob/HEAD/rlhf_llama/deepspeed_chat/training/step1_supervised_finetuning/prompt_eval.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":"451c619b9609c3c0","mcp_get_code":{"code_sha256":"451c619b9609c3c0"}},{"arxiv_id":"2308.02223","paper":"/paper/esrl-efficient-sampling-based-reinforcement","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangclnlp/DeepSpeed-Chat-Extension","path":"rlhf_llama/deepspeed_chat/training/step1_supervised_finetuning/predict.py","file_url":"https://github.com/wangclnlp/DeepSpeed-Chat-Extension/blob/HEAD/rlhf_llama/deepspeed_chat/training/step1_supervised_finetuning/predict.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":"3ba2013469906a98","mcp_get_code":{"code_sha256":"3ba2013469906a98"}},{"arxiv_id":"2307.15593","paper":"/paper/robust-distortion-free-watermarks-for","title":"Robust Distortion-free Watermarks for Language Models","date":"2023-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jthickstun/watermark","path":"watermarking/generation.py","file_url":"https://github.com/jthickstun/watermark/blob/HEAD/watermarking/generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"505be9b1d86f6630","mcp_get_code":{"code_sha256":"505be9b1d86f6630"}},{"arxiv_id":"2307.01467","paper":"/paper/technical-report-for-ego4d-long-term-action","title":"Technical Report for Ego4D Long Term Action Anticipation Challenge 2023","date":"2023-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PanasonicConnect/ego4d_lta_ens_srw_seqdep_verb_noun_cooc","path":"ensemble.py","file_url":"https://github.com/PanasonicConnect/ego4d_lta_ens_srw_seqdep_verb_noun_cooc/blob/HEAD/ensemble.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eaec3ae6c4833b40","mcp_get_code":{"code_sha256":"eaec3ae6c4833b40"}},{"arxiv_id":"2306.04251","paper":"/paper/stochastic-collapse-how-gradient-noise-1","title":"Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks","date":"2023-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ccffccffcc/stochastic_collapse","path":"run/run_teacher_student_general.py","file_url":"https://github.com/ccffccffcc/stochastic_collapse/blob/HEAD/run/run_teacher_student_general.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":"ac76a89a41c4f6bf","mcp_get_code":{"code_sha256":"ac76a89a41c4f6bf"}},{"arxiv_id":"2305.15004","paper":"/paper/llmdet-a-large-language-models-detection-tool","title":"LLMDet: A Third Party Large Language Models Generated Text Detection Tool","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"trustedllm/llmdet","path":"main-experiment/run_main.py","file_url":"https://github.com/trustedllm/llmdet/blob/HEAD/main-experiment/run_main.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0985978d9c86c7ad","mcp_get_code":{"code_sha256":"0985978d9c86c7ad"}},{"arxiv_id":"2305.14766","paper":"/paper/beamsearchqa-large-language-models-are-strong","title":"Allies: Prompting Large Language Model with Beam Search","date":"2023-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/simxns","path":"CAPSTONE/models/generate_query.py","file_url":"https://github.com/microsoft/simxns/blob/HEAD/CAPSTONE/models/generate_query.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"316ed99ac8be6d85","mcp_get_code":{"code_sha256":"316ed99ac8be6d85"}},{"arxiv_id":"2304.09913","paper":"/paper/mars-model-agnostic-biased-object-removal","title":"MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation","date":"2023-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shjo-april/MARS","path":"generate_debiased_masks.py","file_url":"https://github.com/shjo-april/MARS/blob/HEAD/generate_debiased_masks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7a6272d4ec78e50b","mcp_get_code":{"code_sha256":"7a6272d4ec78e50b"}},{"arxiv_id":"2301.10226","paper":"/paper/a-watermark-for-large-language-models","title":"A Watermark for Large Language Models","date":"2023-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BrianPulfer/LMWatermark","path":"src/watermarking.py","file_url":"https://github.com/BrianPulfer/LMWatermark/blob/HEAD/src/watermarking.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e8a3bc02d0c28ef0","mcp_get_code":{"code_sha256":"e8a3bc02d0c28ef0"}},{"arxiv_id":"2301.05571","paper":"/paper/the-2022-n2c2-uw-shared-task-on-extracting","title":"The 2022 n2c2/UW Shared Task on Extracting Social Determinants of Health","date":"2023-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"romanows/sdoh-n2c2","path":"n2c2_ss/generate.py","file_url":"https://github.com/romanows/sdoh-n2c2/blob/HEAD/n2c2_ss/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"3024d5fe7aa433cf","mcp_get_code":{"code_sha256":"3024d5fe7aa433cf"}},{"arxiv_id":"2212.10375","paper":"/paper/self-adaptive-in-context-learning","title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shark-nlp/self-adaptive-icl","path":"src/models/model.py","file_url":"https://github.com/shark-nlp/self-adaptive-icl/blob/HEAD/src/models/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"839daf5f9c094dfa","mcp_get_code":{"code_sha256":"839daf5f9c094dfa"}},{"arxiv_id":"2212.04356","paper":"/paper/robust-speech-recognition-via-large-scale-1","title":"Robust Speech Recognition via Large-Scale Weak Supervision","date":"2022-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ggerganov/whisper.cpp","path":"models/generate-parakeet-test-model.py","file_url":"https://github.com/ggerganov/whisper.cpp/blob/HEAD/models/generate-parakeet-test-model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fef7828e835c938d","mcp_get_code":{"code_sha256":"fef7828e835c938d"}},{"arxiv_id":"2211.17158","paper":"/paper/proximal-residual-flows-for-bayesian-inverse","title":"Proximal Residual Flows for Bayesian Inverse Problems","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johertrich/Proximal_Residual_Flows","path":"circle_example.py","file_url":"https://github.com/johertrich/Proximal_Residual_Flows/blob/HEAD/circle_example.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"78f2d07edb9dc60c","mcp_get_code":{"code_sha256":"78f2d07edb9dc60c"}},{"arxiv_id":"2211.11435","paper":"/paper/zigzag-universal-sampling-free-uncertainty","title":"ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference","date":"2022-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvlab-epfl/zigzag","path":"exps/toy_regression.py","file_url":"https://github.com/cvlab-epfl/zigzag/blob/HEAD/exps/toy_regression.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"58f28107eb819cbe","mcp_get_code":{"code_sha256":"58f28107eb819cbe"}},{"arxiv_id":"2211.10590","paper":"/paper/molecular-structure-property-co-trained","title":"Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model","date":"2022-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinhojsk515/SPMM","path":"d_smiles2pv.py","file_url":"https://github.com/jinhojsk515/SPMM/blob/HEAD/d_smiles2pv.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"67653cf62b485df8","mcp_get_code":{"code_sha256":"67653cf62b485df8"}},{"arxiv_id":"2211.05417","paper":"/paper/can-transformers-reason-in-fragments-of","title":"Can Transformers Reason in Fragments of Natural Language?","date":"2022-11-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"schlevik/nlr","path":"scripts/verify_vampire.py","file_url":"https://github.com/schlevik/nlr/blob/HEAD/scripts/verify_vampire.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b525b5145e14727a","mcp_get_code":{"code_sha256":"b525b5145e14727a"}},{"arxiv_id":"2211.01562","paper":"/paper/pinto-faithful-language-reasoning-using","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","date":"2022-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangpf3/pinto-faithful-language-reasoning","path":"rationalization_prompting.py","file_url":"https://github.com/wangpf3/pinto-faithful-language-reasoning/blob/HEAD/rationalization_prompting.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a751afc2ad7569a8","mcp_get_code":{"code_sha256":"a751afc2ad7569a8"}},{"arxiv_id":"2211.01562","paper":"/paper/pinto-faithful-language-reasoning-using","title":"PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales","date":"2022-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangpf3/pinto-faithful-language-reasoning","path":"rationalization_prompting.py","file_url":"https://github.com/wangpf3/pinto-faithful-language-reasoning/blob/HEAD/rationalization_prompting.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5716784b4097222e","mcp_get_code":{"code_sha256":"5716784b4097222e"}},{"arxiv_id":"2210.14650","paper":"/paper/mocha-a-multi-task-training-approach-for","title":"MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective","date":"2022-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Derekkk/Mocha-EMNLP22","path":"finetune_generation_pipeline.py","file_url":"https://github.com/Derekkk/Mocha-EMNLP22/blob/HEAD/finetune_generation_pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bd0d5e5cd157f481","mcp_get_code":{"code_sha256":"bd0d5e5cd157f481"}},{"arxiv_id":"2207.14288","paper":"/paper/rewriting-geometric-rules-of-a-gan","title":"Rewriting Geometric Rules of a GAN","date":"2022-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"peterwang512/ganwarping","path":"sample.py","file_url":"https://github.com/peterwang512/ganwarping/blob/HEAD/sample.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0d08a481f4674ea","mcp_get_code":{"code_sha256":"c0d08a481f4674ea"}},{"arxiv_id":"2207.12598","paper":"/paper/classifier-free-diffusion-guidance","title":"Classifier-Free Diffusion Guidance","date":"2022-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kjsman/stable-diffusion-pytorch","path":"stable_diffusion_pytorch/pipeline.py","file_url":"https://github.com/kjsman/stable-diffusion-pytorch/blob/HEAD/stable_diffusion_pytorch/pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f3f744a1397430c9","mcp_get_code":{"code_sha256":"f3f744a1397430c9"}},{"arxiv_id":"2106.07447","paper":"/paper/hubert-self-supervised-speech-representation","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","date":"2021-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BirgerMoell/tmh","path":"tmh/generate_code.py","file_url":"https://github.com/BirgerMoell/tmh/blob/HEAD/tmh/generate_code.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e9f1ccc33723e6cc","mcp_get_code":{"code_sha256":"e9f1ccc33723e6cc"}},{"arxiv_id":"2105.14781","paper":"/paper/a-semantic-based-method-for-unsupervised","title":"A Semantic-based Method for Unsupervised Commonsense Question Answering","date":"2021-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"heylinsir/semantic-based-qa","path":"src/run_SEQA_generation.py","file_url":"https://github.com/heylinsir/semantic-based-qa/blob/HEAD/src/run_SEQA_generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e57d410ad181fe8a","mcp_get_code":{"code_sha256":"e57d410ad181fe8a"}},{"arxiv_id":"2102.11495","paper":"/paper/anytime-sampling-for-autoregressive-models-1","title":"Anytime Sampling for Autoregressive Models via Ordered Autoencoding","date":"2021-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Newbeeer/Anytime-Auto-Regressive-Model","path":"transfomer_sample.py","file_url":"https://github.com/Newbeeer/Anytime-Auto-Regressive-Model/blob/HEAD/transfomer_sample.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c65865cbf1037896","mcp_get_code":{"code_sha256":"c65865cbf1037896"}},{"arxiv_id":"2010.04831","paper":"/paper/improving-local-identifiability-in","title":"Improving Local Identifiability in Probabilistic Box Embeddings","date":"2020-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iesl/geometric_graph_embedding","path":"src/graph_modeling/generate/hac.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/hac.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":"32e8c69cc44844db","mcp_get_code":{"code_sha256":"32e8c69cc44844db"}},{"arxiv_id":"2010.04831","paper":"/paper/improving-local-identifiability-in","title":"Improving Local Identifiability in Probabilistic Box Embeddings","date":"2020-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iesl/geometric_graph_embedding","path":"src/graph_modeling/generate/knn_graph.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/knn_graph.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":"6b17a38b61efff88","mcp_get_code":{"code_sha256":"6b17a38b61efff88"}},{"arxiv_id":"2010.04831","paper":"/paper/improving-local-identifiability-in","title":"Improving Local Identifiability in Probabilistic Box Embeddings","date":"2020-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iesl/geometric_graph_embedding","path":"src/graph_modeling/generate/kronecker_graph.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/kronecker_graph.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":"9c877d5a9cfe2a1d","mcp_get_code":{"code_sha256":"9c877d5a9cfe2a1d"}},{"arxiv_id":"2010.04831","paper":"/paper/improving-local-identifiability-in","title":"Improving Local Identifiability in Probabilistic Box Embeddings","date":"2020-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iesl/geometric_graph_embedding","path":"src/graph_modeling/generate/price.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/price.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":"3e86800f7a81f156","mcp_get_code":{"code_sha256":"3e86800f7a81f156"}},{"arxiv_id":"2010.04831","paper":"/paper/improving-local-identifiability-in","title":"Improving Local Identifiability in Probabilistic Box Embeddings","date":"2020-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iesl/geometric_graph_embedding","path":"src/graph_modeling/generate/random_tree.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/random_tree.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":"dc0c718b09c9a0c8","mcp_get_code":{"code_sha256":"dc0c718b09c9a0c8"}},{"arxiv_id":"2008.06048","paper":"/paper/mmm-exploring-conditional-multi-track-music","title":"MMM : Exploring Conditional Multi-Track Music Generation with the Transformer","date":"2020-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AI-Guru/MMM-JSB","path":"source/helpers/samplinghelpers.py","file_url":"https://github.com/AI-Guru/MMM-JSB/blob/HEAD/source/helpers/samplinghelpers.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":"573835f67b3e07a7","mcp_get_code":{"code_sha256":"573835f67b3e07a7"}},{"arxiv_id":"2007.02871","paper":"/paper/dart-open-domain-structured-data-record-to","title":"DART: Open-Domain Structured Data Record to Text Generation","date":"2020-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Mandar-Sharma/TCube","path":"finetuned.py","file_url":"https://github.com/Mandar-Sharma/TCube/blob/HEAD/finetuned.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"96907642b314c1ca","mcp_get_code":{"code_sha256":"96907642b314c1ca"}},{"arxiv_id":"2006.15720","paper":"/paper/progressive-generation-of-long-text","title":"Progressive Generation of Long Text with Pretrained Language Models","date":"2020-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tanyuqian/progressive-generation","path":"generate.py","file_url":"https://github.com/tanyuqian/progressive-generation/blob/HEAD/generate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5084331f911582f8","mcp_get_code":{"code_sha256":"5084331f911582f8"}},{"arxiv_id":"2006.11184","paper":"/paper/poisson-learning-graph-based-semi-supervised","title":"Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates","date":"2020-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jwcalder/GraphLearning","path":"graphlearning/trainsets.py","file_url":"https://github.com/jwcalder/GraphLearning/blob/HEAD/graphlearning/trainsets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f7accee6395b5f14","mcp_get_code":{"code_sha256":"f7accee6395b5f14"}},{"arxiv_id":"2003.02245","paper":"/paper/data-augmentation-using-pre-trained","title":"Data Augmentation using Pre-trained Transformer Models","date":"2020-03-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"megagonlabs/rotom","path":"invda/generate.py","file_url":"https://github.com/megagonlabs/rotom/blob/HEAD/invda/generate.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":"d5838e93b4af1c05","mcp_get_code":{"code_sha256":"d5838e93b4af1c05"}},{"arxiv_id":"1909.00949","paper":"/paper/data-driven-approach-to-encoding-and-decoding","title":"Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures","date":"2019-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hoffmannjordan/Encoding-Decoding-3D-Crystals","path":"Generate.py","file_url":"https://github.com/hoffmannjordan/Encoding-Decoding-3D-Crystals/blob/HEAD/Generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26a09e75f29b8c0d","mcp_get_code":{"code_sha256":"26a09e75f29b8c0d"}},{"arxiv_id":"1909.00949","paper":"/paper/data-driven-approach-to-encoding-and-decoding","title":"Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures","date":"2019-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hoffmannjordan/Encoding-Decoding-3D-Crystals","path":"Generate_Single_Unit_Data.py","file_url":"https://github.com/hoffmannjordan/Encoding-Decoding-3D-Crystals/blob/HEAD/Generate_Single_Unit_Data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f947a0d085163d54","mcp_get_code":{"code_sha256":"f947a0d085163d54"}},{"arxiv_id":"1901.08149","paper":"/paper/transfertransfo-a-transfer-learning-approach","title":"TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents","date":"2019-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"noriyukipy/gptchat","path":"gptchat/chatlm/lib.py","file_url":"https://github.com/noriyukipy/gptchat/blob/HEAD/gptchat/chatlm/lib.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1d561f2cbca372e3","mcp_get_code":{"code_sha256":"1d561f2cbca372e3"}},{"arxiv_id":"1806.11006","paper":"/paper/learning-implicit-generative-models-with-the","title":"Learning Implicit Generative Models with the Method of Learned Moments","date":"2018-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cibeah/molm","path":"src/generate.py","file_url":"https://github.com/cibeah/molm/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":"48afd1f1fd9b238b","mcp_get_code":{"code_sha256":"48afd1f1fd9b238b"}},{"arxiv_id":"1611.08050","paper":"/paper/realtime-multi-person-2d-pose-estimation","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","date":"2016-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/max-human-pose-estimator","path":"core/tf_pose/slidingwindow/SlidingWindow.py","file_url":"https://github.com/ibm/max-human-pose-estimator/blob/HEAD/core/tf_pose/slidingwindow/SlidingWindow.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":"cdb1c9715688f9a1","mcp_get_code":{"code_sha256":"cdb1c9715688f9a1"}},{"arxiv_id":"1508.04025","paper":"/paper/effective-approaches-to-attention-based","title":"Effective Approaches to Attention-based Neural Machine Translation","date":"2015-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"riversdie/chatbot","path":"train_eval.py","file_url":"https://github.com/riversdie/chatbot/blob/HEAD/train_eval.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":"d69ad61c90b8b0e6","mcp_get_code":{"code_sha256":"d69ad61c90b8b0e6"}},{"arxiv_id":"aaai_26497","paper":null,"title":"arXiv:aaai_26497","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hexuandeng/Mono4SiMT","path":"utility/simultaneous_translation/models/nat_utils.py","file_url":"https://github.com/hexuandeng/Mono4SiMT/blob/HEAD/utility/simultaneous_translation/models/nat_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":"a446425731c52c3a","mcp_get_code":{"code_sha256":"a446425731c52c3a"}},{"arxiv_id":"aaai_26259","paper":null,"title":"arXiv:aaai_26259","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"stxupengyu/LSFA","path":"transfer/generator.py","file_url":"https://github.com/stxupengyu/LSFA/blob/HEAD/transfer/generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4c16e05e85e7864d","mcp_get_code":{"code_sha256":"4c16e05e85e7864d"}},{"arxiv_id":"2025.findings-acl.583","paper":null,"title":"arXiv:2025.findings-acl.583","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"CSHaitao/LexiLaw","path":"inference_finetune.py","file_url":"https://github.com/CSHaitao/LexiLaw/blob/HEAD/inference_finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b708930c3633638c","mcp_get_code":{"code_sha256":"b708930c3633638c"}},{"arxiv_id":"2024.naacl-long.326","paper":null,"title":"arXiv:2024.naacl-long.326","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"LanXiu0523/RLHF_instructGPT","path":"applications/inference/prompt_eval.py","file_url":"https://github.com/LanXiu0523/RLHF_instructGPT/blob/HEAD/applications/inference/prompt_eval.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":"451c619b9609c3c0","mcp_get_code":{"code_sha256":"451c619b9609c3c0"}},{"arxiv_id":"2024.naacl-long.176","paper":null,"title":"arXiv:2024.naacl-long.176","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"terarachang/MemPi","path":"utils.py","file_url":"https://github.com/terarachang/MemPi/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":"edd9bacc8fb9cfe9","mcp_get_code":{"code_sha256":"edd9bacc8fb9cfe9"}},{"arxiv_id":"2024.emnlp-main.1138","paper":null,"title":"arXiv:2024.emnlp-main.1138","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"aoi3142/Waterfall","path":"waterfall/group-beam-search/custom_generate/generate.py","file_url":"https://github.com/aoi3142/Waterfall/blob/HEAD/waterfall/group-beam-search/custom_generate/generate.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":"e82bfea8b311483b","mcp_get_code":{"code_sha256":"e82bfea8b311483b"}},{"arxiv_id":"2023.findings-emnlp.730","paper":null,"title":"arXiv:2023.findings-emnlp.730","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"chufeiluo/legalhatespeech","path":"zeroshot/generate_openai.py","file_url":"https://github.com/chufeiluo/legalhatespeech/blob/HEAD/zeroshot/generate_openai.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0c5ceab3960dcd2","mcp_get_code":{"code_sha256":"b0c5ceab3960dcd2"}},{"arxiv_id":"2023.findings-emnlp.566","paper":null,"title":"arXiv:2023.findings-emnlp.566","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SaitejaUtpala/dp_prompt","path":"mechanisms/documentlevel/openai_paraphrase_generation.py","file_url":"https://github.com/SaitejaUtpala/dp_prompt/blob/HEAD/mechanisms/documentlevel/openai_paraphrase_generation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b5ebeb9c7fe2859","mcp_get_code":{"code_sha256":"4b5ebeb9c7fe2859"}},{"arxiv_id":"2023.findings-emnlp.269","paper":null,"title":"arXiv:2023.findings-emnlp.269","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PhoebusSi/Alpaca-CoT","path":"eval/generate.py","file_url":"https://github.com/PhoebusSi/Alpaca-CoT/blob/HEAD/eval/generate.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":"53f1cb672cc37e65","mcp_get_code":{"code_sha256":"53f1cb672cc37e65"}},{"arxiv_id":"2023.findings-emnlp.139","paper":null,"title":"arXiv:2023.findings-emnlp.139","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"TrustedLLM/LLMDet","path":"main-experiment/run_main.py","file_url":"https://github.com/TrustedLLM/LLMDet/blob/HEAD/main-experiment/run_main.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0985978d9c86c7ad","mcp_get_code":{"code_sha256":"0985978d9c86c7ad"}}]}