{"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/precompute-freqs-cis","entry":"precompute_freqs_cis","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":112,"n_papers_ran":88,"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":38,"n_samples_ran":24,"n_samples_fingerprinted":7,"n_places":112,"n_places_pointer_only":47,"by_status":{"ran_honours":5,"ran_violates":8,"ran_draft_wrong":2,"ran_fixture":0,"ran":9,"unverified":14},"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":"2609.15740","paper":"/paper/arxiv-2609-15740","title":"A Language‐Guided Multimodal Foundation Model for Zero‐Shot and Multi‐Task Brain Signal Analysis","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"mingzhi-c/metis-brain-signal-foundation-model","path":"METIS.py","file_url":"https://github.com/mingzhi-c/metis-brain-signal-foundation-model/blob/HEAD/METIS.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":"7a52e1765c783a59","mcp_get_code":{"code_sha256":"7a52e1765c783a59"}},{"arxiv_id":"2606.25391","paper":"/paper/arxiv-2606-25391","title":"From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Zyphra/Zonos","path":"zonos/backbone/_torch.py","file_url":"https://github.com/Zyphra/Zonos/blob/HEAD/zonos/backbone/_torch.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":"69df00a4d0767920","mcp_get_code":{"code_sha256":"69df00a4d0767920"}},{"arxiv_id":"2606.14259","paper":"/paper/arxiv-2606-14259","title":"Beyond a Single Explanation of the Adam-SGD Gap","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"orientino/gap","path":"language/model.py","file_url":"https://github.com/orientino/gap/blob/HEAD/language/model.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":"07d78260ee121828","mcp_get_code":{"code_sha256":"07d78260ee121828"}},{"arxiv_id":"2605.27980","paper":"/paper/arxiv-2605-27980","title":"Periodic RoPE for Infinite Context LLMs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Cominder/miniwin","path":"model/model_miniwin.py","file_url":"https://github.com/Cominder/miniwin/blob/HEAD/model/model_miniwin.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2b0c31e541c23409","mcp_get_code":{"code_sha256":"2b0c31e541c23409"}},{"arxiv_id":"2605.19811","paper":"/paper/arxiv-2605-19811","title":"LionMuon: Alternating Spectral and Sign Descent for Efficient Training","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"brain-lab-research/lion-muon","path":"src/models/llama.py","file_url":"https://github.com/brain-lab-research/lion-muon/blob/HEAD/src/models/llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1d6f89d43fc42e1","mcp_get_code":{"code_sha256":"a1d6f89d43fc42e1"}},{"arxiv_id":"2605.14249","paper":"/paper/arxiv-2605-14249","title":"EnergyLens: Predictive Energy-Aware Exploration for Multi-GPU LLM Inference Optimization","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"meta-llama/llama3","path":"llama/model.py","file_url":"https://github.com/meta-llama/llama3/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2605.06615","paper":"/paper/arxiv-2605-06615","title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on ℓ 1 -norm Lower Bounds","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"epfml/llm-optimizer-benchmark","path":"src/models/llama.py","file_url":"https://github.com/epfml/llm-optimizer-benchmark/blob/HEAD/src/models/llama.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":"a1d6f89d43fc42e1","mcp_get_code":{"code_sha256":"a1d6f89d43fc42e1"}},{"arxiv_id":"2604.11628","paper":"/paper/arxiv-2604-11628","title":"Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"qingyue2014/Rsum","path":"llama/model.py","file_url":"https://github.com/qingyue2014/Rsum/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2602.07425","paper":"/paper/arxiv-2602-07425","title":"Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise","date":"2026-02-07","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"Dingzhen230/Heavy-tailed-Noise-in-LLMs","path":"src/models/llama.py","file_url":"https://github.com/Dingzhen230/Heavy-tailed-Noise-in-LLMs/blob/HEAD/src/models/llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a1d6f89d43fc42e1","mcp_get_code":{"code_sha256":"a1d6f89d43fc42e1"}},{"arxiv_id":"2602.06283","paper":"/paper/arxiv-2602-06283","title":"SOCKET: SOft Collision Kernel EsTimator for Sparse Attention","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"amarka8/SOCKET","path":"GPT-FAST/model.py","file_url":"https://github.com/amarka8/SOCKET/blob/HEAD/GPT-FAST/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"26cf476e99a51b14","mcp_get_code":{"code_sha256":"26cf476e99a51b14"}},{"arxiv_id":"2602.02016","paper":"/paper/arxiv-2602-02016","title":"DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"IST-DASLab/DASH","path":"src/models/llama.py","file_url":"https://github.com/IST-DASLab/DASH/blob/HEAD/src/models/llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1d6f89d43fc42e1","mcp_get_code":{"code_sha256":"a1d6f89d43fc42e1"}},{"arxiv_id":"2602.01212","paper":"/paper/arxiv-2602-01212","title":"SimpleGPT: Improving GPT via A Simple Normalization Strategy","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Ocram7/SimpleGPT","path":"src/torchtitan/models/llama/simplegpt_model.py","file_url":"https://github.com/Ocram7/SimpleGPT/blob/HEAD/src/torchtitan/models/llama/simplegpt_model.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":"6d2474603ba25d5b","mcp_get_code":{"code_sha256":"6d2474603ba25d5b"}},{"arxiv_id":"2601.01313","paper":"/paper/arxiv-2601-01313","title":"Spectral-Window Hybrid (SWH)","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"VladimerKhasia/SWH","path":"swh.py","file_url":"https://github.com/VladimerKhasia/SWH/blob/HEAD/swh.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a5fad1cce30ed63d","mcp_get_code":{"code_sha256":"a5fad1cce30ed63d"}},{"arxiv_id":"2510.06195","paper":"/paper/arxiv-2510-06195","title":"Latent Speech-Text Transformer","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"facebookresearch/lst","path":"lst/base_transformer.py","file_url":"https://github.com/facebookresearch/lst/blob/HEAD/lst/base_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1775c1f6cd5bd79c","mcp_get_code":{"code_sha256":"1775c1f6cd5bd79c"}},{"arxiv_id":"2509.25727","paper":"/paper/arxiv-2509-25727","title":"Boundary-to-Region Supervision for Offline Safe Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"HuikangSu/B2R","path":"model/B2R.py","file_url":"https://github.com/HuikangSu/B2R/blob/HEAD/model/B2R.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dbdbe67ef2907465","mcp_get_code":{"code_sha256":"dbdbe67ef2907465"}},{"arxiv_id":"2507.09846","paper":null,"title":"arXiv:2507.09846","date":null,"month_inferred_from_arxiv_id":"2025-07","title_source":null,"repo":"epfml/llm-baselines","path":"src/models/llama.py","file_url":"https://github.com/epfml/llm-baselines/blob/HEAD/src/models/llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1d6f89d43fc42e1","mcp_get_code":{"code_sha256":"a1d6f89d43fc42e1"}},{"arxiv_id":"2507.03738","paper":"/paper/flow-anchored-consistency-models","title":"Flow-Anchored Consistency Models","date":"2025-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ali-vilab/FACM","path":"ldit/rmsnorm.py","file_url":"https://github.com/ali-vilab/FACM/blob/HEAD/ldit/rmsnorm.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2507.02199","paper":"/paper/latent-chain-of-thought-decoding-the-depth","title":"Latent Chain-of-Thought? Decoding the Depth-Recurrent Transformer","date":"2025-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenquanlu/huginn-latent-cot","path":"huginn-predrank/raven_modeling_minimal.py","file_url":"https://github.com/wenquanlu/huginn-latent-cot/blob/HEAD/huginn-predrank/raven_modeling_minimal.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"db336122f09999c7","mcp_get_code":{"code_sha256":"db336122f09999c7"}},{"arxiv_id":"2507.02092","paper":"/paper/energy-based-transformers-are-scalable","title":"Energy-Based Transformers are Scalable Learners and Thinkers","date":"2025-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alexiglad/EBT","path":"model/ar_ebt_adaln.py","file_url":"https://github.com/alexiglad/EBT/blob/HEAD/model/ar_ebt_adaln.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2506.00385","paper":"/paper/magicodec-simple-masked-gaussian-injected","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","date":"2025-05-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ereboas/MagiCodec","path":"roformer.py","file_url":"https://github.com/Ereboas/MagiCodec/blob/HEAD/roformer.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2505.24722","paper":"/paper/helm-hyperbolic-large-language-models-via","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"graph-and-geometric-learning/helm","path":"helm/modules/helm_mice.py","file_url":"https://github.com/graph-and-geometric-learning/helm/blob/HEAD/helm/modules/helm_mice.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1d8d0f6a118d39b","mcp_get_code":{"code_sha256":"f1d8d0f6a118d39b"}},{"arxiv_id":"2505.23660","paper":"/paper/d-ar-diffusion-via-autoregressive-models","title":"D-AR: Diffusion via Autoregressive Models","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/d-ar","path":"autoregressive/models/gpt.py","file_url":"https://github.com/showlab/d-ar/blob/HEAD/autoregressive/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f0ff4e443413018","mcp_get_code":{"code_sha256":"0f0ff4e443413018"}},{"arxiv_id":"2505.15559","paper":"/paper/moonbeam-a-midi-foundation-model-using-both","title":"Moonbeam: A MIDI Foundation Model Using Both Absolute and Relative Music Attributes","date":"2025-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guozixunnicolas/Moonbeam-MIDI-Foundation-Model","path":"generation/llama/model.py","file_url":"https://github.com/guozixunnicolas/Moonbeam-MIDI-Foundation-Model/blob/HEAD/generation/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2505.14673","paper":"/paper/training-free-watermarking-for-autoregressive","title":"Training-Free Watermarking for Autoregressive Image Generation","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maifoundations/indexmark","path":"autoregressive/models/gpt.py","file_url":"https://github.com/maifoundations/indexmark/blob/HEAD/autoregressive/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f0ff4e443413018","mcp_get_code":{"code_sha256":"0f0ff4e443413018"}},{"arxiv_id":"2505.07447","paper":"/paper/unified-continuous-generative-models","title":"Unified Continuous Generative Models","date":"2025-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LINs-Lab/UCGM","path":"networks/rmsnorm.py","file_url":"https://github.com/LINs-Lab/UCGM/blob/HEAD/networks/rmsnorm.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2505.02707","paper":"/paper/voila-voice-language-foundation-models-for","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","date":"2025-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maitrix-org/Voila","path":"model.py","file_url":"https://github.com/maitrix-org/Voila/blob/HEAD/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ede455eda0bef78","mcp_get_code":{"code_sha256":"3ede455eda0bef78"}},{"arxiv_id":"2503.10568","paper":"/paper/autoregressive-image-generation-with","title":"Autoregressive Image Generation with Randomized Parallel Decoding","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hp-l33/ARPG","path":"models/arpg.py","file_url":"https://github.com/hp-l33/ARPG/blob/HEAD/models/arpg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f0ff4e443413018","mcp_get_code":{"code_sha256":"0f0ff4e443413018"}},{"arxiv_id":"2503.01183","paper":"/paper/diffrhythm-blazingly-fast-and-embarrassingly","title":"DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion","date":"2025-03-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aslp-lab/diffrhythm","path":"model/modules.py","file_url":"https://github.com/aslp-lab/diffrhythm/blob/HEAD/model/modules.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":"5643293edbb8503b","mcp_get_code":{"code_sha256":"5643293edbb8503b"}},{"arxiv_id":"2502.05171","paper":"/paper/scaling-up-test-time-compute-with-latent","title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","date":"2025-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seal-rg/recurrent-pretraining","path":"recpre/legacy_modeling_file.py","file_url":"https://github.com/seal-rg/recurrent-pretraining/blob/HEAD/recpre/legacy_modeling_file.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":"db336122f09999c7","mcp_get_code":{"code_sha256":"db336122f09999c7"}},{"arxiv_id":"2502.05003","paper":"/paper/quest-stable-training-of-llms-with-1-bit","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","date":"2025-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IST-DASLab/QuEST","path":"src/models/llama.py","file_url":"https://github.com/IST-DASLab/QuEST/blob/HEAD/src/models/llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1d6f89d43fc42e1","mcp_get_code":{"code_sha256":"a1d6f89d43fc42e1"}},{"arxiv_id":"2501.18993","paper":"/paper/visual-autoregressive-modeling-for-image","title":"Visual Autoregressive Modeling for Image Super-Resolution","date":"2025-01-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qyp2000/varsr","path":"models/basic_var.py","file_url":"https://github.com/qyp2000/varsr/blob/HEAD/models/basic_var.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a9b92fd04c7a2673","mcp_get_code":{"code_sha256":"a9b92fd04c7a2673"}},{"arxiv_id":"2501.12375","paper":"/paper/video-depth-anything-consistent-depth","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","date":"2025-01-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DepthAnything/Video-Depth-Anything","path":"video_depth_anything/motion_module/attention.py","file_url":"https://github.com/DepthAnything/Video-Depth-Anything/blob/HEAD/video_depth_anything/motion_module/attention.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2501.06589","paper":"/paper/ladder-residual-parallelism-aware","title":"Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping","date":"2025-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mayank31398/ladder-residual-inference","path":"gpt_fast/utils.py","file_url":"https://github.com/mayank31398/ladder-residual-inference/blob/HEAD/gpt_fast/utils.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":"410ff1b0adf4919f","mcp_get_code":{"code_sha256":"410ff1b0adf4919f"}},{"arxiv_id":"2501.06425","paper":"/paper/tensor-product-attention-is-all-you-need","title":"Tensor Product Attention Is All You Need","date":"2025-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tensorgi/t6","path":"model/T6_infer.py","file_url":"https://github.com/tensorgi/t6/blob/HEAD/model/T6_infer.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2501.04003","paper":"/paper/are-vlms-ready-for-autonomous-driving-an","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","date":"2025-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendrivelab/drivelm","path":"challenge/llama_adapter_v2_multimodal7b/llama/llama.py","file_url":"https://github.com/opendrivelab/drivelm/blob/HEAD/challenge/llama_adapter_v2_multimodal7b/llama/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2412.19505","paper":"/paper/drivingworld-constructingworld-model-for","title":"DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT","date":"2024-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yvanyin/drivingworld","path":"modules/tokenizers/vq_model.py","file_url":"https://github.com/yvanyin/drivingworld/blob/HEAD/modules/tokenizers/vq_model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2412.19437","paper":"/paper/deepseek-v3-technical-report","title":"DeepSeek-V3 Technical Report","date":"2024-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepseek-ai/DeepSeek-V3","path":"inference/model.py","file_url":"https://github.com/deepseek-ai/DeepSeek-V3/blob/HEAD/inference/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cfcfae6065924a81","mcp_get_code":{"code_sha256":"cfcfae6065924a81"}},{"arxiv_id":"2412.16526","paper":"/paper/text2midi-generating-symbolic-music-from","title":"Text2midi: Generating Symbolic Music from Captions","date":"2024-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amaai-lab/text2midi","path":"model/transformer_model.py","file_url":"https://github.com/amaai-lab/text2midi/blob/HEAD/model/transformer_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0c7e59e5cad99393","mcp_get_code":{"code_sha256":"0c7e59e5cad99393"}},{"arxiv_id":"2412.09871","paper":"/paper/byte-latent-transformer-patches-scale-better","title":"Byte Latent Transformer: Patches Scale Better Than Tokens","date":"2024-12-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/blt","path":"bytelatent/base_transformer.py","file_url":"https://github.com/facebookresearch/blt/blob/HEAD/bytelatent/base_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1775c1f6cd5bd79c","mcp_get_code":{"code_sha256":"1775c1f6cd5bd79c"}},{"arxiv_id":"2412.08781","paper":"/paper/generative-modeling-with-explicit-memory","title":"Generative Modeling with Explicit Memory","date":"2024-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lins-lab/gmem","path":"models/rmsnorm.py","file_url":"https://github.com/lins-lab/gmem/blob/HEAD/models/rmsnorm.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2412.06660","paper":"/paper/mumu-llama-multi-modal-music-understanding","title":"MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models","date":null,"month_inferred_from_arxiv_id":"2024-12","title_source":"archive","repo":"shansongliu/MuMu-LLaMA","path":"MuMu-LLaMA/llama/llama.py","file_url":"https://github.com/shansongliu/MuMu-LLaMA/blob/HEAD/MuMu-LLaMA/llama/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2412.04062","paper":"/paper/zipar-accelerating-autoregressive-image","title":"ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality","date":"2024-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ThisisBillhe/ZipAR","path":"LlamaGen-ZipAR/autoregressive/models/gpt.py","file_url":"https://github.com/ThisisBillhe/ZipAR/blob/HEAD/LlamaGen-ZipAR/autoregressive/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0f0ff4e443413018","mcp_get_code":{"code_sha256":"0f0ff4e443413018"}},{"arxiv_id":"2411.16585","paper":"/paper/marketgpt-developing-a-pre-trained","title":"MarketGPT: Developing a Pre-trained transformer (GPT) for Modeling Financial Time Series","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"5f447bdd807ed3c0","mcp_get_code":{"code_sha256":"5f447bdd807ed3c0"}},{"arxiv_id":"2411.15867","paper":"/paper/panollama-generating-endless-and-coherent","title":"PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs","date":"2024-11-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"0606zt/panollama","path":"token_generator/gpt.py","file_url":"https://github.com/0606zt/panollama/blob/HEAD/token_generator/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0f0ff4e443413018","mcp_get_code":{"code_sha256":"0f0ff4e443413018"}},{"arxiv_id":"2411.07506","paper":"/paper/fm-ts-flow-matching-for-time-series","title":"FM-TS: Flow Matching for Time Series Generation","date":"2024-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"unites-lab/fmts","path":"FMTS/Models/interpretable_diffusion/transformer.py","file_url":"https://github.com/unites-lab/fmts/blob/HEAD/FMTS/Models/interpretable_diffusion/transformer.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2411.07176","paper":"/paper/more-expressive-attention-with-negative","title":"More Expressive Attention with Negative Weights","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2411.06790","paper":"/paper/large-scale-moral-machine-experiment-on-large","title":"Large-scale moral machine experiment on large language models","date":"2024-11-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kztakemoto/mmllm","path":"llama/model.py","file_url":"https://github.com/kztakemoto/mmllm/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2411.04165","paper":"/paper/bio-xlstm-generative-modeling-representation","title":"Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-jku/dna-xlstm","path":"models/dna_xlstm/xlstm/xlstm_block_stack.py","file_url":"https://github.com/ml-jku/dna-xlstm/blob/HEAD/models/dna_xlstm/xlstm/xlstm_block_stack.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":"2bf924786015498d","mcp_get_code":{"code_sha256":"2bf924786015498d"}},{"arxiv_id":"2410.23856","paper":"/paper/can-language-models-perform-robust-reasoning","title":"Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/NoisyRationales","path":"llm_model/llama/model.py","file_url":"https://github.com/tmlr-group/NoisyRationales/blob/HEAD/llm_model/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2410.15495","paper":"/paper/sea-state-exchange-attention-for-high","title":"SEA: State-Exchange Attention for High-Fidelity Physics Based Transformers","date":"2024-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"parsaesmati/sea","path":"models/temporal.py","file_url":"https://github.com/parsaesmati/sea/blob/HEAD/models/temporal.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2410.14195","paper":"/paper/rethinking-transformer-for-long-contextual","title":"Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"invoker-ll/long-mil","path":"LongMIL.py","file_url":"https://github.com/invoker-ll/long-mil/blob/HEAD/LongMIL.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"721963cc5d972a2f","mcp_get_code":{"code_sha256":"721963cc5d972a2f"}},{"arxiv_id":"2410.11623","paper":"/paper/videgothink-assessing-egocentric-video","title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adacheng/egothink","path":"models/llama_adapter_v2/llama.py","file_url":"https://github.com/adacheng/egothink/blob/HEAD/models/llama_adapter_v2/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2410.06511","paper":"/paper/torchtitan-one-stop-pytorch-native-solution","title":"TorchTitan: One-stop PyTorch native solution for production ready LLM pre-training","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-easl/torchtitan-mixtera","path":"torchtitan/models/llama3/model.py","file_url":"https://github.com/eth-easl/torchtitan-mixtera/blob/HEAD/torchtitan/models/llama3/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"1a557a96fabbca72","mcp_get_code":{"code_sha256":"1a557a96fabbca72"}},{"arxiv_id":"2410.03996","paper":"/paper/on-the-influence-of-gender-and-race-in","title":"On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models","date":"2024-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/llama","path":"llama/model.py","file_url":"https://github.com/facebookresearch/llama/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2410.02705","paper":"/paper/controlar-controllable-image-generation-with","title":"ControlAR: Controllable Image Generation with Autoregressive Models","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hustvl/ControlAR","path":"autoregressive/models/gpt.py","file_url":"https://github.com/hustvl/ControlAR/blob/HEAD/autoregressive/models/gpt.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":"0f0ff4e443413018","mcp_get_code":{"code_sha256":"0f0ff4e443413018"}},{"arxiv_id":"2409.17027","paper":"/paper/counterfactual-token-generation-in-large","title":"Counterfactual Token Generation in Large Language Models","date":"2024-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"networks-learning/counterfactual-llms","path":"src/mistral-inference/moe_one_file_ref.py","file_url":"https://github.com/networks-learning/counterfactual-llms/blob/HEAD/src/mistral-inference/moe_one_file_ref.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"99e0ca21ba709107","mcp_get_code":{"code_sha256":"99e0ca21ba709107"}},{"arxiv_id":"2409.13689","paper":"/paper/temporally-aligned-audio-for-video-with","title":"Temporally Aligned Audio for Video with Autoregression","date":"2024-09-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ilpoviertola/V-AURA","path":"models/modules/sampler/llama.py","file_url":"https://github.com/ilpoviertola/V-AURA/blob/HEAD/models/modules/sampler/llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2c69b343e0f9b255","mcp_get_code":{"code_sha256":"2c69b343e0f9b255"}},{"arxiv_id":"2408.15980","paper":"/paper/in-context-imitation-learning-via-next-token","title":"In-Context Imitation Learning via Next-Token Prediction","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Max-Fu/icrt","path":"icrt/models/policy/llama.py","file_url":"https://github.com/Max-Fu/icrt/blob/HEAD/icrt/models/policy/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2408.15689","paper":"/paper/tempoformer-a-transformer-for-temporally","title":"TempoFormer: A Transformer for Temporally-aware Representations in Change Detection","date":"2024-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ttseriotou/tempoformer","path":"models/rope_mha.py","file_url":"https://github.com/ttseriotou/tempoformer/blob/HEAD/models/rope_mha.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e9daf89ef84b1379","mcp_get_code":{"code_sha256":"e9daf89ef84b1379"}},{"arxiv_id":"2408.11039","paper":"/paper/transfusion-predict-the-next-token-and","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","date":"2024-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VachanVY/Transfusion.torch","path":"src/llama2c.py","file_url":"https://github.com/VachanVY/Transfusion.torch/blob/HEAD/src/llama2c.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5f447bdd807ed3c0","mcp_get_code":{"code_sha256":"5f447bdd807ed3c0"}},{"arxiv_id":"2408.07092","paper":"/paper/post-training-sparse-attention-with-double","title":"Post-Training Sparse Attention with Double Sparsity","date":"2024-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andy-yang-1/doublesparse","path":"models/model.py","file_url":"https://github.com/andy-yang-1/doublesparse/blob/HEAD/models/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26cf476e99a51b14","mcp_get_code":{"code_sha256":"26cf476e99a51b14"}},{"arxiv_id":"2408.01933","paper":"/paper/2408-01933","title":"DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models","date":"2024-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wbw520/DiReCT","path":"llama/model.py","file_url":"https://github.com/wbw520/DiReCT/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2407.15051","paper":"/paper/prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fletcherjiang/llmepet","path":"llm_epet/llama.py","file_url":"https://github.com/fletcherjiang/llmepet/blob/HEAD/llm_epet/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2406.16793","paper":"/paper/adam-mini-use-fewer-learning-rates-to-gain","title":"Adam-mini: Use Fewer Learning Rates To Gain More","date":"2024-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"1a557a96fabbca72","mcp_get_code":{"code_sha256":"1a557a96fabbca72"}},{"arxiv_id":"2406.12288","paper":"/paper/an-investigation-of-neuron-activation-as-a","title":"An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dakingrai/neuron-analysis-cot-arithmetic-reasoning","path":"llama/model.py","file_url":"https://github.com/dakingrai/neuron-analysis-cot-arithmetic-reasoning/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2406.10471","paper":"/paper/personalized-pieces-efficient-personalized","title":"Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts","date":"2024-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"TamSiuhin/Per-Pcs","path":"llama/model.py","file_url":"https://github.com/TamSiuhin/Per-Pcs/blob/HEAD/llama/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ae5f8e51e747d79","mcp_get_code":{"code_sha256":"7ae5f8e51e747d79"}},{"arxiv_id":"2406.10056","paper":"/paper/uniaudio-1-5-large-language-model-driven","title":"UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":"archive","repo":"yangdongchao/llm-codec","path":"llama_inference/llama/model.py","file_url":"https://github.com/yangdongchao/llm-codec/blob/HEAD/llama_inference/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2406.06525","paper":"/paper/autoregressive-model-beats-diffusion-llama","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"foundationvision/llamagen","path":"autoregressive/models/gpt.py","file_url":"https://github.com/foundationvision/llamagen/blob/HEAD/autoregressive/models/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0f0ff4e443413018","mcp_get_code":{"code_sha256":"0f0ff4e443413018"}},{"arxiv_id":"2406.04329","paper":"/paper/simplified-and-generalized-masked-diffusion","title":"Simplified and Generalized Masked Diffusion for Discrete Data","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/md4","path":"md4/models/diffusion/md4.py","file_url":"https://github.com/google-deepmind/md4/blob/HEAD/md4/models/diffusion/md4.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8873a5201399b10b","mcp_get_code":{"code_sha256":"8873a5201399b10b"}},{"arxiv_id":"2406.02255","paper":"/paper/midicaps-a-large-scale-midi-dataset-with-text","title":"MidiCaps: A large-scale MIDI dataset with text captions","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amaai-lab/t2m-inferalign","path":"Text2midi/model/transformer_model.py","file_url":"https://github.com/amaai-lab/t2m-inferalign/blob/HEAD/Text2midi/model/transformer_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"22480b5c1cf849b8","mcp_get_code":{"code_sha256":"22480b5c1cf849b8"}},{"arxiv_id":"2405.18400","paper":"/paper/superposed-decoding-multiple-generations-from","title":"Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RAIVNLab/SuperposedDecoding","path":"superposed/llama/model.py","file_url":"https://github.com/RAIVNLab/SuperposedDecoding/blob/HEAD/superposed/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2405.18392","paper":"/paper/scaling-laws-and-compute-optimal-training","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"epfml/schedules-and-scaling","path":"src/models/llama.py","file_url":"https://github.com/epfml/schedules-and-scaling/blob/HEAD/src/models/llama.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1d6f89d43fc42e1","mcp_get_code":{"code_sha256":"a1d6f89d43fc42e1"}},{"arxiv_id":"2405.13911","paper":"/paper/topa-extend-large-language-models-for-video","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","date":"2024-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2405.10587","paper":"/paper/rdrec-rationale-distillation-for-llm-based","title":"RDRec: Rationale Distillation for LLM-based Recommendation","date":"2024-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WangXFng/RDRec","path":"llama/llama/model.py","file_url":"https://github.com/WangXFng/RDRec/blob/HEAD/llama/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2405.05615","paper":"/paper/memory-space-visual-prompting-for-efficient","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","date":"2024-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jieshibo/memvp","path":"memvp/model.py","file_url":"https://github.com/jieshibo/memvp/blob/HEAD/memvp/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2404.07990","paper":"/paper/openbias-open-set-bias-detection-in-text-to","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"picsart-ai-research/openbias","path":"llama/model.py","file_url":"https://github.com/picsart-ai-research/openbias/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2404.06773","paper":"/paper/adapting-llama-decoder-to-vision-transformer","title":"Adapting LLaMA Decoder to Vision Transformer","date":"2024-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"techmonsterwang/illama","path":"models/illama.py","file_url":"https://github.com/techmonsterwang/illama/blob/HEAD/models/illama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2404.01933","paper":"/paper/prego-online-mistake-detection-in-procedural","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aleflabo/PREGO","path":"step_anticipation/llama/model.py","file_url":"https://github.com/aleflabo/PREGO/blob/HEAD/step_anticipation/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9aef5cccb42aa073","mcp_get_code":{"code_sha256":"9aef5cccb42aa073"}},{"arxiv_id":"2403.19589","paper":"/paper/tod3cap-towards-3d-dense-captioning-in","title":"TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jxbbb/tod3cap","path":"tod3cap_camera/llama/llama.py","file_url":"https://github.com/jxbbb/tod3cap/blob/HEAD/tod3cap_camera/llama/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2403.17343","paper":"/paper/language-models-are-free-boosters-for","title":"Residual-based Language Models are Free Boosters for Biomedical Imaging","date":"2024-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhixinlai/llmboostmedical","path":"2D_classification/models/llama.py","file_url":"https://github.com/zhixinlai/llmboostmedical/blob/HEAD/2D_classification/models/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2403.00522","paper":"/paper/visionllama-a-unified-llama-interface-for","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meituan-automl/visionllama","path":"deit/model_llama.py","file_url":"https://github.com/meituan-automl/visionllama/blob/HEAD/deit/model_llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2402.16181","paper":"/paper/how-can-llm-guide-rl-a-value-based-approach","title":"How Can LLM Guide RL? A Value-Based Approach","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentification/language-integrated-vi","path":"blocksworld/llama/model.py","file_url":"https://github.com/agentification/language-integrated-vi/blob/HEAD/blocksworld/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2402.14905","paper":"/paper/mobilellm-optimizing-sub-billion-parameter","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingyaogong/minimind","path":"model/model_minimind.py","file_url":"https://github.com/jingyaogong/minimind/blob/HEAD/model/model_minimind.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9c1c3b7f0fe82a6d","mcp_get_code":{"code_sha256":"9c1c3b7f0fe82a6d"}},{"arxiv_id":"2402.10631","paper":"/paper/bitdistiller-unleashing-the-potential-of-sub","title":"BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dd-duda/bitdistiller","path":"inference/models/llama.py","file_url":"https://github.com/dd-duda/bitdistiller/blob/HEAD/inference/models/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2402.09181","paper":"/paper/omnimedvqa-a-new-large-scale-comprehensive","title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","date":"2024-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/multi-modality-arena","path":"LVLM_evaluation/Multi_turn_Reasoning/LLaMA-Adapter-v2/models_mae.py","file_url":"https://github.com/opengvlab/multi-modality-arena/blob/HEAD/LVLM_evaluation/Multi_turn_Reasoning/LLaMA-Adapter-v2/models_mae.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2402.08268","paper":"/paper/world-model-on-million-length-video-and","title":"World Model on Million-Length Video And Language With Blockwise RingAttention","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LargeWorldModel/LWM","path":"lwm/llama.py","file_url":"https://github.com/LargeWorldModel/LWM/blob/HEAD/lwm/llama.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":"af9fda12d3dcce5b","mcp_get_code":{"code_sha256":"af9fda12d3dcce5b"}},{"arxiv_id":"2402.06700","paper":"/paper/entropy-regularized-token-level-policy","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"morning9393/etpo","path":"etpo/models/codellama/model.py","file_url":"https://github.com/morning9393/etpo/blob/HEAD/etpo/models/codellama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2402.05935","paper":"/paper/sphinx-x-scaling-data-and-parameters-for-a","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alpha-vllm/llama2-accessory","path":"accessory/model/LLM/llama.py","file_url":"https://github.com/alpha-vllm/llama2-accessory/blob/HEAD/accessory/model/LLM/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2c4423db8989ee05","mcp_get_code":{"code_sha256":"2c4423db8989ee05"}},{"arxiv_id":"2401.05215","paper":"/paper/pre-trained-large-language-models-for-1","title":"Pre-trained Large Language Models for Financial Sentiment Analysis","date":"2024-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luosting/LLaMA-Financial-sentiment-analysis","path":"llm-sentiment-analysis-main/llama/model.py","file_url":"https://github.com/luosting/LLaMA-Financial-sentiment-analysis/blob/HEAD/llm-sentiment-analysis-main/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2312.03700","paper":"/paper/onellm-one-framework-to-align-all-modalities","title":"OneLLM: One Framework to Align All Modalities with Language","date":"2023-12-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csuhan/onellm","path":"model/LLM/onellm.py","file_url":"https://github.com/csuhan/onellm/blob/HEAD/model/LLM/onellm.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2312.00025","paper":"/paper/secure-transformer-inference","title":"Secure Transformer Inference Protocol","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuanmu97/secure-transformer-inference","path":"model.py","file_url":"https://github.com/yuanmu97/secure-transformer-inference/blob/HEAD/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2311.13627","paper":"/paper/vamos-versatile-action-models-for-video","title":"Vamos: Versatile Action Models for Video Understanding","date":"2023-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brown-palm/Vamos","path":"finetune/llama/model.py","file_url":"https://github.com/brown-palm/Vamos/blob/HEAD/finetune/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2311.08268","paper":"/paper/a-wolf-in-sheep-s-clothing-generalized-nested","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NJUNLP/ReNeLLM","path":"llama/llama/model.py","file_url":"https://github.com/NJUNLP/ReNeLLM/blob/HEAD/llama/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2311.07575","paper":"/paper/sphinx-the-joint-mixing-of-weights-tasks-and","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","date":"2023-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"2c4423db8989ee05","mcp_get_code":{"code_sha256":"2c4423db8989ee05"}},{"arxiv_id":"2310.19698","paper":"/paper/when-do-prompting-and-prefix-tuning-work-a","title":"When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aleksandarpetrov/prefix-tuning-theory","path":"llama/llama/model.py","file_url":"https://github.com/aleksandarpetrov/prefix-tuning-theory/blob/HEAD/llama/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9aef5cccb42aa073","mcp_get_code":{"code_sha256":"9aef5cccb42aa073"}},{"arxiv_id":"2310.12973","paper":"/paper/frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziqipang/lm4visualencoding","path":"image_classification/models/llama.py","file_url":"https://github.com/ziqipang/lm4visualencoding/blob/HEAD/image_classification/models/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2310.11374","paper":"/paper/dialoguellm-context-and-emotion-knowledge","title":"DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations","date":"2023-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Dreamyao516/DialogueLLM","path":"llama/model.py","file_url":"https://github.com/Dreamyao516/DialogueLLM/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04a1fa63d6d4b8e4","mcp_get_code":{"code_sha256":"04a1fa63d6d4b8e4"}},{"arxiv_id":"2310.06825","paper":"/paper/mistral-7b","title":"Mistral 7B","date":"2023-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mistralai/mistral-src","path":"src/mistral_inference/rope.py","file_url":"https://github.com/mistralai/mistral-src/blob/HEAD/src/mistral_inference/rope.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":"99e0ca21ba709107","mcp_get_code":{"code_sha256":"99e0ca21ba709107"}},{"arxiv_id":"2310.03185","paper":"/paper/misusing-tools-in-large-language-models-with","title":"Misusing Tools in Large Language Models With Visual Adversarial Examples","date":"2023-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZihanWangKi/VLMToolMisuse","path":"llama_adapter/llama.py","file_url":"https://github.com/ZihanWangKi/VLMToolMisuse/blob/HEAD/llama_adapter/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2309.00615","paper":"/paper/point-bind-point-llm-aligning-point-cloud","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","date":"2023-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziyuguo99/point-bind_point-llm","path":"Point-LLM/llama/llama.py","file_url":"https://github.com/ziyuguo99/point-bind_point-llm/blob/HEAD/Point-LLM/llama/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2309.00638","paper":"/paper/generative-ai-for-end-to-end-limit-order-book","title":"Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network","date":"2023-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aaron-wheeler/marketgpt","path":"equities/fast_model.py","file_url":"https://github.com/aaron-wheeler/marketgpt/blob/HEAD/equities/fast_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5f447bdd807ed3c0","mcp_get_code":{"code_sha256":"5f447bdd807ed3c0"}},{"arxiv_id":"2308.12950","paper":"/paper/code-llama-open-foundation-models-for-code","title":"Code Llama: Open Foundation Models for Code","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/codellama","path":"llama/model.py","file_url":"https://github.com/facebookresearch/codellama/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e93cc5b705c2eb3b","mcp_get_code":{"code_sha256":"e93cc5b705c2eb3b"}},{"arxiv_id":"2308.11276","paper":"/paper/music-understanding-llama-advancing-text-to","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","date":"2023-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crypto-code/mu-llama","path":"MU-LLaMA/llama/llama.py","file_url":"https://github.com/crypto-code/mu-llama/blob/HEAD/MU-LLaMA/llama/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2308.06595","paper":"/paper/visit-bench-a-benchmark-for-vision-language","title":"VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use","date":"2023-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlfoundations/VisIT-Bench","path":"baselines/llama_adapter_v2_utils/llama.py","file_url":"https://github.com/mlfoundations/VisIT-Bench/blob/HEAD/baselines/llama_adapter_v2_utils/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2307.09288","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/Dromedary","path":"llama_dromedary/llama_dromedary/model.py","file_url":"https://github.com/IBM/Dromedary/blob/HEAD/llama_dromedary/llama_dromedary/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2307.03170","paper":"/paper/focused-transformer-contrastive-training-for","title":"Focused Transformer: Contrastive Training for Context Scaling","date":"2023-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CStanKonrad/long_llama","path":"fot_continued_pretraining/EasyLM/models/llama/llama_model.py","file_url":"https://github.com/CStanKonrad/long_llama/blob/HEAD/fot_continued_pretraining/EasyLM/models/llama/llama_model.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":"1d636c739a91d422","mcp_get_code":{"code_sha256":"1d636c739a91d422"}},{"arxiv_id":"2303.09736","paper":"/paper/dynamic-structure-pruning-for-compressing","title":"Dynamic Structure Pruning for Compressing CNNs","date":"2023-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pytorch/examples","path":"distributed/tensor_parallelism/llama2_model.py","file_url":"https://github.com/pytorch/examples/blob/HEAD/distributed/tensor_parallelism/llama2_model.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":"ef236c5425b4e712","mcp_get_code":{"code_sha256":"ef236c5425b4e712"}},{"arxiv_id":"2302.02676","paper":"/paper/languages-are-rewards-hindsight-finetuning","title":"Chain of Hindsight Aligns Language Models with Feedback","date":"2023-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lhao499/CoH","path":"coh/llama.py","file_url":"https://github.com/lhao499/CoH/blob/HEAD/coh/llama.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":"1d636c739a91d422","mcp_get_code":{"code_sha256":"1d636c739a91d422"}},{"arxiv_id":"2203.15556","paper":"/paper/training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"5f447bdd807ed3c0","mcp_get_code":{"code_sha256":"5f447bdd807ed3c0"}},{"arxiv_id":"openreview_utRSxIkoSJ","paper":null,"title":"arXiv:openreview_utRSxIkoSJ","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"hustyyq/ConceptTok","path":"autoregressive/models/gpt.py","file_url":"https://github.com/hustyyq/ConceptTok/blob/HEAD/autoregressive/models/gpt.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":"0f0ff4e443413018","mcp_get_code":{"code_sha256":"0f0ff4e443413018"}},{"arxiv_id":"2025.findings-acl.979","paper":null,"title":"arXiv:2025.findings-acl.979","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Mrshenshen/FRUIT","path":"models/llama_adapter_v2/llama.py","file_url":"https://github.com/Mrshenshen/FRUIT/blob/HEAD/models/llama_adapter_v2/llama.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}},{"arxiv_id":"2023.emnlp-main.534","paper":null,"title":"arXiv:2023.emnlp-main.534","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PreferredAI/superposed-topics","path":"llama/model.py","file_url":"https://github.com/PreferredAI/superposed-topics/blob/HEAD/llama/model.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"14a84c2cbfebc413","mcp_get_code":{"code_sha256":"14a84c2cbfebc413"}}]}