{"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/sample-logits","entry":"sample_logits","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":16,"n_papers_ran":15,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":17,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":2},"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":"2408.01584","paper":"/paper/2408-01584","title":"GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS","date":"2024-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Emerge-Lab/gpudrive","path":"gpudrive/networks/late_fusion.py","file_url":"https://github.com/Emerge-Lab/gpudrive/blob/HEAD/gpudrive/networks/late_fusion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c5743ad5afe917b0","mcp_get_code":{"code_sha256":"c5743ad5afe917b0"}},{"arxiv_id":"2305.13048","paper":"/paper/rwkv-reinventing-rnns-for-the-transformer-era","title":"RWKV: Reinventing RNNs for the Transformer Era","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blinkdl/chatrwkv","path":"RWKV_in_150_lines.py","file_url":"https://github.com/blinkdl/chatrwkv/blob/HEAD/RWKV_in_150_lines.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":"35e590faf9de67ca","mcp_get_code":{"code_sha256":"35e590faf9de67ca"}},{"arxiv_id":"2305.08379","paper":"/paper/tess-text-to-text-self-conditioned-simplex","title":"TESS: Text-to-Text Self-Conditioned Simplex Diffusion","date":"2023-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyh6560new/p3sum","path":"simplex-diffusion-main/sdlm/inference/inference_utils.py","file_url":"https://github.com/lyh6560new/p3sum/blob/HEAD/simplex-diffusion-main/sdlm/inference/inference_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"895366d47515705c","mcp_get_code":{"code_sha256":"895366d47515705c"}},{"arxiv_id":"2304.11062","paper":"/paper/scaling-transformer-to-1m-tokens-and-beyond","title":"Scaling Transformer to 1M tokens and beyond with RMT","date":"2023-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"booydar/transformer-xl","path":"pytorch/utils/log_uniform_sampler.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/utils/log_uniform_sampler.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"2106.06295","paper":"/paper/going-beyond-linear-transformers-with","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","date":"2021-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IDSIA/lmtool-fwms","path":"src/utils/log_uniform_sampler.py","file_url":"https://github.com/IDSIA/lmtool-fwms/blob/HEAD/src/utils/log_uniform_sampler.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"2010.05607","paper":"/paper/the-elephant-in-the-interpretability-room-why","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","date":"2020-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jessevig/bertviz","path":"bertviz/transformers_neuron_view/modeling_transfo_xl_utilities.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"2005.02439","paper":"/paper/contextualizing-hate-speech-classifiers-with","title":"Contextualizing Hate Speech Classifiers with Post-hoc Explanation","date":"2020-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"owaisCS/TestHateSpeech","path":"bert/modeling_transfo_xl_utilities.py","file_url":"https://github.com/owaisCS/TestHateSpeech/blob/HEAD/bert/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"2005.00558","paper":"/paper/pointer-constrained-text-generation-via","title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","date":"2020-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dreasysnail/POINTER","path":"pytorch_transformers/modeling_transfo_xl_utilities.py","file_url":"https://github.com/dreasysnail/POINTER/blob/HEAD/pytorch_transformers/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"2004.03829","paper":"/paper/exploring-versatile-generative-language-model","title":"Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning","date":"2020-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zlinao/VGLM","path":"pytorch_transformers/modeling_transfo_xl_utilities.py","file_url":"https://github.com/zlinao/VGLM/blob/HEAD/pytorch_transformers/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"2002.01808","paper":"/paper/k-adapter-infusing-knowledge-into-pre-trained","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","date":"2020-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/K-Adapter","path":"pytorch_transformers/modeling_transfo_xl_utilities.py","file_url":"https://github.com/microsoft/K-Adapter/blob/HEAD/pytorch_transformers/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"1911.00720","paper":"/paper/zen-pre-training-chinese-text-encoder","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","date":"2019-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SVAIGBA/TwASP","path":"pytorch_pretrained_bert/modeling_transfo_xl_utilities.py","file_url":"https://github.com/SVAIGBA/TwASP/blob/HEAD/pytorch_pretrained_bert/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"1909.05311","paper":"/paper/graph-based-reasoning-over-heterogeneous","title":"Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering","date":"2019-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DecstionBack/AAAI_2020_CommonsenseQA","path":"pytorch_transformers/modeling_transfo_xl_utilities.py","file_url":"https://github.com/DecstionBack/AAAI_2020_CommonsenseQA/blob/HEAD/pytorch_transformers/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"1908.09355","paper":"/paper/patient-knowledge-distillation-for-bert-model","title":"Patient Knowledge Distillation for BERT Model Compression","date":"2019-08-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eunanomist/PKD_BERT","path":"BERT/pytorch_pretrained_bert/modeling_transfo_xl_utilities.py","file_url":"https://github.com/eunanomist/PKD_BERT/blob/HEAD/BERT/pytorch_pretrained_bert/modeling_transfo_xl_utilities.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"1906.08237","paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samwisegamjeee/pytorch-transformers","path":"pytorch_transformers/modeling_transfo_xl_utilities.py","file_url":"https://github.com/samwisegamjeee/pytorch-transformers/blob/HEAD/pytorch_transformers/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"1901.02860","paper":"/paper/transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kimiyoung/transformer-xl","path":"pytorch/mem_transformer.py","file_url":"https://github.com/kimiyoung/transformer-xl/blob/HEAD/pytorch/mem_transformer.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"arxiv_id":"1901.02860","paper":"/paper/transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA/DeepLearningExamples","path":"PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py","file_url":"https://github.com/NVIDIA/DeepLearningExamples/blob/HEAD/PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"582150577e5bd769","mcp_get_code":{"code_sha256":"582150577e5bd769"}},{"arxiv_id":"2024.findings-naacl.32","paper":null,"title":"arXiv:2024.findings-naacl.32","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SnowYJ/sem_syn_separation","path":"optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_transfo_xl_utilities.py","file_url":"https://github.com/SnowYJ/sem_syn_separation/blob/HEAD/optimus_separate_graph_sem_syntax_fuse_gpt2/pytorch_transformers/modeling_transfo_xl_utilities.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":"93228a3eb5c4d179","mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}}]}