{"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":"/census/log","entry":"log","source":"Syntology differential census (groundwork/55, run v2_2026-09-22), per sample; not an archive number","census_date":"2026-09-22","battery_sha256":["b986f7e04d794a0d88ad4c5f32cf63ec3590b5deff0192150737bc5f1c0b4677"],"runner_sha256":["5a452d0e7c0da5b80771d1be2afe3572e253568cf5c5d59a0d08ebd663d00808"],"bucket_key":"positional (rank, kind, dtype) of each array argument; the argument name is not part of the key because the harness draws the shared array from (rank, kind) and casts it to the dtype, whatever the name","bucket_fields":["rank","kind","dtype"],"claim":"Implementations sharing this entry name were each run on one shared input fixed by the positional (rank, kind, dtype) of their array arguments (the bucket). A cluster is the set whose recorded output digest (sha256 of the output rounded to 6 decimals) is identical. Identical values to six decimals on the shared input are agreement on those inputs, not a statement about the whole domain and not a substitution claim.","n_implementations_compared":10,"n_papers":16,"n_buckets":1,"n_distinct_outputs":7,"n_class_bearing":0,"not_compared":{"not_run_on_shared_input":{"n":0,"by_error":{}},"no_array_argument_ran_on_own_fixture_arguments_only":{"n":0,"n_papers":0,"recorded_shared_digest_equals_own_fixture_digest":0},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/log","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":10,"n_papers":16,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2194d6f35f20be49","size":3,"n_papers":3,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[0.5892459750175476,NaN,-0.7422255873680115,NaN,NaN,NaN,NaN,-0.5570629239082336,-0.6560904383659363,-0.04171232134103775,NaN,NaN,NaN,0.8424757122993469,NaN,-0.5968763828277588,-2.7121269702911377,NaN,-0.8390718102455139,NaN,NaN,NaN,NaN,-0.016460565850138664,NaN,-0.8363839983940125,-0.0565938837826252,0.01736660674214363,NaN,0.24233262240886688,NaN,NaN],"values_recorded":32,"members":[{"code_sha256_prefix":"6269424d608eba34","path":"marge_pytorch/autoregressive_wrapper.py","papers":["2003.10555","2006.15020"],"paper_pages":[{"arxiv_id":"2003.10555","page":"/paper/electra-pre-training-text-encoders-as-1"},{"arxiv_id":"2006.15020","page":"/paper/pre-training-via-paraphrasing"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"eps":"1e-09"},"class_bearing":false},{"code_sha256_prefix":"5926a238cd968779","path":"coco_lm_pytorch/coco_lm_pytorch.py","papers":["2102.08473"],"paper_pages":[{"arxiv_id":"2102.08473","page":"/paper/coco-lm-correcting-and-contrasting-text"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"eps":"1e-09"},"class_bearing":false},{"code_sha256_prefix":"c01e5c8df433613c","path":"electra_pytorch/electra_pytorch.py","papers":["2003.10555"],"paper_pages":[{"arxiv_id":"2003.10555","page":"/paper/electra-pre-training-text-encoders-as-1"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"eps":"1e-09"},"class_bearing":false}]},{"output_sha":"95f9ebd4dcc0c22d","size":2,"n_papers":6,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[0.5892459750175476,-46.051700592041016,-0.7422255873680115,-46.051700592041016,-46.051700592041016,-46.051700592041016,-46.051700592041016,-0.5570629239082336,-0.6560904383659363,-0.04171232134103775,-46.051700592041016,-46.051700592041016,-46.051700592041016,0.8424757122993469,-46.051700592041016,-0.5968763828277588,-2.7121269702911377,-46.051700592041016,-0.8390718102455139,-46.051700592041016,-46.051700592041016,-46.051700592041016,-46.051700592041016,-0.016460565850138664,-46.051700592041016,-0.8363839983940125,-0.0565938837826252,0.01736660674214363,-46.051700592041016,0.24233262240886688,-46.051700592041016,-46.051700592041016],"values_recorded":32,"members":[{"code_sha256_prefix":"b5472673332de78e","path":"speculative_decoding/speculative_decoding.py","papers":["2203.16487","1907.05242","2401.02412","2407.12448","2602.02600"],"paper_pages":[{"arxiv_id":"2203.16487","page":"/paper/lossless-speedup-of-autoregressive"},{"arxiv_id":"1907.05242","page":"/paper/large-memory-layers-with-product-keys"},{"arxiv_id":"2401.02412","page":"/paper/llm-augmented-llms-expanding-capabilities"},{"arxiv_id":"2407.12448","page":"/paper/energy-guided-diffusion-sampling-for-offline"},{"arxiv_id":"2602.02600","page":"/paper/arxiv-2602-02600"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"eps":"1e-20"},"class_bearing":false},{"code_sha256_prefix":"0a7e4f0159ab841a","path":"vectree/vectree.py","papers":["2311.17245"],"paper_pages":[{"arxiv_id":"2311.17245","page":"/paper/lightgaussian-unbounded-3d-gaussian"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"eps":"1e-20"},"class_bearing":false}]},{"output_sha":"7948875a4f52e673","size":1,"n_papers":3,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.5892459750175476,-27.63102149963379,-0.7422255873680115,-27.63102149963379,-27.63102149963379,-27.63102149963379,-27.63102149963379,-0.5570629239082336,-0.6560904383659363,-0.04171232134103775,-27.63102149963379,-27.63102149963379,-27.63102149963379,0.8424757122993469,-27.63102149963379,-0.5968763828277588,-2.7121269702911377,-27.63102149963379,-0.8390718102455139,-27.63102149963379,-27.63102149963379,-27.63102149963379,-27.63102149963379,-0.016460565850138664,-27.63102149963379,-0.8363839983940125,-0.0565938837826252,0.01736660674214363,-27.63102149963379,0.24233262240886688,-27.63102149963379,-27.63102149963379],"values_recorded":32,"members":[{"code_sha256_prefix":"d93be7ef30d67f1e","path":"diffusion/text_denoising_diffusion.py","papers":["2212.09462","2408.04220","2602.20528"],"paper_pages":[{"arxiv_id":"2212.09462","page":"/paper/latent-diffusion-for-language-generation-1"},{"arxiv_id":"2408.04220","page":"/paper/diffusion-guided-language-modeling"},{"arxiv_id":"2602.20528","page":"/paper/arxiv-2602-20528"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"eps":"1e-12"},"class_bearing":false}]},{"output_sha":"3fd84e3d9f2b5d88","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.5892465114593506,NaN,-0.7422234416007996,NaN,NaN,NaN,NaN,-0.5570611357688904,-0.6560884714126587,-0.041711267083883286,NaN,NaN,NaN,0.8424761295318604,NaN,-0.5968745350837708,-2.7121119499206543,NaN,-0.8390694856643677,NaN,NaN,NaN,NaN,-0.01645953580737114,NaN,-0.8363816738128662,-0.05659281462430954,0.017367543652653694,NaN,0.24233338236808777,NaN,NaN],"values_recorded":32,"members":[{"code_sha256_prefix":"8f3eea58724263db","path":"vit_pytorch/ats_vit.py","papers":["2110.13100"],"paper_pages":[{"arxiv_id":"2110.13100","page":"/paper/parameter-prediction-for-unseen-deep"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"eps":"1e-06"},"class_bearing":false}]},{"output_sha":"a54a279e425be933","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,-18.42068099975586,-0.7422255873680115,-18.42068099975586,-18.42068099975586,-18.42068099975586,-18.42068099975586,-0.5570629239082336,-0.6560904383659363,-0.04171232134103775,-18.42068099975586,-18.42068099975586,-18.42068099975586,0.0,-18.42068099975586,-0.5968763828277588,-2.7121269702911377,-18.42068099975586,-0.8390718102455139,-18.42068099975586,-18.42068099975586,-18.42068099975586,-18.42068099975586,-0.016460565850138664,-18.42068099975586,-0.8363839983940125,-0.0565938837826252,0.0,-18.42068099975586,0.0,-18.42068099975586,-18.42068099975586],"values_recorded":32,"members":[{"code_sha256_prefix":"b1951f4f25d8e36c","path":"src/losses.py","papers":["1909.06321"],"paper_pages":[{"arxiv_id":"1909.06321","page":"/paper/simple-but-effective-techniques-to-reduce"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"ac559b556f482022","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.5892459750175476,-11.512925148010254,-0.7422255873680115,-11.512925148010254,-11.512925148010254,-11.512925148010254,-11.512925148010254,-0.5570629239082336,-0.6560904383659363,-0.04171232134103775,-11.512925148010254,-11.512925148010254,-11.512925148010254,0.8424757122993469,-11.512925148010254,-0.5968763828277588,-2.7121269702911377,-11.512925148010254,-0.8390718102455139,-11.512925148010254,-11.512925148010254,-11.512925148010254,-11.512925148010254,-0.016460565850138664,-11.512925148010254,-0.8363839983940125,-0.0565938837826252,0.01736660674214363,-11.512925148010254,0.24233262240886688,-11.512925148010254,-11.512925148010254],"values_recorded":32,"members":[{"code_sha256_prefix":"7d6c3243647c53d9","path":"vqshape/model.py","papers":["2411.01006"],"paper_pages":[{"arxiv_id":"2411.01006","page":"/paper/abstracted-shapes-as-tokens-a-generalizable"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{"eps":"1e-05"},"class_bearing":false}]},{"output_sha":"f3ecf67148c42dd8","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.5892460346221924,NaN,-0.7422253489494324,NaN,NaN,NaN,NaN,-0.5570627450942993,-0.6560901999473572,-0.0417121984064579,NaN,NaN,NaN,0.8424757122993469,NaN,-0.5968762040138245,-2.712125062942505,NaN,-0.8390715718269348,NaN,NaN,NaN,NaN,-0.016460444778203964,NaN,-0.8363837003707886,-0.05659376084804535,0.017366724088788033,NaN,0.24233272671699524,NaN,NaN],"values_recorded":32,"members":[{"code_sha256_prefix":"0974a4d82bf5f79d","path":"editor/horse.py","papers":["2601.11441"],"paper_pages":[{"arxiv_id":"2601.11441","page":"/paper/arxiv-2601-11441"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}