{"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/get-timestep-embedding","entry":"get_timestep_embedding","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":11,"n_papers":15,"n_buckets":2,"n_distinct_outputs":5,"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/get-timestep-embedding","buckets":[{"bucket":[[1,"int","int64"]],"n_implementations_compared":9,"n_papers":13,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3f9eb471628ac4ca","size":5,"n_papers":9,"shape":[8,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":5,"torch_reference_conventions_with_this_digest":[],"values":[0.9092974066734314,0.0001999999803956598,-0.416146844625473,1.0,0.8414709568023682,9.99999901978299e-05,0.5403022766113281,1.0,0.14112000167369843,0.0002999999560415745,-0.9899924993515015,0.9999999403953552,0.0,0.0,1.0,1.0,0.8414709568023682,9.99999901978299e-05,0.5403022766113281,1.0,0.9092974066734314,0.0001999999803956598,-0.416146844625473,1.0,0.9092974066734314,0.0001999999803956598,-0.416146844625473,1.0,0.9092974066734314,0.0001999999803956598,-0.416146844625473,1.0],"values_recorded":32,"members":[{"code_sha256_prefix":"cb49209c125de1b4","path":"papers/Conditional_Schrodinger_Bridge_Imputation/models/DGLSB/dglsb.py","papers":["2305.07247","2412.05926","2303.05762","2404.02148","2607.06590"],"paper_pages":[{"arxiv_id":"2305.07247","page":"/paper/provably-convergent-schrodinger-bridge-with"},{"arxiv_id":"2412.05926","page":"/paper/bidm-pushing-the-limit-of-quantization-for"},{"arxiv_id":"2303.05762","page":"/paper/trojdiff-trojan-attacks-on-diffusion-models"},{"arxiv_id":"2404.02148","page":"/paper/diffusion-2-dynamic-3d-content-generation-via"},{"arxiv_id":"2607.06590","page":"/paper/arxiv-2607-06590"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"4"},"class_bearing":false},{"code_sha256_prefix":"3ee5b3663f749813","path":"experiments/ddpm/ddpm/models/deepcache_diffusion.py","papers":["2410.09873"],"paper_pages":[{"arxiv_id":"2410.09873","page":"/paper/training-free-adaptive-diffusion-with-bounded"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"4"},"class_bearing":false},{"code_sha256_prefix":"5bed1adcc20070b2","path":"models/unet_models.py","papers":["2604.25172"],"paper_pages":[{"arxiv_id":"2604.25172","page":"/paper/arxiv-2604-25172"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"4"},"class_bearing":false},{"code_sha256_prefix":"b8dedf14898e5502","path":"diffusion/models/ddpm_arch/sige_fused_unet.py","papers":["2211.02048"],"paper_pages":[{"arxiv_id":"2211.02048","page":"/paper/efficient-spatially-sparse-inference-for"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"4"},"class_bearing":false},{"code_sha256_prefix":"e3f5c3d286e3e169","path":"models/unet.py","papers":["2205.09853"],"paper_pages":[{"arxiv_id":"2205.09853","page":"/paper/masked-conditional-video-diffusion-for"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"4"},"class_bearing":false}]},{"output_sha":"938fec0031e5158e","size":2,"n_papers":2,"shape":[8,8],"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":[0.9092974066734314,0.09269850701093674,0.004308856092393398,0.0001999999803956598,-0.416146844625473,0.9956942200660706,0.999990701675415,1.0,0.8414709568023682,0.046399228274822235,0.0021544331684708595,9.99999901978299e-05,0.5403022766113281,0.9989230036735535,0.9999976754188538,1.0,0.14112000167369843,0.13879810273647308,0.006463258992880583,0.0002999999560415745,-0.9899924993515015,0.9903206825256348,0.9999791383743286,0.9999999403953552,0.0,0.0,0.0,0.0,1.0,1.0,1.0,1.0,0.8414709568023682,0.046399228274822235,0.0021544331684708595,9.99999901978299e-05,0.5403022766113281,0.9989230036735535,0.9999976754188538,1.0,0.9092974066734314,0.09269850701093674,0.004308856092393398,0.0001999999803956598,-0.416146844625473,0.9956942200660706,0.999990701675415,1.0,0.9092974066734314,0.09269850701093674,0.004308856092393398,0.0001999999803956598,-0.416146844625473,0.9956942200660706,0.999990701675415,1.0,0.9092974066734314,0.09269850701093674,0.004308856092393398,0.0001999999803956598,-0.416146844625473,0.9956942200660706,0.999990701675415,1.0],"values_recorded":64,"members":[{"code_sha256_prefix":"0df386409ec75bec","path":"pipeline.py","papers":["2607.13164"],"paper_pages":[{"arxiv_id":"2607.13164","page":"/paper/arxiv-2607-13164"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"8"},"class_bearing":false},{"code_sha256_prefix":"b77c75490c4e7bc2","path":"opencood/models/gencomm_modules/cond_diff.py","papers":["2510.19618"],"paper_pages":[{"arxiv_id":"2510.19618","page":"/paper/arxiv-2510-19618"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"8"},"class_bearing":false}]},{"output_sha":"70f8342d38b2d1a0","size":1,"n_papers":1,"shape":[8,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.9092974066734314,0.019998665899038315,-0.416146844625473,0.9998000264167786,0.8414709568023682,0.009999833069741726,0.5403022766113281,0.9999499917030334,0.14112000167369843,0.029995499178767204,-0.9899924993515015,0.9995500445365906,0.0,0.0,1.0,1.0,0.8414709568023682,0.009999833069741726,0.5403022766113281,0.9999499917030334,0.9092974066734314,0.019998665899038315,-0.416146844625473,0.9998000264167786,0.9092974066734314,0.019998665899038315,-0.416146844625473,0.9998000264167786,0.9092974066734314,0.019998665899038315,-0.416146844625473,0.9998000264167786],"values_recorded":32,"members":[{"code_sha256_prefix":"f9a074c3439ca741","path":"sample.py","papers":["2207.12598"],"paper_pages":[{"arxiv_id":"2207.12598","page":"/paper/classifier-free-diffusion-guidance"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"4","downscale_freq_shift":"0.0","max_period":"10000"},"class_bearing":false}]},{"output_sha":"ace22b3575589b5f","size":1,"n_papers":1,"shape":[8,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.9092974066734314,0.19866931438446045,0.019998665899038315,0.001999998465180397,-0.416146844625473,0.9800665974617004,0.9998000264167786,0.9999979734420776,0.8414709568023682,0.0998334139585495,0.009999833069741726,0.0009999998146668077,0.5403022766113281,0.9950041770935059,0.9999499917030334,0.9999995231628418,0.14112000167369843,0.29552018642425537,0.029995499178767204,0.002999995369464159,-0.9899924993515015,0.9553365111351013,0.9995500445365906,0.9999955296516418,0.0,0.0,0.0,0.0,1.0,1.0,1.0,1.0,0.8414709568023682,0.0998334139585495,0.009999833069741726,0.0009999998146668077,0.5403022766113281,0.9950041770935059,0.9999499917030334,0.9999995231628418,0.9092974066734314,0.19866931438446045,0.019998665899038315,0.001999998465180397,-0.416146844625473,0.9800665974617004,0.9998000264167786,0.9999979734420776,0.9092974066734314,0.19866931438446045,0.019998665899038315,0.001999998465180397,-0.416146844625473,0.9800665974617004,0.9998000264167786,0.9999979734420776,0.9092974066734314,0.19866931438446045,0.019998665899038315,0.001999998465180397,-0.416146844625473,0.9800665974617004,0.9998000264167786,0.9999979734420776],"values_recorded":64,"members":[{"code_sha256_prefix":"8426c417286a4e88","path":"model.py","papers":["2601.08623"],"paper_pages":[{"arxiv_id":"2601.08623","page":"/paper/arxiv-2601-08623"}],"arg_sig_recorded":[["timesteps",1,"int","int64"]],"scalar_args":{"embedding_dim":"8","max_period":"10000"},"class_bearing":false}]}]},{"bucket":[[1,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"21039c3853b86d0f","size":2,"n_papers":2,"shape":[8,4],"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":[-0.7857384085655212,-9.038889402290806e-05,0.618558943271637,1.0,0.1564856618642807,1.5713145330664702e-05,0.9876802563667297,1.0,0.7818402647972107,8.976118988357484e-05,0.6234787702560425,1.0,-0.690511167049408,-7.621954864589497e-05,0.7233217358589172,1.0,-0.17534439265727997,-1.7625554391997866e-05,0.984507143497467,1.0,0.053006865084171295,5.303171292325715e-06,0.9985941648483276,1.0,-0.998339056968689,-0.00016284400771837682,-0.057612016797065735,1.0,-0.17660221457481384,-1.775333112163935e-05,0.9842823147773743,1.0],"values_recorded":32,"members":[{"code_sha256_prefix":"93dc2a74ceb65049","path":"model/TPDM/diffusion.py","papers":["2510.14427"],"paper_pages":[{"arxiv_id":"2510.14427","page":"/paper/arxiv-2510-14427"}],"arg_sig_recorded":[["timesteps",1,"float","float32"]],"scalar_args":{"embedding_dim":"4","flip_sin_to_cos":"False","downscale_freq_shift":"1.0","scale":"1.0","max_period":"10000"},"class_bearing":false},{"code_sha256_prefix":"f3cf5a0b90d04903","path":"toy_example.py","papers":["2309.05153"],"paper_pages":[{"arxiv_id":"2309.05153","page":"/paper/learning-energy-based-models-by-cooperative"}],"arg_sig_recorded":[["timesteps",1,"float","float32"]],"scalar_args":{"embedding_dim":"4","dtype":"torch.float32","max_time":"1000.0"},"class_bearing":false}]}]}]}