{"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/down","entry":"Down","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":5,"n_papers":5,"n_buckets":2,"n_distinct_outputs":5,"n_class_bearing":5,"not_compared":{"not_run_on_shared_input":{"n":1,"by_error":{"RuntimeError":1}},"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/down","buckets":[{"bucket":[[4,"float","float32"]],"n_implementations_compared":4,"n_papers":4,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"66871765409f5bf8","size":1,"n_papers":1,"shape":[2,4,2,2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.5895628333091736,0.0,1.5390958786010742,0.10677928477525711,1.277109980583191,0.3601152002811432,0.0,0.262631893157959,0.0,0.15806707739830017,0.5951679944992065,0.41982340812683105,0.0,0.0,1.2790910005569458,0.10560373961925507,0.5752308368682861,0.0,0.6368750929832458,0.0,0.0,1.1010799407958984,0.0,0.6393845081329346,0.0,1.62506902217865,0.4260306656360626,0.0,0.0,0.0,1.841429591178894,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"4a22918248db80fd","path":"src/model.py","papers":["2601.22707"],"paper_pages":[{"arxiv_id":"2601.22707","page":"/paper/arxiv-2601-22707"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"720a93dc4469eb33","size":1,"n_papers":1,"shape":[2,4,2,2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.0177346467971802,0.685263454914093,0.0,0.0,1.1178950071334839,1.2265362739562988,0.0,0.5852282047271729,0.3811953365802765,0.438713014125824,0.16483990848064423,0.0,0.0,0.0,0.8438734412193298,0.18966054916381836,0.0,0.0,0.4401169717311859,0.0,0.0,0.0,0.0,0.173186257481575,0.0,1.8431978225708008,0.4576224982738495,0.0,0.0,0.0,2.2628917694091797,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"a0fd37e26df21138","path":"model/unet.py","papers":["2011.05479"],"paper_pages":[{"arxiv_id":"2011.05479","page":"/paper/forestnet-classifying-drivers-of"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"a6d7a4d672f43ab8","size":1,"n_papers":1,"shape":[2,4,2,2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.0,0.543642520904541,0.06026868894696236,0.0,0.0,0.5750967860221863,0.0,0.0,1.0790023803710938,0.738349199295044,0.0,0.0,1.0654253959655762,0.5597126483917236,0.25665801763534546,0.0,0.0,1.4843252897262573,1.1169053316116333,0.038133542984724045,0.5047850608825684,0.062368929386138916,0.0,1.4777876138687134,0.0,1.771255612373352,0.0,0.0,0.5407000780105591,0.8280628323554993,0.0,0.0],"values_recorded":32,"members":[{"code_sha256_prefix":"f3bd5522612e8f78","path":"demo/UNet.py","papers":["1505.04597"],"paper_pages":[{"arxiv_id":"1505.04597","page":"/paper/u-net-convolutional-networks-for-biomedical"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"ad2a1e0e17ae817e","size":1,"n_papers":1,"shape":[2,8,2,2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.9774803519248962,0.7711045145988464,0.6186097264289856,0.0,0.7695057988166809,0.08665282279253006,0.7232041954994202,0.20370173454284668,1.6816486120224,0.26663482189178467,0.0,0.0,0.0,0.10780870914459229,0.12330706417560577,0.0,0.4653168022632599,0.0,0.0,0.5065675377845764,0.0,0.0,0.0,0.8953070640563965,0.9293333888053894,0.0,0.0,0.0,1.430499792098999,0.0,0.18337932229042053,0.0,0.0,1.4502112865447998,0.0,0.0,0.0,0.0,0.3590482473373413,0.8346424102783203,1.4525678157806396,0.0,0.0,0.0,0.0,2.0390994548797607,0.6991161108016968,0.0,1.849421739578247,0.0,0.0,0.7302209734916687,0.0,0.5510266423225403,0.28326117992401123,1.7509068250656128,2.0480332374572754,0.0,0.4844285547733307,0.0,0.7833783030509949,0.0,1.1441762447357178,0.0],"values_recorded":64,"members":[{"code_sha256_prefix":"9eca04b186a73e7b","path":"model.py","papers":["2402.12688"],"paper_pages":[{"arxiv_id":"2402.12688","page":"/paper/robust-wide-robust-watermarking-against"}],"arg_sig_recorded":[["x",4,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]},{"bucket":[[4,"float","float32"],[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"a635b70ead97fe40","size":1,"n_papers":1,"shape":[2,4,2,2],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.7783758640289307,-0.19152624905109406,-0.11758115142583847,-0.9725490808486938,0.004629233386367559,0.2511983811855316,-0.1237301453948021,-0.028983665630221367,-0.49235668778419495,-0.04809459298849106,0.30989277362823486,-0.6534065008163452,-0.43374741077423096,-0.02933630347251892,0.5469929575920105,0.13754628598690033,0.5337315797805786,-0.42742523550987244,-0.04388472065329552,-0.3107653558254242,0.11974462866783142,-0.08370659500360489,0.5055766701698303,0.46050646901130676,-0.5289638638496399,-0.6073622107505798,0.14230933785438538,1.3337599039077759,-0.02640647441148758,-0.31081563234329224,0.3546339273452759,-0.06500145047903061],"values_recorded":32,"members":[{"code_sha256_prefix":"2cd19342f659e6e4","path":"lib/model/ecdp.py","papers":["2404.10688"],"paper_pages":[{"arxiv_id":"2404.10688","page":"/paper/efficient-conditional-diffusion-model-with"}],"arg_sig_recorded":[["x",4,"float","float32"],["t_embed",2,"float","float32"],["extra_feats",2,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]}]}