{"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/upfirdn2d-native","entry":"upfirdn2d_native","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":7,"n_buckets":1,"n_distinct_outputs":1,"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/upfirdn2d-native","buckets":[{"bucket":[[4,"float","float32"],[2,"float","float32"]],"n_implementations_compared":5,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"ff886d6b144a1923","size":5,"n_papers":7,"shape":[2,3,7,3],"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":[1.0920968055725098,-2.6609580516815186,0.8650831580162048,-1.252380609512329,3.7355868816375732,-1.7472206354141235,-1.3658593893051147,1.2900365591049194,1.6295565366744995,-1.8494354486465454,0.8904330134391785,1.8000513315200806,0.3635767102241516,1.6363654136657715,3.1753315925598145,0.5648785829544067,1.9676483869552612,2.29318904876709,-0.7073747515678406,-0.41899749636650085,0.6457037329673767,2.2351558208465576,-1.9850105047225952,-0.43508410453796387,3.112703561782837,4.671182632446289,-3.3233723640441895,-2.2205100059509277,-3.6422624588012695,1.0117554664611816,-1.6922434568405151,8.069937705993652,0.37350594997406006,-1.7748624086380005,0.2912631332874298,-1.7103697061538696,-4.375509738922119,-2.467604160308838,0.7463006377220154,0.15279310941696167,0.8081234097480774,-0.23754173517227173,-3.4588685035705566,-1.3579773902893066,-2.8260791301727295,-1.705330729484558,3.6002418994903564,-1.819240927696228,3.6396713256835938,-1.075913906097412,0.6408625245094299,1.0660110712051392,1.3946226835250854,-3.5278632640838623,-2.048476219177246,1.7281239032745361,0.552024781703949,-0.31971922516822815,-4.072368144989014,4.5002593994140625,0.05246517062187195,2.1035544872283936,-0.45815974473953247,-1.7234348058700562,3.214235305786133,2.1753203868865967,0.2273254096508026,5.1556925773620605,-2.121368169784546,0.10266811400651932,5.950077533721924,2.850083351135254,-1.7043712139129639,-7.6238226890563965,5.013742446899414,2.7982053756713867,0.875041663646698,2.260735273361206,5.036233901977539,-5.191300392150879,4.784686088562012,1.257635235786438,-1.9660190343856812,0.5028139352798462,1.3137140274047852,-3.5970726013183594,-1.3093554973602295,-2.1660594940185547,-4.678076267242432,1.5381022691726685,-0.5341664552688599,-0.20481199026107788,-1.0230686664581299,1.260812759399414,2.4732933044433594,-3.7941882610321045,-0.37596651911735535,0.6673815846443176,-1.1155465841293335,-0.9090021252632141,0.6474945545196533,-2.0636188983917236,-0.2908138930797577,0.10572914034128189,-0.05586289241909981,0.8407565355300903,-2.24265193939209,0.7520795464515686,4.301582336425781,7.681952953338623,-1.5021674633026123,-2.713913917541504,-1.7711305618286133,-2.7887747287750244,-6.385270595550537,-3.008147716522217,0.925585925579071,-0.9870018362998962,2.3171401023864746,0.21553997695446014,2.049814462661743,4.413069248199463,-3.6710329055786133,-0.8804181814193726,1.3339269161224365,-0.17190803587436676],"values_recorded":126,"members":[{"code_sha256_prefix":"200baf9e83c9a4de","path":"networks/generator.py","papers":["2301.06281","2409.10966"],"paper_pages":[{"arxiv_id":"2301.06281","page":"/paper/dpe-disentanglement-of-pose-and-expression"},{"arxiv_id":"2409.10966","page":"/paper/cunsb-rfie-context-aware-unpaired-neural-schr"}],"arg_sig_recorded":[["input",4,"float","float32"],["kernel",2,"float","float32"]],"scalar_args":{"up_x":"2","up_y":"2","down_x":"1","down_y":"1","pad_x0":"1","pad_x1":"1","pad_y0":"1","pad_y1":"1"},"class_bearing":false},{"code_sha256_prefix":"fe99cfd294676edb","path":"image_as_reference.py","papers":["2306.13091","2307.08448"],"paper_pages":[{"arxiv_id":"2306.13091","page":"/paper/evading-forensic-classifiers-with-attribute-1"},{"arxiv_id":"2307.08448","page":"/paper/not-all-steps-are-created-equal-selective"}],"arg_sig_recorded":[["input",4,"float","float32"],["kernel",2,"float","float32"]],"scalar_args":{"up_x":"2","up_y":"2","down_x":"1","down_y":"1","pad_x0":"1","pad_x1":"1","pad_y0":"1","pad_y1":"1"},"class_bearing":false},{"code_sha256_prefix":"054eb982e90af080","path":"face_model/gpen_model.py","papers":["2105.06070"],"paper_pages":[{"arxiv_id":"2105.06070","page":"/paper/gan-prior-embedded-network-for-blind-face"}],"arg_sig_recorded":[["input",4,"float","float32"],["kernel",2,"float","float32"]],"scalar_args":{"up_x":"2","up_y":"2","down_x":"1","down_y":"1","pad_x0":"1","pad_x1":"1","pad_y0":"1","pad_y1":"1"},"class_bearing":false},{"code_sha256_prefix":"635cc3f168503039","path":"models/networks.py","papers":["2204.13656"],"paper_pages":[{"arxiv_id":"2204.13656","page":"/paper/unsupervised-multi-modal-medical-image"}],"arg_sig_recorded":[["input",4,"float","float32"],["kernel",2,"float","float32"]],"scalar_args":{"up_x":"2","up_y":"2","down_x":"1","down_y":"1","pad_x0":"1","pad_x1":"1","pad_y0":"1","pad_y1":"1"},"class_bearing":false},{"code_sha256_prefix":"74ff4113f5a7d087","path":"model/sr3_modules/unet.py","papers":["2303.16491"],"paper_pages":[{"arxiv_id":"2303.16491","page":"/paper/implicit-diffusion-models-for-continuous"}],"arg_sig_recorded":[["input",4,"float","float32"],["kernel",2,"float","float32"]],"scalar_args":{"up_x":"2","up_y":"2","down_x":"1","down_y":"1","pad_x0":"1","pad_x1":"1","pad_y0":"1","pad_y1":"1"},"class_bearing":false}]}]}]}