{"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/im2tensor","entry":"im2tensor","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":3,"n_papers":6,"n_buckets":1,"n_distinct_outputs":3,"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":1,"n_papers":1,"recorded_shared_digest_equals_own_fixture_digest":1},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/im2tensor","buckets":[{"bucket":[[3,"float","float32"]],"n_implementations_compared":3,"n_papers":6,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"d84d1d0b4e89c155","size":1,"n_papers":4,"shape":[1,8,2,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-1.007004976272583,-1.0167781114578247,-0.9852566123008728,-0.9925152063369751,-1.00750732421875,-1.009351372718811,-1.0026617050170898,-1.0099736452102661,-0.9868011474609375,-0.9999068975448608,-1.0058454275131226,-0.9927548766136169,-0.9853470325469971,-1.0070393085479736,-1.0007648468017578,-0.9909385442733765,-1.0098730325698853,-1.0066584348678589,-1.000686526298523,-1.0059186220169067,-1.0092661380767822,-1.007957100868225,-0.994127094745636,-0.9870308041572571,-1.0020251274108887,-1.006056547164917,-0.9939257502555847,-1.0024019479751587,-1.0063053369522095,-1.0053802728652954,-1.0078262090682983,-1.0045607089996338,-0.9988157153129578,-0.9934383630752563,-1.0044739246368408,-1.0081086158752441,-0.9921639561653137,-0.9922910928726196,-0.9958587288856506,-0.9852832555770874,-1.011252999305725,-1.0013288259506226,-0.9911817908287048,-0.9902666211128235,-0.9950549602508545,-1.001128077507019,-0.9985216856002808,-0.9902676939964294,-1.002667784690857,-0.9988102912902832,-1.0031648874282837,-1.0071485042572021,-0.9996546506881714,-0.9969439506530762,-1.0055575370788574,-1.009980320930481,-1.0029891729354858,-0.9968085289001465,-0.9924947619438171,-0.9855950474739075,-0.9863408207893372,-0.9929075241088867,-1.0075563192367554,-1.0067445039749146],"values_recorded":64,"members":[{"code_sha256_prefix":"168ec16785d462f0","path":"evaluation.py","papers":["2404.05163","2105.06468","2304.01716","2401.04861"],"paper_pages":[{"arxiv_id":"2404.05163","page":"/paper/semantic-flow-learning-semantic-field-of"},{"arxiv_id":"2105.06468","page":"/paper/dynamic-view-synthesis-from-dynamic-monocular"},{"arxiv_id":"2304.01716","page":"/paper/decoupling-dynamic-monocular-videos-for"},{"arxiv_id":"2401.04861","page":"/paper/ctnerf-cross-time-transformer-for-dynamic"}],"arg_sig_recorded":[["img",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"76047595928a683e","size":1,"n_papers":1,"shape":[1,8,2,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-2.786254405975342,-5.278428077697754,2.7595624923706055,0.90861976146698,-2.91436767578125,-3.3846094608306885,-1.6787282228469849,-3.543281316757202,2.365706205368042,-0.9762551784515381,-2.490597724914551,0.8474996089935303,2.736504554748535,-2.795012950897217,-1.1950349807739258,1.310664176940918,-3.5176093578338623,-2.6978983879089355,-1.1750515699386597,-2.5092430114746094,-3.362865924835205,-3.029071092605591,0.4975947141647339,2.3071436882019043,-1.5164117813110352,-2.5444064140319824,0.5489341020584106,-1.6125088930130005,-2.6078569889068604,-2.3719682693481445,-2.9956839084625244,-2.1629910469055176,-0.6980080008506775,0.6732184886932373,-2.1408610343933105,-3.0676872730255127,0.9981889724731445,0.9657737016677856,0.05601775646209717,2.752763271331787,-3.869518995285034,-1.3388617038726807,1.2486443519592285,1.4820075035095215,0.26098382472991943,-1.2876629829406738,-0.623033881187439,1.4817333221435547,-1.6802914142608643,-0.6966202259063721,-1.8070555925369263,-2.8228631019592285,-0.9119409322738647,-0.2207149863243103,-2.417179584503174,-3.5449717044830322,-1.762251615524292,-0.18616807460784912,0.9138338565826416,2.673264980316162,2.4830844402313232,0.8085800409317017,-2.926863670349121,-2.7198612689971924],"values_recorded":64,"members":[{"code_sha256_prefix":"3d292e9792cfed82","path":"eval_nvidia.py","papers":["2211.11082"],"paper_pages":[{"arxiv_id":"2211.11082","page":"/paper/dynibar-neural-dynamic-image-based-rendering"}],"arg_sig_recorded":[["image",3,"float","float32"]],"scalar_args":{"cent":"1.0","factor":"0.5"},"class_bearing":false}]},{"output_sha":"8bc127eed4dbcc60","size":1,"n_papers":1,"shape":[8,2,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.8931272625923157,-2.139214038848877,1.8797812461853027,0.95430988073349,-0.9571838974952698,-1.1923047304153442,-0.33936411142349243,-1.271640658378601,1.682853102684021,0.011872420087456703,-0.7452988624572754,0.9237498044967651,1.8682522773742676,-0.8975064754486084,-0.0975174680352211,1.155332088470459,-1.2588046789169312,-0.848949134349823,-0.08752579241991043,-0.7546214461326599,-1.1814329624176025,-1.0145355463027954,0.7487973570823669,1.6535718441009521,-0.2582058608531952,-0.7722031474113464,0.7744670510292053,-0.30625444650650024,-0.8039284944534302,-0.6859840750694275,-0.9978419542312622,-0.581495463848114,0.15099599957466125,0.8366092443466187,-0.5704304575920105,-1.0338436365127563,0.9990944862365723,0.9828868508338928,0.5280088782310486,1.8763816356658936,-1.434759497642517,-0.16943085193634033,1.1243221759796143,1.2410037517547607,0.6304919123649597,-0.14383146166801453,0.18848304450511932,1.2408666610717773,-0.34014570713043213,0.15168990194797516,-0.40352779626846313,-0.9114314913749695,0.044029541313648224,0.38964250683784485,-0.7085897922515869,-1.2724858522415161,-0.3811257779598236,0.40691596269607544,0.9569169282913208,1.836632490158081,1.7415422201156616,0.9042900204658508,-0.9634317755699158,-0.8599306344985962],"values_recorded":64,"members":[{"code_sha256_prefix":"5c5d5425a50b6a93","path":"inference.py","papers":["2004.00448"],"paper_pages":[{"arxiv_id":"2004.00448","page":"/paper/rethinking-data-augmentation-for-image-super"}],"arg_sig_recorded":[["im",3,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}