{"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/grad-reverse","entry":"grad_reverse","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":12,"n_papers":17,"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/grad-reverse","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":12,"n_papers":17,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"d7bd5ceec8a69dcd","size":12,"n_papers":17,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":12,"torch_reference_conventions_with_this_digest":[],"values":[1.8026286363601685,-1.5337762832641602,0.47605323791503906,-0.6908870339393616,-0.9028494954109192,-1.0304712057113647,-0.6627609133720398,0.5728892087936401,0.5188759565353394,0.9591456651687622,-0.3971995711326599,-1.5683481693267822,-0.28853508830070496,2.322108745574951,-0.5147839784622192,0.5505285859107971,0.06639543920755386,-1.6228755712509155,0.4321114122867584,-0.4061858654022217,-0.02259422466158867,-1.180782437324524,-0.5368682742118835,0.983674168586731,-0.7956128120422363,0.43327441811561584,0.9449777603149414,1.0175182819366455,-1.225785732269287,1.274217963218689,-1.3222218751907349,-0.5941091179847717],"values_recorded":32,"members":[{"code_sha256_prefix":"29525c5a2d077ac6","path":"models/component.py","papers":["2006.12087","2202.06174"],"paper_pages":[{"arxiv_id":"2006.12087","page":"/paper/progressive-graph-learning-for-open-set"},{"arxiv_id":"2202.06174","page":"/paper/source-free-progressive-graph-learning-for"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"lambd":"0.5"},"class_bearing":false},{"code_sha256_prefix":"2a7e189196f18f84","path":"model.py","papers":["1802.06901","1906.09444"],"paper_pages":[{"arxiv_id":"1802.06901","page":"/paper/deterministic-non-autoregressive-neural"},{"arxiv_id":"1906.09444","page":"/paper/retrieving-sequential-information-for-non"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"7d2aba87eb205634","path":"adapteacher/modeling/meta_arch/rcnn.py","papers":["2412.17284","2111.13216"],"paper_pages":[{"arxiv_id":"2412.17284","page":"/paper/towards-unsupervised-model-selection-for"},{"arxiv_id":"2111.13216","page":"/paper/cross-domain-object-detection-via-adaptive"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"8a26ee1d7d102851","path":"trainer.py","papers":["1812.10352","2601.03090"],"paper_pages":[{"arxiv_id":"1812.10352","page":"/paper/learning-not-to-learn-training-deep-neural"},{"arxiv_id":"2601.03090","page":"/paper/arxiv-2601-03090"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"b5becb520f35423a","path":"exp1.py","papers":["1905.13549","2407.09498"],"paper_pages":[{"arxiv_id":"1905.13549","page":"/paper/190513549"},{"arxiv_id":"2407.09498","page":"/paper/ot-vp-optimal-transport-guided-visual"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"scale":"1.0"},"class_bearing":false},{"code_sha256_prefix":"12adce58fd9ce5ce","path":"tabula/model/transfomer/transformer.py","papers":["2607.19400"],"paper_pages":[{"arxiv_id":"2607.19400","page":"/paper/arxiv-2607-19400"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"lambd":"0.5"},"class_bearing":false},{"code_sha256_prefix":"3953ff0e5f757483","path":"maskrcnn_benchmark/modeling/domain_adaption/DA.py","papers":["2005.02066"],"paper_pages":[{"arxiv_id":"2005.02066","page":"/paper/unsupervised-instance-segmentation-in"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"grl_alpha":"0.5"},"class_bearing":false},{"code_sha256_prefix":"568eece08bf61ac5","path":"algorithms/algorithms.py","papers":["2106.04732"],"paper_pages":[{"arxiv_id":"2106.04732","page":"/paper/adamatch-a-unified-approach-to-semi"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"lambd":"1.0"},"class_bearing":false},{"code_sha256_prefix":"5a2b24f39d01d817","path":"APY/code/model.py","papers":["2003.00845"],"paper_pages":[{"arxiv_id":"2003.00845","page":"/paper/addressing-target-shift-in-zero-shot-learning"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"LAMBDA":"0.5"},"class_bearing":false},{"code_sha256_prefix":"5c9517d15decf27f","path":"module/model.py","papers":["2604.13692"],"paper_pages":[{"arxiv_id":"2604.13692","page":"/paper/arxiv-2604-13692"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"lambda_":"1.0"},"class_bearing":false},{"code_sha256_prefix":"abb34bc87e086cd4","path":"Pytorch/lib/model/faster_rcnn_MV_3/DA.py","papers":["2304.02950"],"paper_pages":[{"arxiv_id":"2304.02950","page":"/paper/multi-view-adversarial-discriminator-mine-the"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"ed0154a7aa37f9c9","path":"models/basenet.py","papers":["2104.00246"],"paper_pages":[{"arxiv_id":"2104.00246","page":"/paper/divergence-optimization-for-noisy-universal"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"lambd":"1.0"},"class_bearing":false}]}]}]}