{"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/gumbel-softmax-sample","entry":"gumbel_softmax_sample","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":14,"n_papers":16,"n_buckets":1,"n_distinct_outputs":4,"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/gumbel-softmax-sample","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":14,"n_papers":16,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"4b71b65a282dc2bb","size":11,"n_papers":12,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":1.862645149230957e-08,"members_with_recorded_values":11,"torch_reference_conventions_with_this_digest":[],"values":[0.22007779777050018,0.00196555582806468,0.0012939530424773693,0.00017989642219617963,0.0003469175717327744,0.0018016101093962789,0.0015339476522058249,0.7728002667427063,0.05890709534287453,0.4178870618343353,0.005254834890365601,0.0006732297479175031,0.0005009148735553026,0.4238051772117615,0.003071265760809183,0.0899004265666008,0.020739721134305,0.0018409527838230133,0.001674994477070868,0.0006529040983878076,0.015313185751438141,0.028255118057131767,0.0009430024074390531,0.9305800795555115,9.282327664550394e-05,0.002330946736037731,0.9716299772262573,0.00023893671459518373,1.042725307343062e-05,0.004534349776804447,1.7346590539091267e-05,0.02114528976380825],"values_recorded":32,"members":[{"code_sha256_prefix":"4650349b06b3d90f","path":"vqapc_model.py","papers":["1904.03240","2005.08392"],"paper_pages":[{"arxiv_id":"1904.03240","page":"/paper/an-unsupervised-autoregressive-model-for"},{"arxiv_id":"2005.08392","page":"/paper/vector-quantized-autoregressive-predictive"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5"},"class_bearing":false},{"code_sha256_prefix":"09ef8173e6e07e61","path":"model_vmtl.py","papers":["2111.05323"],"paper_pages":[{"arxiv_id":"2111.05323","page":"/paper/variational-multi-task-learning-with-gumbel"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5"},"class_bearing":false},{"code_sha256_prefix":"545203c795be4bc9","path":"vision/quantizer.py","papers":["2205.07547"],"paper_pages":[{"arxiv_id":"2205.07547","page":"/paper/sq-vae-variational-bayes-on-discrete"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5"},"class_bearing":false},{"code_sha256_prefix":"626e470a849ef8d9","path":"ibr_game/finetune.py","papers":["2002.01093"],"paper_pages":[{"arxiv_id":"2002.01093","page":"/paper/on-the-interaction-between-supervision-and-1"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temp":"0.5"},"class_bearing":false},{"code_sha256_prefix":"6697676fd57aebe3","path":"maddpg-pytorch/algorithms/maddpg.py","papers":["1706.02275"],"paper_pages":[{"arxiv_id":"1706.02275","page":"/paper/multi-agent-actor-critic-for-mixed"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5"},"class_bearing":false},{"code_sha256_prefix":"6bd331cf7087ed47","path":"cgae.py","papers":["1812.02706"],"paper_pages":[{"arxiv_id":"1812.02706","page":"/paper/variational-coarse-graining-for-molecular"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5","device":"'cpu'"},"class_bearing":false},{"code_sha256_prefix":"7a26c95f374badbf","path":"ec-game/models.py","papers":["2203.13344"],"paper_pages":[{"arxiv_id":"2203.13344","page":"/paper/linking-emergent-and-natural-languages-via-1"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temp":"0.5","tt":"<module 'torch' from '/usr/local/lib/python3.11/site-package","idx_":"10"},"class_bearing":false},{"code_sha256_prefix":"8c49f9e976f85256","path":"models_dy.py","papers":["2007.00631"],"paper_pages":[{"arxiv_id":"2007.00631","page":"/paper/causal-discovery-in-physical-systems-from"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5"},"class_bearing":false},{"code_sha256_prefix":"d069f664a7cf326c","path":"distributions/gumbel.py","papers":["1611.01144"],"paper_pages":[{"arxiv_id":"1611.01144","page":"/paper/categorical-reparameterization-with-gumbel"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5","device":"device(type='cpu')"},"class_bearing":false},{"code_sha256_prefix":"d925dcd18145a559","path":"model/pytorch/model.py","papers":["2101.06861"],"paper_pages":[{"arxiv_id":"2101.06861","page":"/paper/discrete-graph-structure-learning-for-1"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5"},"class_bearing":false},{"code_sha256_prefix":"fce7e94284fafc48","path":"models/LSINet.py","papers":["2602.01585"],"paper_pages":[{"arxiv_id":"2602.01585","page":"/paper/arxiv-2602-01585"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"0.5","eps":"1e-10","device":"None"},"class_bearing":false}]},{"output_sha":"2ddd2140e02ea79c","size":1,"n_papers":2,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.3041975498199463,0.028748169541358948,0.023325279355049133,0.008697188459336758,0.012077602557837963,0.027523133903741837,0.0253964364528656,0.5700346231460571,0.12037739902734756,0.320620059967041,0.03595346584916115,0.012868949212133884,0.011100511066615582,0.32288238406181335,0.02748652547597885,0.14871065318584442,0.09347780048847198,0.02785019762814045,0.026565242558717728,0.016585618257522583,0.08032297343015671,0.10910774767398834,0.019932575523853302,0.6261578798294067,0.007531470153480768,0.03774133697152138,0.770551323890686,0.012083500623703003,0.002524272771552205,0.05263912305235863,0.003255803370848298,0.11367318034172058],"values_recorded":32,"members":[{"code_sha256_prefix":"0d41bbe52278fde1","path":"model_search.py","papers":["2106.06575","2210.13361"],"paper_pages":[{"arxiv_id":"2106.06575","page":"/paper/auto-nba-efficient-and-effective-search-over"},{"arxiv_id":"2210.13361","page":"/paper/nasa-neural-architecture-search-and"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"temperature":"1.0"},"class_bearing":false}]},{"output_sha":"54a41cc635438b5c","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.9868321418762207,0.40095433592796326,0.3058564364910126,0.05772323161363602,0.10565304756164551,0.38022714853286743,0.3431200683116913,0.9962143301963806,0.8204130530357361,0.9700669050216675,0.28953078389167786,0.049619417637586594,0.03739406168460846,0.970472514629364,0.19236384332180023,0.8745596408843994,0.8980756998062134,0.43887144327163696,0.41575685143470764,0.21715012192726135,0.8667689561843872,0.9231011867523193,0.28603628277778625,0.9974769949913025,0.21245424449443817,0.8713711500167847,0.9996459484100342,0.4098238945007324,0.02941286936402321,0.9294679164886475,0.04799393191933632,0.9839881062507629],"values_recorded":32,"members":[{"code_sha256_prefix":"82162a6032091037","path":"imgnet_models/hypernet.py","papers":["2403.14729"],"paper_pages":[{"arxiv_id":"2403.14729","page":"/paper/auto-train-once-controller-network-guided"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"T":"0.5","offset":"0"},"class_bearing":false}]},{"output_sha":"8de8fd95c34475b9","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.6061398983001709,0.08182819932699203,0.012006753124296665,0.13480830192565918,0.10525322705507278,0.05754581838846207,0.3494420349597931,0.34822458028793335,0.14965417981147766,0.5693904757499695,0.011546919122338295,0.12445363402366638,0.06035654991865158,0.4211985170841217,0.23596572875976562,0.0566796250641346,0.20783919095993042,0.08845511823892593,0.015258586965501308,0.2868608832359314,0.78108149766922,0.2545500695705414,0.30603253841400146,0.4268191158771515,0.03636676445603371,0.26032620668411255,0.9611877202987671,0.45387718081474304,0.053308796137571335,0.2667056918144226,0.10855963081121445,0.16827671229839325],"values_recorded":32,"members":[{"code_sha256_prefix":"2cecb1236580790d","path":"model/GroupNet_nba.py","papers":["2204.08770"],"paper_pages":[{"arxiv_id":"2204.08770","page":"/paper/groupnet-multiscale-hypergraph-neural"}],"arg_sig_recorded":[["logits",2,"float","float32"]],"scalar_args":{"tau":"1.0","eps":"1e-10"},"class_bearing":false}]}]}]}