{"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/sinusoidalpositionembeddings","entry":"SinusoidalPositionEmbeddings","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":1,"n_distinct_outputs":3,"n_class_bearing":5,"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/sinusoidalpositionembeddings","buckets":[{"bucket":[[1,"float","float32"]],"n_implementations_compared":5,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"a86b58228a05e5a6","size":3,"n_papers":3,"shape":[8,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[-0.7857384085655212,-0.04194250702857971,-0.0019473686115816236,-9.038889402290806e-05,0.618558943271637,0.9991199970245361,0.9999980926513672,1.0,0.1564856618642807,0.007293332368135452,0.00033852949854917824,1.5713145330664702e-05,0.9876802563667297,0.9999734163284302,0.9999999403953552,1.0,0.7818402647972107,0.0416514091193676,0.0019338453421369195,8.976118988357484e-05,0.6234787702560425,0.9991322159767151,0.999998152256012,1.0,-0.690511167049408,-0.0353706069290638,-0.0016420998144894838,-7.621954864589497e-05,0.7233217358589172,0.999374270439148,0.9999986290931702,1.0,-0.17534439265727997,-0.008180968463420868,-0.00037973112193867564,-1.7625554391997866e-05,0.984507143497467,0.999966561794281,0.9999999403953552,1.0,0.053006865084171295,0.0024615121074020863,0.00011425338016124442,5.303171292325715e-06,0.9985941648483276,0.9999969601631165,1.0,1.0,-0.998339056968689,-0.075513556599617,-0.003508361056447029,-0.00016284400771837682,-0.057612016797065735,0.9971447587013245,0.9999938607215881,1.0,-0.17660221457481384,-0.008240274153649807,-0.00038248399505391717,-1.775333112163935e-05,0.9842823147773743,0.999966025352478,0.9999999403953552,1.0],"values_recorded":64,"members":[{"code_sha256_prefix":"52bb9e202a8ce9ef","path":"Diffusion/DDPM/models/model.py","papers":["2006.11239"],"paper_pages":[{"arxiv_id":"2006.11239","page":"/paper/denoising-diffusion-probabilistic-models"}],"arg_sig_recorded":[["time",1,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"a8e06e074c8ee49d","path":"lib/models/tfm_model.py","papers":["2303.17839"],"paper_pages":[{"arxiv_id":"2303.17839","page":"/paper/learning-procedure-aware-video-representation"}],"arg_sig_recorded":[["time",1,"float","float32"]],"scalar_args":{},"class_bearing":true},{"code_sha256_prefix":"d5b5086713ef6444","path":"models/diffusion_proposal_module.py","papers":["2312.02966"],"paper_pages":[{"arxiv_id":"2312.02966","page":"/paper/diffusion-ss3d-diffusion-model-for-semi-1"}],"arg_sig_recorded":[["time",1,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"21039c3853b86d0f","size":1,"n_papers":1,"shape":[8,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.7857384085655212,-9.038889402290806e-05,0.618558943271637,1.0,0.1564856618642807,1.5713145330664702e-05,0.9876802563667297,1.0,0.7818402647972107,8.976118988357484e-05,0.6234787702560425,1.0,-0.690511167049408,-7.621954864589497e-05,0.7233217358589172,1.0,-0.17534439265727997,-1.7625554391997866e-05,0.984507143497467,1.0,0.053006865084171295,5.303171292325715e-06,0.9985941648483276,1.0,-0.998339056968689,-0.00016284400771837682,-0.057612016797065735,1.0,-0.17660221457481384,-1.775333112163935e-05,0.9842823147773743,1.0],"values_recorded":32,"members":[{"code_sha256_prefix":"c04f520f6e97ec1b","path":"lib/WavePDE.py","papers":["2304.12944"],"paper_pages":[{"arxiv_id":"2304.12944","page":"/paper/latent-traversals-in-generative-models-as"}],"arg_sig_recorded":[["time",1,"float","float32"]],"scalar_args":{},"class_bearing":true}]},{"output_sha":"ebb98a154223944a","size":1,"n_papers":1,"shape":[8,4],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.7857384085655212,-0.03905064985156059,0.618558943271637,0.9992372393608093,0.1564856618642807,0.006790213752537966,0.9876802563667297,0.9999769330024719,0.7818402647972107,0.0387796014547348,0.6234787702560425,0.9992477893829346,-0.690511167049408,-0.03293149545788765,0.7233217358589172,0.999457597732544,-0.17534439265727997,-0.0076166195794939995,0.984507143497467,0.9999709725379944,0.053006865084171295,0.002291706157848239,0.9985941648483276,0.9999973773956299,-0.998339056968689,-0.07031320780515671,-0.057612016797065735,0.9975249767303467,-0.17660221457481384,-0.007671834900975227,0.9842823147773743,0.999970555305481],"values_recorded":32,"members":[{"code_sha256_prefix":"603a0a61606c983d","path":"graph_gen/models/gine_stack_score_matching.py","papers":["2301.10857"],"paper_pages":[{"arxiv_id":"2301.10857","page":"/paper/improving-graph-generation-by-restricting"}],"arg_sig_recorded":[["time",1,"float","float32"]],"scalar_args":{},"class_bearing":true}]}]}]}