{"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/get-1d-sincos-pos-embed-from-grid","entry":"get_1d_sincos_pos_embed_from_grid","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":8,"n_papers":17,"n_buckets":2,"n_distinct_outputs":2,"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/get-1d-sincos-pos-embed-from-grid","buckets":[{"bucket":[[1,"float","float64"]],"n_implementations_compared":6,"n_papers":13,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"f7de1e939f561301","size":6,"n_papers":13,"shape":[8,8],"dtype":"float64","type":"ndarray","finite":true,"max_difference_among_recorded_values":2.394462128574304e-09,"members_with_recorded_values":6,"torch_reference_conventions_with_this_digest":[],"values":[-0.785738420936803,-0.09026586838886821,-0.009038766916584961,-0.0009038888767124271,0.6185589170513504,0.9959177039314059,0.9999591495119327,0.9999995914923658,0.15648565125671215,0.015712499119446482,0.00157131392490955,0.00015713145650471006,0.9876802321352608,0.999876551065891,0.9999987654855127,0.9999999876548527,0.7818402646430671,0.08964071179683285,0.008975999331718892,0.0008976118661297679,0.6234787892004496,0.9959741677315518,0.9999597149065541,0.9999995971463878,-0.6905111908967543,-0.07614577700545333,-0.007621881616104257,-0.0007621954676476743,0.7233217093702817,0.9970966957342883,0.9999709530384521,0.9999997095289923,-0.17534438651294937,-0.017624643748575624,-0.0017625547201716996,-0.0001762555623638873,0.9845071589980428,0.9998446739032697,0.9999984466992228,0.9999999844669882,0.05300686697343842,0.005303147231649198,0.0005303171840452122,5.303172086540496e-05,0.9985941478166493,0.9999859382158528,0.9999998593818322,0.9999999985938183,-0.998339047234083,-0.16212526070310754,-0.016283683104559285,-0.0016284395618946857,-0.05761203665679079,0.9867701859308222,0.9998674120424919,0.9999986740914176,-0.17660221488685782,-0.01775240056888602,-0.0017753323813408303,-0.00017753333045999006,0.9842823058945315,0.9998424137203031,0.9999984240962262,0.9999999842409582],"values_recorded":64,"members":[{"code_sha256_prefix":"e5947aba1d10885f","path":"models_dig.py","papers":["2212.09748","2310.00426","2403.04692","2412.12095","2606.08063","2601.11522"],"paper_pages":[{"arxiv_id":"2212.09748","page":"/paper/scalable-diffusion-models-with-transformers"},{"arxiv_id":"2310.00426","page":"/paper/pixart-a-fast-training-of-diffusion"},{"arxiv_id":"2403.04692","page":"/paper/pixart-s-weak-to-strong-training-of-diffusion"},{"arxiv_id":"2412.12095","page":"/paper/causal-diffusion-transformers-for-generative"},{"arxiv_id":"2606.08063","page":"/paper/arxiv-2606-08063"},{"arxiv_id":"2601.11522","page":"/paper/arxiv-2601-11522"}],"arg_sig_recorded":[["pos",1,"float","float64"]],"scalar_args":{"embed_dim":"8"},"class_bearing":false},{"code_sha256_prefix":"4bdd36eab04c3f62","path":"models/croco.py","papers":["2210.10716","2506.21803","2603.01759"],"paper_pages":[{"arxiv_id":"2210.10716","page":"/paper/croco-self-supervised-pre-training-for-3d"},{"arxiv_id":"2506.21803","page":null},{"arxiv_id":"2603.01759","page":"/paper/arxiv-2603-01759"}],"arg_sig_recorded":[["pos",1,"float","float64"]],"scalar_args":{"embed_dim":"8"},"class_bearing":false},{"code_sha256_prefix":"06a688b14731d363","path":"models/rdt/model.py","papers":["2606.08414"],"paper_pages":[{"arxiv_id":"2606.08414","page":"/paper/arxiv-2606-08414"}],"arg_sig_recorded":[["pos",1,"float","float64"]],"scalar_args":{"embed_dim":"8"},"class_bearing":false},{"code_sha256_prefix":"6a53acdcb72e78dd","path":"models_cross.py","papers":["2304.03283"],"paper_pages":[{"arxiv_id":"2304.03283","page":"/paper/diffusion-models-as-masked-autoencoders"}],"arg_sig_recorded":[["pos",1,"float","float64"]],"scalar_args":{"embed_dim":"8","idx_range":"14"},"class_bearing":false},{"code_sha256_prefix":"7b75bf9ed4e14ba7","path":"models/UDT.py","papers":["2608.01298"],"paper_pages":[{"arxiv_id":"2608.01298","page":"/paper/arxiv-2608-01298"}],"arg_sig_recorded":[["pos",1,"float","float64"]],"scalar_args":{"embed_dim":"8"},"class_bearing":false},{"code_sha256_prefix":"f6dd6f9161d38af6","path":"src/models/predictor.py","papers":["2602.02603"],"paper_pages":[{"arxiv_id":"2602.02603","page":"/paper/arxiv-2602-02603"}],"arg_sig_recorded":[["pos",1,"float","float64"]],"scalar_args":{"embed_dim":"8"},"class_bearing":false}]}]},{"bucket":[[1,"float","float32"]],"n_implementations_compared":2,"n_papers":4,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"f7de1e939f561301","size":2,"n_papers":4,"shape":[8,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":5.960464477539063e-08,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[-0.7857384085655212,-0.09026587009429932,-0.009038766846060753,-0.0009038889547809958,0.618558943271637,0.9959176778793335,0.9999591708183289,0.9999995827674866,0.1564856618642807,0.015712499618530273,0.0015713139437139034,0.00015713146422058344,0.9876802563667297,0.9998765587806702,0.9999987483024597,1.0,0.7818402647972107,0.08964071422815323,0.008975999429821968,0.0008976118988357484,0.6234787702560425,0.9959741830825806,0.9999597072601318,0.9999995827674866,-0.690511167049408,-0.07614577561616898,-0.007621881552040577,-0.000762195501010865,0.7233217358589172,0.9970967173576355,0.9999709725379944,0.9999997019767761,-0.17534439265727997,-0.017624644562602043,-0.0017625547479838133,-0.00017625557666178793,0.984507143497467,0.9998446702957153,0.9999984502792358,1.0,0.053006865084171295,0.0053031472489237785,0.0005303171928972006,5.3031722927698866e-05,0.9985941648483276,0.999985933303833,0.9999998807907104,1.0,-0.998339056968689,-0.16212525963783264,-0.016283683478832245,-0.0016284396406263113,-0.057612016797065735,0.9867702126502991,0.9998674392700195,0.9999986886978149,-0.17660221457481384,-0.017752399668097496,-0.001775332260876894,-0.00017753333668224514,0.9842823147773743,0.9998424053192139,0.9999984502792358,1.0],"values_recorded":64,"members":[{"code_sha256_prefix":"5c8ea92d43ead77d","path":"models/dreamvla_model.py","papers":["2010.11929","2411.12164","2507.04447"],"paper_pages":[{"arxiv_id":"2010.11929","page":"/paper/an-image-is-worth-16x16-words-transformers-1"},{"arxiv_id":"2411.12164","page":"/paper/urbandit-a-foundation-model-for-open-world"},{"arxiv_id":"2507.04447","page":"/paper/dreamvla-a-vision-language-action-model-1"}],"arg_sig_recorded":[["pos",1,"float","float32"]],"scalar_args":{"embed_dim":"8"},"class_bearing":false},{"code_sha256_prefix":"44aacaf688b398e0","path":"models/modeling_pretrain.py","papers":["2506.11777"],"paper_pages":[{"arxiv_id":"2506.11777","page":"/paper/self-supervised-learning-of-echocardiographic"}],"arg_sig_recorded":[["pos",1,"float","float32"]],"scalar_args":{"embed_dim":"8"},"class_bearing":false}]}]}]}