{"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/slerp","entry":"slerp","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":6,"n_papers":6,"n_buckets":2,"n_distinct_outputs":6,"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/slerp","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":5,"n_papers":5,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"13a71becf2dd012f","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.8026288747787476,-1.5337765216827393,0.47605329751968384,-0.6908870935440063,-0.9028496146202087,-1.0304713249206543,-0.6627609729766846,0.5728892683982849,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN],"values_recorded":32,"members":[{"code_sha256_prefix":"6d7397331b84d54f","path":"CoW_generator.py","papers":["1912.04958"],"paper_pages":[{"arxiv_id":"1912.04958","page":"/paper/analyzing-and-improving-the-image-quality-of"}],"arg_sig_recorded":[["low",2,"float","float32"],["high",2,"float","float32"]],"scalar_args":{"val":"0.5"},"class_bearing":false}]},{"output_sha":"2803cfee2d9ac85e","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":[0.6025403738021851,-0.5126747488975525,0.15912389755249023,-0.23093350231647491,-0.30178332328796387,-0.3444417119026184,-0.2215321660041809,0.191491961479187,0.16532593965530396,0.30560609698295593,-0.12655700743198395,-0.49971216917037964,-0.09193398058414459,0.7398778200149536,-0.16402213275432587,0.175411194562912,0.027956431731581688,-0.6833271980285645,0.18194462358951569,-0.17102842032909393,-0.009513513185083866,-0.49717968702316284,-0.22605349123477936,0.41418537497520447,-0.28170618414878845,0.153411403298378,0.3345924913883209,0.3602772355079651,-0.43401941657066345,0.451168030500412,-0.46816498041152954,-0.2103588581085205],"values_recorded":32,"members":[{"code_sha256_prefix":"2762690ed8c0e631","path":"slerp.py","papers":["2405.00571"],"paper_pages":[{"arxiv_id":"2405.00571","page":"/paper/spherical-linear-interpolation-and-text"}],"arg_sig_recorded":[["v0",2,"float","float32"],["v1",2,"float","float32"]],"scalar_args":{"t":"0.5"},"class_bearing":false}]},{"output_sha":"7400de5bca4835ca","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":[0.6025404334068298,-0.5126748085021973,0.15912391245365143,-0.2309335321187973,-0.30178335309028625,-0.3444417417049408,-0.2215321958065033,0.1914919912815094,0.16532595455646515,0.3056061267852783,-0.12655702233314514,-0.4997122287750244,-0.09193398803472519,0.7398778796195984,-0.16402214765548706,0.17541120946407318,0.027956435456871986,-0.6833272576332092,0.18194463849067688,-0.17102843523025513,-0.00951351411640644,-0.4971797466278076,-0.22605352103710175,0.41418543457984924,-0.28170621395111084,0.15341141819953918,0.3345925211906433,0.3602772653102875,-0.4340194761753082,0.45116809010505676,-0.4681650400161743,-0.2103588879108429],"values_recorded":32,"members":[{"code_sha256_prefix":"390974c5e23b0188","path":"lib/model/age_map.py","papers":["2506.20977"],"paper_pages":[{"arxiv_id":"2506.20977","page":"/paper/from-cradle-to-cane-a-two-pass-framework-for"}],"arg_sig_recorded":[["low",2,"float","float32"],["high",2,"float","float32"]],"scalar_args":{"val":"0.5"},"class_bearing":false}]},{"output_sha":"9447548f9ede2c5e","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN],"values_recorded":32,"members":[{"code_sha256_prefix":"3f52e7a30971cc76","path":"eval/counterfactual_generation.py","papers":["2401.11430"],"paper_pages":[{"arxiv_id":"2401.11430","page":"/paper/exploring-diffusion-time-steps-for"}],"arg_sig_recorded":[["a",2,"float","float32"],["b",2,"float","float32"]],"scalar_args":{"alpha":"0.5"},"class_bearing":false}]},{"output_sha":"ef0185a3b8f0bbb9","size":1,"n_papers":1,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.8026286363601685,-1.5337762832641602,0.47605323791503906,-0.6908870339393616,-0.9028494954109192,-1.0304712057113647,-0.6627609133720398,0.5728892087936401,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,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":"dfa7a0f7f0ec846f","path":"generate.py","papers":["2405.20320"],"paper_pages":[{"arxiv_id":"2405.20320","page":"/paper/improving-the-training-of-rectified-flows"}],"arg_sig_recorded":[["low",2,"float","float32"],["high",2,"float","float32"]],"scalar_args":{"val":"0.5"},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"],[3,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"5ddff91cfc87633b","size":1,"n_papers":1,"shape":[2,4,8],"dtype":"float32","type":"Tensor","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[-0.8931273818016052,1.6828533411026,-1.2588047981262207,-0.2582058906555176,0.15099601447582245,-1.4347596168518066,-0.3401457369327545,-0.3811258375644684,-2.139214038848877,0.011872420087456703,-0.848949134349823,-0.7722031474113464,0.8366092443466187,-0.16943085193634033,0.15168990194797516,0.40691596269607544,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,-0.33936411142349243,-0.0975174680352211,0.7487973570823669,-0.9978419542312622,0.5280088782310486,0.18848304450511932,-0.7085897922515869,-0.9634317755699158,-1.271640658378601,1.155332088470459,1.6535718441009521,-0.581495463848114,1.8763816356658936,1.2408666610717773,-1.2724858522415161,-0.8599306344985962],"values_recorded":64,"members":[{"code_sha256_prefix":"c768f8fe79a4c51a","path":"generate.py","papers":["2111.05011"],"paper_pages":[{"arxiv_id":"2111.05011","page":"/paper/rave-a-variational-autoencoder-for-fast-and-1"}],"arg_sig_recorded":[["low",3,"float","float32"],["high",3,"float","float32"]],"scalar_args":{"val":"0.5"},"class_bearing":false}]}]}]}