{"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/inverse-sigmoid","entry":"inverse_sigmoid","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":9,"n_papers":14,"n_buckets":2,"n_distinct_outputs":5,"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/inverse-sigmoid","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":8,"n_papers":13,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"c080a9484751dab9","size":3,"n_papers":5,"shape":[4,8],"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":[6.907755374908447,-6.907755374908447,-0.09586039185523987,-6.907755374908447,-6.907755374908447,-6.907755374908447,-6.907755374908447,0.293648898601532,0.0755397155880928,3.1560299396514893,-6.907755374908447,-6.907755374908447,-6.907755374908447,6.907755374908447,-6.907755374908447,0.20280665159225464,-2.6434245109558105,-6.907755374908447,-0.27324187755584717,-6.907755374908447,-6.907755374908447,-6.907755374908447,-6.907755374908447,4.098546028137207,-6.907755374908447,-0.26850399374961853,2.843423843383789,6.907755374908447,-6.907755374908447,6.907755374908447,-6.907755374908447,-6.907755374908447],"values_recorded":32,"members":[{"code_sha256_prefix":"6897880b6ce14c94","path":"qd_detr/model.py","papers":["2404.04624","2412.13441","2311.08835"],"paper_pages":[{"arxiv_id":"2404.04624","page":"/paper/bridging-the-gap-between-end-to-end-and-two"},{"arxiv_id":"2412.13441","page":"/paper/flashvtg-feature-layering-and-adaptive-score"},{"arxiv_id":"2311.08835","page":"/paper/correlation-guided-query-dependency"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"0.001"},"class_bearing":false},{"code_sha256_prefix":"24d843af1035723e","path":"models/detectors/salience_detr.py","papers":["2403.16131"],"paper_pages":[{"arxiv_id":"2403.16131","page":"/paper/salience-detr-enhancing-detection-transformer-1"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"0.001"},"class_bearing":false},{"code_sha256_prefix":"49611009ffc9cf17","path":"detrex/layers/denoising.py","papers":["2203.01305"],"paper_pages":[{"arxiv_id":"2203.01305","page":"/paper/dn-detr-accelerate-detr-training-by"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"0.001"},"class_bearing":false}]},{"output_sha":"67404bbcfd59267c","size":3,"n_papers":4,"shape":[4,8],"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":[11.512925148010254,-11.512925148010254,-0.09586039185523987,-11.512925148010254,-11.512925148010254,-11.512925148010254,-11.512925148010254,0.293648898601532,0.0755397155880928,3.1560299396514893,-11.512925148010254,-11.512925148010254,-11.512925148010254,11.512925148010254,-11.512925148010254,0.20280665159225464,-2.6434245109558105,-11.512925148010254,-0.27324187755584717,-11.512925148010254,-11.512925148010254,-11.512925148010254,-11.512925148010254,4.098546028137207,-11.512925148010254,-0.26850399374961853,2.843423843383789,11.512925148010254,-11.512925148010254,11.512925148010254,-11.512925148010254,-11.512925148010254],"values_recorded":32,"members":[{"code_sha256_prefix":"83c03ceb1307c6c4","path":"src/models/polygon_models/polygon_net.py","papers":["2103.11161","2507.19993"],"paper_pages":[{"arxiv_id":"2103.11161","page":"/paper/montefloor-extending-mcts-for-reconstructing"},{"arxiv_id":"2507.19993","page":null}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"1e-05"},"class_bearing":false},{"code_sha256_prefix":"a57888d65b00fb2b","path":"alonet/deformable_detr/deformable_transformer.py","papers":["2010.04159"],"paper_pages":[{"arxiv_id":"2010.04159","page":"/paper/deformable-detr-deformable-transformers-for-1"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"1e-05"},"class_bearing":false},{"code_sha256_prefix":"bd7d1844c78a5ac3","path":"models/memotr.py","papers":["2307.15700"],"paper_pages":[{"arxiv_id":"2307.15700","page":"/paper/memotr-long-term-memory-augmented-transformer"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"1e-05"},"class_bearing":false}]},{"output_sha":"9ebb719075988ed0","size":1,"n_papers":4,"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,-0.09586039185523987,NaN,NaN,NaN,NaN,0.293648898601532,0.0755397155880928,3.1560299396514893,NaN,NaN,NaN,NaN,NaN,0.20280665159225464,-2.6434245109558105,NaN,-0.27324187755584717,NaN,NaN,NaN,NaN,4.098546028137207,NaN,-0.26850399374961853,2.843423843383789,NaN,NaN,NaN,NaN,NaN],"values_recorded":32,"members":[{"code_sha256_prefix":"b488da571728b636","path":"utils/general_utils.py","papers":["2311.11284","2403.19495","2506.13348","2601.22990"],"paper_pages":[{"arxiv_id":"2311.11284","page":"/paper/luciddreamer-towards-high-fidelity-text-to-3d"},{"arxiv_id":"2403.19495","page":"/paper/coherentgs-sparse-novel-view-synthesis-with"},{"arxiv_id":"2506.13348","page":"/paper/texturesplat-per-primitive-texture-mapping"},{"arxiv_id":"2601.22990","page":"/paper/arxiv-2601-22990"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"4ba09ae6a4a2b3f5","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":[13.815510749816895,-13.815510749816895,-0.09586039185523987,-13.815510749816895,-13.815510749816895,-13.815510749816895,-13.815510749816895,0.293648898601532,0.0755397155880928,3.1560299396514893,-13.815510749816895,-13.815510749816895,-13.815510749816895,13.815510749816895,-13.815510749816895,0.20280665159225464,-2.6434245109558105,-13.815510749816895,-0.27324187755584717,-13.815510749816895,-13.815510749816895,-13.815510749816895,-13.815510749816895,4.098546028137207,-13.815510749816895,-0.26850399374961853,2.843423843383789,13.815510749816895,-13.815510749816895,13.815510749816895,-13.815510749816895,-13.815510749816895],"values_recorded":32,"members":[{"code_sha256_prefix":"806f660f9474c72d","path":"models/deformable_transformer.py","papers":["2010.04159"],"paper_pages":[{"arxiv_id":"2010.04159","page":"/paper/deformable-detr-deformable-transformers-for-1"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{"eps":"1e-06"},"class_bearing":false}]}]},{"bucket":[[1,"float","float64"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"cb42bb4768585796","size":1,"n_papers":1,"shape":[8],"dtype":"float64","type":"ndarray","finite":false,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[NaN,0.16405435110762945,0.9341936480661275,NaN,NaN,-0.0764750709110733,NaN,NaN],"values_recorded":8,"members":[{"code_sha256_prefix":"a110880086c35bb4","path":"dev/model_validation_experiment.py","papers":["2205.13600"],"paper_pages":[{"arxiv_id":"2205.13600","page":"/paper/myosuite-a-contact-rich-simulation-suite-for"}],"arg_sig_recorded":[["y",1,"float","float64"]],"scalar_args":{"k":"5.0","x0":"0.5"},"class_bearing":false}]}]}]}