{"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/l2norm","entry":"l2norm","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":12,"n_papers":20,"n_buckets":1,"n_distinct_outputs":3,"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/l2norm","buckets":[{"bucket":[[2,"float","float32"]],"n_implementations_compared":12,"n_papers":20,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"2803cfee2d9ac85e","size":10,"n_papers":18,"shape":[4,8],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":5.960464477539063e-08,"members_with_recorded_values":10,"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":"3eb58dae620046d3","path":"CLIP_eval/CLIPure_Cos.py","papers":["2502.18176","2510.19710","2209.04439"],"paper_pages":[{"arxiv_id":"2502.18176","page":"/paper/clipure-purification-in-latent-space-via-clip"},{"arxiv_id":"2510.19710","page":"/paper/arxiv-2510-19710"},{"arxiv_id":"2209.04439","page":"/paper/improved-masked-image-generation-with-token"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"9e5b9ebb30a1dab5","path":"face-cluster-by-infomap.py","papers":["2004.00445","1904.02749","2404.08995"],"paper_pages":[{"arxiv_id":"2004.00445","page":"/paper/learning-to-cluster-faces-via-confidence-and"},{"arxiv_id":"1904.02749","page":"/paper/learning-to-cluster-faces-on-an-affinity"},{"arxiv_id":"2404.08995","page":"/paper/beyond-known-clusters-probe-new-prototypes"}],"arg_sig_recorded":[["vec",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"be7c4a676b9f1e19","path":"DM-GAN+CL/code/pretrain_DAMSM.py","papers":["2310.17468","1904.01310","2404.17273"],"paper_pages":[{"arxiv_id":"2310.17468","page":"/paper/cross-modal-active-complementary-learning-1"},{"arxiv_id":"1904.01310","page":"/paper/dm-gan-dynamic-memory-generative-adversarial"},{"arxiv_id":"2404.17273","page":"/paper/3shnet-boosting-image-sentence-retrieval-via"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{"dim":"1","eps":"1e-08"},"class_bearing":false},{"code_sha256_prefix":"eca6cdf05972a95e","path":"LaVIT/models/modeling_visual_tokenzier.py","papers":["2308.02117","2309.04669","2506.21803"],"paper_pages":[{"arxiv_id":"2308.02117","page":"/paper/vqgraph-graph-vector-quantization-for"},{"arxiv_id":"2309.04669","page":"/paper/unified-language-vision-pretraining-with"},{"arxiv_id":"2506.21803","page":null}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"03e1f23d59a7c45a","path":"model.py","papers":["2310.17468","2101.01368"],"paper_pages":[{"arxiv_id":"2310.17468","page":"/paper/cross-modal-active-complementary-learning-1"},{"arxiv_id":"2101.01368","page":"/paper/similarity-reasoning-and-filtration-for-image"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{"dim":"-1","eps":"1e-08"},"class_bearing":false},{"code_sha256_prefix":"09b2eed13fab23fa","path":"byol_pytorch/byol_pytorch.py","papers":["2006.07733"],"paper_pages":[{"arxiv_id":"2006.07733","page":"/paper/bootstrap-your-own-latent-a-new-approach-to"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"741174c85c8d06ad","path":"model.py","papers":["1707.05612"],"paper_pages":[{"arxiv_id":"1707.05612","page":"/paper/vse-improving-visual-semantic-embeddings-with"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"e4fe846ff705def5","path":"model/cross_modal_attention.py","papers":["2308.15512"],"paper_pages":[{"arxiv_id":"2308.15512","page":"/paper/shatter-and-gather-learning-referring-image"}],"arg_sig_recorded":[["x",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"ebc7297040578822","path":"flash_cosine_sim_attention/flash_cosine_sim_attention.py","papers":["2205.14135"],"paper_pages":[{"arxiv_id":"2205.14135","page":"/paper/flashattention-fast-and-memory-efficient"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"f92e514b398e75d8","path":"model.py","papers":["2002.02814"],"paper_pages":[{"arxiv_id":"2002.02814","page":"/paper/fine-grained-fashion-similarity-learning-by"}],"arg_sig_recorded":[["X",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"52b2d26799446195","size":1,"n_papers":1,"shape":[4,1],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[2.9917142391204834,3.138503074645996,2.3749611377716064,2.8242647647857666],"values_recorded":4,"members":[{"code_sha256_prefix":"f97c5f0657e277e8","path":"interactive.py","papers":["2004.02546"],"paper_pages":[{"arxiv_id":"2004.02546","page":"/paper/ganspace-discovering-interpretable-gan"}],"arg_sig_recorded":[["t",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"73f4a3f4fb69d67f","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":[0.8842244744300842,-0.6213192939758301,0.39343246817588806,-0.3396601676940918,-0.5826104283332825,-0.3348237872123718,-0.4003332853317261,0.41005823016166687,0.2545187473297119,0.38854148983955383,-0.32826411724090576,-0.7710455656051636,-0.18619221448898315,0.7545064687728882,-0.31094950437545776,0.3940531015396118,0.03256825730204582,-0.6574126482009888,0.3571169078350067,-0.19969278573989868,-0.014580094255506992,-0.3836633563041687,-0.3242892622947693,0.7040867209434509,-0.3902635872364044,0.17551566660404205,0.7809734344482422,0.5002415776252747,-0.7910017371177673,0.41402268409729004,-0.7986732721328735,-0.42524686455726624],"values_recorded":32,"members":[{"code_sha256_prefix":"8deabf7913c20741","path":"models/ours/model.py","papers":["2303.17778"],"paper_pages":[{"arxiv_id":"2303.17778","page":"/paper/crossloc3d-aerial-ground-cross-source-3d"}],"arg_sig_recorded":[["inp",2,"float","float32"]],"scalar_args":{"dim":"0"},"class_bearing":false}]}]}]}