{"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/dice-loss","entry":"dice_loss","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":10,"n_papers":16,"n_buckets":4,"n_distinct_outputs":7,"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/dice-loss","buckets":[{"bucket":[[2,"float","float32"],[2,"float","float32"]],"n_implementations_compared":5,"n_papers":7,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"76dbc74111481ab1","size":3,"n_papers":5,"shape":[],"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":[0.22801810503005981],"values_recorded":1,"members":[{"code_sha256_prefix":"ac8fe530cdad4d8c","path":"models/deformable_detr.py","papers":["2112.04888","2303.14404","2601.01908"],"paper_pages":[{"arxiv_id":"2112.04888","page":"/paper/a-bilingual-openworld-video-text-dataset-and"},{"arxiv_id":"2303.14404","page":"/paper/bridging-precision-and-confidence-a-train"},{"arxiv_id":"2601.01908","page":"/paper/arxiv-2601-01908"}],"arg_sig_recorded":[["inputs",2,"float","float32"],["targets",2,"float","float32"]],"scalar_args":{"num_boxes":"2"},"class_bearing":false},{"code_sha256_prefix":"896fc4d5053e27de","path":"vidt/methods/vidt/criterion.py","papers":["2403.06213"],"paper_pages":[{"arxiv_id":"2403.06213","page":"/paper/v-kd-improving-knowledge-distillation-using"}],"arg_sig_recorded":[["inputs",2,"float","float32"],["targets",2,"float","float32"]],"scalar_args":{"num_boxes":"2"},"class_bearing":false},{"code_sha256_prefix":"d0e1858cb2c37a0a","path":"model/VRP_encoder.py","papers":["2402.17726"],"paper_pages":[{"arxiv_id":"2402.17726","page":"/paper/vrp-sam-sam-with-visual-reference-prompt"}],"arg_sig_recorded":[["inputs",2,"float","float32"],["targets",2,"float","float32"]],"scalar_args":{"num_masks":"2.0"},"class_bearing":false}]},{"output_sha":"564e4219dd255360","size":1,"n_papers":1,"shape":[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":[0.00011175870895385742,0.00010156631469726562,0.00017726421356201172,0.00012534856796264648],"values_recorded":4,"members":[{"code_sha256_prefix":"aaf96efc755ee384","path":"modules/solov2.py","papers":["2003.10152"],"paper_pages":[{"arxiv_id":"2003.10152","page":"/paper/solov2-dynamic-faster-and-stronger"}],"arg_sig_recorded":[["input",2,"float","float32"],["target",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]},{"output_sha":"5e014ef453b8e41d","size":1,"n_papers":1,"shape":[],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[12.225685119628906],"values_recorded":1,"members":[{"code_sha256_prefix":"c33d79f2237913d5","path":"scgm_train.py","papers":["2201.08657"],"paper_pages":[{"arxiv_id":"2201.08657","page":"/paper/enhancing-pseudo-label-quality-for-semi"}],"arg_sig_recorded":[["pred",2,"float","float32"],["target",2,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]},{"bucket":[[3,"float","float32"],[3,"float","float32"]],"n_implementations_compared":2,"n_papers":6,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"df6a0aee2aa08518","size":2,"n_papers":6,"shape":[],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":2,"torch_reference_conventions_with_this_digest":[],"values":[0.12528860569000244],"values_recorded":1,"members":[{"code_sha256_prefix":"a1c2083ec2eaeb22","path":"model/PixelLM.py","papers":["2510.03853","2312.02228","2404.05673","2412.04292","2406.20076"],"paper_pages":[{"arxiv_id":"2510.03853","page":"/paper/arxiv-2510-03853"},{"arxiv_id":"2312.02228","page":"/paper/pixellm-pixel-reasoning-with-large-multimodal"},{"arxiv_id":"2404.05673","page":"/paper/cores-orchestrating-the-dance-of-reasoning"},{"arxiv_id":"2412.04292","page":"/paper/sida-social-media-image-deepfake-detection"},{"arxiv_id":"2406.20076","page":"/paper/evf-sam-early-vision-language-fusion-for-text"}],"arg_sig_recorded":[["inputs",3,"float","float32"],["targets",3,"float","float32"]],"scalar_args":{"num_masks":"2.0","scale":"1000","eps":"1e-06"},"class_bearing":false},{"code_sha256_prefix":"b8878eaf16856897","path":"model/VISA.py","papers":["2407.11325"],"paper_pages":[{"arxiv_id":"2407.11325","page":"/paper/visa-reasoning-video-object-segmentation-via"}],"arg_sig_recorded":[["inputs",3,"float","float32"],["targets",3,"float","float32"]],"scalar_args":{"num_masks":"2.0","scale":"1000.0","eps":"1e-06"},"class_bearing":false}]}]},{"bucket":[[4,"float","float32"],[4,"float","float32"]],"n_implementations_compared":2,"n_papers":2,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"544a9ab196054145","size":1,"n_papers":1,"shape":[2,12],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.14528536796569824,0.3565927743911743,1.365173101425171,0.9804857969284058,1.0075560808181763,0.12925058603286743,-0.35837113857269287,0.5458997488021851,0.718760073184967,-0.16378283500671387,-0.29580116271972656,1.41287362575531,0.0782729983329773,-12.984763145446777,0.5731827020645142,0.6251980066299438,-0.052987098693847656,-0.05666983127593994,0.5540411472320557,0.3577420711517334,0.4570399522781372,-0.014366984367370605,0.014309942722320557,1.0278688669204712],"values_recorded":24,"members":[{"code_sha256_prefix":"d91fd9b31c41684e","path":"model/IVM.py","papers":["2405.19783"],"paper_pages":[{"arxiv_id":"2405.19783","page":"/paper/instruction-guided-visual-masking"}],"arg_sig_recorded":[["inputs",4,"float","float32"],["targets",4,"float","float32"]],"scalar_args":{"scale":"1000","eps":"1e-06"},"class_bearing":false}]},{"output_sha":"d101db9612256792","size":1,"n_papers":1,"shape":[],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.41871514916419983],"values_recorded":1,"members":[{"code_sha256_prefix":"b320489855b18380","path":"model/PIXAR.py","papers":["2603.20193"],"paper_pages":[{"arxiv_id":"2603.20193","page":"/paper/arxiv-2603-20193"}],"arg_sig_recorded":[["inputs",4,"float","float32"],["targets",4,"float","float32"]],"scalar_args":{"num_masks":"2.0","eps":"1e-06"},"class_bearing":false}]}]},{"bucket":[[4,"float","float32"],[4,"float","float32"],[4,"float","float32"]],"n_implementations_compared":1,"n_papers":1,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"3812d1aa87324ac2","size":1,"n_papers":1,"shape":[],"dtype":"float32","type":"Tensor","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[0.7340177297592163],"values_recorded":1,"members":[{"code_sha256_prefix":"ef327e5c61768306","path":"train_ic15.py","papers":["1806.02559"],"paper_pages":[{"arxiv_id":"1806.02559","page":"/paper/shape-robust-text-detection-with-progressive"}],"arg_sig_recorded":[["input",4,"float","float32"],["target",4,"float","float32"],["mask",4,"float","float32"]],"scalar_args":{},"class_bearing":false}]}]}]}