{"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/exists","entry":"exists","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":5,"n_papers":103,"n_buckets":1,"n_distinct_outputs":1,"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":10,"n_papers":28,"recorded_shared_digest_equals_own_fixture_digest":10},"output_not_digested_non_numeric":{"n":0,"by_type":{}}},"withdrawn_excluded":0,"code_page":"/code/exists","buckets":[{"bucket":[[1,"int","int64"]],"n_implementations_compared":5,"n_papers":103,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"6c3c396ed6b5c36d","size":5,"n_papers":103,"shape":[],"dtype":"bool","type":"bool","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":5,"torch_reference_conventions_with_this_digest":[],"values":[1.0],"values_recorded":1,"members":[{"code_sha256_prefix":"aa5486a3650902d8","path":"models/visual_concept_tokenizor.py","papers":["2006.16236","2102.05095","2106.03843","2107.02192","2109.08668","2203.07852","2203.08913","2203.16487","2205.10093","2205.13760","2207.06881","2207.11240","2210.06184","2307.06440","2308.00951","2308.16692","2311.00566","2402.01831","2402.17532","2410.14195","1907.05242","1907.01470","1912.04958","1911.03437","2003.05997","1812.01243","1810.00825","2002.08264","1912.12180","2005.08100","2102.12627","2102.12092","2102.07074","2102.03902","2012.00926","2103.17239","2105.08050","2002.09402","2002.05202","2102.13419","2107.03312","2112.04426","2110.13711","2112.05682","2111.12417","2106.03106","2110.05208","2203.00555","2202.04053","2110.06848","2206.10789","2110.11048","2108.09084","2206.13947","2301.13338","2209.03143","2202.12015","2212.02623","2210.02399","2302.06675","2210.00939","2212.00794","2212.10554","2312.02696","2302.03540","2304.09116","2301.09595","2305.02765","2210.16484","2310.10638","2411.10438","2305.09636","2309.15505","2003.02436","2307.06304","2304.06819","2403.17834","2406.02176","2410.01756","2402.02003","2411.15537","2309.02612","2607.06590","2602.02232"],"paper_pages":[{"arxiv_id":"2006.16236","page":"/paper/transformers-are-rnns-fast-autoregressive"},{"arxiv_id":"2102.05095","page":"/paper/is-space-time-attention-all-you-need-for"},{"arxiv_id":"2106.03843","page":"/paper/equivariant-graph-neural-networks-for-3d"},{"arxiv_id":"2107.02192","page":"/paper/long-short-transformer-efficient-transformers"},{"arxiv_id":"2109.08668","page":"/paper/primer-searching-for-efficient-transformers"},{"arxiv_id":"2203.07852","page":"/paper/block-recurrent-transformers"},{"arxiv_id":"2203.08913","page":"/paper/memorizing-transformers-1"},{"arxiv_id":"2203.16487","page":"/paper/lossless-speedup-of-autoregressive"},{"arxiv_id":"2205.10093","page":"/paper/visual-concepts-tokenization"},{"arxiv_id":"2205.13760","page":"/paper/tranception-protein-fitness-prediction-with"},{"arxiv_id":"2207.06881","page":"/paper/recurrent-memory-transformer"},{"arxiv_id":"2207.11240","page":"/paper/discrete-key-value-bottleneck"},{"arxiv_id":"2210.06184","page":"/paper/images-as-weight-matrices-sequential-image"},{"arxiv_id":"2307.06440","page":"/paper/no-train-no-gain-revisiting-efficient"},{"arxiv_id":"2308.00951","page":"/paper/from-sparse-to-soft-mixtures-of-experts"},{"arxiv_id":"2308.16692","page":"/paper/speechtokenizer-unified-speech-tokenizer-for"},{"arxiv_id":"2311.00566","page":"/paper/croma-remote-sensing-representations-with-1"},{"arxiv_id":"2402.01831","page":"/paper/audio-flamingo-a-novel-audio-language-model"},{"arxiv_id":"2402.17532","page":"/paper/retrieval-is-accurate-generation"},{"arxiv_id":"2410.14195","page":"/paper/rethinking-transformer-for-long-contextual"},{"arxiv_id":"1907.05242","page":"/paper/large-memory-layers-with-product-keys"},{"arxiv_id":"1907.01470","page":"/paper/augmenting-self-attention-with-persistent"},{"arxiv_id":"1912.04958","page":"/paper/analyzing-and-improving-the-image-quality-of"},{"arxiv_id":"1911.03437","page":"/paper/smart-robust-and-efficient-fine-tuning-for"},{"arxiv_id":"2003.05997","page":"/paper/efficient-content-based-sparse-attention-with-1"},{"arxiv_id":"1812.01243","page":"/paper/factorized-attention-self-attention-with"},{"arxiv_id":"1810.00825","page":"/paper/set-transformer-a-framework-for-attention"},{"arxiv_id":"2002.08264","page":"/paper/molecule-attention-transformer"},{"arxiv_id":"1912.12180","page":"/paper/axial-attention-in-multidimensional-1"},{"arxiv_id":"2005.08100","page":"/paper/conformer-convolution-augmented-transformer"},{"arxiv_id":"2102.12627","page":"/paper/how-to-represent-part-whole-hierarchies-in-a"},{"arxiv_id":"2102.12092","page":"/paper/zero-shot-text-to-image-generation"},{"arxiv_id":"2102.07074","page":"/paper/transgan-two-transformers-can-make-one-strong"},{"arxiv_id":"2102.03902","page":"/paper/nystromformer-a-nystrom-based-algorithm-for"},{"arxiv_id":"2012.00926","page":"/paper/pi-gan-periodic-implicit-generative"},{"arxiv_id":"2103.17239","page":"/paper/going-deeper-with-image-transformers"},{"arxiv_id":"2105.08050","page":"/paper/pay-attention-to-mlps"},{"arxiv_id":"2002.09402","page":"/paper/accessing-higher-level-representations-in"},{"arxiv_id":"2002.05202","page":"/paper/glu-variants-improve-transformer"},{"arxiv_id":"2102.13419","page":"/paper/iterative-se-3-transformers"},{"arxiv_id":"2107.03312","page":"/paper/soundstream-an-end-to-end-neural-audio-codec"},{"arxiv_id":"2112.04426","page":"/paper/improving-language-models-by-retrieving-from"},{"arxiv_id":"2110.13711","page":"/paper/hierarchical-transformers-are-more-efficient"},{"arxiv_id":"2112.05682","page":"/paper/self-attention-does-not-need-o-n-2-memory"},{"arxiv_id":"2111.12417","page":"/paper/nuwa-visual-synthesis-pre-training-for-neural"},{"arxiv_id":"2106.03106","page":"/paper/uformer-a-general-u-shaped-transformer-for"},{"arxiv_id":"2110.05208","page":"/paper/supervision-exists-everywhere-a-data-1"},{"arxiv_id":"2203.00555","page":"/paper/deepnet-scaling-transformers-to-1000-layers"},{"arxiv_id":"2202.04053","page":"/paper/dall-eval-probing-the-reasoning-skills-and"},{"arxiv_id":"2110.06848","page":"/paper/decoupled-contrastive-learning-1"},{"arxiv_id":"2206.10789","page":"/paper/scaling-autoregressive-models-for-content"},{"arxiv_id":"2110.11048","page":"/paper/mixer-based-lidar-lane-detection-network-and"},{"arxiv_id":"2108.09084","page":"/paper/fastformer-additive-attention-is-all-you-need"},{"arxiv_id":"2206.13947","page":"/paper/long-range-language-modeling-via-gated-state"},{"arxiv_id":"2301.13338","page":"/paper/continuous-spatiotemporal-transformers"},{"arxiv_id":"2209.03143","page":"/paper/audiolm-a-language-modeling-approach-to-audio"},{"arxiv_id":"2202.12015","page":"/paper/learning-to-merge-tokens-in-vision"},{"arxiv_id":"2212.02623","page":"/paper/unifying-vision-text-and-layout-for-universal"},{"arxiv_id":"2210.02399","page":"/paper/phenaki-variable-length-video-generation-from"},{"arxiv_id":"2302.06675","page":"/paper/symbolic-discovery-of-optimization-algorithms-1"},{"arxiv_id":"2210.00939","page":"/paper/improving-sample-quality-of-diffusion-model"},{"arxiv_id":"2212.00794","page":"/paper/scaling-language-image-pre-training-via"},{"arxiv_id":"2212.10554","page":"/paper/a-length-extrapolatable-transformer"},{"arxiv_id":"2312.02696","page":"/paper/analyzing-and-improving-the-training-dynamics"},{"arxiv_id":"2302.03540","page":"/paper/speak-read-and-prompt-high-fidelity-text-to"},{"arxiv_id":"2304.09116","page":"/paper/naturalspeech-2-latent-diffusion-models-are"},{"arxiv_id":"2301.09595","page":"/paper/zorro-the-masked-multimodal-transformer"},{"arxiv_id":"2305.02765","page":"/paper/hifi-codec-group-residual-vector-quantization"},{"arxiv_id":"2210.16484","page":"/paper/a-systematic-survey-of-molecular-pre-trained"},{"arxiv_id":"2310.10638","page":"/paper/in-context-pretraining-language-modeling"},{"arxiv_id":"2411.10438","page":"/paper/mars-unleashing-the-power-of-variance"},{"arxiv_id":"2305.09636","page":"/paper/soundstorm-efficient-parallel-audio"},{"arxiv_id":"2309.15505","page":"/paper/finite-scalar-quantization-vq-vae-made-simple"},{"arxiv_id":"2003.02436","page":"/paper/talking-heads-attention"},{"arxiv_id":"2307.06304","page":"/paper/patch-n-pack-navit-a-vision-transformer-for"},{"arxiv_id":"2304.06819","page":"/paper/modeling-dense-multimodal-interactions"},{"arxiv_id":"2403.17834","page":"/paper/a-foundation-model-utilizing-chest-ct-volumes"},{"arxiv_id":"2406.02176","page":"/paper/aroma-preserving-spatial-structure-for-latent"},{"arxiv_id":"2410.01756","page":"/paper/imagefolder-autoregressive-image-generation"},{"arxiv_id":"2402.02003","page":"/paper/genface-a-large-scale-fine-grained-face"},{"arxiv_id":"2411.15537","page":"/paper/munba-machine-unlearning-via-nash-bargaining"},{"arxiv_id":"2309.02612","page":"/paper/music-source-separation-with-band-split-rope"},{"arxiv_id":"2607.06590","page":"/paper/arxiv-2607-06590"},{"arxiv_id":"2602.02232","page":"/paper/arxiv-2602-02232"}],"arg_sig_recorded":[["val",1,"int","int64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"608e364a9d2376a3","path":"bit_diffusion/bit_diffusion.py","papers":["2208.04202","2211.12444","2306.16819","2505.12500","2510.00303","1711.11585","2006.11239","2006.15020","2208.09392","2301.10972","2301.00704","2303.08385","2402.02906","2410.09614","2601.19040"],"paper_pages":[{"arxiv_id":"2208.04202","page":"/paper/analog-bits-generating-discrete-data-using"},{"arxiv_id":"2211.12444","page":"/paper/can-denoising-diffusion-probabilistic-models"},{"arxiv_id":"2306.16819","page":"/paper/graph-denoising-diffusion-for-inverse-protein"},{"arxiv_id":"2505.12500","page":"/paper/marge-improving-math-reasoning-for-llms-with"},{"arxiv_id":"2510.00303","page":"/paper/arxiv-2510-00303"},{"arxiv_id":"1711.11585","page":"/paper/high-resolution-image-synthesis-and-semantic"},{"arxiv_id":"2006.11239","page":"/paper/denoising-diffusion-probabilistic-models"},{"arxiv_id":"2006.15020","page":"/paper/pre-training-via-paraphrasing"},{"arxiv_id":"2208.09392","page":"/paper/cold-diffusion-inverting-arbitrary-image-1"},{"arxiv_id":"2301.10972","page":"/paper/on-the-importance-of-noise-scheduling-for"},{"arxiv_id":"2301.00704","page":"/paper/muse-text-to-image-generation-via-masked"},{"arxiv_id":"2303.08385","page":"/paper/generating-symbolic-music-using-diffusion"},{"arxiv_id":"2402.02906","page":"/paper/viewfusion-learning-composable-diffusion"},{"arxiv_id":"2410.09614","page":"/paper/exploring-behavior-relevant-and-disentangled"},{"arxiv_id":"2601.19040","page":"/paper/arxiv-2601-19040"}],"arg_sig_recorded":[["x",1,"int","int64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"ac11ce61716f1826","path":"src/byprot/models/dplm2/dplm2.py","papers":["2504.11454","2302.01649","2410.13782"],"paper_pages":[{"arxiv_id":"2504.11454","page":"/paper/elucidating-the-design-space-of-multimodal"},{"arxiv_id":"2302.01649","page":"/paper/structure-informed-language-models-are"},{"arxiv_id":"2410.13782","page":"/paper/dplm-2-a-multimodal-diffusion-protein"}],"arg_sig_recorded":[["obj",1,"int","int64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"4949e222e2fb23e1","path":"DSTPP/DiffusionModel.py","papers":["2606.01273"],"paper_pages":[{"arxiv_id":"2606.01273","page":"/paper/arxiv-2606-01273"}],"arg_sig_recorded":[["x",1,"int","int64"]],"scalar_args":{},"class_bearing":false},{"code_sha256_prefix":"689b78ad9d312313","path":"pretrain_croma.py","papers":["2311.00566"],"paper_pages":[{"arxiv_id":"2311.00566","page":"/paper/croma-remote-sensing-representations-with-1"}],"arg_sig_recorded":[["val",1,"int","int64"]],"scalar_args":{},"class_bearing":false}]}]}]}