{"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/shift-tokens-right","entry":"shift_tokens_right","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":11,"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/shift-tokens-right","buckets":[{"bucket":[[2,"int","int64"]],"n_implementations_compared":9,"n_papers":11,"n_not_digested":0,"not_digested_by_type":{},"clusters":[{"output_sha":"0a8ea04e5471ea23","size":5,"n_papers":7,"shape":[4,8],"dtype":"int64","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":5,"torch_reference_conventions_with_this_digest":[],"values":[2.0,2.0,3.0,2.0,1.0,1.0,3.0,0.0,2.0,1.0,0.0,1.0,3.0,3.0,3.0,3.0,2.0,0.0,0.0,2.0,0.0,2.0,0.0,1.0,2.0,3.0,3.0,1.0,3.0,3.0,2.0,1.0],"values_recorded":32,"members":[{"code_sha256_prefix":"9dfcf8b13847c65f","path":"src/ssvp_slt/modeling/sign_bart.py","papers":["2402.09611","2506.15220"],"paper_pages":[{"arxiv_id":"2402.09611","page":"/paper/towards-privacy-aware-sign-language"},{"arxiv_id":"2506.15220","page":"/paper/video-salmonn-2-captioning-enhanced-audio"}],"arg_sig_recorded":[["input_ids",2,"int","int64"]],"scalar_args":{"pad_token_id":"0","decoder_start_token_id":"2"},"class_bearing":false},{"code_sha256_prefix":"cfb09657fff12fcf","path":"quant/modeling_bart_quant.py","papers":["2406.10507","2306.01841"],"paper_pages":[{"arxiv_id":"2406.10507","page":"/paper/benchmarking-children-s-asr-with-supervised"},{"arxiv_id":"2306.01841","page":"/paper/binary-and-ternary-natural-language"}],"arg_sig_recorded":[["input_ids",2,"int","int64"]],"scalar_args":{"pad_token_id":"0","decoder_start_token_id":"2"},"class_bearing":false},{"code_sha256_prefix":"59b0b785b926c986","path":"kat/modeling.py","papers":["2109.04096"],"paper_pages":[{"arxiv_id":"2109.04096","page":"/paper/a-three-stage-learning-framework-for-low"}],"arg_sig_recorded":[["input_ids",2,"int","int64"]],"scalar_args":{"pad_token_id":"0","decoder_start_token_id":"2"},"class_bearing":false},{"code_sha256_prefix":"5a0796818cb2aaa5","path":"retrieval_reranking/decorate_with_questions.py","papers":["2305.13117"],"paper_pages":[{"arxiv_id":"2305.13117","page":"/paper/averitec-a-dataset-for-real-world-claim-1"}],"arg_sig_recorded":[["input_ids",2,"int","int64"]],"scalar_args":{"pad_token_id":"1","decoder_start_token_id":"2"},"class_bearing":false},{"code_sha256_prefix":"a315b8fc32a18efe","path":"alexa_teacher_models/modeling_atm.py","papers":["2208.01448"],"paper_pages":[{"arxiv_id":"2208.01448","page":"/paper/alexatm-20b-few-shot-learning-using-a-large"}],"arg_sig_recorded":[["input_ids",2,"int","int64"]],"scalar_args":{"pad_token_id":"0","decoder_start_token_id":"2"},"class_bearing":false}]},{"output_sha":"c1a6ea06eb3001b9","size":3,"n_papers":3,"shape":[4,8],"dtype":"int64","type":"Tensor","finite":true,"max_difference_among_recorded_values":0.0,"members_with_recorded_values":3,"torch_reference_conventions_with_this_digest":[],"values":[0.0,2.0,3.0,2.0,1.0,1.0,3.0,0.0,3.0,1.0,0.0,1.0,3.0,3.0,3.0,3.0,0.0,0.0,0.0,2.0,0.0,2.0,0.0,1.0,2.0,3.0,3.0,1.0,3.0,3.0,2.0,1.0],"values_recorded":32,"members":[{"code_sha256_prefix":"7de42cc5069555cd","path":"modelling/translation.py","papers":["2203.04287"],"paper_pages":[{"arxiv_id":"2203.04287","page":"/paper/a-simple-multi-modality-transfer-learning"}],"arg_sig_recorded":[["input_ids",2,"int","int64"]],"scalar_args":{"pad_token_id":"0","ignore_index":"-100"},"class_bearing":false},{"code_sha256_prefix":"8f74136a6faca115","path":"code/run_story_generation_pipeline_rl.py","papers":["2205.01898"],"paper_pages":[{"arxiv_id":"2205.01898","page":"/paper/go-back-in-time-generating-flashbacks-in"}],"arg_sig_recorded":[["input_ids",2,"int","int64"]],"scalar_args":{"pad_token_id":"0"},"class_bearing":false},{"code_sha256_prefix":"e00ccf7847d12b59","path":"KGBART/KGBART_model/modeling_kgbart.py","papers":["2009.12677"],"paper_pages":[{"arxiv_id":"2009.12677","page":"/paper/kg-bart-knowledge-graph-augmented-bart-for"}],"arg_sig_recorded":[["input_ids",2,"int","int64"]],"scalar_args":{"pad_token_id":"0"},"class_bearing":false}]},{"output_sha":"6940e187b17c8ba7","size":1,"n_papers":1,"shape":[4,8],"dtype":"int64","type":"ndarray","finite":true,"max_difference_among_recorded_values":null,"members_with_recorded_values":1,"torch_reference_conventions_with_this_digest":[],"values":[1.0,2.0,3.0,2.0,1.0,1.0,3.0,0.0,1.0,1.0,0.0,1.0,3.0,3.0,3.0,3.0,1.0,0.0,0.0,2.0,0.0,2.0,0.0,1.0,1.0,3.0,3.0,1.0,3.0,3.0,2.0,1.0],"values_recorded":32,"members":[{"code_sha256_prefix":"74c3a00cdeeab013","path":"training/flax/run_distillation.py","papers":["2311.00430"],"paper_pages":[{"arxiv_id":"2311.00430","page":"/paper/distil-whisper-robust-knowledge-distillation"}],"arg_sig_recorded":[["label_ids",2,"int","int64"]],"scalar_args":{"decoder_start_token_id":"1"},"class_bearing":false}]}]}]}