{"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":"/code/get-dataset-itr","entry":"get_dataset_itr","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":6,"n_papers_ran":6,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":3,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":0},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2404.08368","paper":"/paper/asr-advancements-for-indigenous-languages","title":"Automatic Speech Recognition Advancements for Indigenous Languages of the Americas","date":"2024-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"monirome/asr-indigenous-languages","path":"docker/infer.py","file_url":"https://github.com/monirome/asr-indigenous-languages/blob/HEAD/docker/infer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"732cb84e2f814ba6","mcp_get_code":{"code_sha256":"732cb84e2f814ba6"}},{"arxiv_id":"2310.02382","paper":"/paper/unsupervised-speech-recognition-with-n","title":"Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lwang114/graphunsupasr","path":"w2vu_generate.py","file_url":"https://github.com/lwang114/graphunsupasr/blob/HEAD/w2vu_generate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1a82e55d7de6917c","mcp_get_code":{"code_sha256":"1a82e55d7de6917c"}},{"arxiv_id":"2203.16965","paper":"/paper/pada-pruning-assisted-domain-adaptation-for","title":"PADA: Pruning Assisted Domain Adaptation for Self-Supervised Speech Representations","date":"2022-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"732cb84e2f814ba6","mcp_get_code":{"code_sha256":"732cb84e2f814ba6"}},{"arxiv_id":"2101.07597","paper":"/paper/unispeech-unified-speech-representation","title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","date":"2021-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"732cb84e2f814ba6","mcp_get_code":{"code_sha256":"732cb84e2f814ba6"}},{"arxiv_id":"2006.11477","paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","date":"2020-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mailong25/self-supervised-speech-recognition","path":"stt.py","file_url":"https://github.com/mailong25/self-supervised-speech-recognition/blob/HEAD/stt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"732cb84e2f814ba6","mcp_get_code":{"code_sha256":"732cb84e2f814ba6"}},{"arxiv_id":"1508.01211","paper":"/paper/listen-attend-and-spell","title":"Listen, Attend and Spell","date":"2015-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sooftware/Fairseq-Listen-Attend-Spell","path":"fairseq_las/infer.py","file_url":"https://github.com/sooftware/Fairseq-Listen-Attend-Spell/blob/HEAD/fairseq_las/infer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b409833fb8f8509","mcp_get_code":{"code_sha256":"3b409833fb8f8509"}}]}