{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/speech-recognition-on-librispeech-test-other","task":{"name":"Speech Recognition","url":"/task/speech-recognition","note":null},"dataset":{"name":"LibriSpeech test-other","url":"/dataset/librispeech"},"category":"Audio","categories":["Audio","Speech"],"category_note":null,"description":"**Speech Recognition** is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [SpecAugment](https://arxiv.org/pdf/1904.08779v2.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Word Error Rate (WER)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Word Error Rate (WER)":"lower"}},"counts":{"rows":53,"rows_with_code":44,"rows_with_paper_page":52,"rows_dated":52,"rows_using_additional_data":17},"rows":[{"rank_in_archive_order":1,"model":"SAMBA ASR","metrics":{"Word Error Rate (WER)":"2.48"},"uses_additional_data":false,"paper_date":"2025-01-06","paper":"/paper/samba-asr-state-of-the-art-speech-recognition","paper_url":"https://arxiv.org/abs/2501.02832v3","paper_title":"Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"FAdam","metrics":{"Word Error Rate (WER)":"2.49"},"uses_additional_data":false,"paper_date":"2024-05-21","paper":"/paper/fadam-adam-is-a-natural-gradient-optimizer","paper_url":"https://arxiv.org/abs/2405.12807v10","paper_title":"FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information","code":"https://github.com/lessw2020/fadam_pytorch","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"w2v-BERT XXL","metrics":{"Word Error Rate (WER)":"2.5"},"uses_additional_data":false,"paper_date":"2021-08-07","paper":"/paper/w2v-bert-combining-contrastive-learning-and","paper_url":"https://arxiv.org/abs/2108.06209v2","paper_title":"W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training","code":"https://github.com/facebookresearch/fairseq/tree/ust/examples/w2vbert","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"Conformer + Wav2vec 2.0 + SpecAugment-based Noisy Student Training with Libri-Light","metrics":{"Word Error Rate (WER)":"2.6"},"uses_additional_data":false,"paper_date":"2020-10-20","paper":"/paper/pushing-the-limits-of-semi-supervised","paper_url":"https://arxiv.org/abs/2010.10504v2","paper_title":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition","code":"https://github.com/tuanio/noisy-student-training-asr","n_code_links":1,"official":null,"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/pushing-the-limits-of-semi-supervised#ran","syntology_url":"https://syntology.ai/paper/2010.10504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10504"}}}},{"rank_in_archive_order":5,"model":"HuBERT with Libri-Light","metrics":{"Word Error Rate (WER)":"2.9"},"uses_additional_data":false,"paper_date":"2021-06-14","paper":"/paper/hubert-self-supervised-speech-representation","paper_url":"https://arxiv.org/abs/2106.07447v1","paper_title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","code":"https://github.com/huggingface/transformers","n_code_links":11,"official":{"repos":["pytorch/fairseq","huggingface/transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":0,"sample_list":"/paper/hubert-self-supervised-speech-representation#ran","syntology_url":"https://syntology.ai/paper/2106.07447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07447"}}}},{"rank_in_archive_order":6,"model":"wav2vec 2.0 with Libri-Light","metrics":{"Word Error Rate (WER)":"3.0"},"uses_additional_data":false,"paper_date":"2020-06-20","paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","paper_url":"https://arxiv.org/abs/2006.11477v3","paper_title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","code":"https://github.com/huggingface/transformers","n_code_links":25,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":2,"sample_list":"/paper/wav2vec-2-0-a-framework-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2006.11477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11477"}}}},{"rank_in_archive_order":7,"model":"Conv + Transformer + wav2vec2.0 + pseudo labeling","metrics":{"Word Error Rate (WER)":"3.1"},"uses_additional_data":false,"paper_date":"2020-10-22","paper":"/paper/self-training-and-pre-training-are","paper_url":"https://arxiv.org/abs/2010.11430v1","paper_title":"Self-training and Pre-training are Complementary for Speech Recognition","code":"https://github.com/facebookresearch/fairseq","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"WavLM Large","metrics":{"Word Error Rate (WER)":"3.2"},"uses_additional_data":false,"paper_date":"2021-10-26","paper":"/paper/wavlm-large-scale-self-supervised-pre","paper_url":"https://arxiv.org/abs/2110.13900v5","paper_title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","code":"https://github.com/microsoft/unilm","n_code_links":9,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"SpeechStew (1B)","metrics":{"Word Error Rate (WER)":"3.3"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/speechstew-simply-mix-all-available-speech","paper_url":"https://arxiv.org/abs/2104.02133v3","paper_title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":10,"model":"ContextNet + SpecAugment-based Noisy Student Training with Libri-Light","metrics":{"Word Error Rate (WER)":"3.4"},"uses_additional_data":false,"paper_date":"2020-05-19","paper":"/paper/improved-noisy-student-training-for-automatic","paper_url":"https://arxiv.org/abs/2005.09629v2","paper_title":"Improved Noisy Student Training for Automatic Speech Recognition","code":"https://github.com/upskyy/ContextNet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":11,"model":"E-Branchformer (L) + Internal Language Model Estimation","metrics":{"Word Error Rate (WER)":"3.65"},"uses_additional_data":false,"paper_date":"2022-09-30","paper":"/paper/e-branchformer-branchformer-with-enhanced","paper_url":"https://arxiv.org/abs/2210.00077v2","paper_title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","code":"https://github.com/espnet/espnet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"data2vec","metrics":{"Word Error Rate (WER)":"3.7"},"uses_additional_data":false,"paper_date":"2022-02-07","paper":"/paper/data2vec-a-general-framework-for-self-1","paper_url":"https://arxiv.org/abs/2202.03555v3","paper_title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","code":"https://github.com/huggingface/transformers/tree/main/src/transformers/models/data2vec","n_code_links":12,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":0,"sample_list":"/paper/data2vec-a-general-framework-for-self-1#ran","syntology_url":"https://syntology.ai/paper/2202.03555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03555"}}}},{"rank_in_archive_order":13,"model":"Conv + Transformer AM + Iterative Pseudo-Labeling (n-gram LM + Transformer Rescoring)","metrics":{"Word Error Rate (WER)":"3.83"},"uses_additional_data":false,"paper_date":"2020-05-19","paper":"/paper/iterative-pseudo-labeling-for-speech","paper_url":"https://arxiv.org/abs/2005.09267v2","paper_title":"Iterative Pseudo-Labeling for Speech Recognition","code":"https://github.com/facebookresearch/wav2letter/tree/master/recipes/ipl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"Conformer(L)","metrics":{"Word Error Rate (WER)":"3.9"},"uses_additional_data":true,"paper_date":"2020-05-16","paper":"/paper/conformer-convolution-augmented-transformer","paper_url":"https://arxiv.org/abs/2005.08100v1","paper_title":"Conformer: Convolution-augmented Transformer for Speech Recognition","code":"https://github.com/PaddlePaddle/PaddleSpeech","n_code_links":25,"official":null,"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":2,"sample_list":"/paper/conformer-convolution-augmented-transformer#ran","syntology_url":"https://syntology.ai/paper/2005.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08100"}}}},{"rank_in_archive_order":15,"model":"Zipformer+pruned transducer w/ CR-CTC\n(no external language model)","metrics":{"Word Error Rate (WER)":"3.95"},"uses_additional_data":false,"paper_date":"2024-10-07","paper":"/paper/cr-ctc-consistency-regularization-on-ctc-for","paper_url":"https://arxiv.org/abs/2410.05101v4","paper_title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","code":"https://github.com/k2-fsa/icefall","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"SpeechStew (100M)","metrics":{"Word Error Rate (WER)":"4.0"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/speechstew-simply-mix-all-available-speech","paper_url":"https://arxiv.org/abs/2104.02133v3","paper_title":"SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"wav2vec 2.0","metrics":{"Word Error Rate (WER)":"4.1"},"uses_additional_data":true,"paper_date":"2020-06-20","paper":"/paper/wav2vec-2-0-a-framework-for-self-supervised","paper_url":"https://arxiv.org/abs/2006.11477v3","paper_title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","code":"https://github.com/huggingface/transformers","n_code_links":25,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":2,"sample_list":"/paper/wav2vec-2-0-a-framework-for-self-supervised#ran","syntology_url":"https://syntology.ai/paper/2006.11477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11477"}}}},{"rank_in_archive_order":18,"model":"ContextNet(L)","metrics":{"Word Error Rate (WER)":"4.1"},"uses_additional_data":false,"paper_date":"2020-05-07","paper":"/paper/contextnet-improving-convolutional-neural","paper_url":"https://arxiv.org/abs/2005.03191v3","paper_title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","code":"https://github.com/TensorSpeech/TensorFlowASR","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"Conv + Transformer AM (ConvLM with Transformer Rescoring)","metrics":{"Word Error Rate (WER)":"4.11"},"uses_additional_data":true,"paper_date":"2019-11-19","paper":"/paper/end-to-end-asr-from-supervised-to-semi","paper_url":"https://arxiv.org/abs/1911.08460v3","paper_title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","code":"https://github.com/facebookresearch/wav2letter/tree/master/recipes/models/sota/2019","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"CTC + Transformer LM rescoring","metrics":{"Word Error Rate (WER)":"4.20"},"uses_additional_data":true,"paper_date":"2020-05-19","paper":"/paper/fast-simpler-and-more-accurate-hybrid-asr","paper_url":"https://arxiv.org/abs/2005.09150v2","paper_title":"Faster, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"Transformer Transducer","metrics":{"Word Error Rate (WER)":"4.20"},"uses_additional_data":true,"paper_date":"2020-11-05","paper":"/paper/improving-rnn-transducer-based-asr-with","paper_url":"https://arxiv.org/abs/2011.03109v2","paper_title":"Improving RNN Transducer Based ASR with Auxiliary Tasks","code":"https://github.com/upskyy/Transformer-Transducer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"Qwen-Audio","metrics":{"Word Error Rate (WER)":"4.2"},"uses_additional_data":false,"paper_date":"2023-11-14","paper":"/paper/qwen-audio-advancing-universal-audio","paper_url":"https://arxiv.org/abs/2311.07919v2","paper_title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","code":"https://github.com/alibaba-damo-academy/FunASR","n_code_links":2,"official":{"repos":["qwenlm/qwen-audio"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":7,"sample_list":"/paper/qwen-audio-advancing-universal-audio#ran","syntology_url":"https://syntology.ai/paper/2311.07919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.07919"}}}},{"rank_in_archive_order":23,"model":"Conformer(M)","metrics":{"Word Error Rate (WER)":"4.3"},"uses_additional_data":true,"paper_date":"2020-05-16","paper":"/paper/conformer-convolution-augmented-transformer","paper_url":"https://arxiv.org/abs/2005.08100v1","paper_title":"Conformer: Convolution-augmented Transformer for Speech Recognition","code":"https://github.com/PaddlePaddle/PaddleSpeech","n_code_links":25,"official":null,"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":2,"sample_list":"/paper/conformer-convolution-augmented-transformer#ran","syntology_url":"https://syntology.ai/paper/2005.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08100"}}}},{"rank_in_archive_order":24,"model":"Zipformer+CR-CTC\n(no external language model)","metrics":{"Word Error Rate (WER)":"4.35"},"uses_additional_data":false,"paper_date":"2024-10-07","paper":"/paper/cr-ctc-consistency-regularization-on-ctc-for","paper_url":"https://arxiv.org/abs/2410.05101v4","paper_title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","code":"https://github.com/k2-fsa/icefall","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":25,"model":"Zipformer+pruned transducer\n(no external language model)","metrics":{"Word Error Rate (WER)":"4.38"},"uses_additional_data":false,"paper_date":"2023-10-17","paper":"/paper/zipformer-a-faster-and-better-encoder-for","paper_url":"https://arxiv.org/abs/2310.11230v4","paper_title":"Zipformer: A faster and better encoder for automatic speech recognition","code":"https://github.com/k2-fsa/icefall","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"Multistream CNN with Self-Attentive SRU","metrics":{"Word Error Rate (WER)":"4.46"},"uses_additional_data":false,"paper_date":"2020-05-21","paper":"/paper/asapp-asr-multistream-cnn-and-self-attentive","paper_url":"https://arxiv.org/abs/2005.10469v1","paper_title":"ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"ContextNet(M)","metrics":{"Word Error Rate (WER)":"4.5"},"uses_additional_data":true,"paper_date":"2020-05-07","paper":"/paper/contextnet-improving-convolutional-neural","paper_url":"https://arxiv.org/abs/2005.03191v3","paper_title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","code":"https://github.com/TensorSpeech/TensorFlowASR","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"hybrid + Transformer LM rescoring","metrics":{"Word Error Rate (WER)":"4.85"},"uses_additional_data":true,"paper_date":"2019-10-22","paper":"/paper/transformer-based-acoustic-modeling-for","paper_url":"https://arxiv.org/abs/1910.09799v2","paper_title":"Transformer-based Acoustic Modeling for Hybrid Speech Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"Branchformer + GFSA","metrics":{"Word Error Rate (WER)":"4.94"},"uses_additional_data":false,"paper_date":"2023-12-07","paper":"/paper/graph-convolutions-enrich-the-self-attention","paper_url":"https://arxiv.org/abs/2312.04234v5","paper_title":"Graph Convolutions Enrich the Self-Attention in Transformers!","code":"https://github.com/jeongwhanchoi/gfsa","n_code_links":1,"official":{"repos":["jeongwhanchoi/gfsa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":22,"n_constructed":0,"n_ran_checked":11,"n_instrument":11,"n_unverified":7,"n_samples":29,"n_pointer_only_licence":10,"sample_list":"/paper/graph-convolutions-enrich-the-self-attention#ran","syntology_url":"https://syntology.ai/paper/2312.04234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04234"}}}},{"rank_in_archive_order":30,"model":"Hybrid model with Transformer rescoring","metrics":{"Word Error Rate (WER)":"5.0"},"uses_additional_data":false,"paper_date":"2019-05-08","paper":"/paper/rwth-asr-systems-for-librispeech-hybrid-vs","paper_url":"https://arxiv.org/abs/1905.03072v3","paper_title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","code":"https://github.com/rwth-i6/returnn","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"Conformer(S)","metrics":{"Word Error Rate (WER)":"5.0"},"uses_additional_data":true,"paper_date":"2020-05-16","paper":"/paper/conformer-convolution-augmented-transformer","paper_url":"https://arxiv.org/abs/2005.08100v1","paper_title":"Conformer: Convolution-augmented Transformer for Speech Recognition","code":"https://github.com/PaddlePaddle/PaddleSpeech","n_code_links":25,"official":null,"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_samples":7,"n_pointer_only_licence":2,"sample_list":"/paper/conformer-convolution-augmented-transformer#ran","syntology_url":"https://syntology.ai/paper/2005.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.08100"}}}},{"rank_in_archive_order":32,"model":"Conv + Transformer AM (ConvLM  with Transformer Rescoring) (LS only)","metrics":{"Word Error Rate (WER)":"5.18"},"uses_additional_data":false,"paper_date":"2019-11-19","paper":"/paper/end-to-end-asr-from-supervised-to-semi","paper_url":"https://arxiv.org/abs/1911.08460v3","paper_title":"End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures","code":"https://github.com/facebookresearch/wav2letter/tree/master/recipes/models/sota/2019","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"ContextNet(S)","metrics":{"Word Error Rate (WER)":"5.5"},"uses_additional_data":true,"paper_date":"2020-05-07","paper":"/paper/contextnet-improving-convolutional-neural","paper_url":"https://arxiv.org/abs/2005.03191v3","paper_title":"ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context","code":"https://github.com/TensorSpeech/TensorFlowASR","n_code_links":6,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"LSTM Transducer","metrics":{"Word Error Rate (WER)":"5.6"},"uses_additional_data":true,"paper_date":"2021-04-07","paper":"/paper/librispeech-transducer-model-with-internal","paper_url":"https://arxiv.org/abs/2104.03006v2","paper_title":"Librispeech Transducer Model with Internal Language Model Prior Correction","code":"https://github.com/rwth-i6/returnn","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"Transformer","metrics":{"Word Error Rate (WER)":"5.7"},"uses_additional_data":true,"paper_date":"2019-09-13","paper":"/paper/a-comparative-study-on-transformer-vs-rnn-in","paper_url":"https://arxiv.org/abs/1909.06317v2","paper_title":"A Comparative Study on Transformer vs RNN in Speech Applications","code":"https://github.com/espnet/espnet","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"LAS + SpecAugment","metrics":{"Word Error Rate (WER)":"5.8"},"uses_additional_data":true,"paper_date":"2019-04-18","paper":"/paper/specaugment-a-simple-data-augmentation-method","paper_url":"https://arxiv.org/abs/1904.08779v3","paper_title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","code":"https://github.com/mozilla/DeepSpeech","n_code_links":30,"official":null,"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":0,"sample_list":"/paper/specaugment-a-simple-data-augmentation-method#ran","syntology_url":"https://syntology.ai/paper/1904.08779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08779"}}}},{"rank_in_archive_order":37,"model":"Multi-Stream Self-Attention With Dilated 1D Convolutions","metrics":{"Word Error Rate (WER)":"5.80"},"uses_additional_data":false,"paper_date":"2019-10-01","paper":"/paper/state-of-the-art-speech-recognition-using","paper_url":"https://arxiv.org/abs/1910.00716v1","paper_title":"State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D Convolutions","code":"https://github.com/s-omranpour/Pytorch-Speech-Recognition","n_code_links":1,"official":null,"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/state-of-the-art-speech-recognition-using#ran","syntology_url":"https://syntology.ai/paper/1910.00716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00716"}}}},{"rank_in_archive_order":38,"model":"Squeezeformer (L)","metrics":{"Word Error Rate (WER)":"5.97"},"uses_additional_data":false,"paper_date":"2022-06-02","paper":"/paper/squeezeformer-an-efficient-transformer-for","paper_url":"https://arxiv.org/abs/2206.00888v2","paper_title":"Squeezeformer: An Efficient Transformer for Automatic Speech Recognition","code":"https://github.com/NVIDIA/NeMo/tree/main/examples/asr/conf/squeezeformer","n_code_links":4,"official":{"repos":["kssteven418/squeezeformer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":31,"n_constructed":12,"n_ran_checked":28,"n_instrument":3,"n_unverified":18,"n_samples":49,"n_pointer_only_licence":0,"sample_list":"/paper/squeezeformer-an-efficient-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2206.00888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00888"}}}},{"rank_in_archive_order":39,"model":"LAS (no LM)","metrics":{"Word Error Rate (WER)":"6.5"},"uses_additional_data":true,"paper_date":"2019-04-18","paper":"/paper/specaugment-a-simple-data-augmentation-method","paper_url":"https://arxiv.org/abs/1904.08779v3","paper_title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","code":"https://github.com/mozilla/DeepSpeech","n_code_links":30,"official":null,"syntology":{"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":4,"n_samples":18,"n_pointer_only_licence":0,"sample_list":"/paper/specaugment-a-simple-data-augmentation-method#ran","syntology_url":"https://syntology.ai/paper/1904.08779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.08779"}}}},{"rank_in_archive_order":40,"model":"Conformer with Relaxed Attention","metrics":{"Word Error Rate (WER)":"6.85"},"uses_additional_data":false,"paper_date":"2021-07-02","paper":"/paper/relaxed-attention-a-simple-method-to-boost","paper_url":"https://arxiv.org/abs/2107.01275v2","paper_title":"Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech Recognition","code":"https://github.com/freewym/espresso","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"QuartzNet15x5","metrics":{"Word Error Rate (WER)":"7.25"},"uses_additional_data":false,"paper_date":"2019-10-22","paper":"/paper/quartznet-deep-automatic-speech-recognition","paper_url":"https://arxiv.org/abs/1910.10261v1","paper_title":"QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions","code":"https://github.com/NVIDIA/NeMo","n_code_links":15,"official":{"repos":["NVIDIA/NeMo"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":2,"sample_list":"/paper/quartznet-deep-automatic-speech-recognition#ran","syntology_url":"https://syntology.ai/paper/1910.10261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.10261"}}}},{"rank_in_archive_order":42,"model":"tdnn + chain + rnnlm rescoring","metrics":{"Word Error Rate (WER)":"7.63"},"uses_additional_data":true,"paper_date":"2018-04-15","paper":"/paper/neural-network-language-modeling-with-letter","paper_url":"https://www.cs.jhu.edu/~hxu/neural-network-language.pdf","paper_title":"Neural Network Language Modeling with Letter-based Features and Importance Sampling","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"Jasper DR 10x5 (+ Time/Freq Masks)","metrics":{"Word Error Rate (WER)":"7.84"},"uses_additional_data":false,"paper_date":"2019-04-05","paper":"/paper/jasper-an-end-to-end-convolutional-neural","paper_url":"https://arxiv.org/abs/1904.03288v3","paper_title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","code":"https://github.com/osmr/imgclsmob","n_code_links":10,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"Espresso","metrics":{"Word Error Rate (WER)":"8.7"},"uses_additional_data":false,"paper_date":"2019-09-18","paper":"/paper/espresso-a-fast-end-to-end-neural-speech","paper_url":"https://arxiv.org/abs/1909.08723v3","paper_title":"Espresso: A Fast End-to-end Neural Speech Recognition Toolkit","code":"https://github.com/freewym/espresso","n_code_links":1,"official":{"repos":["freewym/espresso"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1,"sample_list":"/paper/espresso-a-fast-end-to-end-neural-speech#ran","syntology_url":"https://syntology.ai/paper/1909.08723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08723"}}}},{"rank_in_archive_order":45,"model":"Jasper DR 10x5","metrics":{"Word Error Rate (WER)":"8.79"},"uses_additional_data":false,"paper_date":"2019-04-05","paper":"/paper/jasper-an-end-to-end-convolutional-neural","paper_url":"https://arxiv.org/abs/1904.03288v3","paper_title":"Jasper: An End-to-End Convolutional Neural Acoustic Model","code":"https://github.com/osmr/imgclsmob","n_code_links":10,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"MT4SSL","metrics":{"Word Error Rate (WER)":"9.6"},"uses_additional_data":false,"paper_date":"2022-11-14","paper":"/paper/mt4ssl-boosting-self-supervised-speech","paper_url":"https://arxiv.org/abs/2211.07321v3","paper_title":"MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets","code":"https://github.com/ddlbojack/mt4ssl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"Convolutional Speech Recognition","metrics":{"Word Error Rate (WER)":"10.47"},"uses_additional_data":true,"paper_date":"2018-12-17","paper":"/paper/fully-convolutional-speech-recognition","paper_url":"http://arxiv.org/abs/1812.06864v2","paper_title":"Fully Convolutional Speech Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"CTC-CRF 4gram-LM","metrics":{"Word Error Rate (WER)":"10.65"},"uses_additional_data":false,"paper_date":"2019-04-16","paper":"/paper/crf-based-single-stage-acoustic-modeling-with","paper_url":"https://ieeexplore.ieee.org/document/8682256","paper_title":"CRF-based Single-stage Acoustic Modeling with CTC Topology","code":"https://github.com/thu-spmi/cat","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"TDNN + pNorm + speed up/down speech","metrics":{"Word Error Rate (WER)":"12.5"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"Deep Speech 2","metrics":{"Word Error Rate (WER)":"13.25"},"uses_additional_data":false,"paper_date":"2015-12-08","paper":"/paper/deep-speech-2-end-to-end-speech-recognition","paper_url":"http://arxiv.org/abs/1512.02595v1","paper_title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","code":"https://github.com/tensorflow/models/tree/master/research/deep_speech","n_code_links":35,"official":{"repos":["PaddlePaddle/PaddleSpeech"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":33,"n_constructed":0,"n_ran_checked":32,"n_instrument":1,"n_unverified":6,"n_samples":39,"n_pointer_only_licence":0,"sample_list":"/paper/deep-speech-2-end-to-end-speech-recognition#ran","syntology_url":"https://syntology.ai/paper/1512.02595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1512.02595"}}}},{"rank_in_archive_order":51,"model":"Local Prior Matching (Large Model, ConvLM LM)","metrics":{"Word Error Rate (WER)":"15.28"},"uses_additional_data":false,"paper_date":"2020-02-24","paper":"/paper/semi-supervised-speech-recognition-via-local","paper_url":"https://arxiv.org/abs/2002.10336v1","paper_title":"Semi-Supervised Speech Recognition via Local Prior Matching","code":"https://github.com/facebookresearch/wav2letter","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"Snips","metrics":{"Word Error Rate (WER)":"16.5"},"uses_additional_data":false,"paper_date":"2018-05-25","paper":"/paper/snips-voice-platform-an-embedded-spoken","paper_url":"http://arxiv.org/abs/1805.10190v3","paper_title":"Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfaces","code":"https://github.com/snipsco/snips-nlu","n_code_links":16,"official":{"repos":["snipsco/nlu-benchmark","snipsco/snips-nlu"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_samples":15,"n_pointer_only_licence":0,"sample_list":"/paper/snips-voice-platform-an-embedded-spoken#ran","syntology_url":"https://syntology.ai/paper/1805.10190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.10190"}}}},{"rank_in_archive_order":53,"model":"Local Prior Matching (Large Model)","metrics":{"Word Error Rate (WER)":"20.84"},"uses_additional_data":true,"paper_date":"2020-02-24","paper":"/paper/semi-supervised-speech-recognition-via-local","paper_url":"https://arxiv.org/abs/2002.10336v1","paper_title":"Semi-Supervised Speech Recognition via Local Prior Matching","code":"https://github.com/facebookresearch/wav2letter","n_code_links":1,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 23 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,589 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 8 proposed a result; of those 8, 8 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 0 were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":53,"metric_columns":1,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1589,"candidates":23,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":8,"no_cell_passed_checks":8,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 8 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":8,"shown_on_page":8,"no_cell_split":{"no_cell_passed_checks_in_ledger":8,"rows_refused_by_rule":8,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.18680","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2608.24168","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2608.10878","outcome":"refused_by_rule","reason":"the table reports a different split or setting than the leaderboard"},{"arxiv_id":"2607.08117","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2603.00683","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2601.10272","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2510.06195","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2509.22220","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":18,"rows_with_any_sample_ran":18,"rows_with_a_run_with_no_instrument_failure":17,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":11,"rows_whose_official_repository_has_a_sample_that_ran":4,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":4,"rows_community_repositories_only":6,"rows_runs_from_other_or_unrecorded_repositories":1,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":14,"distinct_papers_with_any_sample_ran":14,"distinct_papers_with_a_run_with_no_instrument_failure":13,"samples_over_distinct_papers":{"n_ran":154,"n_constructed":12,"n_ran_checked":127,"n_instrument":27,"n_unverified":50,"n_samples":204,"n_pointer_only_licence":27,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":187,"n_constructed":12,"n_ran_checked":155,"n_instrument":32,"n_unverified":58,"n_samples":245,"n_pointer_only_licence":33,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"ec13975efeb43fed83ec8061d6c3b51c5dae70b5cf203a51cf723b070a1c6443","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}