{"url":"/sota/text-summarization-on-gigaword","task":{"name":"Text Summarization","url":"/task/text-summarization","note":null},"dataset":{"name":"GigaWord","url":null},"category":"Natural Language Processing","categories":["Knowledge Base","Natural Language Processing"],"category_note":null,"description":"**Text Summarization** is a natural language processing (NLP) task that involves condensing a lengthy text document into a shorter, more compact version while still retaining the most important information and meaning. The goal is to produce a summary that accurately represents the content of the original text in a concise form. \r\n\r\nThere are different approaches to text summarization, including extractive methods that identify and extract important sentences or phrases from the text, and abstractive methods that generate new text based on the content of the original text.","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":["ROUGE-1","ROUGE-2","ROUGE-L"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"ROUGE-1":"higher","ROUGE-2":"higher","ROUGE-L":"higher"}},"counts":{"rows":41,"rows_with_code":31,"rows_with_paper_page":39,"rows_dated":38,"rows_using_additional_data":11},"rows":[{"rank_in_archive_order":1,"model":"OpenAI/o3-mini","metrics":{"ROUGE-1":"60.12","ROUGE-2":"54.22","ROUGE-L":"57.21"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Riple/Saanvi-v0.1","metrics":{"ROUGE-1":"52.21","ROUGE-2":"45.58","ROUGE-L":"60.29"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Pegasus+DotProd","metrics":{"ROUGE-1":"40.6","ROUGE-2":"21.0","ROUGE-L":"37.0"},"uses_additional_data":true,"paper_date":null,"paper":"/paper/beyond-reptile-meta-learned-dot-product","paper_url":"https://aclanthology.org/2021.findings-emnlp.37","paper_title":"Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"BART-RXF","metrics":{"ROUGE-1":"40.45","ROUGE-2":"20.69","ROUGE-L":"36.56"},"uses_additional_data":false,"paper_date":"2020-08-06","paper":"/paper/better-fine-tuning-by-reducing","paper_url":"https://arxiv.org/abs/2008.03156v1","paper_title":"Better Fine-Tuning by Reducing Representational Collapse","code":"https://github.com/pytorch/fairseq/tree/master/examples/rxf","n_code_links":3,"syntology":null},{"rank_in_archive_order":5,"model":"MUPPET BART Large","metrics":{"ROUGE-1":"40.4","ROUGE-2":"20.54","ROUGE-L":"36.21"},"uses_additional_data":true,"paper_date":"2021-01-26","paper":"/paper/muppet-massive-multi-task-representations","paper_url":"https://arxiv.org/abs/2101.11038v1","paper_title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","code":"https://huggingface.co/facebook/muppet-roberta-base","n_code_links":2,"syntology":null},{"rank_in_archive_order":6,"model":"OFA","metrics":{"ROUGE-1":"39.81","ROUGE-2":"20.66","ROUGE-L":"37.11"},"uses_additional_data":false,"paper_date":"2022-02-07","paper":"/paper/unifying-architectures-tasks-and-modalities","paper_url":"https://arxiv.org/abs/2202.03052v2","paper_title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","code":"https://github.com/modelscope/modelscope","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"Transformer+Rep(Uni)","metrics":{"ROUGE-1":"39.81","ROUGE-2":"20.40","ROUGE-L":"36.93"},"uses_additional_data":true,"paper_date":"2021-04-05","paper":"/paper/rethinking-perturbations-in-encoder-decoders","paper_url":"https://arxiv.org/abs/2104.01853v1","paper_title":"Rethinking Perturbations in Encoder-Decoders for Fast Training","code":"https://github.com/takase/rethink_perturbations","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"Transformer+Wdrop","metrics":{"ROUGE-1":"39.66","ROUGE-2":"20.45","ROUGE-L":"36.59"},"uses_additional_data":true,"paper_date":"2021-04-05","paper":"/paper/rethinking-perturbations-in-encoder-decoders","paper_url":"https://arxiv.org/abs/2104.01853v1","paper_title":"Rethinking Perturbations in Encoder-Decoders for Fast Training","code":"https://github.com/takase/rethink_perturbations","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"ProphetNet","metrics":{"ROUGE-1":"39.51","ROUGE-2":"20.42","ROUGE-L":"36.69"},"uses_additional_data":true,"paper_date":"2020-01-13","paper":"/paper/prophetnet-predicting-future-n-gram-for","paper_url":"https://arxiv.org/abs/2001.04063v3","paper_title":"ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training","code":"https://github.com/huggingface/transformers","n_code_links":5,"syntology":null},{"rank_in_archive_order":10,"model":"ERNIE-GENLARGE (large-scale text corpora)","metrics":{"ROUGE-1":"39.46","ROUGE-2":"20.34","ROUGE-L":"36.74"},"uses_additional_data":true,"paper_date":"2020-01-26","paper":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","paper_url":"https://arxiv.org/abs/2001.11314v3","paper_title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","code":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/ernie_gen/modeling.py","n_code_links":5,"syntology":null},{"rank_in_archive_order":11,"model":"PALM","metrics":{"ROUGE-1":"39.45","ROUGE-2":"20.37","ROUGE-L":"36.75"},"uses_additional_data":false,"paper_date":"2020-04-14","paper":"/paper/palm-pre-training-an-autoencoding","paper_url":"https://arxiv.org/abs/2004.07159v2","paper_title":"PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation","code":"https://github.com/alibaba/AliceMind/tree/main/PALM","n_code_links":2,"syntology":null},{"rank_in_archive_order":12,"model":"Best Summary Length","metrics":{"ROUGE-1":"39.27","ROUGE-2":"20.40","ROUGE-L":"37.75"},"uses_additional_data":false,"paper_date":"2021-04-05","paper":"/paper/a-new-approach-to-overgenerating-and-scoring","paper_url":"https://arxiv.org/abs/2104.01726v1","paper_title":"A New Approach to Overgenerating and Scoring Abstractive Summaries","code":"https://github.com/ucfnlp/varying-length-summ","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"ERNIE-GENLARGE","metrics":{"ROUGE-1":"39.25","ROUGE-2":"20.25","ROUGE-L":"36.53"},"uses_additional_data":true,"paper_date":"2020-01-26","paper":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","paper_url":"https://arxiv.org/abs/2001.11314v3","paper_title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","code":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/ernie_gen/modeling.py","n_code_links":5,"syntology":null},{"rank_in_archive_order":14,"model":"ControlCopying + BPNorm","metrics":{"ROUGE-1":"39.19","ROUGE-2":"20.38","ROUGE-L":"36.69"},"uses_additional_data":false,"paper_date":"2019-11-23","paper":"/paper/controlling-the-amount-of-verbatim-copying-in","paper_url":"https://arxiv.org/abs/1911.10390v1","paper_title":"Controlling the Amount of Verbatim Copying in Abstractive Summarization","code":"https://github.com/ucfnlp/control-over-copying","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"PEGASUS","metrics":{"ROUGE-1":"39.12","ROUGE-2":"19.86","ROUGE-L":"36.24"},"uses_additional_data":true,"paper_date":"2019-12-18","paper":"/paper/pegasus-pre-training-with-extracted-gap","paper_url":"https://arxiv.org/abs/1912.08777v2","paper_title":"PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization","code":"https://github.com/huggingface/transformers","n_code_links":19,"syntology":{"n_ran":15,"n_unverified":4,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"BiSET","metrics":{"ROUGE-1":"39.11","ROUGE-2":"19.78","ROUGE-L":"36.87"},"uses_additional_data":false,"paper_date":"2019-06-12","paper":"/paper/biset-bi-directional-selective-encoding-with","paper_url":"https://arxiv.org/abs/1906.05012v1","paper_title":"BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization","code":"https://github.com/InitialBug/BiSET","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"ControlCopying + SBWR","metrics":{"ROUGE-1":"39.08","ROUGE-2":"20.47","ROUGE-L":"36.69"},"uses_additional_data":false,"paper_date":"2019-11-23","paper":"/paper/controlling-the-amount-of-verbatim-copying-in","paper_url":"https://arxiv.org/abs/1911.10390v1","paper_title":"Controlling the Amount of Verbatim Copying in Abstractive Summarization","code":"https://github.com/ucfnlp/control-over-copying","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"UniLM","metrics":{"ROUGE-1":"38.90","ROUGE-2":"20.05","ROUGE-L":"36.00"},"uses_additional_data":true,"paper_date":"2019-05-08","paper":"/paper/unified-language-model-pre-training-for","paper_url":"https://arxiv.org/abs/1905.03197v3","paper_title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","code":"https://github.com/microsoft/unilm","n_code_links":9,"syntology":null},{"rank_in_archive_order":19,"model":"ERNIE-GENBASE","metrics":{"ROUGE-1":"38.83","ROUGE-2":"20.04","ROUGE-L":"36.20"},"uses_additional_data":true,"paper_date":"2020-01-26","paper":"/paper/ernie-gen-an-enhanced-multi-flow-pre-training","paper_url":"https://arxiv.org/abs/2001.11314v3","paper_title":"ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation","code":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/ernie_gen/modeling.py","n_code_links":5,"syntology":null},{"rank_in_archive_order":20,"model":"MASS","metrics":{"ROUGE-1":"38.73","ROUGE-2":"19.71","ROUGE-L":"35.96"},"uses_additional_data":true,"paper_date":"2019-05-07","paper":"/paper/mass-masked-sequence-to-sequence-pre-training","paper_url":"https://arxiv.org/abs/1905.02450v5","paper_title":"MASS: Masked Sequence to Sequence Pre-training for Language Generation","code":"https://github.com/microsoft/MASS","n_code_links":7,"syntology":null},{"rank_in_archive_order":21,"model":"Mask Attention Network","metrics":{"ROUGE-1":"38.28","ROUGE-2":"19.46","ROUGE-L":"35.46"},"uses_additional_data":false,"paper_date":"2021-03-25","paper":"/paper/mask-attention-networks-rethinking-and","paper_url":"https://arxiv.org/abs/2103.13597v1","paper_title":"Mask Attention Networks: Rethinking and Strengthen Transformer","code":"https://github.com/libertfan/man","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"Concept pointer+RL","metrics":{"ROUGE-1":"38.02","ROUGE-2":"16.97","ROUGE-L":"35.43"},"uses_additional_data":false,"paper_date":"2019-10-18","paper":"/paper/concept-pointer-network-for-abstractive","paper_url":"https://arxiv.org/abs/1910.08486v1","paper_title":"Concept Pointer Network for Abstractive Summarization","code":"https://github.com/wprojectsn/codes","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"Transformer","metrics":{"ROUGE-1":"37.57","ROUGE-2":"18.90","ROUGE-L":"34.69"},"uses_additional_data":false,"paper_date":"2017-06-12","paper":"/paper/attention-is-all-you-need","paper_url":"https://arxiv.org/abs/1706.03762v7","paper_title":"Attention Is All You Need","code":"https://github.com/huggingface/transformers","n_code_links":595,"syntology":{"n_ran":610,"n_unverified":336,"n_samples":946,"n_pointer_only_licence":451}},{"rank_in_archive_order":24,"model":"FTSum_g","metrics":{"ROUGE-1":"37.27","ROUGE-2":"17.65","ROUGE-L":"34.24"},"uses_additional_data":false,"paper_date":"2017-11-13","paper":"/paper/faithful-to-the-original-fact-aware-neural","paper_url":"http://arxiv.org/abs/1711.04434v1","paper_title":"Faithful to the Original: Fact Aware Neural Abstractive Summarization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"Re^3 Sum","metrics":{"ROUGE-1":"37.04","ROUGE-2":"19.03","ROUGE-L":"34.46"},"uses_additional_data":false,"paper_date":"2018-07-01","paper":"/paper/retrieve-rerank-and-rewrite-soft-template","paper_url":"https://aclanthology.org/P18-1015","paper_title":"Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"Seq2seq + E2T_cnn","metrics":{"ROUGE-1":"37.04","ROUGE-2":"16.66","ROUGE-L":"34.93"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/entity-commonsense-representation-for-neural","paper_url":"http://arxiv.org/abs/1806.05504v1","paper_title":"Entity Commonsense Representation for Neural Abstractive Summarization","code":"https://github.com/rktamplayo/Entity2Topic","n_code_links":1,"syntology":null},{"rank_in_archive_order":27,"model":"Concept pointer+DS","metrics":{"ROUGE-1":"37.01","ROUGE-2":"17.1","ROUGE-L":"34.87"},"uses_additional_data":false,"paper_date":"2019-10-18","paper":"/paper/concept-pointer-network-for-abstractive","paper_url":"https://arxiv.org/abs/1910.08486v1","paper_title":"Concept Pointer Network for Abstractive Summarization","code":"https://github.com/wprojectsn/codes","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"Reinforced-Topic-ConvS2S","metrics":{"ROUGE-1":"36.92","ROUGE-2":"18.29","ROUGE-L":"34.58"},"uses_additional_data":false,"paper_date":"2018-05-09","paper":"/paper/a-reinforced-topic-aware-convolutional","paper_url":"https://arxiv.org/abs/1805.03616v3","paper_title":"A Reinforced Topic-Aware Convolutional Sequence-to-Sequence Model for Abstractive Text Summarization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"JointParsing","metrics":{"ROUGE-1":"36.61","ROUGE-2":"18.85","ROUGE-L":"34.33"},"uses_additional_data":false,"paper_date":"2019-11-23","paper":"/paper/joint-parsing-and-generation-for-abstractive","paper_url":"https://arxiv.org/abs/1911.10389v1","paper_title":"Joint Parsing and Generation for Abstractive Summarization","code":"https://github.com/ucfnlp/joint-parse-n-summarize","n_code_links":2,"syntology":null},{"rank_in_archive_order":30,"model":"words-lvt5k-1sent","metrics":{"ROUGE-1":"36.4","ROUGE-2":"17.7","ROUGE-L":"33.71"},"uses_additional_data":false,"paper_date":"2016-02-19","paper":"/paper/abstractive-text-summarization-using-sequence","paper_url":"http://arxiv.org/abs/1602.06023v5","paper_title":"Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond","code":"https://github.com/theamrzaki/text_summurization_abstractive_methods","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"CGU","metrics":{"ROUGE-1":"36.3","ROUGE-2":"18.0","ROUGE-L":"33.8"},"uses_additional_data":false,"paper_date":"2018-05-10","paper":"/paper/global-encoding-for-abstractive-summarization","paper_url":"http://arxiv.org/abs/1805.03989v2","paper_title":"Global Encoding for Abstractive Summarization","code":"https://github.com/lancopku/Global-Encoding","n_code_links":4,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"EndDec+WFE","metrics":{"ROUGE-1":"36.30","ROUGE-2":"17.31","ROUGE-L":"33.88"},"uses_additional_data":false,"paper_date":"2016-12-31","paper":"/paper/cutting-off-redundant-repeating-generations","paper_url":"http://arxiv.org/abs/1701.00138v2","paper_title":"Cutting-off Redundant Repeating Generations for Neural Abstractive Summarization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"DRGD","metrics":{"ROUGE-1":"36.27","ROUGE-2":"17.57","ROUGE-L":"33.62"},"uses_additional_data":false,"paper_date":"2017-08-02","paper":"/paper/deep-recurrent-generative-decoder-for","paper_url":"http://arxiv.org/abs/1708.00625v1","paper_title":"Deep Recurrent Generative Decoder for Abstractive Text Summarization","code":"https://github.com/toru34/li_emnlp_2017","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"SEASS","metrics":{"ROUGE-1":"36.15","ROUGE-2":"17.54","ROUGE-L":"33.63"},"uses_additional_data":false,"paper_date":"2017-04-24","paper":"/paper/selective-encoding-for-abstractive-sentence","paper_url":"http://arxiv.org/abs/1704.07073v1","paper_title":"Selective Encoding for Abstractive Sentence Summarization","code":"https://github.com/magic282/SEASS","n_code_links":2,"syntology":null},{"rank_in_archive_order":35,"model":"Pointer + Coverage + EntailmentGen + QuestionGen","metrics":{"ROUGE-1":"35.98","ROUGE-2":"17.76","ROUGE-L":"33.63"},"uses_additional_data":false,"paper_date":"2018-05-28","paper":"/paper/soft-layer-specific-multi-task-summarization","paper_url":"http://arxiv.org/abs/1805.11004v1","paper_title":"Soft Layer-Specific Multi-Task Summarization with Entailment and Question Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":36,"model":"Struct+2Way+Word","metrics":{"ROUGE-1":"35.47","ROUGE-2":"17.66","ROUGE-L":"33.52"},"uses_additional_data":false,"paper_date":"2018-06-14","paper":"/paper/structure-infused-copy-mechanisms-for","paper_url":"http://arxiv.org/abs/1806.05658v2","paper_title":"Structure-Infused Copy Mechanisms for Abstractive Summarization","code":"https://github.com/KaiQiangSong/struct_infused_summ","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"Seq2seq + selective + MTL + ERAM","metrics":{"ROUGE-1":"35.33","ROUGE-2":"17.27","ROUGE-L":"33.19"},"uses_additional_data":false,"paper_date":"2018-08-01","paper":"/paper/ensure-the-correctness-of-the-summary","paper_url":"https://aclanthology.org/C18-1121","paper_title":"Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":38,"model":"RAS-Elman","metrics":{"ROUGE-1":"33.78","ROUGE-2":"15.97","ROUGE-L":"31.15"},"uses_additional_data":false,"paper_date":"2016-06-01","paper":"/paper/abstractive-sentence-summarization-with","paper_url":"https://aclanthology.org/N16-1012","paper_title":"Abstractive Sentence Summarization with Attentive Recurrent Neural Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":39,"model":"Abs+","metrics":{"ROUGE-1":"31"},"uses_additional_data":false,"paper_date":"2015-09-02","paper":"/paper/a-neural-attention-model-for-abstractive","paper_url":"http://arxiv.org/abs/1509.00685v2","paper_title":"A Neural Attention Model for Abstractive Sentence Summarization","code":"https://github.com/tensorflow/models/tree/master/research/textsum","n_code_links":4,"syntology":null},{"rank_in_archive_order":40,"model":"Abs","metrics":{"ROUGE-1":"30.88"},"uses_additional_data":false,"paper_date":"2015-09-02","paper":"/paper/a-neural-attention-model-for-abstractive","paper_url":"http://arxiv.org/abs/1509.00685v2","paper_title":"A Neural Attention Model for Abstractive Sentence Summarization","code":"https://github.com/tensorflow/models/tree/master/research/textsum","n_code_links":4,"syntology":null},{"rank_in_archive_order":41,"model":"Contextual Match","metrics":{"ROUGE-1":"26.48","ROUGE-2":"10.05","ROUGE-L":"24.41"},"uses_additional_data":false,"paper_date":"2019-07-31","paper":"/paper/simple-unsupervised-summarization-by-1","paper_url":"https://arxiv.org/abs/1907.13337v1","paper_title":"Simple Unsupervised Summarization by Contextual Matching","code":"https://github.com/jzhou316/Unsupervised-Sentence-Summarization","n_code_links":1,"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,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N 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).","rows_with_graph_line":8,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":633,"n_unverified":350,"n_samples":983,"n_pointer_only_licence":452,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":634,"n_unverified":350,"n_samples":984,"n_pointer_only_licence":453,"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"}}}