{"url":"/sota/graph-classification-on-peptides-func","task":{"name":"Graph Classification","url":"/task/graph-classification","note":null},"dataset":{"name":"Peptides-func","url":"/dataset/pascalvoc-sp"},"category":"Graphs","categories":["Graphs"],"category_note":null,"description":"**Graph Classification** is a task that involves classifying a graph-structured data into different classes or categories. Graphs are a powerful way to represent relationships and interactions between different entities, and graph classification can be applied to a wide range of applications, such as social network analysis, bioinformatics, and recommendation systems. In graph classification, the input is a graph, and the goal is to learn a classifier that can accurately predict the class of the graph.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Hierarchical Graph Pooling with Structure Learning](https://github.com/cszhangzhen/HGP-SL) )</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":["AP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AP":"higher"}},"counts":{"rows":44,"rows_with_code":42,"rows_with_paper_page":44,"rows_dated":44,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"ESA + RWSE (Edge set attention, Random Walk Structural Encoding, + validation set)","metrics":{"AP":"0.7479"},"uses_additional_data":true,"paper_date":"2024-02-16","paper":"/paper/masked-attention-is-all-you-need-for-graphs","paper_url":"https://arxiv.org/abs/2402.10793v2","paper_title":"An end-to-end attention-based approach for learning on graphs","code":"https://github.com/davidbuterez/edge-set-attention","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"ECFP + LightGBM","metrics":{"AP":"0.7460"},"uses_additional_data":false,"paper_date":"2025-01-29","paper":"/paper/molecular-fingerprints-are-strong-models-for","paper_url":"https://arxiv.org/abs/2501.17901v1","paper_title":"Molecular Fingerprints Are Strong Models for Peptide Function Prediction","code":"https://github.com/arch4ngel21/scikit-fingerprints","n_code_links":4,"syntology":null},{"rank_in_archive_order":3,"model":"ESA + RWSE (Edge set attention, Random Walk Structural Encoding, tuned)","metrics":{"AP":"0.7357±0.0036"},"uses_additional_data":false,"paper_date":"2024-02-16","paper":"/paper/masked-attention-is-all-you-need-for-graphs","paper_url":"https://arxiv.org/abs/2402.10793v2","paper_title":"An end-to-end attention-based approach for learning on graphs","code":"https://github.com/davidbuterez/edge-set-attention","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"TT + LightGBM","metrics":{"AP":"0.7318"},"uses_additional_data":false,"paper_date":"2025-01-29","paper":"/paper/molecular-fingerprints-are-strong-models-for","paper_url":"https://arxiv.org/abs/2501.17901v1","paper_title":"Molecular Fingerprints Are Strong Models for Peptide Function Prediction","code":"https://github.com/arch4ngel21/scikit-fingerprints","n_code_links":4,"syntology":null},{"rank_in_archive_order":5,"model":"S²GCN","metrics":{"AP":"0.7311±0.0066"},"uses_additional_data":false,"paper_date":"2024-05-29","paper":"/paper/spatio-spectral-graph-neural-networks","paper_url":"https://arxiv.org/abs/2405.19121v2","paper_title":"Spatio-Spectral Graph Neural Networks","code":"https://github.com/sigeisler/s2gnn","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"RDKit + LightGBM","metrics":{"AP":"0.7311"},"uses_additional_data":false,"paper_date":"2025-01-29","paper":"/paper/molecular-fingerprints-are-strong-models-for","paper_url":"https://arxiv.org/abs/2501.17901v1","paper_title":"Molecular Fingerprints Are Strong Models for Peptide Function Prediction","code":"https://github.com/arch4ngel21/scikit-fingerprints","n_code_links":4,"syntology":null},{"rank_in_archive_order":7,"model":"GCN+","metrics":{"AP":"0.7261 ± 0.0067"},"uses_additional_data":false,"paper_date":"2025-02-13","paper":"/paper/unlocking-the-potential-of-classic-gnns-for","paper_url":"https://arxiv.org/abs/2502.09263v1","paper_title":"Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence","code":"https://github.com/LUOyk1999/GNNPlus","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":8,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"GraphGPS + HDSE","metrics":{"AP":"0.7156±0.0058"},"uses_additional_data":false,"paper_date":"2023-08-22","paper":"/paper/transformers-for-capturing-multi-level-graph","paper_url":"https://arxiv.org/abs/2308.11129v4","paper_title":"Enhancing Graph Transformers with Hierarchical Distance Structural Encoding","code":"https://github.com/luoyk1999/hdse","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"DRew-GCN+LapPE","metrics":{"AP":"0.7150±0.0044"},"uses_additional_data":false,"paper_date":"2023-05-13","paper":"/paper/drew-dynamically-rewired-message-passing-with","paper_url":"https://arxiv.org/abs/2305.08018v2","paper_title":"DRew: Dynamically Rewired Message Passing with Delay","code":"https://github.com/bengutteridge/drew","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":7,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"GRED+LapPE","metrics":{"AP":"0.7133±0.0011"},"uses_additional_data":false,"paper_date":"2023-12-03","paper":"/paper/recurrent-distance-encoding-neural-networks","paper_url":"https://arxiv.org/abs/2312.01538v3","paper_title":"Recurrent Distance Filtering for Graph Representation Learning","code":"https://github.com/skeletondyh/gred","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":9,"n_samples":21,"n_pointer_only_licence":21}},{"rank_in_archive_order":11,"model":"NeuralWalker","metrics":{"AP":"0.7096 ± 0.0078"},"uses_additional_data":false,"paper_date":"2024-06-05","paper":"/paper/learning-long-range-dependencies-on-graphs","paper_url":"https://arxiv.org/abs/2406.03386v2","paper_title":"Learning Long Range Dependencies on Graphs via Random Walks","code":"https://github.com/borgwardtlab/neuralwalker","n_code_links":1,"syntology":{"n_ran":13,"n_unverified":0,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"GRED","metrics":{"AP":"0.7085±0.0027"},"uses_additional_data":false,"paper_date":"2023-12-03","paper":"/paper/recurrent-distance-encoding-neural-networks","paper_url":"https://arxiv.org/abs/2312.01538v3","paper_title":"Recurrent Distance Filtering for Graph Representation Learning","code":"https://github.com/skeletondyh/gred","n_code_links":1,"syntology":{"n_ran":12,"n_unverified":9,"n_samples":21,"n_pointer_only_licence":21}},{"rank_in_archive_order":13,"model":"ESA (Edge set attention, no positional encodings, tuned)","metrics":{"AP":"0.7071±0.0015"},"uses_additional_data":false,"paper_date":"2024-02-16","paper":"/paper/masked-attention-is-all-you-need-for-graphs","paper_url":"https://arxiv.org/abs/2402.10793v2","paper_title":"An end-to-end attention-based approach for learning on graphs","code":"https://github.com/davidbuterez/edge-set-attention","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"GRIT","metrics":{"AP":"0.6988±0.0082"},"uses_additional_data":false,"paper_date":"2023-05-27","paper":"/paper/graph-inductive-biases-in-transformers","paper_url":"https://arxiv.org/abs/2305.17589v1","paper_title":"Graph Inductive Biases in Transformers without Message Passing","code":"https://github.com/liamma/grit","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":6,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"CKGCN","metrics":{"AP":"0.6952"},"uses_additional_data":false,"paper_date":"2024-04-21","paper":"/paper/ckgconv-general-graph-convolution-with","paper_url":"https://arxiv.org/abs/2404.13604v2","paper_title":"CKGConv: General Graph Convolution with Continuous Kernels","code":"https://github.com/networkslab/ckgconv","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":16,"model":"Graph ViT","metrics":{"AP":"0.6942±0.0075"},"uses_additional_data":false,"paper_date":"2022-12-27","paper":"/paper/a-generalization-of-vit-mlp-mixer-to-graphs","paper_url":"https://arxiv.org/abs/2212.13350v2","paper_title":"A Generalization of ViT/MLP-Mixer to Graphs","code":"https://github.com/XiaoxinHe/Graph-ViT-MLPMixer","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":17,"model":"GraphMLPMixer","metrics":{"AP":"0.6921±0.0054"},"uses_additional_data":false,"paper_date":"2022-12-27","paper":"/paper/a-generalization-of-vit-mlp-mixer-to-graphs","paper_url":"https://arxiv.org/abs/2212.13350v2","paper_title":"A Generalization of ViT/MLP-Mixer to Graphs","code":"https://github.com/XiaoxinHe/Graph-ViT-MLPMixer","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"GatedGCN-HSG","metrics":{"AP":"0.6866±0.0038"},"uses_additional_data":false,"paper_date":"2024-06-22","paper":"/paper/next-level-message-passing-with-hierarchical","paper_url":"https://arxiv.org/abs/2406.15852v2","paper_title":"Next Level Message-Passing with Hierarchical Support Graphs","code":"https://github.com/carlosinator/support-graphs","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":6,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":19,"model":"ESA (Edge set attention, no positional encodings, not tuned)","metrics":{"AP":"0.6863±0.0044"},"uses_additional_data":false,"paper_date":"2024-02-16","paper":"/paper/masked-attention-is-all-you-need-for-graphs","paper_url":"https://arxiv.org/abs/2402.10793v2","paper_title":"An end-to-end attention-based approach for learning on graphs","code":"https://github.com/davidbuterez/edge-set-attention","n_code_links":1,"syntology":null},{"rank_in_archive_order":20,"model":"GCN-tuned","metrics":{"AP":"0.6860±0.0050"},"uses_additional_data":false,"paper_date":"2023-09-01","paper":"/paper/where-did-the-gap-go-reassessing-the-long","paper_url":"https://arxiv.org/abs/2309.00367v2","paper_title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","code":"https://github.com/toenshoff/lrgb","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"MGT+WavePE","metrics":{"AP":"0.6817±0.0064"},"uses_additional_data":false,"paper_date":"2023-02-17","paper":"/paper/multiresolution-graph-transformers-and","paper_url":"https://arxiv.org/abs/2302.08647v4","paper_title":"Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures","code":"https://github.com/vijaydwivedi75/lrgb","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"PathNN","metrics":{"AP":"0.6816±0.0026"},"uses_additional_data":false,"paper_date":"2023-06-09","paper":"/paper/path-neural-networks-expressive-and-accurate","paper_url":"https://arxiv.org/abs/2306.05955v1","paper_title":"Path Neural Networks: Expressive and Accurate Graph Neural Networks","code":"https://github.com/gasmichel/pathnns_expressive","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"GatedGCN-tuned","metrics":{"AP":"0.6765±0.0047"},"uses_additional_data":false,"paper_date":"2023-09-01","paper":"/paper/where-did-the-gap-go-reassessing-the-long","paper_url":"https://arxiv.org/abs/2309.00367v2","paper_title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","code":"https://github.com/toenshoff/lrgb","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"GatedGCN+RWSE+virtual node","metrics":{"AP":"0.6685±0.0062"},"uses_additional_data":false,"paper_date":"2023-01-27","paper":"/paper/on-the-connection-between-mpnn-and-graph","paper_url":"https://arxiv.org/abs/2301.11956v4","paper_title":"On the Connection Between MPNN and Graph Transformer","code":"https://github.com/chen-cai-osu/mpnn-gt-connection","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"TIGT","metrics":{"AP":"0.6679"},"uses_additional_data":false,"paper_date":"2024-02-03","paper":"/paper/topology-informed-graph-transformer","paper_url":"https://arxiv.org/abs/2402.02005v1","paper_title":"Topology-Informed Graph Transformer","code":"https://github.com/leemingo/tigt","n_code_links":2,"syntology":{"n_ran":14,"n_unverified":7,"n_samples":21,"n_pointer_only_licence":21}},{"rank_in_archive_order":26,"model":"Graph Diffuser","metrics":{"AP":"0.6651±0.0010"},"uses_additional_data":false,"paper_date":"2023-03-01","paper":"/paper/diffusing-graph-attention","paper_url":"https://arxiv.org/abs/2303.00613v1","paper_title":"Diffusing Graph Attention","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"GINE-tuned","metrics":{"AP":"0.6621±0.0067"},"uses_additional_data":false,"paper_date":"2023-09-01","paper":"/paper/where-did-the-gap-go-reassessing-the-long","paper_url":"https://arxiv.org/abs/2309.00367v2","paper_title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","code":"https://github.com/toenshoff/lrgb","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"ViT-PS","metrics":{"AP":"0.6575"},"uses_additional_data":true,"paper_date":"2023-06-05","paper":"/paper/learning-probabilistic-symmetrization-for-1","paper_url":"https://arxiv.org/abs/2306.02866v3","paper_title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","code":"https://github.com/jw9730/lps","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":13,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":29,"model":"CIN++-500k","metrics":{"AP":"0.6569±0.0117"},"uses_additional_data":false,"paper_date":"2023-06-06","paper":"/paper/cin-enhancing-topological-message-passing","paper_url":"https://arxiv.org/abs/2306.03561v1","paper_title":"CIN++: Enhancing Topological Message Passing","code":"https://github.com/twitter-research/cwn","n_code_links":1,"syntology":null},{"rank_in_archive_order":30,"model":"GPS","metrics":{"AP":"0.6535±0.0041"},"uses_additional_data":false,"paper_date":"2022-05-25","paper":"/paper/recipe-for-a-general-powerful-scalable-graph","paper_url":"https://arxiv.org/abs/2205.12454v4","paper_title":"Recipe for a General, Powerful, Scalable Graph Transformer","code":"https://github.com/rampasek/GraphGPS","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":18,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"GPS-tuned","metrics":{"AP":"0.6534±0.0091"},"uses_additional_data":false,"paper_date":"2023-09-01","paper":"/paper/where-did-the-gap-go-reassessing-the-long","paper_url":"https://arxiv.org/abs/2309.00367v2","paper_title":"Where Did the Gap Go? Reassessing the Long-Range Graph Benchmark","code":"https://github.com/toenshoff/lrgb","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"Exphormer","metrics":{"AP":"0.6527±0.0043"},"uses_additional_data":false,"paper_date":"2023-03-10","paper":"/paper/exphormer-sparse-transformers-for-graphs","paper_url":"https://arxiv.org/abs/2303.06147v2","paper_title":"Exphormer: Sparse Transformers for Graphs","code":"https://github.com/hamed1375/exphormer","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"MOLTOP","metrics":{"AP":"0.6459 ± 0.0005"},"uses_additional_data":false,"paper_date":"2024-10-17","paper":"/paper/molecular-topological-profile-moltop-simple-1","paper_url":"https://ebooks.iospress.nl/doi/10.3233/FAIA240663","paper_title":"Molecular Topological Profile (MOLTOP) - Simple and Strong Baseline for Molecular Graph Classification","code":"https://github.com/j-adamczyk/MOLTOP","n_code_links":1,"syntology":null},{"rank_in_archive_order":34,"model":"SAN+RWSE","metrics":{"AP":"0.6439±0.0075"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/long-range-graph-benchmark","paper_url":"https://arxiv.org/abs/2206.08164v4","paper_title":"Long Range Graph Benchmark","code":"https://github.com/vijaydwivedi75/lrgb","n_code_links":2,"syntology":null},{"rank_in_archive_order":35,"model":"EIGENFORMER","metrics":{"AP":"0.6414"},"uses_additional_data":false,"paper_date":"2024-01-31","paper":"/paper/graph-transformers-without-positional","paper_url":"https://arxiv.org/abs/2401.17791v3","paper_title":"Graph Transformers without Positional Encodings","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":36,"model":"SAN+LapPE","metrics":{"AP":"0.6384±0.0121"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/long-range-graph-benchmark","paper_url":"https://arxiv.org/abs/2206.08164v4","paper_title":"Long Range Graph Benchmark","code":"https://github.com/vijaydwivedi75/lrgb","n_code_links":2,"syntology":null},{"rank_in_archive_order":37,"model":"Transformer+LapPE","metrics":{"AP":"0.6326±0.0126"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/long-range-graph-benchmark","paper_url":"https://arxiv.org/abs/2206.08164v4","paper_title":"Long Range Graph Benchmark","code":"https://github.com/vijaydwivedi75/lrgb","n_code_links":2,"syntology":null},{"rank_in_archive_order":38,"model":"GatedGCN+RWSE","metrics":{"AP":"0.6069±0.0035"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/long-range-graph-benchmark","paper_url":"https://arxiv.org/abs/2206.08164v4","paper_title":"Long Range Graph Benchmark","code":"https://github.com/vijaydwivedi75/lrgb","n_code_links":2,"syntology":null},{"rank_in_archive_order":39,"model":"GIN","metrics":{"AP":"0.6043±0.0216"},"uses_additional_data":false,"paper_date":"2018-10-01","paper":"/paper/how-powerful-are-graph-neural-networks","paper_url":"http://arxiv.org/abs/1810.00826v3","paper_title":"How Powerful are Graph Neural Networks?","code":"https://github.com/dmlc/dgl/tree/master/examples/mxnet/gin","n_code_links":19,"syntology":{"n_ran":3,"n_unverified":7,"n_samples":10,"n_pointer_only_licence":5}},{"rank_in_archive_order":40,"model":"GCN + PANDA","metrics":{"AP":"0.6028±0.0031"},"uses_additional_data":false,"paper_date":"2024-06-06","paper":"/paper/panda-expanded-width-aware-message-passing","paper_url":"https://arxiv.org/abs/2406.03671v2","paper_title":"PANDA: Expanded Width-Aware Message Passing Beyond Rewiring","code":"https://github.com/jeongwhanchoi/panda","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":2,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":41,"model":"GCN","metrics":{"AP":"0.5930±0.0023"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/long-range-graph-benchmark","paper_url":"https://arxiv.org/abs/2206.08164v4","paper_title":"Long Range Graph Benchmark","code":"https://github.com/vijaydwivedi75/lrgb","n_code_links":2,"syntology":null},{"rank_in_archive_order":42,"model":"GatedGCN","metrics":{"AP":"0.5864±0.0077"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/long-range-graph-benchmark","paper_url":"https://arxiv.org/abs/2206.08164v4","paper_title":"Long Range Graph Benchmark","code":"https://github.com/vijaydwivedi75/lrgb","n_code_links":2,"syntology":null},{"rank_in_archive_order":43,"model":"GCNII","metrics":{"AP":"0.5543±0.0078"},"uses_additional_data":false,"paper_date":"2020-07-04","paper":"/paper/simple-and-deep-graph-convolutional-networks-1","paper_url":"https://arxiv.org/abs/2007.02133v1","paper_title":"Simple and Deep Graph Convolutional Networks","code":"https://github.com/chennnM/GCNII/tree/master/PyG/ogbn-arxiv","n_code_links":4,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":4}},{"rank_in_archive_order":44,"model":"GINE","metrics":{"AP":"0.5498±0.0079"},"uses_additional_data":false,"paper_date":"2022-06-16","paper":"/paper/long-range-graph-benchmark","paper_url":"https://arxiv.org/abs/2206.08164v4","paper_title":"Long Range Graph Benchmark","code":"https://github.com/vijaydwivedi75/lrgb","n_code_links":2,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+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":25,"rows_with_any_sample_ran":23,"distinct_papers_with_graph_line":20,"distinct_papers_with_any_sample_ran":18,"samples_over_distinct_papers":{"n_ran":101,"n_unverified":101,"n_samples":202,"n_pointer_only_licence":62,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":130,"n_unverified":132,"n_samples":262,"n_pointer_only_licence":83,"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"}}}