{"url":"/task/molecular-property-prediction","name":"Molecular Property Prediction","slug":"molecular-property-prediction","description_markdown":"Molecular property prediction is the task of predicting the properties of a molecule from its structure.","categories":[{"name":"Graphs","url":"/area/graphs"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":354,"papers_with_code":199,"benchmarks":18,"benchmark_tables_in_archive":18,"benchmark_tables_shown":18,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":21,"subtasks":4,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","slug":"molecular-property-prediction-on-bbbp-1","dataset":"BBBP","dataset_url":"/dataset/bbbp-scaffold","rows_in_archive":29,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"DumplingGNN","paper_title":"Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure","paper_url":"/paper/dumpling-gnn-hybrid-gnn-enables-better-adc","paper_date":"2024-09-23","arxiv_id":"2410.05278","code_links":[],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-freesolv","slug":"molecular-property-prediction-on-freesolv","dataset":"FreeSolv","dataset_url":"/dataset/freesolv-scaffold","rows_in_archive":22,"metrics":["RMSE","R2"],"first_row_in_archive_order":{"model":"ESA (Edge set attention, no positional encodings)","paper_title":"An end-to-end attention-based approach for learning on graphs","paper_url":"/paper/masked-attention-is-all-you-need-for-graphs","paper_date":"2024-02-16","arxiv_id":"2402.10793","code_links":[{"title":"davidbuterez/edge-set-attention","url":"https://github.com/davidbuterez/edge-set-attention"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","slug":"molecular-property-prediction-on-bace-1","dataset":"BACE","dataset_url":"/dataset/bace-scaffold","rows_in_archive":20,"metrics":["ROC-AUC","RMSE"],"first_row_in_archive_order":{"model":"MolXPT","paper_title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","paper_url":"/paper/molxpt-wrapping-molecules-with-text-for","paper_date":"2023-05-18","arxiv_id":"2305.10688","code_links":[{"title":"zequnl/molxpt","url":"https://huggingface.co/zequnl/molxpt"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","slug":"molecular-property-prediction-on-clintox-1","dataset":"clintox","dataset_url":"/dataset/clintox","rows_in_archive":20,"metrics":["ROC-AUC","Molecules (M)"],"first_row_in_archive_order":{"model":"Deep-CBN","paper_title":"Integrating convolutional layers and biformer network with forward-forward and backpropagation training","paper_url":"/paper/integrating-convolutional-layers-and-biformer","paper_date":"2025-02-28","arxiv_id":null,"code_links":[{"title":"akianfar/Deep-CBN","url":"https://github.com/akianfar/Deep-CBN"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-esol","slug":"molecular-property-prediction-on-esol","dataset":"ESOL","dataset_url":"/dataset/esol-scaffold","rows_in_archive":20,"metrics":["RMSE","R2"],"first_row_in_archive_order":{"model":"ESA (Edge set attention, no positional encodings)","paper_title":"An end-to-end attention-based approach for learning on graphs","paper_url":"/paper/masked-attention-is-all-you-need-for-graphs","paper_date":"2024-02-16","arxiv_id":"2402.10793","code_links":[{"title":"davidbuterez/edge-set-attention","url":"https://github.com/davidbuterez/edge-set-attention"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","slug":"molecular-property-prediction-on-tox21-1","dataset":"Tox21","dataset_url":"/dataset/tox21-1","rows_in_archive":20,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"Deep-CBN","paper_title":"Integrating convolutional layers and biformer network with forward-forward and backpropagation training","paper_url":"/paper/integrating-convolutional-layers-and-biformer","paper_date":"2025-02-28","arxiv_id":null,"code_links":[{"title":"akianfar/Deep-CBN","url":"https://github.com/akianfar/Deep-CBN"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","slug":"molecular-property-prediction-on-sider-1","dataset":"SIDER","dataset_url":"/dataset/sider","rows_in_archive":19,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"BioAct-Het","paper_title":"BioAct-Het: A Heterogeneous Siamese Neural Network for Bioactivity Prediction Using Novel Bioactivity Representatio","paper_url":"/paper/bioact-het-a-heterogeneous-siamese-neural","paper_date":"2023-10-15","arxiv_id":null,"code_links":[{"title":"CBRC-lab/BioAct-Het","url":"https://github.com/CBRC-lab/BioAct-Het"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on","slug":"molecular-property-prediction-on","dataset":"Lipophilicity","dataset_url":null,"rows_in_archive":13,"metrics":["RMSE"],"first_row_in_archive_order":{"model":"Uni-Mol","paper_title":"Uni-Mol: A Universal 3D Molecular Representation Learning Framework","paper_url":"/paper/uni-mol-a-universal-3d-molecular","paper_date":"2022-09-08","arxiv_id":null,"code_links":[{"title":"dptech-corp/Uni-Mol","url":"https://github.com/dptech-corp/Uni-Mol"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-dataset","slug":"molecular-property-prediction-on-hiv-dataset","dataset":"HIV dataset","dataset_url":"/dataset/qm9-charge-densities-and-energies-calculated","rows_in_archive":11,"metrics":["AUC"],"first_row_in_archive_order":{"model":"DVMP","paper_title":"Dual-view Molecule Pre-training","paper_url":"/paper/dual-view-molecule-pre-training","paper_date":"2021-06-17","arxiv_id":"2106.10234","code_links":[{"title":"microsoft/DVMP","url":"https://github.com/microsoft/DVMP"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-qm7","slug":"molecular-property-prediction-on-qm7","dataset":"QM7","dataset_url":"/dataset/qm7","rows_in_archive":8,"metrics":["MAE"],"first_row_in_archive_order":{"model":"Uni-Mol","paper_title":"Uni-Mol: A Universal 3D Molecular Representation Learning Framework","paper_url":"/paper/uni-mol-a-universal-3d-molecular","paper_date":"2022-09-08","arxiv_id":null,"code_links":[{"title":"dptech-corp/Uni-Mol","url":"https://github.com/dptech-corp/Uni-Mol"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-qm8","slug":"molecular-property-prediction-on-qm8","dataset":"QM8","dataset_url":"/dataset/qm8","rows_in_archive":8,"metrics":["MAE"],"first_row_in_archive_order":{"model":"Uni-Mol","paper_title":"Uni-Mol: A Universal 3D Molecular Representation Learning Framework","paper_url":"/paper/uni-mol-a-universal-3d-molecular","paper_date":"2022-09-08","arxiv_id":null,"code_links":[{"title":"dptech-corp/Uni-Mol","url":"https://github.com/dptech-corp/Uni-Mol"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-qm9","slug":"molecular-property-prediction-on-qm9","dataset":"QM9","dataset_url":"/dataset/qm9","rows_in_archive":8,"metrics":["MAE"],"first_row_in_archive_order":{"model":"Uni-Mol","paper_title":"Uni-Mol: A Universal 3D Molecular Representation Learning Framework","paper_url":"/paper/uni-mol-a-universal-3d-molecular","paper_date":"2022-09-08","arxiv_id":null,"code_links":[{"title":"dptech-corp/Uni-Mol","url":"https://github.com/dptech-corp/Uni-Mol"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-toxcast-1","slug":"molecular-property-prediction-on-toxcast-1","dataset":"ToxCast","dataset_url":"/dataset/toxcast-scaffold","rows_in_archive":8,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"DumplingGNN","paper_title":"Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure","paper_url":"/paper/dumpling-gnn-hybrid-gnn-enables-better-adc","paper_date":"2024-09-23","arxiv_id":"2410.05278","code_links":[],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-moleculenet","slug":"molecular-property-prediction-on-moleculenet","dataset":"MoleculeNet","dataset_url":"/dataset/moleculenet","rows_in_archive":5,"metrics":["AUC"],"first_row_in_archive_order":{"model":"Uni-Mol","paper_title":"Galactica: A Large Language Model for Science","paper_url":"/paper/galactica-a-large-language-model-for-science-1","paper_date":"2022-11-16","arxiv_id":"2211.09085","code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/molecular-property-prediction-on-muv-1","slug":"molecular-property-prediction-on-muv-1","dataset":"MUV","dataset_url":"/dataset/muv","rows_in_archive":5,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"Deep-CBN","paper_title":"Integrating convolutional layers and biformer network with forward-forward and backpropagation training","paper_url":"/paper/integrating-convolutional-layers-and-biformer","paper_date":"2025-02-28","arxiv_id":null,"code_links":[{"title":"akianfar/Deep-CBN","url":"https://github.com/akianfar/Deep-CBN"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-1","slug":"molecular-property-prediction-on-hiv-1","dataset":"HIV","dataset_url":"/dataset/qm9-charge-densities-and-energies-calculated","rows_in_archive":4,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"Deep-CBN","paper_title":"Integrating convolutional layers and biformer network with forward-forward and backpropagation training","paper_url":"/paper/integrating-convolutional-layers-and-biformer","paper_date":"2025-02-28","arxiv_id":null,"code_links":[{"title":"akianfar/Deep-CBN","url":"https://github.com/akianfar/Deep-CBN"}],"syntology":null}},{"leaderboard":"/sota/molecular-property-prediction-on-clearance","slug":"molecular-property-prediction-on-clearance","dataset":"Clearance","dataset_url":null,"rows_in_archive":2,"metrics":["RMSE"],"first_row_in_archive_order":{"model":"SPMM","paper_title":"Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model","paper_url":"/paper/molecular-structure-property-co-trained","paper_date":"2022-11-19","arxiv_id":"2211.10590","code_links":[{"title":"jinhojsk515/SPMM","url":"https://github.com/jinhojsk515/SPMM"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/molecular-property-prediction-on-pcba","slug":"molecular-property-prediction-on-pcba","dataset":"PCBA","dataset_url":"/dataset/pcba","rows_in_archive":2,"metrics":["ROC-AUC"],"first_row_in_archive_order":{"model":"DumplingGNN","paper_title":"Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure","paper_url":"/paper/dumpling-gnn-hybrid-gnn-enables-better-adc","paper_date":"2024-09-23","arxiv_id":"2410.05278","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/moleculenet","name":"MoleculeNet","full_name":"","num_papers_in_archive":240},{"url":"/dataset/qm9","name":"QM9","full_name":"","num_papers_in_archive":76},{"url":"/dataset/tox21-1","name":"Tox21","full_name":"","num_papers_in_archive":30},{"url":"/dataset/bbbp-scaffold","name":"BBBP (Blood-Brain Barrier Penetration)","full_name":"","num_papers_in_archive":28},{"url":"/dataset/esol-scaffold","name":"ESOL (Estimated SOLubility)","full_name":"","num_papers_in_archive":25},{"url":"/dataset/freesolv-scaffold","name":"FreeSolv (Free Solvation)","full_name":"","num_papers_in_archive":24},{"url":"/dataset/qm7","name":"QM7","full_name":"","num_papers_in_archive":24},{"url":"/dataset/bace-scaffold","name":"BACE (β-secretase enzyme)","full_name":"","num_papers_in_archive":22},{"url":"/dataset/qm9-charge-densities-and-energies-calculated","name":"HIV (Human Immunodeficiency Virus)","full_name":"","num_papers_in_archive":20},{"url":"/dataset/md22","name":"MD22","full_name":"MD22","num_papers_in_archive":20},{"url":"/dataset/clintox","name":"clintox","full_name":"","num_papers_in_archive":19},{"url":"/dataset/sider","name":"SIDER","full_name":"SIDER","num_papers_in_archive":19},{"url":"/dataset/molecule3d","name":"Molecule3D","full_name":"","num_papers_in_archive":17},{"url":"/dataset/toxcast-scaffold","name":"ToxCast (Toxicity Forecaster)","full_name":"","num_papers_in_archive":15},{"url":"/dataset/muv","name":"MUV","full_name":"","num_papers_in_archive":12},{"url":"/dataset/qm8","name":"QM8","full_name":"","num_papers_in_archive":6},{"url":"/dataset/guacamol","name":"Guacamol","full_name":"Guacamol","num_papers_in_archive":5},{"url":"/dataset/pcba","name":"PCBA","full_name":"","num_papers_in_archive":4},{"url":"/dataset/photoswitch","name":"Photoswitch","full_name":"","num_papers_in_archive":3},{"url":"/dataset/multi-labelled-smiles-odors-dataset","name":"Multi-Labelled SMILES Odors dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pubchem18","name":"PubChem18","full_name":"PubChem 2018","num_papers_in_archive":1}],"subtasks":[{"url":"/task/3d-geometry-prediction","name":"3D Geometry Prediction"},{"url":"/task/mixture-property-prediction","name":"mixture property prediction"},{"url":"/task/nmr-j-coupling","name":"NMR J-coupling"},{"url":"/task/odor-descriptor-prediction","name":"Odor Descriptor Prediction"}],"parent_tasks":[{"url":"/task/atomistic-description","name":"Atomistic Description"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":199,"tagged_in_all":354,"items":[{"url":"/paper/graph-attention-networks","title":"Graph Attention Networks","date":"2017-10-30","arxiv_id":"1710.10903","repositories_listed":93,"syntology":{"n":106,"n_ran":50,"n_unverified":56,"n_pointer_only":43}},{"url":"/paper/semi-supervised-classification-with-graph","title":"Semi-Supervised Classification with Graph Convolutional Networks","date":"2016-09-09","arxiv_id":"1609.02907","repositories_listed":55,"syntology":{"n":58,"n_ran":31,"n_unverified":27,"n_pointer_only":22}},{"url":"/paper/neural-message-passing-for-quantum-chemistry","title":"Neural Message Passing for Quantum Chemistry","date":"2017-04-04","arxiv_id":"1704.01212","repositories_listed":20,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/how-powerful-are-graph-neural-networks","title":"How Powerful are Graph Neural Networks?","date":"2018-10-01","arxiv_id":"1810.00826","repositories_listed":19,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":5}},{"url":"/paper/pre-training-graph-neural-networks","title":"Strategies for Pre-training Graph Neural Networks","date":"2019-05-29","arxiv_id":"1905.12265","repositories_listed":11,"syntology":{"n":14,"n_ran":10,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/how-attentive-are-graph-attention-networks","title":"How Attentive are Graph Attention Networks?","date":"2021-05-30","arxiv_id":"2105.14491","repositories_listed":8,"syntology":{"n":16,"n_ran":6,"n_unverified":10,"n_pointer_only":1}},{"url":"/paper/principal-neighbourhood-aggregation-for-graph","title":"Principal Neighbourhood Aggregation for Graph Nets","date":"2020-04-12","arxiv_id":"2004.05718","repositories_listed":8,"syntology":{"n":55,"n_ran":33,"n_unverified":22,"n_pointer_only":48}},{"url":"/paper/autogluon-tabular-robust-and-accurate-automl","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","date":"2020-03-13","arxiv_id":"2003.06505","repositories_listed":7,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/do-transformers-really-perform-bad-for-graph","title":"Do Transformers Really Perform Bad for Graph Representation?","date":"2021-06-09","arxiv_id":"2106.05234","repositories_listed":5,"syntology":null},{"url":"/paper/infograph-unsupervised-and-semi-supervised","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","date":"2019-07-31","arxiv_id":"1908.01000","repositories_listed":5,"syntology":null},{"url":"/paper/moleculenet-a-benchmark-for-molecular-machine","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","date":"2017-03-02","arxiv_id":"1703.00564","repositories_listed":5,"syntology":null},{"url":"/paper/a-molecular-multimodal-foundation-model","title":"A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language","date":"2022-09-12","arxiv_id":"2209.05481","repositories_listed":4,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/equiformer-equivariant-graph-attention","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","date":"2022-06-23","arxiv_id":"2206.11990","repositories_listed":4,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/recipe-for-a-general-powerful-scalable-graph","title":"Recipe for a General, Powerful, Scalable Graph Transformer","date":"2022-05-25","arxiv_id":"2205.12454","repositories_listed":4,"syntology":{"n":21,"n_ran":3,"n_unverified":18,"n_pointer_only":0}},{"url":"/paper/are-learned-molecular-representations-ready","title":"Analyzing Learned Molecular Representations for Property Prediction","date":"2019-04-02","arxiv_id":"1904.01561","repositories_listed":4,"syntology":{"n":15,"n_ran":3,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/triplet-interaction-improves-graph","title":"Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers","date":"2024-02-07","arxiv_id":"2402.04538","repositories_listed":3,"syntology":{"n":13,"n_ran":10,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/isotropic-gaussian-processes-on-finite-spaces","title":"Isotropic Gaussian Processes on Finite Spaces of Graphs","date":"2022-11-03","arxiv_id":"2211.01689","repositories_listed":3,"syntology":null},{"url":"/paper/molecule3d-a-benchmark-for-predicting-3d","title":"Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphs","date":"2021-09-30","arxiv_id":"2110.01717","repositories_listed":3,"syntology":null},{"url":"/paper/chemberta-large-scale-self-supervised","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","date":"2020-10-19","arxiv_id":"2010.09885","repositories_listed":3,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/grover-self-supervised-message-passing","title":"Self-Supervised Graph Transformer on Large-Scale Molecular Data","date":"2020-06-18","arxiv_id":"2007.02835","repositories_listed":3,"syntology":null},{"url":"/paper/guacamol-benchmarking-models-for-de-novo","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","date":"2018-11-22","arxiv_id":"1811.09621","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/gotennet-rethinking-efficient-3d-equivariant","title":"GotenNet: Rethinking Efficient 3D Equivariant Graph Neural Networks","date":"2025-04-24","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/publishing-neural-networks-in-drug-discovery","title":"Publishing Neural Networks in Drug Discovery Might Compromise Training Data Privacy","date":"2024-10-22","arxiv_id":"2410.16975","repositories_listed":2,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":6}},{"url":"/paper/scikit-fingerprints-easy-and-efficient","title":"Scikit-fingerprints: easy and efficient computation of molecular fingerprints in Python","date":"2024-07-18","arxiv_id":"2407.13291","repositories_listed":2,"syntology":null},{"url":"/paper/the-role-of-model-architecture-and-scale-in","title":"The Role of Model Architecture and Scale in Predicting Molecular Properties: Insights from Fine-Tuning RoBERTa, BART, and LLaMA","date":"2024-05-02","arxiv_id":"2405.00949","repositories_listed":2,"syntology":null},{"url":"/paper/comparative-analysis-of-llama-and-chatgpt","title":"Can Large Language Models Understand Molecules?","date":"2024-01-05","arxiv_id":"2402.00024","repositories_listed":2,"syntology":null},{"url":"/paper/asymmetric-contrastive-multimodal-learning","title":"Advancing Drug Discovery with Enhanced Chemical Understanding via Asymmetric Contrastive Multimodal Learning","date":"2023-11-11","arxiv_id":"2311.06456","repositories_listed":2,"syntology":null},{"url":"/paper/lo-hi-practical-ml-drug-discovery-benchmark-1","title":"Lo-Hi: Practical ML Drug Discovery Benchmark","date":"2023-10-10","arxiv_id":"2310.06399","repositories_listed":2,"syntology":null},{"url":"/paper/on-the-stability-of-expressive-positional","title":"On the Stability of Expressive Positional Encodings for Graphs","date":"2023-10-04","arxiv_id":"2310.02579","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/uncertainty-quantification-for-molecular","title":"Uncertainty Quantification for Molecular Property Predictions with Graph Neural Architecture Search","date":"2023-07-19","arxiv_id":"2307.10438","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","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)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}