Five computational developability guidelines for therapeutic antibody profiling
Open accessPublished version of a preprint
Abstract
Therapeutic mAbs must not only bind to their target but must also be free from "developability issues" such as poor stability or high levels of aggregation. While small-molecule drug discovery benefits from Lipinski's rule of five to guide the selection of molecules with appropriate biophysical properties, there is currently no in silico analog for antibody design. Here, we model the variable domain structures of a large set of post-phase-I clinical-stage antibody therapeutics (CSTs) and calculate in silico metrics to estimate their typical properties. In each case, we contextualize the CST distribution against a snapshot of the human antibody gene repertoire. We describe guideline values for five metrics thought to be implicated in poor developability: the total length of the complementarity-determining regions (CDRs), the extent and magnitude of surface hydrophobicity, positive charge and negative charge in the CDRs, and asymmetry in the net heavy- and light-chain surface charges. The guideline cutoffs for each property were derived from the values seen in CSTs, and a flagging system is proposed to identify nonconforming candidates. On two mAb drug discovery sets, we were able to selectively highlight sequences with developability issues. We make available the Therapeutic Antibody Profiler (TAP), a computational tool that builds downloadable homology models of variable domain sequences, tests them against our five developability guidelines, and reports potential sequence liabilities and canonical forms. TAP is freely available at opig.stats.ox.ac.uk/webapps/sabdab-sabpred/TAP.php.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Established structural bioinformatics methods such as homology modelling, protein-protein docking or protein interface prediction are already used for rational antibody design.
“Established structural bioinformatics methods such as homology modelling [6, 7], protein–protein docking [8, 9] or protein interface prediction [10] are already used for rational antibody design [11–13].”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
Natural preferences in antibody repertoires can be used as a reference to assess the biophysical properties of therapeutic antibodies or to develop naturally focused surface display libraries.
“Among others, such natural preferences can be used as a reference to assess the biophysical properties of therapeutic antibodies [13] or to develop naturally focused surface display libraries [26].”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
Resources exist that curate the therapeutic antibody information, such as TABS and SAbDab-Therapeutic-Antibodies.
“Resources exist that curate the therapeutic antibody information, such as TABS (https://tabs.craic.com/) and SAbDab-Therapeutic-Antibodies [13].”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
Accurate structural information can be used during Lead Optimization to assess developability indicators such as hydrophobicity that rely on accurate models of the molecular surface of the paratope and epitope.
“Accurate structural information can be used during the Lead Optimization stage to assess various developability indicators, such as hydrophobicity [13] that rely on accurate models of the molecular surface of the paratope and epitope.”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
Among Raybould et al.'s guidelines, a structure-based hydrophobicity score is calculated and compared to the distribution of the same score in naturally sourced NGS sequences.
“Among these a structure-based hydrophobicity score is calculated and the value is then compared to the distribution of the same score in naturally sourced NGS sequences.”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
Raybould et al.'s work demonstrates a new paradigm in employing naturally-sourced NGS data to guide therapeutic antibody development.
“This work demonstrates a new paradigm in employing the vast amount of naturally-sourced NGS data to guide therapeutic antibody development.”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
Score values diverging significantly from the natural distribution are highlighted and associated sequences flagged for developability risk.
“Score values diverging significantly from the natural distribution are highlighted and the associated sequences flagged for developability risk.”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
An alternative approach to developability pre-selection is to use natural antibody sequences under the assumption that they have favorable biophysical properties.
“An alternative approach is to use natural antibody sequences under the assumption that they have favorable biophysical properties [13].”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
The field currently benefits from a steady stream of new data from NGS of B-cell Receptors and increasing resources for downloading such data.
“In this respect, the field currently benefits from a steady stream of new data from NGS of B-cell Receptors (BCRs, to be used as proxy for antibodies) [212, 213] and there is an increasing number of resources available for downloading such data [17], which are being used to analyze therapeutic antibodies [13].”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
Raybould et al. stipulate five computational guidelines to define favorable biophysical properties in antibody therapeutics.
“In this study Raybould et al. stipulate five computational guidelines to define favorable biophysical properties in antibody therapeutics.”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [13]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Berman, H. M. (2000) · Nucleic Acids Research · doi:10.1093/nar/28.1.235 · Cited by 40,196 · see citing works
A simple method for displaying the hydropathic character of a protein
Kyte, J., & Doolittle, R. F. (1982) · Journal of Molecular Biology · doi:10.1016/0022-2836(82)90515-0 · Cited by 22,694 · see citing works
Lipinski, C. A., Lombardo, F., Dominy, B. W., & Feeney, P. J. (2001) · Advanced Drug Delivery Reviews · doi:10.1016/s0169-409x(00)00129-0 · Cited by 18,139 · see citing works
Ultrastructural Characterization of the Lower Motor System in a Mouse Model of Krabbe Disease
Cappello, V., Marchetti, L., Parlanti, P., Landi, S., Tonazzini, I., Cecchini, M., Piazza, V., & Gemmi, M. (2016) · Scientific Reports · doi:10.1038/s41598-016-0001-8 · Cited by 13,097 · see citing works
Lipinski, C. A., Lombardo, F., Dominy, B. W., & Feeney, P. J. (1997) · Advanced Drug Delivery Reviews · doi:10.1016/s0169-409x(96)00423-1 · Cited by 11,484 · see citing works
Solvation energy in protein folding and binding
Eisenberg, D., & McLachlan, A. (1986) · Nature · doi:10.1038/319199a0 · Cited by 1,775 · see citing works
Experimentally determined hydrophobicity scale for proteins at membrane interfaces
Wimley, W. C., & White, S. H. (1996) · Nature Structural & Molecular Biology · doi:10.1038/nsb1096-842 · Cited by 1,657 · see citing works
Canonical structures for the hypervariable regions of immunoglobulins
Chothia, C., & Lesk, A. M. (1987) · Journal of Molecular Biology · doi:10.1016/0022-2836(87)90412-8 · Cited by 1,406 · see citing works
Environment and exposure to solvent of protein atoms. Lysozyme and insulin
Shrake, A., & Rupley, J. A. (1973) · Journal of Molecular Biology · doi:10.1016/0022-2836(73)90011-9 · Cited by 1,387 · see citing works
Conformations of immunoglobulin hypervariable regions
Chothia, C., Lesk, A. M., Tramontano, A. L., Levitt, M., Smith‐Gill, S. J., Air, G. M., Sheriff, S., PADLAN, E. A., Davies, D. R., Tulip, W. R., et al. (1989) · Nature · doi:10.1038/342877a0 · Cited by 1,185 · see citing works
Recognition of transmembrane helices by the endoplasmic reticulum translocon
Hessa, T., Kim, H., Bihlmaier, K., Lundin, C., Boekel, J., Andersson, H. M., Nilsson, I., White, S. H., & von HEIJNE, G. (2005) · Nature · doi:10.1038/nature03216 · Cited by 996 · see citing works
Lefranc, M., Pommie, C., Ruíz, M., Giudicelli, V., Foulquier, E., Truong, L., Contet, V., & Lefranc, G. (2002) · Developmental & Comparative Immunology · doi:10.1016/s0145-305x(02)00039-3 · Cited by 823 · see citing works
Lefranc, M., Pommie, C., Kaas, Q., Duprat, É., Bosc, N., Guiraudou, D., Jean, C., Ruíz, M., da Piedade, I., Rouard, M., et al. (2004) · Developmental & Comparative Immunology · doi:10.1016/j.dci.2004.07.003 · Cited by 808 · see citing works
SAbDab: the structural antibody database
Dunbar, J., Krawczyk, K., Leem, J., Baker, T., Fuchs, A., Georges, G., Shi, J., & Deane, C. M. (2014) · Nucleic Acids Research · doi:10.1093/nar/gkt1043 · Cited by 674 · see citing works
Self-citationBiophysical properties of the clinical-stage antibody landscape
Jain, T., Sun, T., Durand, S., Hall, A., Houston, N. R., Nett, J. H., Sharkey, B., Bobrowicz, B., Caffry, I., Yu, Y., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1616408114 · Cited by 629 · cited 2× · see citing works
“As a dataset of mAbs unlikely to suffer with developability issues, we used the variable domain heavy- and light-chain sequences of 137 clinical-stage antibody therapeutics (137 CSTs) (18).”
BackgroundMethodDesign of therapeutic proteins with enhanced stability
Chennamsetty, N., Voynov, V., Kayser, V., Helk, B., & Trout, B. L. (2009) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0904191106 · Cited by 597 · see citing works
Petrescu, A. (2003) · Glycobiology · doi:10.1093/glycob/cwh008 · Cited by 469 · see citing works
A new clustering of antibody CDR loop conformations
North, B., Lehmann, A., & Dunbrack, R. L. (2011) · Journal of Molecular Biology · doi:10.1016/j.jmb.2010.10.030 · Cited by 380 · see citing works
Black, S. D., & Mould, D. R. (1991) · Analytical Biochemistry · doi:10.1016/0003-2697(91)90045-u · Cited by 376 · see citing works
Empirical Correlation Between Hydrophobic Free Energy and Aqueous Cavity Surface Area
Reynolds, J. A., Gilbert, D. B., & Tanford, C. (1974) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.71.8.2925 · Cited by 292 · see citing works
Yadav, S., Laue, T. M., Kalonia, D. S., Singh, S. N., & Shire, S. J. (2012) · Molecular Pharmaceutics · doi:10.1021/mp200566k · Cited by 282 · see citing works
Sharma, V. K., Patapoff, T. W., Kabakoff, B., Pai, S., Hilario, E., Zhang, B., Li, C., Borisov, O., Kelley, R. F., Chorny, I., et al. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1421779112 · Cited by 256 · see citing works
Kovaltsuk, A., Leem, J., Kelm, S., Snowden, J., Deane, C. M., & Krawczyk, K. (2018) · The Journal of Immunology · doi:10.4049/jimmunol.1800708 · Cited by 247 · see citing works
Self-citationDevelopability Assessment During the Selection of Novel Therapeutic Antibodies
Jarasch, A., Koll, H., Regula, J. T., Bader, M., Papadimitriou, A., & Kettenberger, H. (2015) · Journal of Pharmaceutical Sciences · doi:10.1002/jps.24430 · Cited by 242 · see citing works
ABodyBuilder: automated antibody structure prediction with data-driven accuracy estimation
Leem, J., Dunbar, J., Georges, G., Shi, J., & Deane, C. M. (2016) · mAbs · doi:10.1080/19420862.2016.1205773 · Cited by 238 · see citing works
Self-citationDevelopability Index: A Rapid In Silico Tool for the Screening of Antibody Aggregation Propensity
Lauer, T. M., Agrawal, N. J., Chennamsetty, N., Egodage, K. L., Helk, B., & Trout, B. L. (2011) · Journal of Pharmaceutical Sciences · doi:10.1002/jps.22758 · Cited by 206 · see citing works
DeKosky, B. J., Lungu, O. I., Park, D., Johnson, E. L., Charab, W., Chrysostomou, C., Kuroda, D., Ellington, A. D., Ippolito, G. C., Gray, J. J., et al. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1525510113 · Cited by 189 · see citing works
Xu, Y., Roach, W., Sun, T., Jain, T. S., Prinz, B., Yu, T. Y., Torrey, J., Thomas, J., Bobrowicz, P., Vásquez, M., et al. (2013) · Protein Engineering Design and Selection · doi:10.1093/protein/gzt047 · Cited by 178 · see citing works
Assessment of chemical modifications of sites in the CDRs of recombinant antibodies
Haberger, M., Bomans, K., Diepold, K., Hook, M., Gassner, J., Schlothauer, T., Zwick, A., Spick, C., Kepert, J. F., Hienz, B., et al. (2014) · mAbs · doi:10.4161/mabs.27876 · Cited by 163 · see citing works
Sydow, J. F., Lipsmeier, F., Larraillet, V., Hilger, M., Mautz, B., Mølhøj, M., Küntzer, J., Klostermann, S., Schoch, J., Voelger, H. R., et al. (2014) · PLoS ONE · doi:10.1371/journal.pone.0100736 · Cited by 161 · see citing works
Second antibody modeling assessment (AMA-II)
Almagro, J. C., Teplyakov, A., Luo, J., Sweet, R. W., Kodangattil, S., Hernandez‐Guzman, F., & Gilliland, G. L. (2014) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.24567 · Cited by 144 · see citing works
Datta‐Mannan, A., Thangaraju, A., Leung, D., Tang, Y., Witcher, D. R., Lu, J., & Wroblewski, V. J. (2015) · mAbs · doi:10.1080/19420862.2015.1016696 · Cited by 141 · see citing works
Dobson, C., Devine, P. W. A., Phillips, J. J., Higazi, D. R., Lloyd, C., Popovic, B., Arnold, J., Buchanan, A. G., Lewis, A. R., Goodman, J., et al. (2016) · Scientific Reports · doi:10.1038/srep38644 · Cited by 121 · see citing works
Self-citationAggregation risk prediction for antibodies and its application to biotherapeutic development
Obrezanova, O., Arnell, A., de la Cuesta, R. G., Berthelot, M. E., Gallagher, T. R., Zurdo, J., & Stallwood, Y. (2015) · mAbs · doi:10.1080/19420862.2015.1007828 · Cited by 107 · see citing works
Heiden, J. A. V., Stathopoulos, P., Zhou, J. Q., Chen, L., Gilbert, T. J., Bolen, C. R., Barohn, R. J., Dimachkie, M. M., Ciafaloni, E., Broering, T. J., et al. (2017) · The Journal of Immunology · doi:10.4049/jimmunol.1601415 · Cited by 103 · see citing works
Courtois, F., Agrawal, N. J., Lauer, T. M., & Trout, B. L. (2015) · mAbs · doi:10.1080/19420862.2015.1112477 · Cited by 99 · see citing works
Tsuchiya, Y., & Mizuguchi, K. (2016) · Protein Science · doi:10.1002/pro.2874 · Cited by 86 · see citing works
Shi, B., Ma, L., He, X., Wang, X., Wang, P., Zhou, L., & Yao, X. (2014) · Theoretical Biology and Medical Modelling · doi:10.1186/1742-4682-11-30 · Cited by 81 · see citing works
Jain, T., Boland, T., Lilov, A., Burnina, I., Brown, M., Xu, Y., & Vásquez, M. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx519 · Cited by 61 · see citing works
Length-independent structural similarities enrich the antibody CDR canonical class model
Nowak, J., BAKER, T. S., Georges, G. J., Kelm, S., Klostermann, S., Shi, J., Sridharan, S., & Deane, C. M. (2016) · mAbs · doi:10.1080/19420862.2016.1158370 · Cited by 54 · see citing works
Self-citationThe Use of Amino Acid Patterns of Classified Helices and Strands in Secondary Structure Prediction
Zhu, Z., & Blundell, T. L. (1996) · Journal of Molecular Biology · doi:10.1006/jmbi.1996.0397 · Cited by 43 · see citing works
Popovic, B., Gibson, S. J., Senussi, T., et al. (2017) · Protein Engineering Design and Selection · doi:10.1093/protein/gzx001 · Cited by 10 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
ProGen2: Exploring the boundaries of protein language models
Nijkamp, E., Ruffolo, J. A., Weinstein, E. N., Naik, N., & Madani, A. (2023) · Cell Systems · doi:10.1016/j.cels.2023.10.002 · Cited by 480 · see citing works
Mason, D. M., Friedensohn, S., Weber, C. R., Jordi, C., Wagner, B., Meng, S. M., Ehling, R. A., Bonati, L., Dahinden, J., Gainza, P., et al. (2021) · Nature Biomedical Engineering · doi:10.1038/s41551-021-00699-9 · Cited by 308 · see citing works
Predicting antibody developability profiles through early stage discovery screening
Bailly, M., Mieczkowski, C., Juan, V., Metwally, E., Tomazela, D., Baker, J., Uchida, M., Kofman, E., Raoufi, F., Motlagh, S., et al. (2020) · mAbs · doi:10.1080/19420862.2020.1743053 · Cited by 228 · see citing works
Computational approaches to therapeutic antibody design: established methods and emerging trends
Norman, R. A., Ambrosetti, F., Bonvin, A. M. J. J., Colwell, L. J., Kelm, S., Kumar, S., & Krawczyk, K. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbz095 · Cited by 219 · see citing works
“In this respect, the field currently benefits from a steady stream of new data from NGS of B-cell Receptors (BCRs, to be used as proxy for antibodies) [212, 213] and there is an increasing number of resources available for downloading such data [17], which are being used to analyze therapeutic antibodies [13].”
BackgroundMethodInfluentialSelf-citationAntibody structure prediction using interpretable deep learning
Ruffolo, J. A., Sulam, J., & Gray, J. J. (2022) · Patterns · doi:10.1016/j.patter.2021.100406 · Cited by 216 · see citing works
Thera-SAbDab: the therapeutic structural antibody database
Raybould, M. I. J., Marks, C., Lewis, A. P., Shi, J., Bujotzek, A., Taddese, B., & Deane, C. M. (2020) · Nucleic Acids Research · doi:10.1093/nar/gkz827 · Cited by 199 · see citing works
“Links to appropriate SAbPred (21) informatics tools (such as ABodyBuilder (22) for variable domain structure modelling, and TAP (18) for developability assessment) are also provided.”
BackgroundMethodDLAB-deep learning methods for structure-based virtual screening of antibodies
Schneider, C., Buchanan, A., Taddese, B., & Deane, C. M. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btab660 · Cited by 102 · see citing works
Self-citationIn silico proof of principle of machine learning-based antibody design at unconstrained scale
Akbar, R., Robert, P. A., Weber, C. R., Widrich, M., Frank, R., Pavlović, M., Scheffer, L., Chernigovskaya, M., Snapkov, I., Slabodkin, A., et al. (2022) · mAbs · doi:10.1080/19420862.2022.2031482 · Cited by 94 · see citing works
Brown, A. J., Snapkov, I., Akbar, R., Pavlović, M., Miho, E., Sandve, G. K., & Greiff, V. (2019) · Molecular Systems Design & Engineering · doi:10.1039/c9me00071b · Cited by 59 · see citing works
Grinshpun, B., Thorsteinson, N., Pereira, J. N., Rippmann, F., Nannemann, D., Sood, V. D., & Fomekong Nanfack, Y. (2021) · mAbs · doi:10.1080/19420862.2021.1932230 · Cited by 52 · see citing works
Lai, P.-K., Fernando, A., Cloutier, T. K., Kingsbury, J. S., Gokarn, Y., Halloran, K. T., Calero-Rubio, C., & Trout, B. L. (2021) · Journal of Pharmaceutical Sciences · doi:10.1016/j.xphs.2020.12.014 · Cited by 45 · see citing works
Thorsteinson, N., Gunn, J. R., Kelly, K., Long, W., & Labute, P. (2021) · mAbs · doi:10.1080/19420862.2021.1981805 · Cited by 42 · see citing works
Looking for therapeutic antibodies in next generation sequencing repositories
Krawczyk, K., Raybould, M., Kovaltsuk, A., & Deane, C. M. (2019) · doi:10.1101/572958 · Cited by 29 · see citing works
Self-citationThe therapeutic antibody profiler for computational developability assessment
Raybould, M. I. J., & Deane, C. M. (2022) · Methods in molecular biology · doi:10.1007/978-1-0716-1450-1_5 · Cited by 25 · see citing works
Self-citationPredicting the conformational flexibility of antibody and T-cell receptor CDRs
Spoendlin, F. C., Fernández-Quintero, M. L., Raghavan, S. S. R., Turner, H. L., Gharpure, A., Loeffler, J. R., Wong, W. K., Bujotzek, A., Georges, G., Ward, A. B., et al. (2025) · doi:10.1101/2025.03.19.644119 · Cited by 20 · see citing works
Self-citation
- Authors
- Raybould, M. I. J., Marks, C., Krawczyk, K., Taddese, B., Nowak, J., Lewis, A. P., Bujotzek, A., Shi, J., & Deane, C. M.
- Affiliations
- University of Oxford (GB)
- Department of Antibody Discovery and Protein Engineering, MedImmune, Cambridge CB21 6GH, United Kingdom;
- Department of Statistics, University of Oxford, Oxford OX1 3LB, United Kingdom;
- GlaxoSmithKline (United Kingdom) (GB)
- Roche Pharma Research and Early Development, Large Molecule Research, Roche Innovation Center Munich, DE-82377 Penzberg, Germany;
- UCB Pharma (United Kingdom) (GB)
- Corresponding author
- Deane, Charlotte M.
- ORCID
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2019-02-14
- Volume
- 116
- Issue
- 10
- Pages
- 4025-4030
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC6410772
- OpenAlex
- W2913847447
- Cited by
- 357
- References
- 42
- Citations by year
- 2026: 60 · 2025: 53 · 2024: 56 · 2023: 58 · 2022: 45 · 2021: 41 · 2020: 26 · 2019: 18
- FWCI
- 21.48
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- RCUK | Engineering and Physical Sciences Research Council (EP/L016044/1)
- RCUK | Medical Research Council (EP/L016044/1)
- Topics
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Monoclonal and Polyclonal Antibodies Research
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Keywords
- therapeutic monoclonal antibodies, developability, antibody design, hypervariable region, surface hydrophobicity, surface charge, antibody stability, aggregation, homology modeling
- MeSH terms
- Antibodies, Monoclonal, Computer Simulation, Humans, Models, Molecular, Complementarity Determining Regions, Drug Discovery
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
