Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

Rafael Gómez-Bombarelli, Jennifer N. Wei, David Duvenaud, et al. · ACS Central Science · 2018 · chemistry · 10.1021/acscentsci.7b00572 · record gomez-bombarelli2018-molecular-design
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (xml); every evidence string verified as an exact substring of that text before merging. method is system-or-tool-building: the paper builds, trains and benchmarks a model rather than testing a hypothesis, though its evaluation (property-prediction MAE table, genetic-algorithm baseline comparison) is computational-experimental. The 'contradicts' relation records an explicitly stated deficiency of the prior discrete-search approach that motivates the method; it is a stated limitation of that prior work, not a refutation of a specific published result. 2026-08-12, 2026-08-15 and 2026-08-28 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node. Update, 15 September 2026: EXCEPTION, measured with the merge gate's own predicate (Paper.locate): 3 quote(s) on this record are not found as one exact string in the current staged text - content_tags.statistics[0].evidence, content_tags.statistics[1].evidence, content_tags.statistics[3].evidence. The sentence above does not hold for them as written. Where a row records why - the quote is grounded in another copy of the paper, joins two passages with an ellipsis, or differs from the staged text by extraction noise - that note stays on the row.

Some words in these quotes contain the wrong character. The PDF this text was extracted from substituted 1 character inside a word — a currency sign or a stray accent where a letter pair belongs, as in signi¢cantly for significantly, or a single ligature glyph, as in conﬁdence. They are valid characters in the wrong place, so they survive every encoding check. The quotes keep them for the same reason as above, and a search of this page will not find the affected words.

2 quotations on this page contain a reference number where the paper printed a superscript. This journal style prints citations as raised numerals — parameters^12,13 — and the extraction flattened them into the line, so the sentence reads parameters 12 , 13 . The digits are citation markers and not part of what the author wrote. The quotes keep them for the same reason they keep every other extraction fault: a quote is reproduced exactly or it proves nothing.

3 quotes on this page were cut from a different copy of this article. This project holds two extractions of this paper: the plain text every other quote here is anchored in, and the publisher’s own HTML edition, which we are not licensed to republish. They are verbatim in the second and cannot be found in the first — not because the tagging is wrong, but because the extraction damaged the passage: a page number dropped into the middle of a number, a formula moved out of its sentence, a ligature where two letters belong. The record names the copy for each one. The quote is the paper’s; the extraction is not.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.

Other fields define these differently the same word, defined another way in another discipline
representation 47 fields · standard-deviation 3 fields · SMILES 2 fields · autoencoder 2 fields · InChI 2 fields

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 26 concept tags on this paper, 23 are grounded in a quoted sentence. 22 carry the tagger's gloss of what the term means in this paper, which is not something the article can license.

molecular representation variational autoencoder generative chemistry latent space optimization latent representation SMILES InChI autoencoder information bottleneck chemical space gradient-based optimization inverse design challenge Virtual screening encoder network decoder network property prediction task latent space dead areas doubly probabilistic model spherical interpolation slerp synthetic accessibility score Quantitative Estimation of Drug-likeness Gaussian process model joint training for property prediction teacher forcing encoding molecules into a continuous latent space so new molecules are generated by decoding/interpolating vectors (and properties optimized by moving in that space) an information bottleneck forces the network to keep only what is statistically salient - the compression is what makes the vector a representation rather than a copy the variational penalty fills in the space: adding noise to the encoding forces the decoder to handle points between molecules, so the space has no dead areas training the property predictor JOINTLY is what aligns the geometry with the chemistry - otherwise moving in the space would not move the property invalid outputs are filtered rather than prevented - the decoder is allowed to be wrong and a cheminformatics toolkit discards the failures molecules continuous representation encoder decoder chemical latent optimization inverse design SMILES strings predictor continuous representation property values string representation Bayesian mean mean of regression regression model standard-deviation standard deviation system-or-tool-building

Legend

second reading	`alternatives`	an independent re-reading of a facet, recorded whether or not it agrees
relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
contribution	`contribution`	what the paper claims to add
control	`controls`	an experiment run to eliminate a rival explanation
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
object of study	`object_of_study`	what the paper is about — the thing it investigates
phenomenon	`phenomenon`	the effect or regularity under study
research question	`research_question`	the question the paper sets itself
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
transfer	`transfers`	a method or concept carried in from another field
unrecordable relation	`unhoused_relations`	a relation the paper asserts that this vocabulary cannot express, with the reason

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://doi.org/10.1021/acscentsci.7b00572. The reading view exists for the papers whose licence permits it.

Every tag on this page

alternatives 2 · claim_relations 5 · claim_type 1 · concept_edges 5 · concepts 23 · content_tags 22 · contribution 1 · controls 1 · limitations 10 · mechanisms 5 · method 1 · object_of_study 1 · phenomenon 1 · research_question 1 · senses 19 · transfers 3 · unhoused_relations 1

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; 2 of 5 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
object_of_study	Chemical space, and how to search it by turning molecules into vectors that can be optimised with gradients. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`object_of_study`		the paper's words
research_question	Molecular space is discrete and unstructured, so gradients cannot guide a search through it - can it be made continuous instead? Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`research_question`		the paper's words
contribution	An encoder/decoder/predictor trained jointly, so that molecules become points in a continuous space where optimisation and interpolation are ordinary operations. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`contribution`		the paper's words
claim_type	method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	automated molecular design in chemical space Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	system-or-tool-building Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: system-or-tool-building	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: encoding molecules into a continuous latent space so new molecules are generated by decoding/interpolating vectors (and properties optimized by moving in that space)	`mechanisms[0]`		the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: an information bottleneck forces the network to keep only what is statistically salient - the compression is what makes the vector a representation rather than a copy	`mechanisms[1]`	1.0	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: the variational penalty fills in the space: adding noise to the encoding forces the decoder to handle points between molecules, so the space has no dead areas	`mechanisms[2]`	1.0	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: training the property predictor JOINTLY is what aligns the geometry with the chemistry - otherwise moving in the space would not move the property	`mechanisms[3]`	0.9	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: invalid outputs are filtered rather than prevented - the decoder is allowed to be wrong and a cheminformatics toolkit discards the failures	`mechanisms[4]`	1.0	the tagger's words
limitations	optimization in molecular space is hard because the search space is large, discrete, and unstructured Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any claim of coverage over chemical space: Quotation withheld	`limitations[0]`		the tagger's words
limitations	Decoded molecules can be graph-valid but chemically undesirable. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the generated molecules: THE AUTOENCODER SOMETIMES PRODUCED MOLECULES THAT ARE FORMALLY VALID AS GRAPHS BUT CONTAIN MOIETIES THAT ARE NOT DESIRABLE BECAUSE OF STABILITY OR SYNTHETIC CONSTRAINTS	`limitations[1]`		the tagger's words
limitations	SMILES syntax fragility means the decoder still emits invalid molecules despite the variational constraint. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the decoder's output: THE CHARACTER-BY-CHARACTER NATURE OF THE SMILES REPRESENTATION AND THE FRAGILITY OF ITS INTERNAL SYNTAX CAN STILL RESULT IN THE OUTPUT OF INVALID strings	`limitations[2]`		the tagger's words
limitations	Requiring the decoder to learn SMILES validity makes the learning problem harder than it needs to be. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the learning problem as posed: FORCING THE DECODER TO PRODUCE VALID SMILES STRINGS MAKES THE LEARNING PROBLEM UNNECESSARILY HARD SINCE THE DECODER MUST ALSO IMPLICITLY LEARN WHICH STRINGS ARE VALID SMILES	`limitations[3]`		the tagger's words
limitations	Decoding succeeds only near known molecules; random latent points almost always fail. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any claim about generating novel molecules: THE PROBABILITY OF DECODING FROM A POINT IN LATENT SPACE IS DEPENDENT ON HOW CLOSE THIS POINT IS TO THE LATENT REPRESENTATIONS OF OTHER MOLECULES - a decoding rate of 73-79% NEAR known molecules	`limitations[4]`		the tagger's words
limitations	Property-prediction accuracy is only comparable to graph convolutions for some properties and is not fully optimised. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the property-prediction comparison: PERFORMANCE FOR ELECTRONIC PROPERTIES ARE SIMILAR TO GRAPH CONVOLUTIONS FOR SOME PROPERTIES, and accuracy COULD BE IMPROVED	`limitations[5]`		the tagger's words
limitations	The graph-output alternative the authors prefer is not yet solvable. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the graph-output alternative the authors prefer: BUILDING A NEURAL NETWORK WHICH CAN OUTPUT ARBITRARY GRAPHS IS AN OPEN PROBLEM	`limitations[6]`		the tagger's words
limitations	The decoder still emits chemically invalid strings, because SMILES syntax is fragile and the model works character by character. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. duplicate of: limitations[2] · what this limits: the same scope as limitations[2] - SMILES syntax fragility still yields invalid output	`limitations[7]`	1.0	the tagger's words
limitations	Without the variational constraint the latent space contains dead regions that decode to nothing valid. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the latent space without the variational constraint: IT MAY BE SPARSE AND MAY CONTAIN LARGE DEAD AREAS, WHICH DECODE TO INVALID SMILES STRINGS	`limitations[8]`	1.0	the tagger's words
limitations	The choice of string encoding is load-bearing and only partly explained - InChI performed substantially worse and the reason is offered as a presumption. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: every result in the paper, which is conditional on the encoding: WE ALSO TESTED InChI AS AN ALTERNATIVE STRING REPRESENTATION, BUT FOUND IT TO PERFORM SUBSTANTIALLY WORSE THAN SMILES, PRESUMABLY DUE TO A MORE COMPLEX SYNTAX THAT INCLUDES COUNTING AND ARITHMETIC	`limitations[9]`	1.0	the tagger's words
transfers	a variational autoencoder mapping molecules (SMILES strings) into a continuous latent space for automatic chemical design Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[0]`		the tagger's words
transfers	the variational autoencoder with recurrent encoder and decoder, taken from Bowman et al.'s work on English sentences and applied to molecules as strings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[1]`	1.0	the tagger's words
transfers	the idea that a low-dimensional continuous code supports interpolation and analogy, imported as the reason a molecular latent space should be navigable Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[2]`	1.0	the tagger's words
controls	only CANONICALISED SMILES strings used for training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the same molecule appearing as several different strings - SMILES is not unique, so an uncanonicalised set would teach the model that one compound is many, and inflate apparent diversity in the latent space the paper is about · outcome (stated by the tagger, no quotation): held	`controls[0]`	0.95	the tagger's words
concepts	variational autoencoder Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: variational autoencoder	`concepts[1]`		the paper's words
concepts	latent representation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: latent representation	`concepts[4]`	1.0	the paper's words
concepts	SMILES Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: SMILES	`concepts[5]`	1.0	the paper's words
concepts	InChI Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: InChI	`concepts[6]`	1.0	the paper's words
concepts	autoencoder Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: autoencoder	`concepts[7]`	1.0	the paper's words
concepts	information bottleneck Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: information bottleneck	`concepts[8]`	0.85	the paper's words
concepts	chemical space Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: chemical space	`concepts[9]`	1.0	the paper's words
concepts	gradient-based optimization Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: gradient-based optimization	`concepts[10]`	1.0	the paper's words
concepts	inverse design challenge Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: inverse design challenge	`concepts[11]`	0.95	the paper's words
concepts	Virtual screening Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Virtual screening	`concepts[12]`	0.95	the paper's words
concepts	encoder network Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: encoder network	`concepts[13]`	0.95	the paper's words
concepts	decoder network Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: decoder network	`concepts[14]`	0.95	the paper's words
concepts	property prediction task Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: property prediction task	`concepts[15]`	0.95	the paper's words
concepts	latent space Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: latent space	`concepts[16]`	0.95	the paper's words
concepts	dead areas Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: dead areas	`concepts[17]`	0.95	the paper's words
concepts	doubly probabilistic model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: doubly probabilistic model	`concepts[18]`	0.95	the paper's words
concepts	spherical interpolation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: spherical interpolation	`concepts[19]`	0.95	the paper's words
concepts	slerp Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: slerp	`concepts[20]`	0.95	the paper's words
concepts	synthetic accessibility score Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: synthetic accessibility score	`concepts[21]`	0.95	the paper's words
concepts	Quantitative Estimation of Drug-likeness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Quantitative Estimation of Drug-likeness	`concepts[22]`	0.95	the paper's words
concepts	Gaussian process model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Gaussian process model	`concepts[23]`	0.95	the paper's words
concepts	joint training for property prediction Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: joint training for property prediction	`concepts[24]`	0.95	the paper's words
concepts	teacher forcing Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: teacher forcing	`concepts[25]`	0.95	the paper's words
unhoused_relations	spherical interpolation → slerp Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. The parenthetical introduces slerp as the short name for spherical interpolation. This is an abbreviation/short-form relation: it is not class membership, containment, identity of two independently named concepts, distinction, contrast, operationalisation, causation, or renaming across fields.	`unhoused_relations[0]`	0.95	the tagger's words
senses	representation - DISCRETE: the molecule as a symbol string, which a chemist can read and a machine can turn back into a structure Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	representation - CONTINUOUS: the molecule as a real-valued vector, on which arithmetic and gradients are defined Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	representation - LATENT: specifically the compressed code inside the bottleneck, which is a representation because it discards, not because it depicts Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
senses	representation - as used across images, text, speech and music, where the same low-dimensional continuous code supports interpolation and analogy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[3]`	1.0	the tagger's words
senses	inverse design challenge - searching chemistry by mapping molecules into continuous neural representations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[4]`	0.95	the tagger's words
senses	Virtual screening - computationally assaying large libraries and experimentally testing selected leads Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[5]`	0.95	the tagger's words
senses	encoder network - converts each molecular string to a fixed-dimensional vector Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[6]`	0.95	the tagger's words
senses	decoder network - converts vectors back into molecular strings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[7]`	0.95	the tagger's words
senses	property prediction task - predicts molecular properties from the latent vector during joint training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[8]`	0.95	the tagger's words
senses	latent space - the encoder's vector space, functioning as a continuous molecular representation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[9]`	0.95	the tagger's words
senses	dead areas - sparse latent-space regions that decode into invalid SMILES strings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[10]`	0.95	the tagger's words
senses	doubly probabilistic model - stochastic in both encoding noise and decoder output sampling Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[11]`	0.95	the tagger's words
senses	spherical interpolation - follows a circular arc to remain in high-probability latent-space regions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[12]`	0.95	the tagger's words
senses	slerp - the paper's short form for spherical interpolation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[13]`	0.95	the tagger's words
senses	synthetic accessibility score - SAS, a property used to compare generated molecule sets Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[14]`	0.95	the tagger's words
senses	Quantitative Estimation of Drug-likeness - QED, ranging from zero to one with higher values more drug-like Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[15]`	0.95	the tagger's words
senses	Gaussian process model - a lightweight smooth-function model used to smooth the optimization landscape Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[16]`	0.95	the tagger's words
senses	joint training for property prediction - organizes latent-space molecules by property value Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[17]`	0.95	the tagger's words
senses	teacher forcing - feeds the previous sampled character to the GRU, improving valid outputs but complicating training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[18]`	0.95	the tagger's words
alternatives	method: computational-model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. a second reading DIFFERING from the recorded value. Recorded: system-or-tool-building — note: a second reading, verbatim-verified, disagreeing with the value on the record. Not applied - a person decides.	`alternatives.method`		the tagger's words
alternatives	phenomenon: the discreteness of chemical space as an obstacle to searching it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. a second reading DIFFERING from the recorded value. Recorded: automated molecular design in chemical space — note: a second reading, verbatim-verified, disagreeing with the value on the record. Not applied - a person decides.	`alternatives.phenomenon`		the tagger's words
claim_relations	builds-on → autoencoders (deep generative models, AI) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
claim_relations	builds-on → Bowman et al. (ref 20), variational autoencoders with recurrent encoder/decoder for English sentences Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`		the tagger's words
claim_relations	contradicts → existing discrete search methods for chemical space (genetic algorithms and discrete interpolation techniques, refs 10-18) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[2]`		the tagger's words
claim_relations	builds-on → Bowman et al., variational autoencoders for written English sentences Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[3]`	1.0	the tagger's words
claim_relations	contradicts → fixed-library and genetic-algorithm approaches to molecular search Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[4]`	0.9	the tagger's words
concept_edges	information bottleneck —part-of→ autoencoder Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: information bottleneck · autoencoder	`concept_edges[1]`		the tagger's words
concept_edges	SMILES —contrasted-with→ InChI Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: SMILES · InChI	`concept_edges[2]`		the tagger's words
concept_edges	information bottleneck —causes→ latent representation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but endpoint by anaphora: 'This bottleneck' = the information bottleneck (previous sentence); 'latent representation' is written 'compressed representation'. also in: information bottleneck · latent representation	`concept_edges[4]`		the tagger's words
concept_edges	encoder network —part-of→ autoencoder Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The paper explicitly says the autoencoder is comprised of the encoder and decoder networks. also in: encoder network · autoencoder	`concept_edges[6]`	0.95	the tagger's words
concept_edges	decoder network —part-of→ autoencoder Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The paper explicitly says the autoencoder is comprised of the encoder and decoder networks. also in: decoder network · autoencoder	`concept_edges[7]`	0.95	the tagger's words
content_tags	hundreds of thousands — training set size of existing molecules Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	< 9 — size regime of one demonstration molecule set Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`		the tagger's words
content_tags	10^8 synthesised vs 10^23–10^60 possible — the size of the search problem the method addresses Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[2]`	1.0	the tagger's words
content_tags	An autoencoder maps SMILES-encoded molecules to a continuous vector space. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[0]`		the tagger's words
content_tags	EVIDENCE CORRECTED (RE-GROUNDED) · Continuous representations allow gradient-based optimization to guide the search for optimized functional compounds. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. EVIDENCE CORRECTED: RE-GROUNDED. The published string was in NEITHER copy of the paper. Ours read 'THESE representations'; the paper says 'CONTINUOUS representations', and continuity is the property the whole method rests on - it is what makes gradient-based optimization possible at all. The demonstrative dropped the reason.	`content_tags.findings[1]`		the tagger's words
content_tags	Once molecules are points in a continuous space, generation becomes arithmetic - decode a random vector, perturb a known molecule, interpolate between two. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[2]`	1.0	the tagger's words
content_tags	The encoding matters: SMILES works and InChI works substantially worse, apparently because its syntax involves counting and arithmetic. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[3]`	1.0	the tagger's words
content_tags	The search problem is one of scale: about 10^8 substances have ever been made, against an estimated 10^23 to 10^60 drug-like possibilities. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[4]`	1.0	the tagger's words
content_tags	Genetic generation of compounds requires manually specified heuristics for mutation and crossover. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[5]`	1.0	the tagger's words
content_tags	continuous representation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: continuous representation	`content_tags.variables[0]`		the tagger's words
content_tags	property values Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: property values	`content_tags.variables[1]`		the tagger's words
content_tags	string representation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: string representation	`content_tags.variables[2]`	1.0	the tagger's words
content_tags	SMILES strings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: SMILES strings	`content_tags.definitions[1]`		the tagger's words
content_tags	latent representation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: latent representation	`content_tags.definitions[2]`	1.0	the tagger's words
content_tags	information bottleneck Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: information bottleneck	`content_tags.definitions[3]`	1.0	the tagger's words
content_tags	variational autoencoder Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: variational autoencoder	`content_tags.definitions[4]`	1.0	the tagger's words
content_tags	encoder Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: encoder	`content_tags.definitions[5]`		the tagger's words
content_tags	decoder Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: decoder	`content_tags.definitions[6]`		the tagger's words
content_tags	predictor Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: predictor	`content_tags.definitions[7]`		the tagger's words
content_tags	mean Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: mean	`content_tags.statistics[1]`		the tagger's words
content_tags	regression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: regression	`content_tags.statistics[2]`		the tagger's words
content_tags	regression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: regression	`content_tags.statistics[4]`	0.9	the tagger's words

Interpretive choices

Tags that could not be placed in the text:

content_tags.statistics[0] — quotation withheld — the page has already reproduced as much of this paper as the rights budget allows
NOT MACHINE-VOUCHED: not-in-our-copy - The quote is in the original web page we fetched for this paper, but not in the text we tag against, which was extracted differently. Checked with ligatures, hyphens, spacing and punctuation set aside.
content_tags.statistics[3] — quotation withheld — the page has already reproduced as much of this paper as the rights budget allows
NOT MACHINE-VOUCHED: not-in-our-copy - The quote is in the original web page we fetched for this paper, but not in the text we tag against, which was extracted differently. Checked with ligatures, hyphens, spacing and punctuation set aside.

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.