The Name of the Title Is Hope
[!NOTE] Overleaf Project: git.overleaf.com/
6ac144780808c76eacfe6f316ae05e2e72446c974da5a114
Last Synced: 2026-10-0811-0313:51:0508:01:48 (via PA Git Sync)
Source File:main.sigconf-authordraft.tex
\textbf{LearningThe GradientName Descentof withthe andTitle withoutIs an AI ScaffoldHope
[!ABSTRACT] A clear and well-documented \LaTeX\ document is presented as an article formatted for publication by ACM in a conference proceedings or journal publication. Based on the ``
Kyotoacmart''baby'':documentIsna,class,Karo,thisStergiosarticle presents and explains many of the common variations, as well as many of the formatting elements an author may use in the preparation of the documentation of their work.
\orcid{1234-5678-9012}
\city{Dublin} \state{Ohio} \country{USA} }
rv{"a}ld} rv{"a}ld Group} \city{Hekla} \country{Iceland}}
\city{Rocquencourt} \country{France} }
\city{Doimukh} \state{Arunachal Pradesh} \country{India}}
\city{Haidian Qu} \state{Beijing Shi} \country{China}}
\city{San Antonio} \state{Texas} \country{USA}}
rv{"a}ld Group} \city{Hekla} \country{Iceland}}
\city{New York} \country{USA}}
\renewcommand{\shortauthors}{Trovato et al.}
\begin{CCSXML} <concept_id>00000000.0000000.0000000</concept_id> <concept_desc>Do Not Use This Code, Generate the Correct Terms for Your Paper</concept_desc> <concept_significance>500</concept_significance> <concept_id>00000000.00000000.00000000</concept_id> <concept_desc>Do Not Use This Code, Generate the Correct Terms for Your Paper</concept_desc> <concept_significance>300</concept_significance> <concept_id>00000000.00000000.00000000</concept_id> <concept_desc>Do Not Use This Code, Generate the Correct Terms for Your Paper</concept_desc> <concept_significance>100</concept_significance> <concept_id>00000000.00000000.00000000</concept_id> <concept_desc>Do Not Use This Code, Generate the Correct Terms for Your Paper</concept_desc> <concept_significance>100</concept_significance> \end{CCSXML}
\ccsdesc[500]{Do Not Use This CodeGenerate the Correct Terms for Your Paper}
\ccsdesc[300]{Do Not Use This CodeGenerate the Correct Terms for Your Paper}
\ccsdesc{Do Not Use This CodeGenerate the Correct Terms for Your Paper}
\ccsdesc[100]{Do Not Use This CodeGenerate the Correct Terms for Your Paper}
\keywords{Do, Not, Use, This, Code, Put, the, Correct, Terms, for, Your, Paper}
\received{20 February 2007} \received[revised]{12 March 2009} \received[accepted]{5 June 2009}
Background: Why Gradient Descent?Introduction
GradientACM's descentconsolidated article template, introduced in 2017, provides a
consistent \LaTeX\ style for use across ACM publications, and
incorporates accessibility and metadata-extraction functionality
necessary for future Digital Library endeavors. Numerous ACM and
SIG-specific \LaTeX\ templates have been examined, and their unique
features incorporated into this single new template.
If you are new to publishing with ACM, this document is a valuable guide to the process of preparing your work for publication. If you have published with ACM before, this document provides insight and instruction into more recent changes to the article template.
The \verb|acmart|'' document class can be used to prepare articles for any ACM publication --- conference or journal, and for any stage of publication, from review to final camera-ready'' copy, to the
author's own version, with {\itshape very} few changes to the source.
Template Overview
As noted in the introduction, the \verb|acmart|'' document class can be used to prepare many different kinds of documentation --- a double-anonymous initial submission of a full-length technical paper, a two-page SIGGRAPH Emerging Technologies abstract, a camera-ready''
journal article, a SIGCHI Extended Abstract, and more --- all by
selecting the appropriate {\itshape template style} and {\itshape
template parameters}.
This document will explain the major features of the document class. For further information, the {\itshape \LaTeX\ User's Guide} is available from https://www.acm.org/publications/proceedings-template.
Template Styles
The primary parameter given to the ``\verb|acmart|'' document class is
the optimization{\itshape routinetemplate behindstyle} almostwhich corresponds to the kind of publication
or SIG publishing the work. This parameter is enclosed in square
brackets and is a part of the {\verb|documentclass|} command:
\begin{verbatim}
\documentclass[STYLE]{acmart}
\end{verbatim}
Journals use one of three template styles. All but three ACM journals use the {\verb|acmsmall|} template style:
acmsmall}: The default journal template style.
{acmlarge}: Used by JOCCH and TAP.
{acmtog}: Used by TOG.
The majority of conference proceedings documentation will use the {\verb|acmconf|} template style.
sigconf}: The default proceedings template style.
{sigchi}: Used for SIGCHI conference articles.
{sigplan}: Used for SIGPLAN conference articles.
Template Parameters
In addition to specifying the {\itshape template style} to be used in formatting your work, there are a number of {\itshape template parameters} which modify some part of the applied template style. A complete list of these parameters can be found in the {\itshape \LaTeX\ User's Guide.}
Frequently-used parameters, or combinations of parameters, include:
anonymous,review}: Suitable for a ``double-anonymous''
conference submission. Anonymizes the work and includes line
numbers. Use with the \string\acmSubmissionID command to print the
submission's unique ID on each page of the work.
{authorversion}: Produces a version of the work suitable
for posting by the author.
{screen}: Produces colored hyperlinks.
This document uses the following string as the first command in the source file: \begin{verbatim} \documentclass[sigconf,authordraft]{acmart} \end{verbatim}
Modifications
Modifying the template --- including but not limited to: adjusting margins, typeface sizes, line spacing, paragraph and list definitions, and the use of the \verb|\vspace| command to manually adjust the vertical spacing between elements of your work --- is not allowed.
{\bfseries Your document will be returned to you for revision if modifications are discovered.}
Typefaces
The \verb|acmart|'' document class requires the use of the Libertine'' typeface family. Your \TeX\ installation should include
this set of packages. Please do not substitute other typefaces. The
\verb|lmodern|'' and \verb|ltimes|'' packages should not be used,
as they will override the built-in typeface families.
Title Information
The title of your work should use capital letters appropriately - https://capitalizemytitle.com/ has useful rules for capitalization. Use the {\verb|title|} command to define the title of your work. If your work has a subtitle, define it with the {\verb|subtitle|} command. Do not insert line breaks in your title.
If your title is lengthy, you must define a short version to be used in the page headers, to prevent overlapping text. The \verb|title| command has a ``short title'' parameter: \begin{verbatim}
\end{verbatim}
Authors and Affiliations
\end{verbatim}
The article template's documentation, available at https://www.acm.org/publications/proceedings-template, has a complete explanation of these commands and tips for their effective use.
Rights Information
Regardless of the rights management choice, the author will receive a copy of the completed rights form once it has been submitted. This form contains \LaTeX\ commands that must be copied into the source document. When the document source is compiled, these commands and their parameters add formatted text to several areas of the final document:
Rights information is unique to the work; if you are preparing several works for an event, make sure to use the correct set of commands with each of the works.
The ACM Reference Format text is required for all articles over one page in length, and is optional for one-page articles (abstracts).
CCS Concepts and User-Defined Keywords
Two elements of the ``acmart'' document class provide powerful taxonomic tools for you to help readers find your work in an online search.
The ACM Computing Classification System --- https://www.acm.org/publications/class-2012 --- is a set of classifiers and concepts that describe the computing discipline. Authors can select entries from this classification system, via https://dl.acm.org/ccs/ccs.cfm, and generate the commands to be included in the \LaTeX\ source.
User-defined keywords are a comma-separated list of words and phrases of the authors' choosing, providing a more flexible way of describing the research being presented.
CCS concepts and user-defined keywords are required for for all articles over two pages in length, and are optional for one- and two-page articles (or abstracts).
Sectioning Commands
Your work should use standard \LaTeX\ sectioning commands:
\verb|\section|, \verb|\subsection|, \verb|\subsubsection|,
\verb|\paragraph|, and \verb|\subparagraph|. The sectioning levels up to
\verb|\subsubsection| should be numbered; do not remove the numbering
from the ideacommands.
Simulating a sectioning command by setting the first word or words of
teachinga novicesparagraph in boldface or italicized text is {\bfseries not allowed.}
Below are examples of sectioning commands.
Subsection
\label{sec:subsection}
This is a subsection.
Subsubsection
\label{sec:subsubsection}
This is a subsubsection.
Paragraph:
This is a paragraph.
\subparagraph{Subparagraph}
This is a subparagraph.
Tables
The \verb|acmart|'' document class includes the \verb|booktabs|''
package --- https://ctan.org/pkg/booktabs --- for preparing
high-quality tables.
Table captions are placed {\itshape above} the table.
Because tables cannot be split across pages, the best placement for
them is typically the top of the page nearest their initial cite. To
ensure this proper ``floating'' placement of tables, use the
environment table to programenclose neuralthe networks.table's During our discussions we concluded that end-to-end implementation is too demanding for novice participants: code, architecture, and optimization would be learned at once,contents and the
studytable couldcaption. notThe tellcontents which part caused learning. We therefore narrowedof the projecttable itself must go in the
tabular environment, to onebe corealigned concept,properly in rows and
comparedcolumns, three candidates (gradient descent, text analytics / dimensionality reduction, recursion). We chose gradient descent because:
* **It keepswith the neural-networkdesired umbrella.**horizontal Itand vertical rules. Again,
detailed instructions on tabular material are found in the
\LaTeX\ User's Guide.
Immediately following this sentence is the keypoint mechanismat ofwhich
neural-networkTable training[tab:freq] andis complementsincluded in the introductoryinput materialfile; our participants see in their machine learning course.
* **It is self-contained and testable in one hour.** It has clear right and wrong answers (compute a step, predict a trajectory, diagnose a failing run), and its typical misconceptions are well known: a larger learning rate is always faster,compare the
algorithm always finds the global minimum, and the update goes *along* the gradient.
* **A digital tool can add value beyond high-school calculus.** Participants know derivatives, but the behaviorplacement of the algorithmtable (step size, curvature, oscillation in ravines, stalling at saddles) is hard to grasp from equations alone and becomes visible in an interactive 3D landscape.
Target population.: Bachelor students (about 20), preferably second-year, who know derivatives and partial derivatives but have not yet been taught gradient descent. Master's students are excluded to keep the baseline comparable.
Theoretical grounding.: We build on the course principle that learning depends on the cognitive activity learners performhere with the technology, not on the technology itself, and on the ICAP framework. A visualization alone supports passive or active engagement, depending on how learners use it. The AI affordance is meant to push learners towards constructive and interactive engagement by prompting them to predict, explain, and revise. Our question is therefore not does AI help?'' but does this AI affordance change what learners do, and does that improve learning?''
Learning Goal
Overall learning goal.: Learners understand gradient descent well enough to apply it to a simple function and to reason about how its behavior depends on the learning rate and on the shape of the loss surface.
Learning objectives.: After the session, learners can:
* **Compute** one gradient descent update for a given one- or two-variable function, starting point, and learning rate, with the correct numerical result.
* **Explain** in one or two sentences why the update moves opposite to the gradient.
* **Predict** whether a run with a given learning rate will converge slowly, converge quickly, oscillate, or diverge, and justify the prediction.
* **Diagnose** a given loss curve or trajectory that fails to converge, and propose a change of learning rate that fixes it.
Objectives 1--2 target knowledge and understanding, objectives 3--4 application and analysis (Bloom). Each uses an action verb and can be measured with a test item.
Scope.: To fit the one-hour limit, the study uses plain gradient descent with the learning rate as the main parameter. Optimizer variants (Momentum, RMSprop, Adam), which the prototype also offers, are out of scope and switched off. Prerequisites: derivative and partial derivative of a polynomial; no programming is required.
Available Approach
Existing prototype.: We proceed with a visual 3D Gradient Descent Lab (<gradient.stergios.ch>), a Django application with Three.js graphics where all computation runstable in the browser.printed Relevant features:
* split-screen layout: a narrow control panel (missions, surface selector, learning-rate slider, step controls) and a large 3D canvas with a ball rolling along the gradient descent trajectory, with a toggle to a 2D contour map showing gradient directions;
* five gamified missionsoutput of
increasingthis difficulty (convex bowl, saddle, Rosenbrock ravine, multi-modal Himmelblau, Rastrigin), plus procedurally generated random surfaces;
* hover cards that explain each parameter (equation, intuition, ``too low'' vs.\ ``too high'' consequences);
* automatic telemetry: pseudonymous session ID plus logged inputs, hyperparameters, and outcomes (stored in SQLite).
Learning mechanisms (course toolbox).:document.
\begin{center}table}
\smallcaption{Frequency of Special Characters}
\label{tab:freq}
\begin{tabular}{@{}>{\raggedright\arraybackslash}p{3.0cm} >{\raggedright\arraybackslash}p{12.7cm}@{}}ccl}
\toprule
MechanismNon-English or Math& How it appears in the activity\Frequency&Comments\
\midrule
Contrasting cases\O & Runs1 within small,1,000& medium,For andSwedish largenames\
learning rates on the same surface; bowl vs.$\ ravine.\
Undoingpi$ & Predict-then-observe1 tasksin expose5& theCommon ``biggerin ismath\
faster'' misconception.\
Self-explanation$ & After4 ain run, learners write why the trajectory behaved as it did.\
Feedback5 & InformationUsed onin thebusiness\
correctness of predictions and how to improve.$\
Deliberate practicePsi^2_1$ & Repeated1 missionsin with40,000& varyingUnexplained surfaces and starting points.\usage\
\bottomrule
\end{tabular}
\end{center}table}
StudyTo structure.:set Followinga ourwider earliertable, taskwhich analysis,takes learners first work through practice missions withup the supportwhole width of theirthe conditionpage's
andlive thenarea, solveuse testthe missionsenvironment withouttable* anyto supportenclose inthe bothtable's
groups, so that we measure learning rather than performance with help.
Condition A: no AI (control).: The prototype as built: missions, score,contents and the fixedtable hovercaption. explanationAs cardswith a single-column table, this
wide table will ``float'' to a location deemed more
desirable. Immediately following this sentence is the point at which
Table [tab:commands] is included in the input file; again, it is
instructive to compare the placement of the table here with the table
in the printed output of this document.
\begin{table*}
\caption{Some Typical Commands}
\label{tab:commands}
\begin{tabular}{ccl}
\toprule
Command &A Number & Comments\
\midrule
{\char'134author} & 100& Author \
{\char'134table}& 300 & For tables\
{\char'134table*}& 400& For wider tables\
\bottomrule
\end{tabular}
\end{table*}
Always use midrule to separate table header rows from data rows, and use it only for this purpose. This enables assistive technologies to recognise table headers and support their users in navigating tables more easily.
Math Equations
You may want to display math equations in three distinct styles: inline, numbered or non-numbered display. Each of the three are discussed in the next sections.
Inline (In-text) Equations
A formula that appears in the running text is called an inline or
in-text formula. It is produced by the math environment,
which can be invoked with the usual
{\char'134begin,\ldots{\char'134}end} construction or with
the short form $\,\ldots$. You can use any of the symbols
and structures, from $\alpha$ to $\omega$, available in
\LaTeX [Lamport:LaTeX]; this section will simply show a few
examples of in-text equations in context. Notice how this equation:
\begin{math}
\lim_{n\rightarrow \infty}x=0
\end{math},
set here in in-line math style, looks slightly different when
set in display style. (See next section).
Display Equations
A numbered display equation---one set off by vertical space from the text and centered horizontally---is produced by the equation environment. An unnumbered display equation is produced by the displaymath environment.
Again, in either environment, you can use any of the symbols and
structures available in \LaTeX@; this section will just give a couple
of examples of display equations in context. First, consider the
equation, shown as generican rulesinline equation above:
\begin{equation}
\lim_{n\rightarrow \infty}x=0
\end{equation}
Notice how it is formatted somewhat differently in
the displaymath
environment. Now, we'll enter an unnumbered equation:
\begin{displaymath}
\sum_{i=0}^{\infty} x + 1
\end{displaymath}
and follow it with another numbered equation:
\begin{equation}
\sum_{i=0}^{\infty}x_i=\int_{0}^{\pi+2} f
\end{equation}
just to demonstrate \LaTeX's able handling of hownumbering.
Figures
The performance.``\verb|figure|'' Predictionenvironment should be used for figures. One or
more images can be placed within a figure. If your figure contains
third-party material, you must clearly identify it as such, as shown
in the example below.
\begin{figure}[h]
\centering
\includegraphics[width=\linewidth]{sample-franklin}
\caption{1907 Franklin Model D roadster. Photograph by Harris &
Ewing, Inc. [Public domain], via Wikimedia
Commons. (https://goo.gl/VLCRBB).}
\Description{A woman and self-explanationa promptsgirl in white dresses sit in an open car.}
\end{figure}
Your figures should contain a caption which describes the figure to the reader.
Figure captions are present,placed but{\itshape answersbelow} receivethe only fixed, pre-written feedback.figure.
ConditionEvery B:figure AI-scaffolded.:should Samealso environmenthave a figure description unless it is purely
decorative. These descriptions convey what’s in the image to someone
who cannot see it. They are also used by search engine crawlers for
indexing images, and missions,when plusimages cannot be loaded.
A figure description must be unformatted plain text less than 2000
characters long (including spaces). {\bfseries Figure descriptions
should not repeat the figure caption – their purpose is to capture
important information that is not already provided in the caption or
the main text of the paper.} For figures that convey important and
complex new information, a short text description may not be
adequate. More complex alternative descriptions can be placed in an
AIappendix assistantand referenced in a sideshort panelfigure description. For example,
provide a data table capturing the information in a bar chart, or a
structured list representing a graph. For additional information
regarding how best to write figure descriptions and why doing this is
so important, please see
https://www.acm.org/publications/taps/describing-figures/.
The ``Teaser Figure''
* no direct answers and no computationbody of the updatearticle, spanning the page. If you wish to have such a
figure in your article, place the command immediately before the
\verb|| command:
\begin{verbatim}
\begin{teaserfigure}
\includegraphics[width=\textwidth]{sampleteaser}
\caption{figure caption}
\Description{figure description}
\end{teaserfigure}
\end{verbatim}
Citations and Bibliographies
The use of \BibTeX\ for the learner; only guided hints, Socratic questions,preparation and high-level suggestions;
* prompts that ask learners to articulate reasoning and notice gaps (*problematizing* scaffolding, not only *structuring*);
* access to the current simulation state (learning rate, trajectory, loss), fixed system prompt, and full logging.
This keeps the AI in serviceformatting of the learner'one's
productive effort rather than replacing it.
Still to build (next steps).: (i) AI side panel and system prompt; (ii) predict-first and self-explanation prompts in both conditions; (iii) test missions on unseen surfaces without support; (iv) integration of pre-/post-test items and surveys; (v) a switch that disables optimizer variants and unused levels. Stergios leads the implementation; Isna, together with the TA, defines the pre-screening and pre-test instrument.
Open design decision.: As an alternative or later extension we could compare AI roles, AI as tutor (expert guidance) vs.\ AI as peer (co-learner). With about 20 participants we keep two groups (10 vs.\ 10) and avoid factorial designs, which would leave only five per cell.
Research Questions
\begin{description}[leftmargin=1.2cm, labelwidth=1cm, style=nextline]
* [RQ1] Does adding an AI-based Socratic scaffold to an interactive gradient descent lab lead to higher post-test scores than the same lab with fixed feedback?
* [RQ2] Does the AI-scaffolded condition lead to better performance on unassisted test missions and transfer items (surfaces not seen during practice)?
* [RQ3 (exploratory)] How do learners use the assistant (e.g., asking for answers vs.\ explaining their reasoning), and how do usage, perceived cognitive load, and motivation relate to learning gain?
\end{description}
We expect, but do not assume, that the AI condition helps mainly through more and better self-explanations. With around 20 participants the studyreferences is exploratory,strongly andrecommended. weAuthors' reportnames effectshould sizesbe and uncertainty rather than relying on significance alone.
Methodology
\label{sec:method}
Design.: Between-subjects pre-test / intervention / post-test study with two conditions (A: no AI, B: AI-scaffolded). A pre-quiz is administered before grouping, and participants are randomly assigned, stratified by pre-test score so that prior knowledge is balanced.
Participants and recruitment.: About 20 Bachelor students (10 per condition), recruited through contacts of the team and course channels. A short pre-screening test filters genuine novices.
Procedure: (about 60 minutes, individual sessions):
* Consent, background questionnaire (prior knowledge, AI literacy) and pre-testcomplete
--- 10use minfull *first Practicenames missions(Donald inE. theKnuth'') assignednot condition,initials same(D. tasksE. and time limitKnuth'') --- 25 min
* Unassisted test missions on unseen surfaces (no hints, no AI, no hover cards) --- 10 min
* Post-test (parallel to the pre-test, plus transfer items) and survey --- 15 min
Pre- and post-test items are parallel versions (different numbers and functions, same structure) and counterbalanced across participants.
Measures.:
* *Learning (primary):* post-test score and normalized gain, scored with a rubric per objective (justifications scored 0--2 by two raters).
* *Unassisted test missions:* success, number of steps to reach the target, and time, relative to the difficulty of the surface (complexity vs.\ performance).
* *Process (from telemetry):* runs per mission, share of predictions made before running, time between interactions as an engagement indicator, and, in condition B, number and type of AI messages.
* *Survey:* AI literacy, intrinsic motivation, perceived cognitive load, and perceived helpfulness, kept separate from learning since perceived and actual learning can diverge.
* *Optional delayed measure:* performance on the related assignment in the machine learning course, if the course staff agree to share it.
Analysis.: Post-test and test-mission scores are compared between conditions with ANCOVA using the pre-test as covariate, plus a non-parametric check (Mann--Whitney U); we report effect sizes with confidence intervals. AI dialogues and self-explanations are coded qualitatively (request for answer, reasoning attempt, misconception expressed) by two coders with agreement reported. Process measures are interpreted only in relation to the learning outcome.
Threats and mitigations.:
* *Small sample:* analysis plan and items are fixed in advance; results are exploratory.
* *Gamification:* the score can reward trial-and-error tuning instead of reasoning. Both groups see the same score, predict-first prompts are required, and the unassistedsalient testidentifying missionsfeatures checkof whethera
reasoningreference transferred.should *be *AIincluded: givingtitle, awayyear, answers:*volume, number, pages,
article DOI, etc.
The bibliography is included in your source document with these two
commands, placed just before the system prompt is tested with adversarial inputs and all outputs are logged.
* *Time on task and rater bias:* fixed time limits; raters are blind to condition.
Ethics and data.: The current telemetry records every visitor automatically. For the study we will obtain informed consent that explicitly describes this logging, keep only pseudonymous IDs, and store data on a protected server. The AI interaction logs of the team's own work are submitted with the milestones as required by the course.\verb|
Timeline.:
* Oct 8 (M3): project plan and first working prototype; TA validation of idea and recruitment pipeline
* Autumn break to week 8: implement AI panel and test missions, pilot, finalize items and pre-screening test
* Nov 5 (M4): study plan and finished implementations for both conditions
* Weeks 9--12: run about 20 sessions (about 30 hours of testing including set-up)
* Weeks 13--14: analysis; Dec 15: presentation; Jan 7: final report
* Mid-January 2027: paper for IJCAI 2027 (Human-Centred AI track; abstract about Jan 12, full paper about Jan 19), emphasizing the human--AI interaction design, error correction, and cognitive load / transfer