Event owner lens
Use this record to benchmark whether a comparable event makes the work after the room visible. The score is 43/100, so the next move is to benchmark the weakest pillars before repeating the format.
applied learning or working session agenda analysis
Heal Workshop 2025
This applied learning or working session in Technology / AI / Startup shows 42 visible agenda rows from heal-workshop.github.io and scores 43/100: a moderate design signal with incomplete evidence. The clearest public signals sit in Participation Architecture and Personalization; the main limits are Follow Through and Network Design. Visible mechanisms include Participant work, Network design, Learning transfer, and Personalization. The public record does not show follow-up or tracking, so the score should be... A practical reading: For a reader, this is a comparison record more than a model to copy: it reads as an applied learning or working session, with the strongest visible signal in participation architecture and personalization and the biggest open question around follow through and network design. The practical test is whether the published agenda connects the room to post-event continuation and evidence. This page is an original public-evidence analysis, not a copy of the source agenda or an endorsement of the event. The score places the visible agenda in the moderate design signal band. The strongest visible pillars are Participation Architecture, Personalization, and Learning Transfer; the thinnest visible pillars are Follow Through, Network Design, and Evidence Maturity. Visible mechanisms include Participant work, Network design, Learning transfer, and Personalization. The extracted agenda preview includes 60 visible rows. The most common formats are Workshop, Unknown, and Presentation; the most common inferred purposes are Co Creation, Participant Work, and Unknown.
Eight-pillar fingerprint
Hover any pillar to see what it measures and, where it scored low, what the agenda is missing.
Participation Architecture?85
Participation Architecture - 85/100. Participant work, contribution, interaction, and alternatives to passive broadcast.
Follow Through?5
Follow Through - 5/100. Owners, dates, commitments, progress checks, and accountability after the room.Missing: Add named owners, dates, implementation checkpoints, and a visible post-event continuation path.
Problem Specificity?46
Problem Specificity - 46/100. A clear costly problem, objective, decision, or performance target.
Personalization?65
Personalization - 65/100. Role, path, goal, preparation, or connection tailoring for participants.
Network Design?16
Network Design - 16/100. Structured weak ties, bridge-building, mixers, and relationship persistence.Missing: Replace generic networking blocks with designed introductions, ask-offer exchanges, peer groups, or bridge-building rituals.
Learning Transfer?55
Learning Transfer - 55/100. Applied practice, feedback, workplace use, refreshers, and 30-90 day transfer.
Evidence Maturity?37
Evidence Maturity - 37/100. Baseline, comparison, follow-up, isolation, and attribution confidence.Missing: Add baseline measurement, comparison logic, tracking, or post-event impact reporting so effectiveness is not inferred only from format.
Future-of-Work Fit?46
Future-of-Work Fit - 46/100. Value against time, hybrid reality, accessibility, AI, and meeting load.
Fix the gaps
Field-tested exercises matched to this agenda's weakest pillars, from the exercise library.
Follow Through (5/100)
Exercises that strengthen it: Mental Toughness Workshop • WorkshopBank · 15% Solutions • WorkshopBank · Network Patches
Network Design (16/100)
Exercises that strengthen it: Fun Trust-Building Group Game for Team Connection - Izzat... · Exciting Group Trust Activity for Building Confidence... · PFP: September 2005
Problem Specificity (46/100)
Exercises that strengthen it: 0 - “Two Person Scene” Theory · Challenge Axis - Knowmium: The Un-Training Consultancy · Fist to Five • WorkshopBank
Agenda Preview
The actual agenda we captured. Every block is classified by format and purpose. Open any block to see how we read it; the colored edge shows whether it is participant work, broadcast, logistics, or a showcase.
Room vs wrapper
73 percent of the 60 classified blocks put participants to work; the rest broadcast, show, or handle logistics. That mix is what drives the participation score.
Participant workBroadcastShowcaseLogistics
all eventCall for Participation Accepted Work Key Information & Agenda CHI 2025 CHI 2024PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
14:15 to 15:45( CEST and CEST)PresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventKeynote SpeakerKeynoteExpert framing+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventWorkshop date : Wednesday, April 15, 2026WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
14:15 to 15:45Time : and CESTPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventContact : heal.workshop@gmail.comWorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
14:15 to 14:25Time: CESTPresentationKnowledge transfer+
Format · BroadcastPresentationSpeakers present, the audience receives. Awareness only unless paired with practice or follow-up.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventKeynoteKeynoteExpert framing+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventInteractive Poster SessionPoster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all eventBalancing Emergence and Controllability of Dynamic-Generative Games through Human-AI Co-Authorization - Minji Kim...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventChild Safety in Generative AI: An Expert-Guided and Incident-Grounded Evaluation Framework - Haein Kong...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventCUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents - Marta Sumyk, Oleksandr Kosovan...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventFrom Method to Interface: Human-Centred Auditing Under Resource and Access Constraints - Anonymous Author(s)...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventIdentifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level - Hannah Cha...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventReporting and Reviewing LLM-Integrated Systems in HCI: Challenges and Considerations - Eugene Syriani, Ian Arawjo, Karla Felix Navarro...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventWhen Humans Become Regime Stabilizers: A Hidden Failure Mode in Agent-in-the-Loop LLM Evaluation - Vinicius Buri Lux...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventWhen Should Agents Evaluate? A Principled Framework for Human-AI Task Allocation in Language Model Evaluation - Sasha Mitts...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventRevitalizing Local Democracy: A Human-Centered Audit of LLMs in City Council Journalism - David Xia, Chris Maury...WorkshopParticipant work+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisParticipant work is implied by the formatInferred from format
all eventHEAL@CHI'26UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventCall for Participation Accepted Work Key Information & Agenda CHI 2025 CHI 2024UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
14:15 to 15:45 ( CEST and CEST)UnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventHEAL is back for its third iteration at CHI 2026! This workshop addresses the ongoing "evaluation crisis" in LLM research and practice by bringing together HCI and AI researchers to rethink LLM evaluation and auditing from a human-centered perspective.WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventBuilding on successful workshops at CHI 2024 and CHI 2025, we continue exploring topics around understanding stakeholders' needs and goals, establishing human-centered evaluation and auditing methods, developing tools and resources, and fostering community collaboration.WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventKeynote SpeakerKeynoteThought Leadership+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisMediumRead from source
all eventWorkshop date : Wednesday, April 15, 2026WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
14:15 to 15:45 Time : and CESTUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventContact : heal.workshop@gmail.comWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
14:15 to 14:25 Time: CESTUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisMediumRead from source
all eventKeynoteKeynoteThought Leadership+
Format · BroadcastKeynoteA featured talk from the stage. Builds awareness and energy, produces no participant output on its own.
Evidence basisMediumRead from source
all eventInteractive Poster SessionPoster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all eventPlease note: Authors of submitted and accepted work have reserved spaces at the workshop and will present their contributions in the interactive poster session. Others are warmly welcome to join as audience members as long as on-site capacity allows. This is a new format we are trying this year, so we appreciate your flexibility as we see how it goes on premise.Opening RemarksOrientation+
Format · BroadcastOpening RemarksFraming or welcome from the stage. Orients the room, not participatory.
Evidence basisMediumRead from source
all eventAuditing the auditor: evaluating and implementing LLMs and agentic AI performance within heterogeneous data, zero fault-tolerant environment of financial audit and analysis - Jingkun (Charly) Zhu, Wojtek Buczynski [[Link]](https://heal-workshop.github.io/chi2026papers/Auditing%20the%20auditor%20evaluating%20and%20implementing%20LLMs%20and%20agentic%20AI%20performance.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventAuditing Text-to-Image Model Safety under Implicit Prompts with Human and LLM-Assisted Evaluation - Shiqi Chen, Zhaofeng Niu, Bowen Wang, Yang Song, Isidro Butaslac, Liangzhi Li [[Link]](https://heal-workshop.github.io/chi2026papers/Auditing%20Text-to-Image%20Model%20Safety%20under%20Implicit%20Prompts%20with%20Human%20and%20LLM-As.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventBalancing Emergence and Controllability of Dynamic-Generative Games through Human-AI Co-Authorization - Minji Kim [[Link]](https://heal-workshop.github.io/chi2026papers/Balancing%20Emergence%20and%20Controllability%20of%20Dynamic-Generative%20Games%20through%20Huma.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventCasual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset - Hyojeong Yu, Minsung Kim, Hyukhun Koh, Kyomin Jung [[Link]](https://heal-workshop.github.io/chi2026papers/Casual%20as%20an%20Anchor%20Resolving%20Supervision%20Misalignment%20in%20Formality%20Transfer%20Dat.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventChild Safety in Generative AI: An Expert-Guided and Incident-Grounded Evaluation Framework - Haein Kong [[Link]](https://heal-workshop.github.io/chi2026papers/Child%20Safety%20in%20Generative%20AI%20An%20Expert-Guided%20and%20Incident-Grounded%20Evaluation%20.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventCUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents - Marta Sumyk, Oleksandr Kosovan [[Link]](https://heal-workshop.github.io/chi2026papers/CUAAudit%20Meta-Evaluation%20of%20Vision-Language%20Models%20as%20Auditors%20of%20Autonomous%20Com.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventEvaluating LLM-Generated Lessons from the Language Learning Students' Perspective: A Short Case Study on Duolingo - Carlos Rafael Catalan, Patricia Nicole Monderin, Lheane Marie Dizon, Gap Estrella, Raymund John Sarmiento, Marie Antoinette Patalagsa [[Link]](https://heal-workshop.github.io/chi2026papers/Evaluating%20LLM-Generated%20Lessons%20from%20the%20Language%20Learning%20Students%20Perspective.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventFrom Method to Interface: Human-Centred Auditing Under Resource and Access Constraints - Anonymous Author(s) [[Link]](https://heal-workshop.github.io/chi2026papers/From%20Method%20to%20Interface%20Human-Centred%20Auditing%20Under%20Resource%20and%20Access%20Constr.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventHuman-Centered Evaluation of an LLM-Based Process Modeling Copilot: A Mixed-Methods Study with Domain Experts - Chantale Lauer, Peter Pfeiffer, Nijat Mehdiyev [[Link]](https://heal-workshop.github.io/chi2026papers/Human-Centered%20Evaluation%20of%20an%20LLM-Based%20Process%20Modeling%20Copilot%20A%20Mixed-Metho.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventHuman-Centred LLM Privacy Audits: Findings and Frictions - Dimitri Staufer, David Hartmann [[Link]](https://heal-workshop.github.io/chi2026papers/Human-Centred%20LLM%20Privacy%20Audits%20Findings%20and%20Frictions.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventHumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants - Benjamin Sturgeon, Jacob Haimes, Daniel Samuelson, Jacy Reese Anthis [[Link]](https://heal-workshop.github.io/chi2026papers/HumanAgencyBench%20Scalable%20Evaluation%20of%20Human%20Agency%20Support%20in%20AI%20Assistants.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventIdentifying Harm in Personalized, Generative AI Systems Requires User-Centered Auditing at the Interaction Level - Hannah Cha [[Link]](https://heal-workshop.github.io/chi2026papers/Identifying%20Harm%20in%20Personalized%20Generative%20AI%20Systems%20Requires%20User-Centered%20Au.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventInvestigation of Expressiveness Performance of Large Language Models for HRM Simulations - Atsuhiro Fujii, Kazuma Negita, Keisuke Masuda, Wataru Uno, Daisuke Nakama [[Link]](https://heal-workshop.github.io/chi2026papers/Investigation%20of%20Expressiveness%20Performance%20of%20Large%20Language%20Models%20for%20HRM%20Sim.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventInvisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks - Majeed Kazemitabaar, Jessica Y. Bo, Mengqing Deng, Michael Inzlicht, Ashton Anderson [[Link]](https://heal-workshop.github.io/chi2026papers/Invisible%20Saboteurs%20Sycophantic%20LLMs%20Mislead%20Novices%20in%20Problem-Solving%20Tasks.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventLearning from Learners: Human-Centered Evaluation of Conversational Agents in Educational Settings - Emily Doherty, Michael Buchanan, E. Margaret Perkoff, Indrani Dey, Leanne Hirshfield [[Link]](https://heal-workshop.github.io/chi2026papers/Learning%20from%20Learners%20Human-Centered%20Evaluation%20of%20Conversational%20Agents%20in%20Edu.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventManaging Multi-Agent Research Systems: A Dashboard for Human Oversight of Coordinating AI Agents - Brian Kitano, Bryan Russett, Evan Carlson, Alex Kesling [[Link]](https://heal-workshop.github.io/chi2026papers/Managing%20Multi-Agent%20Research%20Systems%20A%20Dashboard%20for%20Human%20Oversight%20of%20Coordin.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventNo Man Is an Island: Explainable Graph-LLM Agents for Real-Time Clinical Reasoning - Ratna Kandala, Akshata Kishore Moharir, Niva Manchanda, Samantha Adorno [[Link]](https://heal-workshop.github.io/chi2026papers/No%20Man%20Is%20an%20Island%20Explainable%20Graph-LLM%20Agents%20for%20Real-Time%20Clinical%20Reasonin.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventPosition: We Must Proactively Address AI Safety Debt - Peter Wallich, Raymond Douglas [[Link]](https://heal-workshop.github.io/chi2026papers/Position%20We%20Must%20Proactively%20Address%20AI%20Safety%20Debt.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventReporting and Reviewing LLM-Integrated Systems in HCI: Challenges and Considerations - Eugene Syriani, Ian Arawjo, Karla Felix Navarro [[Link]](https://heal-workshop.github.io/chi2026papers/Reporting%20and%20Reviewing%20LLM-Integrated%20Systems%20in%20HCI%20Challenges%20and%20Considerati.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventSeverity-Dependent Bias in LLM Evaluators: A Span-Level Audit of Polarizing Language Detection in Everyday News - Prerana Khatiwada, Kathleen Higgins, Ashrey Mahesh, Varun Pappu, Benjamin E. Bagozzi, Matthew Louis Mauriello [[Link]](https://heal-workshop.github.io/chi2026papers/Severity-Dependent%20Bias%20in%20LLM%20Evaluators%20A%20Span-Level%20Audit%20of%20Polarizing%20Langu.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventSurfacing Governing Principles for Chatbots: A Workbench and Comparative Study - M. Antonietta Grasso, Jisun Park, Jutta Willamowski, Laurent Besacier, Jos Rozen [[Link]](https://heal-workshop.github.io/chi2026papers/Surfacing%20Governing%20Principles%20for%20Chatbots%20A%20Workbench%20and%20Comparative%20Study.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventSynthetic user requirements: Sense making at early stages of product development - Valeria Resendez, Andrew Hornback, Harinishree Sathu, J. Ben Tamo, Yining Yuan, Nese Baz, Funda Yildirim, Russell Chan, May D. Wang, Maria Fernanda Cabrera, Simone Borsci [[Link]](https://heal-workshop.github.io/chi2026papers/Synthetic%20user%20requirements%20Sense%20making%20at%20early%20stages%20of%20product%20development.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventThrough the Looking Glass of Multilingual AI: Contrasting Language- and Name Script-Dependent Ethnic Hierarchies in GPT and DeepSeek - Annabella Sakunkoo, Jonathan Sakunkoo [[Link]](https://heal-workshop.github.io/chi2026papers/Through%20the%20Looking%20Glass%20of%20Multilingual%20AI%20Contrasting%20Language-%20and%20Name%20Scri.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventVerbalizing LLMs' Assumptions About the User to Calibrate Expectations and Reduce Sycophancy - Myra Cheng, Sunny Yu, Lujain Ibrahim, Diyi Yang, Dan Jurafsky [[Link]](https://heal-workshop.github.io/chi2026papers/Verbalizing%20LLMs%20Assumptions%20About%20the%20User%20to%20Calibrate%20Expectations%20and%20Reduce.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventWhen Humans Become Regime Stabilizers: A Hidden Failure Mode in Agent-in-the-Loop LLM Evaluation - Vinicius Buri Lux [[Link]](https://heal-workshop.github.io/chi2026papers/When%20Humans%20Become%20Regime%20Stabilizers%20A%20Hidden%20Failure%20Mode%20in%20Agent-in-the-Loop.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventWhen Should Agents Evaluate? A Principled Framework for Human-AI Task Allocation in Language Model Evaluation - Sasha Mitts [[Link]](https://heal-workshop.github.io/chi2026papers/When%20Should%20Agents%20Evaluate%20A%20Principled%20Framework%20for%20Human-AI%20Task%20Allocation%20.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventWhen Your Boss is an AI: Identity Label Bias in LLM Task Allocation Decisions - Amirsiavosh Bashardoust, Selma Riedo, Yuanjun Feng, Yash Raj Shrestha [[Link]](https://heal-workshop.github.io/chi2026papers/When%20Your%20Boss%20is%20an%20AI%20Identity%20Label%20Bias%20in%20LLM%20Task%20Allocation%20Decisions.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventRevitalizing Local Democracy: A Human-Centered Audit of LLMs in City Council Journalism - David Xia, Chris Maury [[Link]](https://heal-workshop.github.io/chi2026papers/Revitalizing%20Local%20Democracy%20A%20Human-Centered%20Audit%20of%20LLMs%20in%20City%20Council%20Jou.pdf)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventSubmission Types: Position papers, full or in-progress empirical studies, literature reviews, system demos, method descriptions, or encore of published work (non-archival).DemoShowcase+
Format · Participant workDemoA hands-on or applied walkthrough that invites attendee questions and direct engagement.
Evidence basisMediumRead from source
The Full Reading
Why It Ranks This Way +
Calibrated from GES design 45/100 and verified 44/100, then capped for no visible follow-up, tracking, or impact mechanism.
Reader Takeaway. For a reader, this is a comparison record more than a model to copy: it reads as an applied learning or working session, with the strongest visible signal in participation architecture and personalization and the biggest open question around follow through and network design. The practical test is whether the published agenda connects the room to post-event continuation and evidence.
Strongest signals: Participation Architecture, Personalization, and Learning Transfer. Weakest signals: Follow Through, Network Design, and Evidence Maturity.
How This Agenda Could Improve +
- Add named owners, dates, implementation checkpoints, and a visible post-event continuation path.
- Replace generic networking blocks with designed introductions, ask-offer exchanges, peer groups, or bridge-building rituals.
- Add baseline measurement, comparison logic, tracking, or post-event impact reporting so effectiveness is not inferred only from format.
Fastest next move: Add named owners, dated next steps, and a visible continuation path before treating the event as outcome-ready.
Role-Specific Reading +
Sponsor lens
Look beyond exposure. Strong sponsor value would show qualified interaction, problem work, buyer learning, customer evidence, or follow-up. The practical sponsor move is to look for structured introductions, buyer-seller fit, and relationship persistence.
Designer lens
The agenda is useful as a pattern sample from heal-workshop.github.io. Redesign attention should go first to the lowest-scoring pillars; in practice, turn the thinnest agenda blocks into participant work.
Executive lens
Treat the visible agenda as an operating plan. The executive move is to require owners, dates, and evidence before treating the event as strategic. If owners, proof, and follow-through are not visible, the public record does not yet prove strategic movement.
Aggregator lens
Treat the source URL as evidence, not decoration. The data-product move is to label the source boundary clearly before ranking the record before ranking or syndicating the record.
What GES Means Here +
The Gathering Effectiveness Score is a strict 0-100 public-evidence reading of the agenda across eight pillars. It rewards visible participant work, follow-through, transfer, network design, and proof mechanisms more than polish, speaker fame, attendance, or satisfaction.
Visible mechanisms: Participant work, Network design, Learning transfer, Personalization.
Evidence boundary: Scores reflect visible agenda/source evidence and should not be read as proof of causal event impact.
Limitations, Score Caps, and Review Flags +
Limitations
- No visible follow-up, progress monitoring, or longitudinal tracking.
- No baseline measurement is visible.
Score caps
- 42: No visible follow-up, tracking, or impact mechanism.
Review flags
- Fourth-loop score cap: No visible follow-up, tracking, or impact mechanism.
- No source-backed follow-up, validation, baseline, tracking, or impact evidence.
- No tracking, validation, feedback, or impact measurement found in the visible source text.
- High cleanup rate: many extracted rows were hidden or merged as fragments.
- Original category was unknown; publication category is inferred.
Is this proof the event worked? +
No. This is a strict public-evidence reading of the agenda. Proof would require baseline, comparison, follow-up, attribution, and impact evidence beyond the listing.
What should a reader inspect first? +
Start with the source URL, then compare the eight pillar scores against the agenda rows. The biggest opportunities usually sit in follow-through, evidence maturity, and participant work.
Why publish weak records? +
Weak records are part of the map. They show where public agendas still describe sessions and speakers more often than outcomes, commitments, transfer, or proof.
How should I use the rows? +
Read the agenda rows as the visible design trace: formats, purposes, and evidence labels show what the public source made inspectable, not everything that happened in the room. This is a source-grounded interpretation of the public agenda record, not a copy of the source, and not an endorsement of the event.
Embed the verified badge +
This record is in the hand-verified gold set. Copy the snippet below to embed the verified badge on your own site.
<a href="https://unitedwetransform.com/events/evt_2025_chi2025_acm_org_for_attendees_program_at_a_glance_workshops_heal_workshop_g"><img src="https://unitedwetransform.com/badge/ges-verified.svg" alt="GES verified by United We Transform" height="40"></a>Where To Go Next
Compare this agenda against other Technology / AI / Startup events scored on the same eight pillars.