Event owner lens
Use this record to benchmark whether a comparable event makes the work after the room visible. The score is 38/100, so the next move is to benchmark the weakest pillars before repeating the format.
applied learning or working session agenda analysis
ICML - Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI - 2021 - Call for Workshops
This applied learning or working session in Technology / AI / Startup shows 28 visible agenda rows from icml.cc and scores 38/100: a thin but inspectable design signal. The clearest public signals sit in Participation Architecture and Learning Transfer; the main limits are Follow Through and Network Design. Visible mechanisms include Participant work, Network design, and Learning transfer. The public record does not show follow-up or tracking, so the score should be read as design intent rather than durable impact. 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 learning transfer 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 thin outcome architecture band. The strongest visible pillars are Participation Architecture, Learning Transfer, and Problem Specificity; the thinnest visible pillars are Follow Through, Network Design, and Personalization. Visible mechanisms include Participant work, Network design, and Learning transfer. The extracted agenda preview includes 45 visible rows. The most common formats are Workshop, Panel, and Poster Session; the most common inferred purposes are Co Creation, Participant Work, and Deliberation.
Eight-pillar fingerprint
Hover any pillar to see what it measures and, where it scored low, what the agenda is missing.
Participation Architecture?89
Participation Architecture - 89/100. 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?44
Problem Specificity - 44/100. A clear costly problem, objective, decision, or performance target.
Personalization?31
Personalization - 31/100. Role, path, goal, preparation, or connection tailoring for participants.Missing: Create role-based paths, prepared questions, tailored breakouts, or participant-specific next steps.
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?33
Evidence Maturity - 33/100. Baseline, comparison, follow-up, isolation, and attribution confidence.
Future-of-Work Fit?34
Future-of-Work Fit - 34/100. 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
Personalization (31/100)
Exercises that strengthen it: Journey Mapping • WorkshopBank · Group Energiser & Perspective-Changing Exercise - Paradigm... · Photo Storytelling
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
78 percent of the 45 classified blocks put participants to work; the rest broadcast, show, or handle logistics. That mix is what drives the participation score.
Participant workBroadcastShowcaseLogistics
all eventICML Call for WorkshopsWorkshopParticipant 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 eventThe list of accepted workshops can be found...hereWorkshopParticipant 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 eventWorkshopsWorkshopParticipant 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 eventBelow, we include the criteria by which workshop submissions will be evaluatedWorkshopParticipant 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 event1. Fit for ICML (connections to rest of program and past workshops)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 event8. Room for contributed work (posters and contributed talks)Poster sessionShowcase+
Format · ShowcasePoster sessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisOutcome inferred from formatInferred from format
all event9. Open discussion/panelPanelDiscussion+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventImportant dates for workshop submissionsWorkshopParticipant 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 eventWorkshop Application Deadline: Feb 13, 2026 AOEWorkshopParticipant 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 eventWorkshop Notification: Mar 20, 2026 AOEWorkshopParticipant 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 event<https://cmt3.research.microsoft.com/ICMLWORKSHOPS2021>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 eventWorkshop titleWorkshopParticipant 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 eventA brief description of the topics to be covered, and an explanation as to why the workshop will appeal to ICML audiencesWorkshopParticipant 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 eventA short description and rough timetable of the planned activities (talks, posters, panels)PanelDiscussion+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisNo participant output visible from this rowRead from source, no work signal
all eventA description of the history of the workshop (if it previously took place, then when/where)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 eventICML 2021 Workshop ChairsWorkshopParticipant 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 eventworkshop-chairs@icml.ccWorkshopParticipant 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 eventAbout ICMLUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventSchedule for Unregistered AttendeesUnknownUnknown+
Format · BroadcastUnknownFormat not classified from the source; treated as a broadcast block by default.
Evidence basisLowRead from source
all eventICML Call for WorkshopsWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventFollowing the ICML 2021 main conference, workshops will be held on Friday, July 23rd, and Saturday, July 24th. We invite researchers interested in chairing one of these workshops to submit proposals. Workshop organizers have several responsibilities, including coordinating workshop participation and content, publicizing and providing the program in a timely manner, and moderating the program throughout the workshop.WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventICML also solicits proposals for affinity workshops. The format and aims of these workshops should be described by the workshop organizers, following, for instance, the template set out by similar workshops (WiML, Black in AI, LatinX in AI, Queer in AI, New in ML, {Dis}Ability in AI, Muslims in ML, Indigenous in AI), at NeurIPS/ICLR/ICML. The affinity workshops are typically held during the main conference or the day before. Affinity workshop proposals should follow a similar format as regular workshop proposals (see below) and should be emailed directly to workshop-chairs@icml.cc with the subject line "Affinity workshop: [name of workshop]." The deadline for affinity workshop proposals is Feb 13, 2026 AOE.WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventThe list of accepted workshops can be found...hereWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventWorkshopsWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventThe goal of the workshops is to provide an informal forum for researchers to discuss emerging research questions and challenges. Workshops will last for one day, with morning and afternoon sessions and free time between the sessions for individual exchange. To encourage workshop variety, all workshops will be one-day workshops.WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventThe workshops can be on any subject relevant to an appreciable fraction of the ICML community. Schedules should encourage lively debates, and topics should lean more towards exploring new ideas, open problems, and interdisciplinary areas, compared with the main conference. Workshops should encourage contributed content and reserve a significant portion of time for open discussion/panel discussion and posters. A diverse group of speakers is more likely to bring diverse and surprising viewpoints on a topic. As a result, we encourage workshop organizers to be cognizant of designing panels and speaker lists that are inclusive.PanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
all eventBelow, we include the criteria by which workshop submissions will be evaluated:WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all event1. Fit for ICML (connections to rest of program and past workshops)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all event8. Room for contributed work (posters and contributed talks)Poster SessionShowcase+
Format · ShowcasePoster SessionPresenters display work; attendees browse and ask questions. Some interaction, not structured work.
Evidence basisMediumRead from source
all event9. Open discussion/panelPanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
all eventWorkshops submissions will be made through CMT. Please follow the URL below and check the required format for the application well before the proposal deadline. You may submit and update your application online right up until this deadline.WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventImportant dates for workshop submissions:WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventWorkshop Application Deadline: Feb 13, 2026 AOEWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventWorkshop Notification: Mar 20, 2026 AOEWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all event<https://cmt3.research.microsoft.com/ICMLWORKSHOPS2021>WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventThe organizers of each accepted workshop can name four individuals per day of the workshop to receive complimentary workshop registrations. In the event the conference sells out, each workshop will be given a number of guaranteed registrations for the workshop contributors, so please let us know in the application how many registrations you anticipate you will need.WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventWorkshop titleWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventA brief description of the topics to be covered, and an explanation as to why the workshop will appeal to ICML audiencesWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventA short description and rough timetable of the planned activities (talks, posters, panels)PanelDeliberation+
Format · BroadcastPanelExperts discuss while the audience watches. Surfaces perspective but rarely creates participant work.
Evidence basisMediumRead from source
all eventA description of the history of the workshop (if it previously took place, then when/where)WorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventSimilar past and current events at ICML and NeurIPS in the last 1-2 years, even if not organized by the present workshop organizers. New workshops are welcome to build on prior workshops if a good case is made; completely original workshops are also welcome.Opening RemarksOrientation+
Format · BroadcastOpening RemarksFraming or welcome from the stage. Orients the room, not participatory.
Evidence basisMediumRead from source
all eventA brief description of how you plan to make the workshop interactive (e.g., pre-recorded videos vs. live sessions) and how you plan to engage potential attendees across the globe in vastly different time zonesWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventWorkshop review committeeWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventICML 2021 Workshop ChairsWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
all eventworkshop-chairs@icml.ccWorkshopCo Creation+
Format · Participant workWorkshopParticipants work on a problem and produce something. The strongest signal of participation architecture.
Evidence basisMediumRead from source
The Full Reading
Why It Ranks This Way +
Calibrated from GES design 39/100 and verified 38/100 with no fourth-loop cap.
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 learning transfer 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, Learning Transfer, and Problem Specificity. Weakest signals: Follow Through, Network Design, and Personalization.
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.
- Create role-based paths, prepared questions, tailored breakouts, or participant-specific next steps.
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 icml.cc. 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.
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
- No fourth-loop score cap applied.
Review flags
- 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_2021_icml_self_improving_language_models_for_evolutionary_program_synthesis_a_ca_94810f"><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.