Research program / tracks

Four permanent tracks

Every research round contributes to one or more long-running tracks, so questions carry forward instead of ending with a paper.

T1
Collaborative Intelligence
When does dividing reasoning across specialists help, and when does it fragment evidence?
Communication protocols between agents, evidence exchange versus conclusion sharing, correlated errors, and how disagreement should change a conclusion.
Round 54 Round 53 Round 52 Round 51 Round 50 Round 49 Round 48 Round 47 Round 46 Round 45 Round 44 Round 43 Round 17 Round 15 Round 10 Round 3
Read the Collaborative Intelligence track →
Rounds
16
Hypotheses
31
T2
Artificial Cognitive Architecture
How should capable models be organized into a system?
Role specialization, working memory, selective activation, controllers that allocate effort, and brain-inspired ideas treated as testable engineering hypotheses, not emulation.
Round 54 Round 53 Round 52 Round 51 Round 50 Round 49 Round 42 Round 41 Round 40 Round 39 Round 38 Round 37 Round 36 Round 35 Round 34 Round 33 Round 32 Round 31 Round 30 Round 29 Round 28 Round 27 Round 26 Round 25 Round 24 Round 23 Round 22 Round 21 Round 20 Round 19 Round 18 Round 17 Round 16 Round 15 Round 11 Round 10 Round 9 Round 8 Round 3
Read the Artificial Cognitive Architecture track →
Rounds
39
Hypotheses
48
T3
Reasoning & Verification
How does a system know when an answer is ready to release?
Claim-level evidence review, bounded repair, revision drift, terminal release gates, and calibration of the final revised answer.
Round 54 Round 53 Round 52 Round 51 Round 50 Round 48 Round 47 Round 46 Round 45 Round 44 Round 43 Round 42 Round 41 Round 40 Round 39 Round 38 Round 37 Round 36 Round 35 Round 34 Round 33 Round 32 Round 31 Round 30 Round 29 Round 28 Round 27 Round 26 Round 25 Round 24 Round 23 Round 22 Round 21 Round 20 Round 19 Round 18 Round 16 Round 14 Round 13 Round 12 Round 11
Read the Reasoning & Verification track →
Rounds
41
Hypotheses
123
T4
Evaluation Science
How do we measure whether an architecture change actually improved reasoning?
Endpoint definition, scorer failure modes, matched-cost comparisons, ablations, and the separation of diagnostic scores from adjudicated quality.
Round 54 Round 53 Round 52 Round 51 Round 50 Round 49 Round 48 Round 47 Round 46 Round 45 Round 44 Round 43 Round 42 Round 41 Round 40 Round 39 Round 38 Round 37 Round 36 Round 35 Round 34 Round 33 Round 32 Round 31 Round 30 Round 29 Round 28 Round 27 Round 26 Round 25 Round 24 Round 23 Round 22 Round 21 Round 20 Round 19 Round 18 Round 17 Round 16 Round 15 Round 14 Round 13 Round 12
Read the Evaluation Science track →
Rounds
43
Hypotheses
55

Collaborative Intelligence

Artificial Cognitive Architecture

Reasoning & Verification

Evaluation Science