One Signal, Many Feeds: An Empirical-Response Agent-Based Model of Coordination Failure in Algorithmic Creator Discovery (1.0.0)
An empirical-response agent-based model of how many personalized feeds execute a shared low-exposure creator-discovery objective. Built from the KuaiRec dataset: the big interaction matrix initializes a transparent rank-8 matrix-factorization platform learner and the activity schedule, while the near-complete small matrix returns observed viewing responses only after a user-video pair is exposed. Four exploration policies (synchronous low-exposure targeting, uniform exploration, per-user random tie-breaking, capacity-balanced coordination) are compared over 28 rounds at a nominal 10% exploration budget, across 30 paired seeds (core) and 10 paired seeds (bias-only probe), with slot-level redundancy, cross-user collision, and coverage diagnostics.
This release accompanies an anonymised manuscript under review at the Journal of Artificial Societies and Social Simulation.
The model represents 1,411 users, 3,327 videos, 2,031 authors, and an adaptive platform over 28 discrete rounds derived from the KuaiRec big-matrix activity calendar. Exploration policies differ only in how a fixed 10% slot budget is allocated; all policies share the opportunity schedule, response oracle, initial checkpoints, and online update rule.
Archive contents: analysis pipeline scripts (01-16), frozen machine-readable protocols with input hashes, initial model checkpoints, aggregate result tables, the complete ODD protocol record, and publication figures. Raw KuaiRec files are not redistributed; obtain them from the official dataset repository and verify against the input hashes in data_contract/. Row-level oracle tables are excluded by design.
Reproduction entry point: see README inside the archive; each script records its runtime hash, and result JSONs record input SHA-256 values.
Release Notes
First release, prepared for anonymous peer review at the Journal of Artificial Societies and Social Simulation. Contains the full analysis pipeline (scripts 01-08 and 10), frozen machine-readable experiment protocols with input hashes, immutable model checkpoints, aggregate result tables, publication figures, and complete ODD documentation. See the narrative documentation for reproduction instructions.
Associated Publications
Not yet.
One Signal, Many Feeds: An Empirical-Response Agent-Based Model of Coordination Failure in Algorithmic Creator Discovery 1.0.0
Submitted by
Haocheng Wang
Published Aug 06, 2026
Last modified Aug 06, 2026
An empirical-response agent-based model of how many personalized feeds execute a shared low-exposure creator-discovery objective. Built from the KuaiRec dataset: the big interaction matrix initializes a transparent rank-8 matrix-factorization platform learner and the activity schedule, while the near-complete small matrix returns observed viewing responses only after a user-video pair is exposed. Four exploration policies (synchronous low-exposure targeting, uniform exploration, per-user random tie-breaking, capacity-balanced coordination) are compared over 28 rounds at a nominal 10% exploration budget, across 30 paired seeds (core) and 10 paired seeds (bias-only probe), with slot-level redundancy, cross-user collision, and coverage diagnostics.
This release accompanies an anonymised manuscript under review at the Journal of Artificial Societies and Social Simulation.
The model represents 1,411 users, 3,327 videos, 2,031 authors, and an adaptive platform over 28 discrete rounds derived from the KuaiRec big-matrix activity calendar. Exploration policies differ only in how a fixed 10% slot budget is allocated; all policies share the opportunity schedule, response oracle, initial checkpoints, and online update rule.
Archive contents: analysis pipeline scripts (01-16), frozen machine-readable protocols with input hashes, initial model checkpoints, aggregate result tables, the complete ODD protocol record, and publication figures. Raw KuaiRec files are not redistributed; obtain them from the official dataset repository and verify against the input hashes in data_contract/. Row-level oracle tables are excluded by design.
Reproduction entry point: see README inside the archive; each script records its runtime hash, and result JSONs record input SHA-256 values.
Release Notes
First release, prepared for anonymous peer review at the Journal of Artificial Societies and Social Simulation. Contains the full analysis pipeline (scripts 01-08 and 10), frozen machine-readable experiment protocols with input hashes, immutable model checkpoints, aggregate result tables, publication figures, and complete ODD documentation. See the narrative documentation for reproduction instructions.