{"paper_id":"2610.01897","title":"Shared Models, Selective Trading, and Order Flow","authors":["Victoria Ruojie Li","Arka Prava Bandyopadhyay"],"paper_date":"2026-10-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2610.01897","page_url":"https://thequant.space/flowcharts/shared-models-selective-trading-and-order-flow/","scores":{"empirical_rigor":7,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper contributes a measured distinction between installed model diversity and active representation of models in trading, rather than discovering heterogeneous LLM behavior.","quote":"Our contribution is a measured distinction between installed and active model composition, not the discovery of heterogeneous LLM behavior.","summary":"We study whether model diversity survives selection into trading. In synthetic markets with a fixed mixture of three language-model families, news presentation changes their representation among submitted orders. At the announcement round, Qwen's share of submitted orders shifts by 48 percentage…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Agents’ actions are independent conditional on a fixed cell and a fixed population assignment, with buy, sell, and hold probabilities summing to one.","type":"model","stated":"explicit","quote":"Suppose that, conditional on a fixed cell and a fixed population assignment, agents’ actions are independent, with buy, sell, and hold probabilities bi, si, hi, summing to one.","support":"full"},{"assumption":"Direction exchangeability among active agents conditional on seed and round is assumed for the null hypothesis.","type":"statistical","stated":"explicit","quote":"The null assumes direction exchangeability among active agents conditional on seed and round.","support":"full"},{"assumption":"The event round is exactly t = 5 or t = 12, with t = 5 used for participation and rationale counts.","type":"other","stated":"explicit","quote":"The event round is exactly t = 5 or t = 12, 5 used for participation and rationale counts.","support":"full"},{"assumption":"The event window comprises the event round and the following two rounds for co‑action and homogeneous‑flow analyses.","type":"other","stated":"explicit","quote":"The event window comprises that round and the following two rounds, used for the stated co-action and homogeneous-flow analyses.","support":"full"},{"assumption":"Background liquidity is thick and constrains the price response, implying elastic liquidity supply.","type":"market","stated":"explicit","quote":"The exact prompt and recorded treatment texts are reproduced in Appendix D. The thick background liquidity constrains the price response.","support":"full"},{"assumption":"Agents face disclosed cash, inventory, fees, a five‑share cap and a mean‑variance objective, and utility regret is measured relative to the best feasible decision.","type":"execution","stated":"explicit","quote":"Agents face disclosed cash, inventory, fees, a five-share cap and a stated mean–variance objective. For a provider with slope 1/λ, a signed order q at pre-order midpoint m costs C(q; m) = mq + q2 2λ + k|q|, m+ = m + q/λ.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Synthetic market simulations with three language‑model families","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"In synthetic markets with a fixed mixture of three language-model families, news presentation changes their representation among submitted orders.","support":"full"},{"name":"Audited decision logs (115,500 decisions)","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"No JSON parse failures occur in the 115,500 decisions in that audited set.","support":"full"},{"name":"News text bundles (Design A factual, layoff factual, explanatory, etc.)","provider":null,"kind":"text-news","access":"unknown","period":null,"universe":null,"quote":"40 News 06 Used in: Design A factual, t = 5. News 07 Used in: Layoff factual, cash-first, t = 5.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R4a","candidates":{"front_matter":"n/a","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Order cost includes a linear term, quadratic impact term (q^2/(2λ)) and a fee proportional to |q| (k|q|).","card_quote":"For a provider with slope 1/λ, a signed order q at pre-order midpoint m costs C(q; m) = mq + q2 2λ + k|q|, m+ = m + q/λ.","meaning":"the paper reports no trading or execution result; the cost the extractor found is a model parameter"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"In the financing announcement, Qwen's share of submitted orders shifts by 48 percentage points, with little change in net order counts.","kind":"performance","quote":"At the announcement round, Qwen's share of submitted orders shifts by 48 percentage points in the financing event, with little change in net order counts.","support":"full"},{"finding":"In the layoff event, Mistral's share shifts by 40 percentage points and net counts reverse sign.","kind":"performance","quote":"In the workforce-reduction event, Mistral's share shifts by 40 percentage points while net counts reverse sign.","support":"full"},{"finding":"Homogeneous model populations remove opposing flow when the active family supplies an extreme direction.","kind":"theoretical","quote":"Homogeneous populations remove opposing flow when their active decisions share a direction.","support":"full"},{"finding":"Selection can improve or worsen price accuracy even when aggregate demand sensitivity is unchanged.","kind":"theoretical","quote":"An analytical decomposition shows why selection can improve or worsen price accuracy even at unchanged aggregate demand sensitivity.","support":"full"},{"finding":"Presentation bundles change the family composition of submitted orders in both synthetic announcement settings.","kind":"performance","quote":"In two synthetic announcement settings, presentation bundles change the family composition of submitted orders. The layoff contrast moves both active representation and aggregate direction; the financing contrast shows that large representation changes can coexist with little change in signed order counts.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T19:39:18Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}