{"paper_id":"2512.17923","title":"Inferring Latent Market Forces: Evaluating LLM Detection of Gamma Exposure Patterns via Obfuscation Testing","authors":["Christopher Regan","Ying Xie"],"paper_date":"2025-12-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2512.17923v2","page_url":"https://thequant.space/flowcharts/inferring-latent-market-forces-evaluating-llm-detection-of/","scores":{"empirical_rigor":7,"math_complexity":2.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a novel obfuscation testing methodology to validate whether large language models detect structural market patterns through causal reasoning.","quote":"We introduce obfuscation testing, a novel methodology for validating whether large language models detect structural market patterns through causal reasoning rather than temporal association.","summary":"We introduce obfuscation testing, a novel methodology for validating whether large language models detect structural market patterns through causal reasoning rather than temporal association. Testing three dealer hedging constraint patterns (gamma positioning, stock pinning, 0DTE hedging) on 242…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Practitioner gamma exposure calculations assume aggregate customers are net short calls and net long puts.","type":"market","stated":"explicit","quote":"Practitioner gamma exposure (GEX) calculations assume aggregate customers are net short calls and net long puts, an assumption that generally holds for index options."},{"assumption":"Dealers must hedge gamma exposure to maintain delta neutrality regardless of measurement methodology.","type":"market","stated":"explicit","quote":"Dealers must hedge gamma exposure to maintain delta neutrality regardless of measurement methodology, so detected patterns reflect fundamental market mechanics rather than artifacts of any particular estimation formula."},{"assumption":"Detection threshold is set at 60% confidence for mechanical classification.","type":"statistical","stated":"explicit","quote":"Detection threshold set at 60% confidence for MECHANICAL classification, with 95% confidence intervals using binomial proportion tests."},{"assumption":"Null hypothesis assumes 50% random detection; detection must significantly exceed this baseline.","type":"statistical","stated":"explicit","quote":"Our null hypothesis assumes 50% random detection; actual detection must significantly exceed this baseline (binomial test, p < 0.05)."},{"assumption":"Transaction costs are 5 basis points per trade.","type":"execution","stated":"explicit","quote":"TC is transaction costs (5 basis points per trade)."}]},"datasets":{"status":"available","items":[{"name":"S&P 500 ETF (SPY) options data","provider":null,"kind":"options","access":"public","period":"2024-01-02 to 2024-12-31","universe":"SPY options across strikes ±10% from spot","quote":"We analyze S&P 500 ETF (SPY) options data covering 2024 from January 2 to December 31. Our dataset comprises 242 trading days (95.6% of 253 expected trading days), with end-of-day snapshots including complete bid/ask spreads, open interest, implied volatility, and Greeks for all available strikes and expirations."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"5 basis points per trade","quote":"TC is transaction costs (5 basis points per trade).","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"5 basis points per trade","card_quote":"TC is transaction costs (5 basis points per trade).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"LLMs achieve a 71.5% detection rate of dealer hedging patterns using unbiased prompts across 242 trading days.","kind":"performance","quote":"we find LLMs achieve 71.5% detection rate using unbiased prompts that provide only raw gamma exposure values without regime labels or temporal context."},{"finding":"Forward market behavior materializes for 91.2% of detections, indicating high predictive accuracy.","kind":"predictive-accuracy","quote":"Result: 91.2% accuracy across all detections"},{"finding":"Causal attribution (WHO→WHOM→WHAT) is correct for 100% of detected patterns.","kind":"statistical","quote":"Result: 100% correct causal attribution for detected patterns"},{"finding":"Detection rates remain stable across quarters (68.2%–73.6%) despite economic alpha declining from +21 bps to 0 bps.","kind":"performance","quote":"Detection rates remain stable (100% to 84%) while net alpha declines from +21 bps to -1 bp across quarters, validating structural pattern detection independent of economic outcomes."},{"finding":"Bootstrap resampling yields a mean detection rate of 71.3% (std 2.1%), confirming result stability.","kind":"statistical","quote":"Bootstrap resampling (10,000 iterations) yields consistent detection rates (mean: 71.3%, std: 2.1%), confirming result stability."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":28,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/iAmGiG/gex-llm-patterns","note":null},"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":1,"extracted_at":"2026-11-14T17:19:38Z"},"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/"}