{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_earningsedge","slug":"earningsedge","name":"EarningsEdge","type":"product","url":"https://www.earningsedge.ai","page_url":"https://unfragile.ai/earningsedge","categories":["data-analysis"],"tags":[],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_earningsedge__cap_0","uri":"capability://data.processing.analysis.earnings.transcript.extraction.and.parsing","name":"earnings-transcript-extraction-and-parsing","description":"Automatically extracts structured data from unstructured earnings call transcripts and SEC filings (10-K, 10-Q, 8-K) using NLP-based document parsing and entity recognition. The system identifies key sections (management discussion, guidance, risk factors) and normalizes formatting across different filing formats and company styles, enabling downstream analysis on standardized data structures rather than raw text.","intents":["I want to quickly extract earnings guidance, revenue projections, and management commentary from 50+ earnings transcripts without manual copy-pasting","I need to compare how different companies structure their earnings disclosures to identify anomalies or red flags","I want to track changes in management tone and risk language across quarterly filings to detect sentiment shifts"],"best_for":["retail investors analyzing multiple companies in parallel","portfolio managers needing rapid earnings intake workflows","quantitative traders building earnings-driven signals"],"limitations":["OCR accuracy on scanned PDFs may degrade extraction quality for older filings or non-standard formats","Entity recognition may conflate similar company names or misidentify forward-looking statements vs. historical data","Parsing latency scales with document length; 100+ page filings may take 30-60 seconds per document"],"requires":["Access to earnings transcripts (via SEC EDGAR API, company investor relations sites, or third-party data providers)","Internet connectivity for real-time filing retrieval","Sufficient storage for caching parsed documents (estimated 10-50 MB per 100 filings)"],"input_types":["PDF (SEC filings)","plain text (earnings call transcripts)","HTML (investor relations web pages)"],"output_types":["JSON (structured metadata: guidance, key metrics, speaker attribution)","CSV (tabular earnings data for spreadsheet import)","text (normalized transcript with section labels)"],"categories":["data-processing-analysis","document-parsing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_1","uri":"capability://data.processing.analysis.sentiment.analysis.on.earnings.content","name":"sentiment-analysis-on-earnings-content","description":"Applies fine-tuned sentiment classification models to earnings transcripts, management commentary, and analyst Q&A sections to quantify management tone, confidence levels, and risk perception. The system uses transformer-based models (likely BERT or similar) trained on financial language corpora to detect nuanced sentiment beyond simple positive/negative polarity, including hedging language, uncertainty markers, and shifts in tone across different speakers (CEO vs. CFO).","intents":["I want to quantify whether management sounds more or less confident about future growth compared to last quarter","I need to detect when executives use hedging language or downplay risks, which might signal hidden concerns","I want to compare sentiment across different earnings calls to identify outliers or unusual management behavior"],"best_for":["sentiment-driven traders looking for early signals of management confidence shifts","fundamental analysts seeking quantitative backing for qualitative observations","portfolio managers monitoring management quality and transparency"],"limitations":["Sentiment models trained on general financial text may misclassify industry-specific jargon or technical language as negative when it's neutral","Sarcasm, irony, and context-dependent sentiment in live Q&A sections are difficult to classify accurately","Sentiment scores are relative and lack absolute calibration; a score of 0.6 doesn't directly map to price movement probability"],"requires":["Parsed earnings transcript data (from earnings-transcript-extraction capability)","Pre-trained financial sentiment model or access to fine-tuning data","Computational resources for transformer inference (GPU recommended for <1 second latency per transcript)"],"input_types":["text (earnings transcript sections)","structured JSON (speaker-attributed quotes)"],"output_types":["JSON (sentiment scores per section, speaker, or sentence)","CSV (aggregated sentiment metrics by company/quarter)","visualization (sentiment trend charts)"],"categories":["data-processing-analysis","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_10","uri":"capability://planning.reasoning.portfolio.impact.analysis.for.earnings","name":"portfolio-impact-analysis-for-earnings","description":"Analyzes the potential impact of earnings announcements on a user's portfolio, aggregating earnings data, sentiment, and price predictions across all holdings. The system calculates portfolio-level exposure to earnings events (e.g., 'your portfolio has 5 earnings announcements in the next week') and estimates potential portfolio volatility or returns based on individual stock predictions. May include scenario analysis (e.g., 'if all earnings beat, portfolio return is +2%') and correlation analysis between holdings.","intents":["I want to know how much of my portfolio is exposed to earnings announcements in the next week so I can manage risk","I need to estimate the potential impact of upcoming earnings on my portfolio value to decide if I should hedge","I want to see which holdings have the highest earnings-driven volatility so I can rebalance if needed"],"best_for":["portfolio managers managing multi-position portfolios with earnings exposure","risk managers assessing earnings-driven portfolio volatility","retail investors wanting to understand their earnings event risk"],"limitations":["Aggregating individual stock predictions to portfolio level introduces compounding error; portfolio-level prediction accuracy is lower than individual stock accuracy","Correlation assumptions may be wrong; stocks in the same sector may move differently based on company-specific earnings surprises","Scenario analysis assumes independence between earnings outcomes; in reality, sector-wide earnings misses are correlated","No built-in hedging recommendations; analysis is informational only"],"requires":["User portfolio data (holdings, quantities, entry prices)","Individual stock earnings predictions and sentiment scores","Historical correlation data between holdings"],"input_types":["JSON (portfolio holdings, earnings data for each holding)","structured data (historical correlations, volatility estimates)"],"output_types":["JSON (portfolio-level earnings exposure, potential impact estimates)","CSV (earnings calendar for portfolio holdings)","visualization (portfolio earnings exposure heatmap, scenario analysis)"],"categories":["planning-reasoning","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_11","uri":"capability://tool.use.integration.earnings.data.export.and.integration","name":"earnings-data-export-and-integration","description":"Enables export of earnings data, sentiment scores, and predictions in standard formats (CSV, JSON, Excel) for integration with external tools (spreadsheets, trading platforms, custom analysis tools). May include API endpoints for programmatic access to earnings data and real-time data feeds. Supports integration with popular platforms (TradingView, Interactive Brokers, etc.) via webhooks or native integrations.","intents":["I want to export earnings data to Excel so I can build my own analysis models","I need to integrate EarningsEdge sentiment scores into my trading platform via API so I can automate my trading","I want to set up a webhook that sends earnings alerts to my Slack channel so my team is notified immediately"],"best_for":["quantitative traders building custom analysis tools","teams wanting to integrate earnings data into their workflow","developers building applications that consume earnings data"],"limitations":["API rate limits may restrict high-frequency data access","Data freshness varies by export format; real-time API may have lower latency than batch CSV exports","Integration with third-party platforms requires platform-specific API knowledge","No built-in data transformation; users must handle format conversion and data cleaning"],"requires":["API infrastructure for data export (REST API, GraphQL, or similar)","Authentication and rate limiting for API access","Webhook infrastructure for real-time notifications"],"input_types":["JSON (earnings data, sentiment scores, predictions)"],"output_types":["CSV (tabular export for spreadsheets)","JSON (structured data for APIs)","Excel (formatted export with charts)","webhook payloads (real-time notifications)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_2","uri":"capability://data.processing.analysis.multi.source.market.sentiment.aggregation","name":"multi-source-market-sentiment-aggregation","description":"Aggregates sentiment signals from multiple sources (earnings transcripts, analyst reports, social media, news articles, options market data) into a unified sentiment score or signal. The system likely uses weighted averaging or ensemble methods to combine heterogeneous data sources, with configurable weights reflecting data quality, timeliness, and predictive power. Integration points may include APIs for news aggregation (Bloomberg, Reuters), social media sentiment (Twitter/X, StockTwits), and options market data (implied volatility, put/call ratios).","intents":["I want a single 'sentiment score' that combines earnings sentiment, news sentiment, and retail trader sentiment to gauge overall market perception","I need to detect divergences between institutional sentiment (options market) and retail sentiment (social media) as potential trading signals","I want to weight earnings sentiment more heavily than social media noise because earnings are more predictive"],"best_for":["quantitative traders building multi-factor sentiment models","retail investors wanting a 'consensus view' without manually checking 10 different sources","portfolio managers monitoring real-time sentiment shifts across their holdings"],"limitations":["Aggregation weights are arbitrary without backtesting; equal weighting or platform-chosen weights may not reflect actual predictive power","Sentiment from different sources (earnings vs. social media) may not be directly comparable; a 0.7 sentiment score from earnings is not equivalent to 0.7 from Twitter","Lagging data sources (analyst reports, news articles) may be stale by the time they're aggregated, reducing signal quality","No built-in mechanism to detect and filter coordinated sentiment manipulation or bot activity on social media"],"requires":["API keys or data subscriptions for multiple sentiment sources (news APIs, social media APIs, options data providers)","Real-time or near-real-time data ingestion infrastructure","Sentiment models for each source type (earnings, news, social media, options)"],"input_types":["JSON (sentiment scores from individual sources)","structured data (options market metrics: IV, put/call ratio)","text (news articles, social media posts)"],"output_types":["JSON (aggregated sentiment score, source breakdown, confidence intervals)","CSV (time-series sentiment data for backtesting)","visualization (sentiment dashboard with source contribution)"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_3","uri":"capability://data.processing.analysis.earnings.surprise.detection.and.quantification","name":"earnings-surprise-detection-and-quantification","description":"Compares actual reported earnings metrics (EPS, revenue, guidance) against consensus estimates and historical trends to quantify the magnitude and direction of surprises. The system retrieves consensus estimates from data providers (FactSet, Bloomberg, Yahoo Finance API), calculates surprise ratios (actual vs. estimate), and flags statistically significant deviations. May include anomaly detection to identify unusual patterns (e.g., massive beats on revenue but misses on guidance) that warrant deeper investigation.","intents":["I want to automatically flag earnings that beat or miss consensus by more than 5% so I can investigate them immediately","I need to track whether a company consistently beats or misses guidance to assess management credibility","I want to identify earnings surprises that contradict market expectations (e.g., beat on numbers but negative guidance) as potential trading signals"],"best_for":["event-driven traders looking for earnings surprise alpha","fundamental analysts assessing management guidance accuracy","quantitative researchers building earnings surprise prediction models"],"limitations":["Consensus estimates are backward-looking and may not reflect the most recent analyst revisions; using stale estimates reduces signal quality","Surprise magnitude alone doesn't predict price movement; a 10% EPS beat may be priced in if it was widely expected","Guidance surprises are harder to quantify than earnings surprises because guidance is often qualitative or ranges rather than point estimates","Data latency: consensus estimates may not be updated until after market close, limiting intraday trading opportunities"],"requires":["Access to consensus estimate data (via FactSet, Bloomberg, Yahoo Finance API, or similar)","Real-time or same-day earnings announcement data","Historical earnings data for trend analysis and baseline calculation"],"input_types":["JSON (reported earnings metrics from parsed filings)","structured data (consensus estimates from data providers)","historical time-series (prior quarter/year earnings)"],"output_types":["JSON (surprise magnitude, direction, statistical significance)","CSV (earnings surprise metrics for backtesting)","alerts (real-time notifications for significant surprises)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_4","uri":"capability://planning.reasoning.predictive.price.movement.scoring","name":"predictive-price-movement-scoring","description":"Generates forward-looking probability scores or confidence levels for stock price movements following earnings announcements, based on machine learning models trained on historical earnings data, sentiment signals, surprise metrics, and price action. The model likely uses gradient boosting (XGBoost, LightGBM) or neural networks to combine multiple features (earnings surprise, sentiment, volatility, sector trends) into a single prediction score. Outputs may include directional probability (likelihood of up/down move), magnitude estimates (expected % move), and confidence intervals.","intents":["I want a probability score for whether a stock will move up or down after earnings so I can size my position accordingly","I need to estimate the expected magnitude of a post-earnings move to set stop-loss and take-profit levels","I want to identify low-confidence predictions where the model is uncertain, so I can avoid trading those setups"],"best_for":["options traders pricing earnings moves and selling volatility","event-driven traders looking for high-conviction setups","retail investors wanting quantitative backing for earnings trades"],"limitations":["Model accuracy is not transparently disclosed; without backtesting results, it's impossible to assess whether predictions are better than random or simple heuristics","Historical earnings patterns may not persist; market regimes change, and models trained on 2015-2020 data may not work in 2024","Predictions are probabilistic, not deterministic; a 70% probability of up move still means 30% chance of down move, and actual outcomes will vary","Model may be overfit to recent data or specific sectors, reducing generalization to new companies or market conditions","Black-box nature of ML models makes it difficult to understand which factors drive predictions or to adjust for regime changes"],"requires":["Historical earnings data (5+ years recommended for robust model training)","Feature engineering pipeline (sentiment scores, surprise metrics, volatility, sector data)","ML infrastructure for model training and inference (Python, scikit-learn, XGBoost, or similar)","Backtesting framework to validate model accuracy before live trading"],"input_types":["JSON (earnings metrics, sentiment scores, surprise ratios)","structured data (historical price data, volatility, sector trends)","time-series (prior earnings outcomes for training)"],"output_types":["JSON (probability score, confidence interval, feature importance)","CSV (predictions for backtesting)","visualization (probability distribution, confidence bands)"],"categories":["planning-reasoning","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_5","uri":"capability://automation.workflow.watchlist.and.alert.management","name":"watchlist-and-alert-management","description":"Enables users to create custom watchlists of companies and set rule-based alerts for earnings events, sentiment thresholds, or price movements. The system likely uses a rules engine to evaluate conditions (e.g., 'alert me if earnings surprise > 10% AND sentiment score > 0.7') and triggers notifications via email, SMS, or in-app push. Watchlist data is persisted in a user database, and alerts are evaluated in real-time or on a scheduled basis as new earnings data arrives.","intents":["I want to monitor 20 stocks in my portfolio and get notified immediately when earnings are released","I want to set up an alert that triggers only when earnings surprise AND sentiment are both positive, to avoid false signals","I want to track which alerts have led to profitable trades so I can refine my alert rules over time"],"best_for":["active traders managing multiple positions and needing real-time alerts","portfolio managers monitoring earnings across their holdings","retail investors wanting to automate their earnings monitoring workflow"],"limitations":["Alert fatigue: too many alerts reduce signal quality and lead to decision paralysis","Rules engine may not support complex logic (e.g., 'alert if sentiment is positive AND surprise is positive BUT guidance is negative'); overly simple rule sets miss nuanced setups","Notification delivery latency: email/SMS may arrive seconds or minutes after the condition is triggered, reducing actionability","No built-in mechanism to track alert performance or A/B test different rule sets"],"requires":["User authentication and account management system","Database for storing watchlists and alert rules (SQL or NoSQL)","Real-time or near-real-time data pipeline for evaluating alert conditions","Notification service (email, SMS, push notification API)"],"input_types":["JSON (watchlist symbols, alert rules)","structured data (earnings data, sentiment scores, price data)"],"output_types":["notifications (email, SMS, in-app alerts)","JSON (alert history, performance metrics)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_6","uri":"capability://data.processing.analysis.comparative.earnings.analysis.across.peers","name":"comparative-earnings-analysis-across-peers","description":"Enables side-by-side comparison of earnings metrics, guidance, and sentiment across peer companies or industry groups. The system normalizes metrics across companies (e.g., revenue growth %, margin trends, guidance changes) and highlights outliers or divergences. May include peer grouping logic (automatic or manual) and visualization tools to show relative performance. Useful for identifying which companies in a sector are outperforming or underperforming relative to peers.","intents":["I want to see how Company A's revenue growth compares to its 5 closest competitors to assess relative strength","I need to identify which companies in the semiconductor sector are guiding down while others guide up, to find relative winners/losers","I want to compare management tone across a sector to see if pessimism is widespread or company-specific"],"best_for":["sector analysts comparing relative performance across industry groups","fundamental investors identifying relative value opportunities","traders looking for relative strength/weakness signals within sectors"],"limitations":["Normalization of metrics across companies with different business models (e.g., SaaS vs. hardware) may be misleading","Peer grouping is subjective; automatic peer selection may group non-comparable companies","Sentiment comparison across companies assumes sentiment models are equally accurate for all companies, which may not be true","Requires earnings data for all peers; missing data for one company breaks the comparison"],"requires":["Earnings data for multiple companies (from earnings-transcript-extraction capability)","Peer grouping logic (manual or automatic based on industry classification)","Normalized metrics calculation (handling different fiscal year ends, accounting standards)"],"input_types":["JSON (earnings metrics for multiple companies)","structured data (peer group definitions, industry classifications)"],"output_types":["JSON (comparative metrics, outlier flags)","CSV (peer comparison table for spreadsheet analysis)","visualization (peer comparison charts, heatmaps)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_7","uri":"capability://data.processing.analysis.historical.earnings.pattern.analysis","name":"historical-earnings-pattern-analysis","description":"Analyzes historical earnings patterns for individual companies to identify recurring trends, seasonality, or management behavior patterns. The system compares current earnings against historical baselines (same quarter last year, 5-year average, trend line) and flags deviations. May include analysis of management guidance accuracy over time, consistency of beat/miss patterns, and changes in key metrics (margins, growth rates). Useful for assessing management credibility and predicting future earnings quality.","intents":["I want to see if Company X consistently beats earnings or if recent beats are anomalies","I need to assess whether management's guidance is reliable by comparing past guidance to actual results","I want to identify if a company's margins are trending up or down relative to historical averages"],"best_for":["fundamental analysts assessing management quality and earnings sustainability","long-term investors evaluating business quality and predictability","quantitative researchers building earnings quality metrics"],"limitations":["Historical patterns may not persist; a company that consistently beat earnings may start missing if business fundamentals change","Seasonality analysis requires 5+ years of data; companies with shorter histories or recent IPOs lack sufficient history","Management changes, M&A activity, or business model shifts can invalidate historical patterns","Guidance accuracy analysis is backward-looking and doesn't predict future accuracy"],"requires":["5+ years of historical earnings data for each company","Time-series analysis tools (Python, R, or similar)","Baseline calculation methods (moving averages, trend lines, seasonal decomposition)"],"input_types":["time-series (historical earnings metrics, guidance, actual results)","structured data (company events: M&A, management changes, business model shifts)"],"output_types":["JSON (historical patterns, trend analysis, guidance accuracy metrics)","CSV (time-series data for visualization)","visualization (historical trend charts, seasonality plots)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_8","uri":"capability://automation.workflow.earnings.calendar.and.scheduling","name":"earnings-calendar-and-scheduling","description":"Maintains a real-time earnings calendar showing upcoming earnings announcement dates, times, and expected metrics. The system integrates with company investor relations data, SEC filing schedules, and market data providers to populate and update the calendar. Users can filter by date range, sector, market cap, or custom criteria. May include integration with trading platforms to enable one-click trading on earnings events.","intents":["I want to see all earnings announcements for the next 2 weeks so I can plan my trading schedule","I need to filter earnings calendar to show only mega-cap tech companies with high expected volatility","I want to set a reminder for earnings announcements so I don't miss important events"],"best_for":["active traders planning earnings-driven trading strategies","portfolio managers tracking earnings dates for their holdings","retail investors wanting to stay informed about upcoming earnings"],"limitations":["Earnings dates are sometimes changed or delayed; calendar may be out of sync with actual announcement times","Expected metrics (consensus estimates) may be stale or inaccurate","No built-in analysis of earnings quality or expected volatility; calendar is primarily informational"],"requires":["Real-time data integration with SEC EDGAR, company investor relations sites, or market data providers","Database for storing earnings calendar data","User interface for filtering and viewing calendar"],"input_types":["structured data (earnings dates, times, expected metrics)"],"output_types":["JSON (earnings calendar data, filtered results)","CSV (earnings calendar export for spreadsheet/calendar apps)","visualization (calendar view, list view)"],"categories":["automation-workflow","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_earningsedge__cap_9","uri":"capability://planning.reasoning.backtesting.framework.for.earnings.strategies","name":"backtesting-framework-for-earnings-strategies","description":"Provides a backtesting engine for testing earnings-based trading strategies against historical data. Users define strategy rules (e.g., 'buy if earnings surprise > 10% AND sentiment > 0.7, hold for 5 days') and the system simulates trades on historical earnings data, calculating returns, win rate, Sharpe ratio, and other performance metrics. May include walk-forward analysis to test strategy robustness across different time periods and market regimes.","intents":["I want to test my earnings trading strategy on 5 years of historical data to see if it's profitable before risking real money","I need to compare the performance of different alert rules to identify which combinations are most profitable","I want to understand how my strategy performs in different market regimes (bull, bear, high volatility) to assess robustness"],"best_for":["quantitative traders developing and validating earnings strategies","retail investors wanting to backtest their trading ideas before live trading","strategy researchers studying earnings alpha and market efficiency"],"limitations":["Backtesting assumes perfect execution and no slippage; real trading will have worse results due to bid-ask spreads, commissions, and execution delays","Backtesting on historical data may overfit to past patterns; strategies that work on 2015-2020 data may fail in 2024","Survivorship bias: backtesting only includes companies that survived to the present, excluding delisted or bankrupt companies","Look-ahead bias: if sentiment or surprise data is not properly time-stamped, backtesting may use future information","No built-in mechanism to account for market impact of large positions or liquidity constraints"],"requires":["Historical earnings data (5+ years recommended)","Historical price data (OHLCV) for backtesting","Strategy definition language or UI for specifying rules","Backtesting engine (Python, C++, or similar) for fast simulation"],"input_types":["JSON (strategy rules, parameters)","time-series (historical earnings data, price data, sentiment scores)"],"output_types":["JSON (backtest results: returns, Sharpe ratio, win rate, drawdown)","CSV (trade-by-trade results for analysis)","visualization (equity curve, drawdown chart, performance metrics)"],"categories":["planning-reasoning","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":40,"verified":false,"data_access_risk":"high","permissions":["Access to earnings transcripts (via SEC EDGAR API, company investor relations sites, or third-party data providers)","Internet connectivity for real-time filing retrieval","Sufficient storage for caching parsed documents (estimated 10-50 MB per 100 filings)","Parsed earnings transcript data (from earnings-transcript-extraction capability)","Pre-trained financial sentiment model or access to fine-tuning data","Computational resources for transformer inference (GPU recommended for <1 second latency per transcript)","User portfolio data (holdings, quantities, entry prices)","Individual stock earnings predictions and sentiment scores","Historical correlation data between holdings","API infrastructure for data export (REST API, GraphQL, or similar)"],"failure_modes":["OCR accuracy on scanned PDFs may degrade extraction quality for older filings or non-standard formats","Entity recognition may conflate similar company names or misidentify forward-looking statements vs. historical data","Parsing latency scales with document length; 100+ page filings may take 30-60 seconds per document","Sentiment models trained on general financial text may misclassify industry-specific jargon or technical language as negative when it's neutral","Sarcasm, irony, and context-dependent sentiment in live Q&A sections are difficult to classify accurately","Sentiment scores are relative and lack absolute calibration; a score of 0.6 doesn't directly map to price movement probability","Aggregating individual stock predictions to portfolio level introduces compounding error; portfolio-level prediction accuracy is lower than individual stock accuracy","Correlation assumptions may be wrong; stocks in the same sector may move differently based on company-specific earnings surprises","Scenario analysis assumes independence between earnings outcomes; in reality, sector-wide earnings misses are correlated","No built-in hedging recommendations; analysis is informational only","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.31666666666666665,"quality":0.72,"ecosystem":0.15000000000000002,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.35,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:30.283Z","last_scraped_at":"2026-04-05T13:23:42.561Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=earningsedge","compare_url":"https://unfragile.ai/compare?artifact=earningsedge"}},"signature":"vf8MWDdeahrPbU7usIdym5sPyHReyHBFZHgG8SLGhKMkup4P7Haj6uorteLbcRojgyBeAKk0K44EdiI5ScoZBQ==","signedAt":"2026-06-21T17:23:41.773Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/earningsedge","artifact":"https://unfragile.ai/earningsedge","verify":"https://unfragile.ai/api/v1/verify?slug=earningsedge","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}