{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_mara","slug":"mara","name":"MARA","type":"product","url":"https://www.mara-solutions.com","page_url":"https://unfragile.ai/mara","categories":["text-writing"],"tags":[],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_mara__cap_0","uri":"capability://tool.use.integration.multi.platform.review.aggregation.and.unified.inbox","name":"multi-platform review aggregation and unified inbox","description":"Consolidates reviews from disparate sources (Google, Yelp, Facebook, industry-specific platforms) into a single dashboard by implementing platform-specific API connectors that poll review feeds at configurable intervals, normalize metadata (reviewer name, rating, timestamp, platform origin), and deduplicate entries across sources. Uses a centralized data model to abstract platform differences, allowing unified filtering, sorting, and triage without requiring users to visit each platform individually.","intents":["I need to see all reviews across Google, Yelp, and Facebook in one place without logging into each platform separately","I want to prioritize which reviews to respond to first based on rating, recency, or platform visibility","I need to track which reviews I've already responded to across all platforms to avoid duplicate replies"],"best_for":["small to mid-sized service businesses (restaurants, salons, medical practices) managing 50+ reviews monthly across 3+ platforms","multi-location enterprises needing centralized review triage across franchise locations"],"limitations":["API rate limits on review platforms (e.g., Google My Business API allows ~1000 requests/day) may cause delays in real-time sync for high-volume businesses","Platform API changes or deprecations require manual connector updates; no automatic fallback to web scraping","Deduplication logic may fail for reviews posted simultaneously across platforms with slight text variations","No support for private/internal review platforms or custom review systems without API documentation"],"requires":["Active business accounts on target review platforms (Google My Business, Yelp, Facebook)","API credentials/OAuth tokens for each platform (setup varies by platform)","Internet connectivity for continuous polling (recommended: webhook support for real-time updates, not guaranteed)"],"input_types":["platform API responses (JSON)","OAuth tokens","business account identifiers"],"output_types":["normalized review objects (JSON)","unified dashboard UI with filterable review feed","CSV export of aggregated reviews"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_1","uri":"capability://text.generation.language.ai.powered.review.response.suggestion.with.brand.voice.consistency","name":"ai-powered review response suggestion with brand voice consistency","description":"Analyzes incoming reviews using NLP to extract sentiment, key topics (service quality, pricing, staff, cleanliness), and urgency signals, then generates contextual response templates using a fine-tuned language model trained on business-specific brand voice examples. The system learns from user-approved responses to refine future suggestions, maintaining tone consistency through a brand voice profile (formal/casual, empathetic/direct) that acts as a constraint during generation. Responses are ranked by relevance and customization effort required.","intents":["I want AI to draft a response to this negative review that matches our brand tone without sounding generic","I need to reply to 20+ reviews today but don't want to write each response from scratch","I want to ensure all our responses sound like they come from the same person/brand, not a patchwork of different voices"],"best_for":["hospitality and service businesses (restaurants, hotels, salons) receiving 50+ reviews monthly with consistent brand voice requirements","teams with limited customer service staff who need to scale response capacity without hiring"],"limitations":["Generated responses are often generic templates requiring 30-60% manual customization to address specific review details, reducing promised time savings","Fine-tuning on brand voice requires 20-50 example responses to establish patterns; insufficient training data results in tone drift","No context awareness of previous customer interactions or history; each review is treated independently, missing opportunity for personalized follow-up","Struggles with sarcasm, cultural nuance, or highly specific service failures that require domain expertise to address credibly","No built-in A/B testing to measure response effectiveness or sentiment impact on future reviews"],"requires":["Minimum 5-10 pre-approved response examples to establish brand voice profile","Review text in English (language support unclear for other languages)","Optional: historical response data for fine-tuning (improves quality but not required)"],"input_types":["review text (string)","reviewer rating (1-5 or similar)","review metadata (platform, date, reviewer name)","brand voice examples (text samples)"],"output_types":["ranked list of response suggestions (text)","confidence scores per suggestion","tone/sentiment tags applied to original review"],"categories":["text-generation-language","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_10","uri":"capability://automation.workflow.review.monitoring.and.alert.configuration","name":"review monitoring and alert configuration","description":"Enables users to set up custom alerts triggered by specific review conditions (e.g., rating < 3, mentions of health/safety issues, competitor mentions, sudden volume spikes). Alerts are delivered via email, SMS, Slack, or in-app notifications with configurable frequency (immediate, daily digest, weekly summary). Users can define alert rules using a rule builder UI or JSON configuration. Supports alert escalation (e.g., notify manager if responder doesn't reply within 2 hours) and integration with incident management systems.","intents":["I want to be notified immediately if someone posts a 1-star review mentioning food poisoning","I want a daily digest of all new reviews instead of individual notifications","I want to escalate critical reviews to my manager if I don't respond within 2 hours"],"best_for":["reputation-sensitive businesses (healthcare, finance, hospitality) requiring rapid response to critical reviews","teams with distributed members needing flexible notification channels (email, SMS, Slack)","businesses wanting to avoid alert fatigue through intelligent batching and filtering"],"limitations":["Alert rules are static; no machine learning to auto-optimize thresholds based on business outcomes","Escalation logic is simple (time-based); no intelligent routing based on team member availability or expertise","SMS alerts incur per-message costs; no built-in cost controls or usage limits","Alert delivery is not guaranteed (depends on email/SMS provider reliability); no retry logic for failed deliveries","No integration with incident management systems (PagerDuty, Opsgenie); escalation is limited to internal team notifications"],"requires":["Review aggregation capability must be active","Alert rule configuration (UI or JSON)","Optional: notification channel credentials (Slack webhook, SMS provider API key)"],"input_types":["alert rule (condition + action)","notification channel (email, SMS, Slack, in-app)","optional: escalation policy (time-based or manual)"],"output_types":["alert notification (email/SMS/Slack/in-app)","alert history/log (JSON or UI feed)","escalation status (assigned, escalated, resolved)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_2","uri":"capability://planning.reasoning.review.prioritization.and.triage.based.on.business.impact.signals","name":"review prioritization and triage based on business impact signals","description":"Ranks reviews using a multi-factor scoring algorithm that weights sentiment (negative reviews prioritized), reviewer influence (high-follower accounts, verified purchasers), platform visibility (Google/Yelp weighted higher than niche platforms), and business impact signals (mentions of staff, pricing, or service quality issues). Allows users to customize weighting rules and set alert thresholds (e.g., notify immediately if rating < 3 and mentions 'food poisoning'). Implements rule-based filtering to surface reviews requiring urgent response vs those that can be batched.","intents":["I want to respond to the most damaging reviews first, not just the newest ones","I need alerts when a review mentions specific issues (health/safety, fraud accusations) that require immediate response","I want to ignore spam/bot reviews and focus on genuine customer feedback"],"best_for":["businesses receiving 50+ reviews monthly across multiple platforms where manual triage is time-prohibitive","reputation-sensitive industries (healthcare, finance, hospitality) where negative reviews require rapid response"],"limitations":["Scoring algorithm is opaque; users cannot easily understand why a review was prioritized, making it difficult to trust or override rankings","No built-in spam/bot detection; relies on platform-provided verification signals (verified purchaser, account age) which vary by platform","Weighting customization requires manual configuration; no machine learning to auto-optimize weights based on business outcomes (e.g., which reviews actually drove customer churn)","Alert thresholds are static; no adaptive alerting based on business seasonality or campaign timing","No integration with CRM or customer data to cross-reference reviewers and identify high-value customers whose reviews warrant priority"],"requires":["Review data from aggregation capability (review text, rating, platform, reviewer metadata)","Optional: custom weighting rules configuration (defaults provided)","Optional: alert notification channel (email, Slack, SMS)"],"input_types":["normalized review objects (from aggregation capability)","custom weighting rules (JSON or UI form)","alert threshold configuration"],"output_types":["prioritized review queue (ranked list)","alert notifications (email/Slack/SMS)","priority score per review (numeric)"],"categories":["planning-reasoning","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_3","uri":"capability://tool.use.integration.review.response.publishing.and.multi.platform.synchronization","name":"review response publishing and multi-platform synchronization","description":"Enables users to compose a single response in the MARA interface and publish it across multiple platforms (Google, Yelp, Facebook, etc.) simultaneously using platform-specific API endpoints. Handles platform-specific constraints (character limits, formatting restrictions, allowed HTML tags) by truncating or reformatting responses automatically. Tracks publication status per platform and provides audit logs showing when responses were published, by whom, and any platform-specific errors. Supports scheduled publishing and bulk response operations.","intents":["I want to reply to a review on Google and Yelp with the same response without copying/pasting between platforms","I need to ensure my response meets each platform's character limits and formatting rules automatically","I want an audit trail showing which reviews I've responded to and when, for compliance and team accountability"],"best_for":["businesses managing reviews across 3+ platforms who want to avoid manual cross-posting","teams requiring audit trails for compliance (healthcare, finance) or internal accountability"],"limitations":["Platform APIs have different rate limits and may reject bulk operations; publishing 50+ responses simultaneously may fail on some platforms","Platform-specific constraints (character limits, allowed HTML) require automatic truncation, which may remove important context or tone","No support for platform-specific response features (e.g., Google's 'owner response' vs Yelp's 'business response' have different visibility/formatting rules); responses are normalized to lowest-common-denominator format","Scheduled publishing relies on MARA's infrastructure uptime; no guarantee of exact publish time across platforms","No rollback capability; once published, responses cannot be automatically unpublished across all platforms if an error is discovered"],"requires":["API credentials/OAuth tokens for each target platform (same as aggregation capability)","Review aggregation capability must be active (to identify which reviews to respond to)","Response text (from AI suggestion or manual composition)"],"input_types":["review ID (from aggregation)","response text (string)","target platforms (list of platform names)","optional: scheduled publish time (ISO 8601 datetime)"],"output_types":["publication status per platform (success/failure)","platform-specific error messages","audit log entry (timestamp, user, review ID, platforms, response text)","published response URL per platform"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_4","uri":"capability://data.processing.analysis.review.analytics.and.sentiment.trend.reporting","name":"review analytics and sentiment trend reporting","description":"Aggregates review data over time to generate dashboards and reports showing sentiment distribution (positive/neutral/negative %), average rating trends, topic frequency analysis (which issues are mentioned most often), and platform-specific performance metrics (e.g., Google vs Yelp average ratings). Uses time-series analysis to detect sentiment shifts (e.g., sudden drop in ratings after a specific date) and correlate with business events. Exports reports as PDF or CSV for stakeholder communication. Supports custom date ranges and filtering by platform, location, or topic.","intents":["I want to see if our average rating is improving or declining over the past 3 months","I need to identify which service issues (staff, pricing, cleanliness) are mentioned most frequently in negative reviews","I want to compare our ratings across Google, Yelp, and Facebook to understand platform-specific reputation gaps","I need a report to show my board/investors how our customer satisfaction is trending"],"best_for":["multi-location businesses needing location-level sentiment comparison","businesses with seasonal patterns (e.g., restaurants, hotels) wanting to correlate reviews with business events","management/board-level stakeholders requiring high-level reputation metrics for decision-making"],"limitations":["Topic frequency analysis relies on keyword matching or basic NLP; may miss nuanced issues or conflate unrelated topics (e.g., 'staff' mentions in both positive and negative contexts counted equally)","Sentiment trend analysis is purely descriptive (shows what happened) without causal inference; cannot determine whether rating drop was due to service quality change, competitor activity, or external factors","No predictive analytics; cannot forecast future sentiment or identify at-risk customers before they leave negative reviews","Custom date ranges and filtering require manual report generation; no scheduled/automated report delivery","Platform-specific metrics are limited to what each platform's API exposes; some platforms don't provide reviewer demographics or detailed engagement metrics"],"requires":["Minimum 30 days of review data in MARA system (to establish baseline trends)","Review aggregation capability must be active and syncing data","Optional: custom date range and filtering parameters"],"input_types":["aggregated review data (from aggregation capability)","date range (start/end dates)","optional: platform filter, location filter, topic filter"],"output_types":["sentiment distribution chart (% positive/neutral/negative)","average rating trend line (time-series)","topic frequency histogram (most-mentioned issues)","platform comparison table (avg rating by platform)","PDF/CSV report export"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_5","uri":"capability://automation.workflow.team.collaboration.and.response.workflow.management","name":"team collaboration and response workflow management","description":"Enables multiple team members to access the review dashboard, assign reviews to specific users for response, and track response status (assigned, in-progress, responded, published). Implements role-based access control (manager, responder, viewer) with different permissions (e.g., responders can draft responses but managers must approve before publishing). Provides activity feeds showing who responded to which reviews and when, and supports comments/notes on reviews for internal team discussion. Integrates with email/Slack to notify assigned users of new reviews.","intents":["I want to assign reviews to different team members based on their expertise (e.g., staff issues to manager, pricing questions to sales)","I need to ensure all responses are reviewed and approved by a manager before publishing to maintain quality","I want my team to be notified immediately when a new review is assigned to them","I need visibility into which team member is responsible for each review and whether they've responded"],"best_for":["teams with 3+ members managing reviews collaboratively","businesses requiring approval workflows for compliance or quality control","distributed teams (multiple locations) needing centralized review management"],"limitations":["Role-based access control is coarse-grained (manager/responder/viewer); no fine-grained permissions (e.g., responder can only respond to reviews from their location)","No built-in conflict resolution if two team members are assigned the same review; relies on manual deconfliction","Activity feeds are append-only; no ability to track response edits or version history if a response is modified before publishing","Slack/email notifications may be noisy for high-volume review streams; no intelligent batching or digest options","No SLA tracking or escalation; cannot automatically flag reviews that have been assigned but not responded to within X hours"],"requires":["Multiple user accounts (team members must have MARA accounts)","Optional: Slack workspace or email integration for notifications","Optional: manager account for approval workflows"],"input_types":["review ID (from aggregation)","assigned user (team member email or ID)","optional: approval status (draft, approved, rejected)","optional: internal notes/comments (text)"],"output_types":["assignment notification (email/Slack)","activity feed (JSON or UI feed)","response status dashboard (assigned/in-progress/responded)","approval workflow UI (manager view)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_6","uri":"capability://safety.moderation.review.authenticity.and.spam.detection","name":"review authenticity and spam detection","description":"Analyzes incoming reviews for signals of inauthenticity (bot-generated text, suspicious reviewer patterns, platform ToS violations) using heuristics and machine learning models trained on known spam/fake review datasets. Flags reviews with low authenticity scores for manual review, and optionally filters them from the main dashboard. Detects patterns like multiple reviews from the same IP address, reviews posted in rapid succession, or text matching known spam templates. Integrates with platform-provided verification signals (verified purchaser badges, account age) to supplement detection.","intents":["I want to identify and ignore fake/spam reviews so I'm not wasting time responding to bots","I need to flag reviews that violate platform ToS (e.g., competitor sabotage, incentivized reviews) for potential removal","I want to understand which reviews are from genuine customers vs suspicious accounts"],"best_for":["businesses in competitive industries (e.g., e-commerce, hospitality) vulnerable to review manipulation","businesses with high review volume where manual spam identification is impractical"],"limitations":["Spam detection models are trained on historical data; sophisticated fake reviews designed to evade detection may not be caught","False positive rate is unknown; legitimate reviews may be flagged as spam, causing users to ignore genuine customer feedback","No integration with platform-native spam reporting; flagged reviews must be manually reported to each platform","Heuristics rely on platform-provided signals (verified purchaser, account age) which vary by platform and may not be available via API","No feedback loop to improve detection; users cannot easily report false positives/negatives to retrain models"],"requires":["Review aggregation capability must be active","Review text and metadata (reviewer account age, IP address if available, platform verification signals)"],"input_types":["review text (string)","reviewer metadata (account age, verification status, IP address if available)","platform-provided authenticity signals"],"output_types":["authenticity score (0-100)","spam flags (list of detected issues: bot-like text, suspicious IP, rapid posting, etc.)","filtered review dashboard (optional: hide low-authenticity reviews)"],"categories":["safety-moderation","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_7","uri":"capability://text.generation.language.review.response.template.library.and.customization","name":"review response template library and customization","description":"Provides a library of pre-written response templates for common scenarios (thanking positive reviewers, addressing service complaints, responding to pricing objections, handling health/safety concerns). Users can browse templates, customize them for their brand voice, and save custom templates for reuse. Templates are tagged by scenario and sentiment, enabling quick search and filtering. Integrates with the AI response suggestion capability to use templates as starting points for generation, rather than generating responses from scratch.","intents":["I want a starting point for responses to common issues without writing from scratch each time","I want to ensure consistent messaging across my team when responding to similar issues","I want to quickly find a template for a specific scenario (e.g., health/safety concern) without browsing the entire library"],"best_for":["teams with limited writing experience who benefit from structured templates","businesses with high review volume where template reuse significantly reduces response time","industries with regulatory requirements (healthcare, finance) where response consistency is critical"],"limitations":["Pre-built templates are generic and may not reflect specific business context; require customization for each use","Template library is static; no machine learning to suggest which template is most relevant for a given review","No A/B testing of templates to measure which responses drive better outcomes (e.g., higher customer satisfaction, fewer follow-up complaints)","Customized templates are stored per user; no sharing mechanism to propagate best-performing templates across the team","No version control; if a template is edited, previous versions are lost"],"requires":["Template library (provided by MARA or user-created)","Optional: custom template creation and storage"],"input_types":["template search query (text or tags)","review metadata (sentiment, topic) for template recommendation","custom template text (for saving)"],"output_types":["template list (filtered by search/tags)","template text (for copying/customization)","saved custom templates (per user or team)"],"categories":["text-generation-language","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_8","uri":"capability://memory.knowledge.business.profile.and.brand.voice.configuration","name":"business profile and brand voice configuration","description":"Allows users to create and maintain a business profile including company name, industry, location(s), brand voice guidelines (tone, values, communication style), and response preferences (e.g., always offer compensation for negative reviews, never mention competitors). The profile acts as context for AI response generation and team collaboration, ensuring all responses align with brand identity. Supports multiple profiles for multi-brand or multi-location businesses. Changes to the profile are versioned and tracked for audit purposes.","intents":["I want to define our brand voice so AI responses sound like us, not generic","I need to set company-wide response policies (e.g., always offer compensation for 1-star reviews) that apply across all team members","I want to maintain separate brand voices for different business units or locations"],"best_for":["businesses with strong brand identity or specific response policies","multi-location or multi-brand enterprises needing profile separation","teams requiring consistency enforcement across response workflows"],"limitations":["Brand voice configuration is manual; no machine learning to infer tone from historical responses","Profile changes are not automatically propagated to in-progress responses; only new responses use updated profile","No validation that responses actually follow the defined brand voice; profile is used only as a constraint during generation, not enforced post-hoc","Limited to text-based brand voice definition; no support for visual brand guidelines or tone examples beyond text samples","Version history is append-only; no ability to revert to previous profile versions if changes are made in error"],"requires":["Business information (name, industry, location)","Optional: brand voice guidelines (text description or examples)","Optional: response policies (rules/preferences)"],"input_types":["business profile data (JSON or UI form)","brand voice examples (text samples)","response policies (rules/preferences)"],"output_types":["business profile object (JSON)","brand voice constraint (used by AI response generation)","profile version history (audit log)"],"categories":["memory-knowledge","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_mara__cap_9","uri":"capability://data.processing.analysis.review.data.export.and.integration.with.external.systems","name":"review data export and integration with external systems","description":"Enables bulk export of review data (aggregated reviews, responses, analytics) in standard formats (CSV, JSON) for integration with external systems (CRM, business intelligence tools, spreadsheets). Supports scheduled exports (e.g., daily or weekly) delivered via email or uploaded to cloud storage (Google Drive, Dropbox, S3). Provides API endpoints for programmatic access to review data, enabling custom integrations. Exports include metadata (platform, date, reviewer info) and response history.","intents":["I want to export all our reviews to a spreadsheet for analysis in Excel or Google Sheets","I need to sync review data into our CRM so customer service reps can see reviews when handling support tickets","I want to automate daily exports to our data warehouse for business intelligence reporting"],"best_for":["businesses with existing data infrastructure (CRM, BI tools, data warehouse) wanting to integrate review data","teams requiring custom analysis or reporting beyond MARA's built-in analytics","enterprises with data governance requirements (e.g., data residency, audit trails)"],"limitations":["API rate limits may restrict high-frequency exports for large review volumes","Scheduled exports require MARA infrastructure uptime; no guarantee of delivery if service is down","No built-in data transformation; exports are raw data requiring downstream processing to match target system schemas","CRM/BI integrations are not pre-built; users must implement custom ETL logic or use third-party tools (Zapier, Make)","Exports include only review data and responses; no integration with team collaboration data (assignments, comments, approval status)"],"requires":["Review aggregation capability must be active","Optional: API key for programmatic access","Optional: cloud storage credentials (Google Drive, Dropbox, S3) for scheduled exports"],"input_types":["export format (CSV, JSON)","date range and filters (platform, location, sentiment)","optional: destination (email, cloud storage, API endpoint)"],"output_types":["CSV or JSON file with review data","scheduled export delivery (email or cloud storage)","API response (JSON) for programmatic access"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":38,"verified":false,"data_access_risk":"high","permissions":["Active business accounts on target review platforms (Google My Business, Yelp, Facebook)","API credentials/OAuth tokens for each platform (setup varies by platform)","Internet connectivity for continuous polling (recommended: webhook support for real-time updates, not guaranteed)","Minimum 5-10 pre-approved response examples to establish brand voice profile","Review text in English (language support unclear for other languages)","Optional: historical response data for fine-tuning (improves quality but not required)","Review aggregation capability must be active","Alert rule configuration (UI or JSON)","Optional: notification channel credentials (Slack webhook, SMS provider API key)","Review data from aggregation capability (review text, rating, platform, reviewer metadata)"],"failure_modes":["API rate limits on review platforms (e.g., Google My Business API allows ~1000 requests/day) may cause delays in real-time sync for high-volume businesses","Platform API changes or deprecations require manual connector updates; no automatic fallback to web scraping","Deduplication logic may fail for reviews posted simultaneously across platforms with slight text variations","No support for private/internal review platforms or custom review systems without API documentation","Generated responses are often generic templates requiring 30-60% manual customization to address specific review details, reducing promised time savings","Fine-tuning on brand voice requires 20-50 example responses to establish patterns; insufficient training data results in tone drift","No context awareness of previous customer interactions or history; each review is treated independently, missing opportunity for personalized follow-up","Struggles with sarcasm, cultural nuance, or highly specific service failures that require domain expertise to address credibly","No built-in A/B testing to measure response effectiveness or sentiment impact on future reviews","Alert rules are static; no machine learning to auto-optimize thresholds based on business outcomes","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.2833333333333333,"quality":0.6799999999999999,"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":"2026-05-24T12:16:31.857Z","last_scraped_at":"2026-04-05T13:23:42.562Z","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=mara","compare_url":"https://unfragile.ai/compare?artifact=mara"}},"signature":"L4E29jR/QGzR9nmk9j3JHy3pWzxJ1rE/71/vRFJ8jdOwMV7cbnWpDdEJHE8Dga3x0v6XCs+geJJCuPOEVU74AQ==","signedAt":"2026-06-21T04:27:40.465Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/mara","artifact":"https://unfragile.ai/mara","verify":"https://unfragile.ai/api/v1/verify?slug=mara","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"}}