HelixSo / candidate_schema.json
sf0Jmn's picture
Upload folder using huggingface_hub
9350b4b verified
Raw
History Blame Contribute Delete
8.82 kB
{
"$schema": "http://json-schema.org/draft-07/schema#",
"title": "Redrob Candidate Profile Schema",
"description": "Schema for a single candidate profile in the Intelligent Candidate Discovery & Ranking Challenge dataset.",
"type": "object",
"required": [
"candidate_id",
"profile",
"career_history",
"education",
"skills",
"redrob_signals"
],
"properties": {
"candidate_id": {
"type": "string",
"pattern": "^CAND_[0-9]{7}$",
"description": "Unique identifier for the candidate. Format: CAND_XXXXXXX (7 digits)."
},
"profile": {
"type": "object",
"required": [
"anonymized_name",
"headline",
"summary",
"location",
"country",
"years_of_experience",
"current_title",
"current_company",
"current_company_size",
"current_industry"
],
"properties": {
"anonymized_name": { "type": "string", "description": "Anonymized full name." },
"headline": { "type": "string", "description": "One-line professional headline." },
"summary": { "type": "string", "description": "Multi-sentence professional summary." },
"location": { "type": "string", "description": "City, region/state." },
"country": { "type": "string" },
"years_of_experience": { "type": "number", "minimum": 0, "maximum": 50 },
"current_title": { "type": "string" },
"current_company": { "type": "string" },
"current_company_size": {
"type": "string",
"enum": ["1-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001-10000", "10001+"]
},
"current_industry": { "type": "string" }
}
},
"career_history": {
"type": "array",
"minItems": 1,
"maxItems": 10,
"items": {
"type": "object",
"required": ["company", "title", "start_date", "end_date", "duration_months", "is_current", "industry", "company_size", "description"],
"properties": {
"company": { "type": "string" },
"title": { "type": "string" },
"start_date": { "type": "string", "format": "date" },
"end_date": { "type": ["string", "null"], "format": "date" },
"duration_months": { "type": "integer", "minimum": 0 },
"is_current": { "type": "boolean" },
"industry": { "type": "string" },
"company_size": {
"type": "string",
"enum": ["1-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001-10000", "10001+"]
},
"description": { "type": "string", "description": "Role responsibilities and achievements." }
}
}
},
"education": {
"type": "array",
"minItems": 0,
"maxItems": 5,
"items": {
"type": "object",
"required": ["institution", "degree", "field_of_study", "start_year", "end_year"],
"properties": {
"institution": { "type": "string" },
"degree": { "type": "string" },
"field_of_study": { "type": "string" },
"start_year": { "type": "integer", "minimum": 1970, "maximum": 2030 },
"end_year": { "type": "integer", "minimum": 1970, "maximum": 2035 },
"grade": { "type": ["string", "null"], "description": "GPA / percentage / class." },
"tier": {
"type": "string",
"enum": ["tier_1", "tier_2", "tier_3", "tier_4", "unknown"],
"description": "Internal tiering for institution prestige."
}
}
}
},
"skills": {
"type": "array",
"minItems": 0,
"items": {
"type": "object",
"required": ["name", "proficiency", "endorsements"],
"properties": {
"name": { "type": "string" },
"proficiency": {
"type": "string",
"enum": ["beginner", "intermediate", "advanced", "expert"]
},
"endorsements": { "type": "integer", "minimum": 0 },
"duration_months": { "type": "integer", "minimum": 0, "description": "Months the candidate has used this skill" }
}
}
},
"certifications": {
"type": "array",
"items": {
"type": "object",
"required": ["name", "issuer", "year"],
"properties": {
"name": { "type": "string" },
"issuer": { "type": "string" },
"year": { "type": "integer" }
}
}
},
"languages": {
"type": "array",
"items": {
"type": "object",
"required": ["language", "proficiency"],
"properties": {
"language": { "type": "string" },
"proficiency": {
"type": "string",
"enum": ["basic", "conversational", "professional", "native"]
}
}
}
},
"redrob_signals": {
"type": "object",
"description": "Simulated platform activity and engagement signals from the Redrob ecosystem.",
"required": [
"profile_completeness_score",
"signup_date",
"last_active_date",
"open_to_work_flag",
"profile_views_received_30d",
"applications_submitted_30d",
"recruiter_response_rate",
"avg_response_time_hours",
"skill_assessment_scores",
"connection_count",
"endorsements_received",
"notice_period_days",
"expected_salary_range_inr_lpa",
"preferred_work_mode",
"willing_to_relocate",
"github_activity_score",
"search_appearance_30d",
"saved_by_recruiters_30d",
"interview_completion_rate",
"offer_acceptance_rate",
"verified_email",
"verified_phone",
"linkedin_connected"
],
"properties": {
"profile_completeness_score": {
"type": "number",
"minimum": 0,
"maximum": 100,
"description": "Percentage of profile completeness."
},
"signup_date": { "type": "string", "format": "date" },
"last_active_date": { "type": "string", "format": "date" },
"open_to_work_flag": { "type": "boolean" },
"profile_views_received_30d": { "type": "integer", "minimum": 0 },
"applications_submitted_30d": { "type": "integer", "minimum": 0 },
"recruiter_response_rate": {
"type": "number",
"minimum": 0,
"maximum": 1,
"description": "Fraction of recruiter messages the candidate has responded to."
},
"avg_response_time_hours": { "type": "number", "minimum": 0 },
"skill_assessment_scores": {
"type": "object",
"description": "Dict of skill_name -> score 0-100. Assessments completed on Redrob platform.",
"additionalProperties": { "type": "number", "minimum": 0, "maximum": 100 }
},
"connection_count": { "type": "integer", "minimum": 0 },
"endorsements_received": { "type": "integer", "minimum": 0 },
"notice_period_days": { "type": "integer", "minimum": 0, "maximum": 180 },
"expected_salary_range_inr_lpa": {
"type": "object",
"required": ["min", "max"],
"properties": {
"min": { "type": "number", "minimum": 0 },
"max": { "type": "number", "minimum": 0 }
},
"description": "Expected salary in INR Lakhs Per Annum."
},
"preferred_work_mode": {
"type": "string",
"enum": ["remote", "hybrid", "onsite", "flexible"]
},
"willing_to_relocate": { "type": "boolean" },
"github_activity_score": {
"type": "number",
"minimum": -1,
"maximum": 100,
"description": "0-100 score based on commits, PRs, stars in last 12 months. -1 if no GitHub linked."
},
"search_appearance_30d": {
"type": "integer",
"minimum": 0,
"description": "Number of times profile appeared in recruiter searches in last 30 days."
},
"saved_by_recruiters_30d": {
"type": "integer",
"minimum": 0,
"description": "Number of recruiters who saved this profile in last 30 days."
},
"interview_completion_rate": {
"type": "number",
"minimum": 0,
"maximum": 1,
"description": "Fraction of scheduled interviews actually attended."
},
"offer_acceptance_rate": {
"type": "number",
"minimum": -1,
"maximum": 1,
"description": "Historical offer acceptance rate. -1 if no offer history."
},
"verified_email": { "type": "boolean" },
"verified_phone": { "type": "boolean" },
"linkedin_connected": { "type": "boolean" }
}
}
}
}