{"observation":{"id":"5b56599e-9097-45b1-836f-6b1dd96005fd","tool":"affinda","tool_name":"Affinda","criterion":"noise-in-output","criterion_name":"Noise in output","criterion_definition":"Does it add incorrect or hallucinated fields?","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"Incorrect or hallucinated fields mean the resume parser is not producing reliable structured data, which is central to the job. (3 of 3 judges)","scenario":"clean-single-column-resume-rugved-nichite","scenario_name":"Clean single-column resume — Rugved Nichite","group_tag":"resume-parsing","scenario_description":"A professionally structured single-column resume for Rugved Nichite, used as the baseline input for parser accuracy across standard resume fields.","modality":"pdf","input_text":null,"input_artifact_refs":[{"alt":null,"url":"https://d3epheqghktydj.cloudfront.net/parseur-input1-rugved-nichite-cleanresume-d776e5470f6f.pdf","role":"input"}],"stresses":["baseline field extraction","contact info accuracy","work experience parsing","education and CGPA extraction","skills and certifications extraction"],"verdict":"failed","score":null,"score_total":null,"note":"The parser injects non-skill noise into the skills list, including certification-derived items such as AWS Certified Cloud Practitioner and IBM Mainframe.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-screenshot-202026-05-05-20120443-b5aaa4f8e2be.png","role":"input","alt":"Research media screenshot 202026 05 05 20120443.png"},{"url":"https://d3epheqghktydj.cloudfront.net/research-media-image-581b3b3ff325.png","role":"output","alt":null},{"url":"https://d3epheqghktydj.cloudfront.net/research-media-image-24f770ca17e2.png","role":"output","alt":null}],"run_id":"cbbef4db-964c-49fa-a57f-a2977822bdfc","study_title":"Parse resumes into structured data using an API","study_kind":"generation","research_task":"86b9jm30n","tested_at":null,"completeness":"input-and-output","input":{"state":"files","text":null,"files":[{"url":"https://d3epheqghktydj.cloudfront.net/parseur-input1-rugved-nichite-cleanresume-d776e5470f6f.pdf","filename":"parseur-input1-rugved-nichite-cleanresume-d776e5470f6f.pdf","alt":"Clean single-column resume — Rugved Nichite","role":"input"}],"modality":"pdf","stresses":["baseline field extraction","contact info accuracy","work experience parsing","education and CGPA extraction","skills and certifications extraction"]},"tool_page_slug":"affinda","tool_url":"https://aidemos.com/tools/affinda","permalink":"https://aidemos.com/evidence/5b56599e-9097-45b1-836f-6b1dd96005fd","api_url":"https://ai.aidemos.com/v1/observations/5b56599e-9097-45b1-836f-6b1dd96005fd"},"peers":[{"id":"f89caf00-224f-4aa6-8199-1b2b68ea6d2f","tool":"extracta-ai","tool_name":"Extracta.ai","verdict":"struggled","score":null,"score_total":null,"note":"Puts four programming languages — Python, JavaScript, SQL, and Bash — into the Languages field even though the resume does not contain a spoken-languages section.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-screenshot-202026-05-05-20124028-cbdba62c2569.png","evidence_url":"https://aidemos.com/evidence/f89caf00-224f-4aa6-8199-1b2b68ea6d2f"},{"id":"6abbae90-956b-467b-ae65-3395f2da49df","tool":"hireability","tool_name":"Hireability","verdict":"failed","score":null,"score_total":null,"note":"The competency extractor introduced noise by labeling all 29 competencies as beginner and including non-skill terms such as Intern, Science, and Framework as competencies.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/hireability-hireability-task1-beginner-noise-edade670275f.png","evidence_url":"https://aidemos.com/evidence/6abbae90-956b-467b-ae65-3395f2da49df"},{"id":"8421c170-76dc-4c5c-9767-77137b7087f7","tool":"hrflow","tool_name":"HrFlow","verdict":"failed","score":null,"score_total":null,"note":"It injects non-skill fragments into the skills list, including 'ml apis', 'lambda', 's3', 'ml', and 'rest apis'.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-image-5381d8e8011f.png","evidence_url":"https://aidemos.com/evidence/8421c170-76dc-4c5c-9767-77137b7087f7"},{"id":"2d4131f4-f6fb-4d07-bf37-3d1a2135f950","tool":"skima-ai","tool_name":"Skima AI","verdict":"failed","score":null,"score_total":null,"note":"The parser preserved raw bullet/number formatting in responsibilities, leaking duplicated bullet characters into the extracted text.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/skima-ai-03-duplicate-bullets-693039b12af9.png","evidence_url":"https://aidemos.com/evidence/2d4131f4-f6fb-4d07-bf37-3d1a2135f950"}],"other_criteria":[{"id":"a3e3a1a6-fae3-4f52-a367-4f0f213c6a13","criterion":"accuracy","criterion_name":"Accuracy","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"It identified the degree record but left the CGPA numeric score empty, missing the visible 8.2 value while keeping the unit as CGPA.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/a3e3a1a6-fae3-4f52-a367-4f0f213c6a13"},{"id":"1a6eb5ca-e960-4d56-9f4a-a6744370ed42","criterion":"accuracy","criterion_name":"Accuracy","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"It split one LinkedIn profile into two website fields and dropped the /in/ path segment, so the URL was not reconstructed as a single complete value.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/1a6eb5ca-e960-4d56-9f4a-a6744370ed42"},{"id":"3f3be4ae-57da-4303-9ac6-15fd31b1aee2","criterion":"field-coverage","criterion_name":"Field coverage","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"On the clean resume, the parser covered the standard resume sections expected by the benchmark: identity/contact, work experience, education, skills, and certifications.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/3f3be4ae-57da-4303-9ac6-15fd31b1aee2"}],"appears_in":[{"page_type":"ranking","slug":"resume-parsing-api","title":"Best AI Tools for Parsing Resumes via API (2026)","url":"https://aidemos.com/best/resume-parsing-api","binding":"run"}],"same_scenario":[{"id":"f89caf00-224f-4aa6-8199-1b2b68ea6d2f","tool":"extracta-ai","tool_name":"Extracta.ai","verdict":"struggled","score":null,"score_total":null,"note":"Puts four programming languages — Python, JavaScript, SQL, and Bash — into the Languages field even though the resume does not contain a spoken-languages section."},{"id":"6abbae90-956b-467b-ae65-3395f2da49df","tool":"hireability","tool_name":"Hireability","verdict":"failed","score":null,"score_total":null,"note":"The competency extractor introduced noise by labeling all 29 competencies as beginner and including non-skill terms such as Intern, Science, and Framework as competencies."},{"id":"8421c170-76dc-4c5c-9767-77137b7087f7","tool":"hrflow","tool_name":"HrFlow","verdict":"failed","score":null,"score_total":null,"note":"It injects non-skill fragments into the skills list, including 'ml apis', 'lambda', 's3', 'ml', and 'rest apis'."},{"id":"2d4131f4-f6fb-4d07-bf37-3d1a2135f950","tool":"skima-ai","tool_name":"Skima AI","verdict":"failed","score":null,"score_total":null,"note":"The parser preserved raw bullet/number formatting in responsibilities, leaking duplicated bullet characters into the extracted text."}]}