{"observation":{"id":"8421c170-76dc-4c5c-9767-77137b7087f7","tool":"hrflow","tool_name":"HrFlow","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":"It injects non-skill fragments into the skills list, including 'ml apis', 'lambda', 's3', 'ml', and 'rest apis'.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-image-5381d8e8011f.png","role":"input","alt":"Research media image.png"},{"url":"https://d3epheqghktydj.cloudfront.net/research-media-image-12512e7d6438.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":"hrflow","tool_url":"https://aidemos.com/tools/hrflow","permalink":"https://aidemos.com/evidence/8421c170-76dc-4c5c-9767-77137b7087f7","api_url":"https://ai.aidemos.com/v1/observations/8421c170-76dc-4c5c-9767-77137b7087f7"},"peers":[{"id":"5b56599e-9097-45b1-836f-6b1dd96005fd","tool":"affinda","tool_name":"Affinda","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.","artifact_count":3,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-screenshot-202026-05-05-20120443-b5aaa4f8e2be.png","evidence_url":"https://aidemos.com/evidence/5b56599e-9097-45b1-836f-6b1dd96005fd"},{"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":"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":"372b36f6-3720-49f7-82fe-e7e711582fd1","criterion":"accuracy","criterion_name":"Accuracy","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"On the clean resume, it still misses a listed task bullet ('Evaluated 10+ AI/ML APIs...') and does not return CGPA.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/372b36f6-3720-49f7-82fe-e7e711582fd1"},{"id":"16ecdece-b2b7-4e4b-a26e-f6271ad59376","criterion":"field-coverage","criterion_name":"Field coverage","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"On the clean resume, it extracted the core resume fields: name, email, phone, work experience, education, and skills.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/16ecdece-b2b7-4e4b-a26e-f6271ad59376"},{"id":"cf59ea98-f74d-48cd-bf4f-23c3ef417532","criterion":"output-quality","criterion_name":"Output quality","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"Overall output is usable, but the clean-resume parse still shows normalization and classification issues.","artifact_count":3,"evidence_url":"https://aidemos.com/evidence/cf59ea98-f74d-48cd-bf4f-23c3ef417532"}],"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":"5b56599e-9097-45b1-836f-6b1dd96005fd","tool":"affinda","tool_name":"Affinda","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."},{"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":"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."}]}