{"observation":{"id":"490221bf-4f71-43fd-a88a-fe2777655a90","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":"messy-real-world-resume-john-kumar","scenario_name":"Messy real-world resume — John Kumar","group_tag":"resume-parsing","scenario_description":"A poorly formatted, inconsistent real-world resume for John Kumar, used to test robustness against noisy structure, inconsistent dates, and mixed-content sections.","modality":"pdf","input_text":null,"input_artifact_refs":[{"alt":null,"url":"https://d3epheqghktydj.cloudfront.net/parseur-input3-john-kumar-messyresume-75275a848042.pdf","role":"input"}],"stresses":["messy formatting robustness","section detection fallback","inconsistent date parsing","soft-skills extraction","noise and hallucination control"],"verdict":"failed","score":null,"score_total":null,"note":"The skills output includes hallucinated taxonomy noise, such as Business Education, that does not appear in the resume.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/research-media-image-d6a62fc24445.png","role":"input","alt":"Research media image.png"},{"url":"https://d3epheqghktydj.cloudfront.net/research-media-image-852e99ffc6c7.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-input3-john-kumar-messyresume-75275a848042.pdf","filename":"parseur-input3-john-kumar-messyresume-75275a848042.pdf","alt":"Messy real-world resume — John Kumar","role":"input"}],"modality":"pdf","stresses":["messy formatting robustness","section detection fallback","inconsistent date parsing","soft-skills extraction","noise and hallucination control"]},"tool_page_slug":"affinda","tool_url":"https://aidemos.com/tools/affinda","permalink":"https://aidemos.com/evidence/490221bf-4f71-43fd-a88a-fe2777655a90","api_url":"https://ai.aidemos.com/v1/observations/490221bf-4f71-43fd-a88a-fe2777655a90"},"peers":[{"id":"f4a9dbe8-9c63-425b-a0b9-39c490e6965a","tool":"cvparserpro","tool_name":"CVParserPro","verdict":"failed","score":null,"score_total":null,"note":"The parser hallucinated unsupported month values in the work date range, expanding 2019–2021 into January 2019 to December 2021.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/cvparserpro-p7-month-hallucination-e794ae0ec6e7.png","evidence_url":"https://aidemos.com/evidence/f4a9dbe8-9c63-425b-a0b9-39c490e6965a"},{"id":"7ec0595e-ec84-427a-a9c7-22c290258f01","tool":"extracta-ai","tool_name":"Extracta.ai","verdict":"struggled","score":null,"score_total":null,"note":"Emits a blank Languages item when the resume has no languages section, leaving an empty placeholder instead of omitting the field.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-screenshot-202026-05-05-20124544-174ecd83f60c.png","evidence_url":"https://aidemos.com/evidence/7ec0595e-ec84-427a-a9c7-22c290258f01"},{"id":"53baa4b9-f590-4704-af4d-1715255eb658","tool":"hireability","tool_name":"Hireability","verdict":"failed","score":null,"score_total":null,"note":"The certification field merged three content types — certifications, skills, and references — into one extracted value instead of separating them.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/hireability-hireability-task3-certs-refs-merged-mock-c80cee78a881.png","evidence_url":"https://aidemos.com/evidence/53baa4b9-f590-4704-af4d-1715255eb658"},{"id":"88d0b110-6c68-48a4-be94-bb032e62ab16","tool":"hrflow","tool_name":"HrFlow","verdict":"mixed","score":null,"score_total":null,"note":"The messy parse can bleed location text into a task item, prepending 'Pune' to one extracted responsibility.","artifact_count":0,"thumbnail":null,"evidence_url":"https://aidemos.com/evidence/88d0b110-6c68-48a4-be94-bb032e62ab16"},{"id":"f3504830-9157-4146-a34d-a211439d3ce7","tool":"skima-ai","tool_name":"Skima AI","verdict":"failed","score":null,"score_total":null,"note":"The messy-resume skills block was collapsed into a single concatenated string with no separators, making the field hard to reuse downstream.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/skima-ai-09-input3-skills-concatenated-mock-d25303702406.png","evidence_url":"https://aidemos.com/evidence/f3504830-9157-4146-a34d-a211439d3ce7"}],"other_criteria":[{"id":"6b3eb118-2ba6-4652-b602-ce3fd5db643a","criterion":"accuracy","criterion_name":"Accuracy","rank_role":"decisive","verdict":"failed","score":null,"score_total":null,"note":"Its total experience calculation overstates tenure: it returned 7.3 years even though the resume explicitly says 3 years of experience.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/6b3eb118-2ba6-4652-b602-ce3fd5db643a"},{"id":"ad0979bc-e449-450a-b06b-f5c12fa6da9b","criterion":"field-coverage","criterion_name":"Field coverage","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"It extracted one certification but silently dropped the AWS Basics Coursera 2022 certificate, so the certification coverage was incomplete on the messy resume.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/ad0979bc-e449-450a-b06b-f5c12fa6da9b"},{"id":"adc87f30-2a28-4fd8-a203-a64e455e74e9","criterion":"messy-resume-handling","criterion_name":"Messy resume handling","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"The parser handled the messy resume gracefully, still extracting the main identity, work history, education entries, skills, objective, and hobbies despite non-standard dates and raw dash-style bullets.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/adc87f30-2a28-4fd8-a203-a64e455e74e9"}],"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":"f4a9dbe8-9c63-425b-a0b9-39c490e6965a","tool":"cvparserpro","tool_name":"CVParserPro","verdict":"failed","score":null,"score_total":null,"note":"The parser hallucinated unsupported month values in the work date range, expanding 2019–2021 into January 2019 to December 2021."},{"id":"7ec0595e-ec84-427a-a9c7-22c290258f01","tool":"extracta-ai","tool_name":"Extracta.ai","verdict":"struggled","score":null,"score_total":null,"note":"Emits a blank Languages item when the resume has no languages section, leaving an empty placeholder instead of omitting the field."},{"id":"53baa4b9-f590-4704-af4d-1715255eb658","tool":"hireability","tool_name":"Hireability","verdict":"failed","score":null,"score_total":null,"note":"The certification field merged three content types — certifications, skills, and references — into one extracted value instead of separating them."},{"id":"88d0b110-6c68-48a4-be94-bb032e62ab16","tool":"hrflow","tool_name":"HrFlow","verdict":"mixed","score":null,"score_total":null,"note":"The messy parse can bleed location text into a task item, prepending 'Pune' to one extracted responsibility."},{"id":"f3504830-9157-4146-a34d-a211439d3ce7","tool":"skima-ai","tool_name":"Skima AI","verdict":"failed","score":null,"score_total":null,"note":"The messy-resume skills block was collapsed into a single concatenated string with no separators, making the field hard to reuse downstream."}]}