{"observation":{"id":"88d0b110-6c68-48a4-be94-bb032e62ab16","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":"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":"mixed","score":null,"score_total":null,"note":"The messy parse can bleed location text into a task item, prepending 'Pune' to one extracted responsibility.","evidence_state":"observed","source":null,"artifacts":[],"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-only","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":"hrflow","tool_url":"https://aidemos.com/tools/hrflow","permalink":"https://aidemos.com/evidence/88d0b110-6c68-48a4-be94-bb032e62ab16","api_url":"https://ai.aidemos.com/v1/observations/88d0b110-6c68-48a4-be94-bb032e62ab16"},"peers":[{"id":"490221bf-4f71-43fd-a88a-fe2777655a90","tool":"affinda","tool_name":"Affinda","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.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/research-media-image-d6a62fc24445.png","evidence_url":"https://aidemos.com/evidence/490221bf-4f71-43fd-a88a-fe2777655a90"},{"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":"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":"979b5f53-2a09-4a4a-9bc1-e6cf8836f843","criterion":"accuracy","criterion_name":"Accuracy","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"On the messy resume, it keeps the main contact/work/education structure but misses the soft-skill section and certification entries.","artifact_count":0,"evidence_url":"https://aidemos.com/evidence/979b5f53-2a09-4a4a-9bc1-e6cf8836f843"},{"id":"52292f45-5536-47bf-bb98-bae22d735d29","criterion":"field-coverage","criterion_name":"Field coverage","rank_role":"decisive","verdict":"worked","score":null,"score_total":null,"note":"Even on the messy resume, it still returns the standard contact, experience, education, and technical-skills sections.","artifact_count":0,"evidence_url":"https://aidemos.com/evidence/52292f45-5536-47bf-bb98-bae22d735d29"},{"id":"38efacdb-841e-4b48-ab20-6ccd7916d0b8","criterion":"messy-resume-handling","criterion_name":"Messy resume handling","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"It parses a poorly formatted resume without crashing, but degrades by dropping soft skills, omitting certifications, and losing most task bullets.","artifact_count":0,"evidence_url":"https://aidemos.com/evidence/38efacdb-841e-4b48-ab20-6ccd7916d0b8"},{"id":"2cb7ceb9-2755-46c7-8fe5-ca539f649643","criterion":"output-quality","criterion_name":"Output quality","rank_role":"decisive","verdict":"mixed","score":null,"score_total":null,"note":"The messy-resume output is moderate overall: contact and basic structure survive, but the result is incomplete for soft skills, certifications, and task detail.","artifact_count":0,"evidence_url":"https://aidemos.com/evidence/2cb7ceb9-2755-46c7-8fe5-ca539f649643"}],"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":"490221bf-4f71-43fd-a88a-fe2777655a90","tool":"affinda","tool_name":"Affinda","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."},{"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":"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."}]}