{ "story_id": "9207275e1d08f36903b8b21ef0dbd456", "desk": "drm3", "revision": 1, "published_at": "2026-09-03T04:00:00.000Z", "content_hash": "e77b14359343457fe42a0d829e45cadd0f1521a89f6cbabba59677b003fecab0", "hash_basis": "sha256 over `headline\\ndek\\nprose`, plus `\\n` + the canonical citations JSON when any source is placed, plus `\\n#blog` for blogs", "basis": { "headline": "Team Monolith and Smart Talent Institute Data AI Course for 997 Students Enters Final Phase", "dek": "2026 AI Companion Project data AI course for 997 Korean students enters final phase ahead of hackathon and demo day.", "prose": "Team Monolith and Smart Talent Development Institute announced on 2026-08-01 that the 16-session data AI course of the 2026 AI Companion Project, organized by the Korea Foundation for the Advancement of Science and Creativity, is in its final phase. [^1]\n\nResearchers introduced ExecRetrieval, a new benchmark designed to test the functional correctness of code-embedding retrieval systems. [^2]\n\nAn AI file analysis agent is a flexible tool that accepts a file, accesses it, reads relevant content, understands natural language questions, and produces an answer without manual searching. [^3]\n\nHigh school students analyzed diabetes data, built Python-based regression and classification models, and developed a web app for disease risk guidance and a prevention advice game. [^4]\n\nMiddle school students in the course measured school temperature and humidity with micro:bit sensors, used Entry-based AI for learning, and created webpages proposing solutions to urban heat island effects. [^5]\n\nThe data AI course curriculum is structured in six stages from sustainable development goal topic selection to data collection, preprocessing, visualization, AI learning, and final output production. [^6]\n\nThe buggy distractors in the ExecRetrieval benchmark are generated by mechanical mutations that make a single targeted edit to the canonical implementation. [^7]\n\nThe canonical implementation scored below at least one of its four paired distractors in 67% to 78% of queries on the leading systems. [^8]\n\nThe top hosted system achieved an exec@1 score of only 0.331 on the ExecRetrieval benchmark. [^9]\n\nDevelopers are advised to store OpenAI API keys as environment variables rather than hardcoding them to prevent accidental exposure if the project is uploaded to platforms like GitHub. [^10]\n\nThe architecture distinguishes between the AI model, which handles language understanding, and the Python program, which manages the workflow and file access. [^11]\n\nThe tutorial demonstrates building an agent using Python and the OpenAI API, specifically utilizing the Responses API to send uploaded files as inputs for analysis. [^12]", "cited": "[{\"statement\":\"Team Monolith and Smart Talent Development Institute announced on 2026-08-01 that the 16-session data AI course of the 2026 AI Companion Project, organized by the Korea Foundation for the Advancement of Science and Creativity, is in its final phase.\",\"source\":\"동아일보\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T06:26:04.000Z\",\"publisher_count\":1,\"sources\":[\"동아일보\"]},{\"statement\":\"Researchers introduced ExecRetrieval, a new benchmark designed to test the functional correctness of code-embedding retrieval systems.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"An AI file analysis agent is a flexible tool that accepts a file, accesses it, reads relevant content, understands natural language questions, and produces an answer without manual searching.\",\"source\":\"freecodecamp.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T15:44:15.000Z\",\"publisher_count\":1,\"sources\":[\"freecodecamp.org\"]},{\"statement\":\"High school students analyzed diabetes data, built Python-based regression and classification models, and developed a web app for disease risk guidance and a prevention advice game.\",\"source\":\"동아일보\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T06:26:04.000Z\",\"publisher_count\":1,\"sources\":[\"동아일보\"]},{\"statement\":\"Middle school students in the course measured school temperature and humidity with micro:bit sensors, used Entry-based AI for learning, and created webpages proposing solutions to urban heat island effects.\",\"source\":\"동아일보\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T06:26:04.000Z\",\"publisher_count\":1,\"sources\":[\"동아일보\"]},{\"statement\":\"The data AI course curriculum is structured in six stages from sustainable development goal topic selection to data collection, preprocessing, visualization, AI learning, and final output production.\",\"source\":\"동아일보\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T06:26:04.000Z\",\"publisher_count\":1,\"sources\":[\"동아일보\"]},{\"statement\":\"The buggy distractors in the ExecRetrieval benchmark are generated by mechanical mutations that make a single targeted edit to the canonical implementation.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The canonical implementation scored below at least one of its four paired distractors in 67% to 78% of queries on the leading systems.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"The top hosted system achieved an exec@1 score of only 0.331 on the ExecRetrieval benchmark.\",\"source\":\"arXiv.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-03T04:00:00.000Z\",\"publisher_count\":1,\"sources\":[\"arXiv.org\"]},{\"statement\":\"Developers are advised to store OpenAI API keys as environment variables rather than hardcoding them to prevent accidental exposure if the project is uploaded to platforms like GitHub.\",\"source\":\"freecodecamp.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T15:44:15.000Z\",\"publisher_count\":1,\"sources\":[\"freecodecamp.org\"]},{\"statement\":\"The architecture distinguishes between the AI model, which handles language understanding, and the Python program, which manages the workflow and file access.\",\"source\":\"freecodecamp.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T15:44:15.000Z\",\"publisher_count\":1,\"sources\":[\"freecodecamp.org\"]},{\"statement\":\"The tutorial demonstrates building an agent using Python and the OpenAI API, specifically utilizing the Responses API to send uploaded files as inputs for analysis.\",\"source\":\"freecodecamp.org\",\"instrument\":\"News\",\"claim_key\":null,\"published_at\":\"2026-09-01T15:44:15.000Z\",\"publisher_count\":1,\"sources\":[\"freecodecamp.org\"]}]", "kind": "news" }, "receipt_verify": "Ed25519 over the dot-joined string `slice_hash.cursor_from.cursor_to.view.view_version.row_count`; public_key and sig are base64url of the raw 32-byte key / 64-byte signature", "receipt": null, "receipt_note": "this revision predates receipt-keeping (before v0.37.0); the filed row lives in the record", "generation_chain": { "wire": { "stream": "fountain_news", "story_id": "135579f0e985eda0e69b90ebb788b4a2", "thread_id": "e6c901a3ca65daaf7b680cb9cf06d784", "thread_label": "Python", "novelty": "UPDATE", "content_hash": "13eb501d8ce782d81296481e52bd1a7b1cf19d96b7c1d9eefe5e98b0d94d6624", "last_published_at": "2026-09-03T04:00:00.000Z", "read_receipt": { "slice_hash": "a6974819026a155e1c79c99aba73ab29d5f9d0aaa9cffb05e88a08023354a690", "cursor_from": "eyJ0cyI6IjIwMjYtMDktMDNUMDM6MzI6MTkuMDAwMDAwWiIsImlkIjoiNzMzZDYyYTFiNGQwMmJmNjYzNTk3YjhmN2JhZDBiZTIiLCJ2IjoiMSJ9", "cursor_to": "eyJ0cyI6IjIwMjYtMDktMDNUMDQ6MDk6MDAuMDAwMDAwWiIsImlkIjoiNjQ5MjI3ZDNmNWQyMGQ3NmI1ZTE1NGNhODNlMTI0ZTMiLCJ2IjoiMSJ9", "view": "v_fountain_news", "view_version": "1", "row_count": 100, "window_days": 3, "bytes_scanned": 12568115, "credits": 8, "price_per_100_rows": 8, "sig": "k4fkL1dHRNIJwSawY8K6wWBrTSdTIRM-buyZr56gcruiCoH5_IdJUeMzPH7d51ZTXAE0Qe6xSFoDys5UGTzsAw", "public_key": "bMUigy8O0jOnBxQ4Sc-5lwhIZ8LQVAhxMbR7qESVuUE", "signer_path": "lakehouse/data-extract/v1", "alg": "Ed25519", "signed": true } }, "written_at": "2026-09-03T06:46:26.685Z" }, "cited_facts": [ { "statement": "Team Monolith and Smart Talent Development Institute announced on 2026-08-01 that the 16-session data AI course of the 2026 AI Companion Project, organized by the Korea Foundation for the Advancement of Science and Creativity, is in its final phase.", "source": "동아일보", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T06:26:04.000Z", "publisher_count": 1, "sources": [ "동아일보" ] }, { "statement": "Researchers introduced ExecRetrieval, a new benchmark designed to test the functional correctness of code-embedding retrieval systems.", "source": "arXiv.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-03T04:00:00.000Z", "publisher_count": 1, "sources": [ "arXiv.org" ] }, { "statement": "An AI file analysis agent is a flexible tool that accepts a file, accesses it, reads relevant content, understands natural language questions, and produces an answer without manual searching.", "source": "freecodecamp.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T15:44:15.000Z", "publisher_count": 1, "sources": [ "freecodecamp.org" ] }, { "statement": "High school students analyzed diabetes data, built Python-based regression and classification models, and developed a web app for disease risk guidance and a prevention advice game.", "source": "동아일보", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T06:26:04.000Z", "publisher_count": 1, "sources": [ "동아일보" ] }, { "statement": "Middle school students in the course measured school temperature and humidity with micro:bit sensors, used Entry-based AI for learning, and created webpages proposing solutions to urban heat island effects.", "source": "동아일보", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T06:26:04.000Z", "publisher_count": 1, "sources": [ "동아일보" ] }, { "statement": "The data AI course curriculum is structured in six stages from sustainable development goal topic selection to data collection, preprocessing, visualization, AI learning, and final output production.", "source": "동아일보", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T06:26:04.000Z", "publisher_count": 1, "sources": [ "동아일보" ] }, { "statement": "The buggy distractors in the ExecRetrieval benchmark are generated by mechanical mutations that make a single targeted edit to the canonical implementation.", "source": "arXiv.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-03T04:00:00.000Z", "publisher_count": 1, "sources": [ "arXiv.org" ] }, { "statement": "The canonical implementation scored below at least one of its four paired distractors in 67% to 78% of queries on the leading systems.", "source": "arXiv.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-03T04:00:00.000Z", "publisher_count": 1, "sources": [ "arXiv.org" ] }, { "statement": "The top hosted system achieved an exec@1 score of only 0.331 on the ExecRetrieval benchmark.", "source": "arXiv.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-03T04:00:00.000Z", "publisher_count": 1, "sources": [ "arXiv.org" ] }, { "statement": "Developers are advised to store OpenAI API keys as environment variables rather than hardcoding them to prevent accidental exposure if the project is uploaded to platforms like GitHub.", "source": "freecodecamp.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T15:44:15.000Z", "publisher_count": 1, "sources": [ "freecodecamp.org" ] }, { "statement": "The architecture distinguishes between the AI model, which handles language understanding, and the Python program, which manages the workflow and file access.", "source": "freecodecamp.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T15:44:15.000Z", "publisher_count": 1, "sources": [ "freecodecamp.org" ] }, { "statement": "The tutorial demonstrates building an agent using Python and the OpenAI API, specifically utilizing the Responses API to send uploaded files as inputs for analysis.", "source": "freecodecamp.org", "instrument": "News", "claim_key": null, "published_at": "2026-09-01T15:44:15.000Z", "publisher_count": 1, "sources": [ "freecodecamp.org" ] } ], "note": "A signature proves who filed this and that it has not changed since. It never makes a claim true." }