{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2019-05-28T02:09:44.005760+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "2019-05-08 How to Feed Your Robot.pdf": { "checksum": "md5:df657eaa028196dca4899bd5949fef6d", "ext": "pdf", "id": "46c8cf14-d0c7-47e4-bdb7-bbfce3845db6", "key": "2019-05-08 How to Feed Your Robot.pdf", "metadata": null, "mimetype": "application/pdf", "size": 856760 } }, "order": [], "total_bytes": 856760 }, "id": "3233117", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/3233117/access", "access_links": "https://zenodo.org/api/records/3233117/access/links", "access_request": "https://zenodo.org/api/records/3233117/access/request", "access_users": "https://zenodo.org/api/records/3233117/access/users", "archive": "https://zenodo.org/api/records/3233117/files-archive", "archive_media": "https://zenodo.org/api/records/3233117/media-files-archive", "communities": "https://zenodo.org/api/records/3233117/communities", "communities-suggestions": "https://zenodo.org/api/records/3233117/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.3233117", "draft": "https://zenodo.org/api/records/3233117/draft", "files": "https://zenodo.org/api/records/3233117/files", "latest": "https://zenodo.org/api/records/3233117/versions/latest", "latest_html": "https://zenodo.org/records/3233117/latest", "media_files": "https://zenodo.org/api/records/3233117/media-files", "parent": "https://zenodo.org/api/records/3233116", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.3233116", "parent_html": "https://zenodo.org/records/3233116", "requests": "https://zenodo.org/api/records/3233117/requests", "reserve_doi": "https://zenodo.org/api/records/3233117/draft/pids/doi", "self": "https://zenodo.org/api/records/3233117", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.3233117", "self_html": "https://zenodo.org/records/3233117", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:3233117/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:3233117/sequence/default", "versions": "https://zenodo.org/api/records/3233117/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "Rockefeller Foundation" } ], "person_or_org": { "family_name": "Evan Tachovsky", "name": "Evan Tachovsky", "type": "personal" } } ], "description": "
While algorithms and computing power get all the press, the special sauce behind many recent machine learning breakthroughs are meticulously labeled training data. Developing and maintaining these data sets as public goods is both an art and a science. In this talk I'll present a new set of best practices gleaned from interview with ~20 data set builders, maintainers, and funders. Topics include: encouraging collaboration between rival data teams; finding and addressing ethical issues with crowd labeling; launching competitions to spur data set use; and revenue generation models for sustainability.
", "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2019-05-28", "publisher": "Zenodo", "resource_type": { "id": "presentation", "title": { "de": "Pr\u00e4sentation", "en": "Presentation" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "subjects": [ { "subject": "Machine learning" }, { "subject": "Training data" }, { "subject": "Data curation" } ], "title": "How to Feed Your Robot: Building and Maintaining Open Machine Learning Datasets", "version": "1" }, "parent": { "access": { "owned_by": { "user": 68342 } }, "communities": { "default": "dc195fdc-3151-48b3-bc7e-5ef1b572c3e1", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2019-05-02T22:10:05.509285+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "dc195fdc-3151-48b3-bc7e-5ef1b572c3e1", "links": {}, "metadata": { "curation_policy": "", "page": "Slides from presentations at csv,conf,v4 in Portland, OR, USA on May 8-9, 2019.
\r\n\r\ncsv,conf brings diverse groups together to discuss data topics, and features stories about data sharing and data analysis from science, journalism, government, and open source.
\r\n\r\ncsv,conf is a non-profit community conference run by folks who really love data and sharing knowledge. If you are as passionate about data and its application to society as we are, then this is the conference for you.
\r\n\r\ncsv,conf conferences aren't just about spreadsheets. We curate content on broader topics like advancing the art of data collaboration- from putting your data on GitHub, to producing meaningful insight by running large scale distributed processing on a cluster.
", "title": "csv,conf,v4" }, "revision_id": 0, "slug": "csvconfv4", "updated": "2023-04-24T20:51:26.852747+00:00" } ], "ids": [ "dc195fdc-3151-48b3-bc7e-5ef1b572c3e1" ] }, "id": "3233116", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3233116", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.3233117", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:3233117", "provider": "oai" } }, "revision_id": 5, "stats": { "all_versions": { "data_volume": 69397560.0, "downloads": 81, "unique_downloads": 77, "unique_views": 195, "views": 208 }, "this_version": { "data_volume": 69397560.0, "downloads": 81, "unique_downloads": 77, "unique_views": 195, "views": 208 } }, "status": "published", "updated": "2020-01-20T17:34:15.427177+00:00", "versions": { "index": 1, "is_latest": true } }