{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2020-10-30T14:01:22.655107+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 4, "enabled": true, "entries": { "2020_30_10_13_19_228_sample.json": { "checksum": "md5:7cee61cbb6536072f196c720eb42f342", "ext": "json", "id": "60d323a7-fd97-4f2b-9efe-ec012b1df67c", "key": "2020_30_10_13_19_228_sample.json", "metadata": null, "mimetype": "application/json", "size": 1216353 }, "LICENSE.txt": { "checksum": "md5:073166a882909625d915271f737ae197", "ext": "txt", "id": "b6e0276b-faf8-4591-a94e-0b5e9e0c755a", "key": "LICENSE.txt", "metadata": null, "mimetype": "text/plain", "size": 157 }, "map_labels.csv": { "checksum": "md5:899ce40cf7e19d76b19cd1454a5ecc2c", "ext": "csv", "id": "719a4b30-2baf-497d-87e1-354e1c8db419", "key": "map_labels.csv", "metadata": null, "mimetype": "text/csv", "size": 22267 }, "newspaper_maps.zip": { "checksum": "md5:ea81ef0b964ff9295d19e7ba42b51540", "ext": "zip", "id": "b9aad096-3d5e-4887-bde9-a37a53c9c201", "key": "newspaper_maps.zip", "metadata": null, "mimetype": "application/zip", "size": 314305730 } }, "order": [], "total_bytes": 315544507 }, "id": "4156510", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/4156510/access", "access_links": "https://zenodo.org/api/records/4156510/access/links", "access_request": "https://zenodo.org/api/records/4156510/access/request", "access_users": "https://zenodo.org/api/records/4156510/access/users", "archive": "https://zenodo.org/api/records/4156510/files-archive", "archive_media": "https://zenodo.org/api/records/4156510/media-files-archive", "communities": "https://zenodo.org/api/records/4156510/communities", "communities-suggestions": "https://zenodo.org/api/records/4156510/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.4156510", "draft": "https://zenodo.org/api/records/4156510/draft", "files": "https://zenodo.org/api/records/4156510/files", "latest": "https://zenodo.org/api/records/4156510/versions/latest", "latest_html": "https://zenodo.org/records/4156510/latest", "media_files": "https://zenodo.org/api/records/4156510/media-files", "parent": "https://zenodo.org/api/records/4156509", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.4156509", "parent_html": "https://zenodo.org/records/4156509", "requests": "https://zenodo.org/api/records/4156510/requests", "reserve_doi": "https://zenodo.org/api/records/4156510/draft/pids/doi", "self": "https://zenodo.org/api/records/4156510", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.4156510", "self_html": "https://zenodo.org/records/4156510", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:4156510/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:4156510/sequence/default", "versions": "https://zenodo.org/api/records/4156510/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "contributors": [ { "affiliations": [ { "name": "British Library" } ], "person_or_org": { "family_name": "van Strien", "given_name": "Daniel", "identifiers": [ { "identifier": "0000-0003-1684-6556", "scheme": "orcid" } ], "name": "van Strien, Daniel", "type": "personal" }, "role": { "id": "datacurator", "title": { "de": "DatenkuratorIn", "en": "Data curator" } } } ], "creators": [ { "affiliations": [ { "name": "British Library" } ], "person_or_org": { "family_name": "van Strien", "given_name": "Daniel", "identifiers": [ { "identifier": "0000-0003-1684-6556", "scheme": "orcid" } ], "name": "van Strien, Daniel", "type": "personal" } } ], "description": "
The Dataset contains images derived from the Newspaper Navigator (news-navigator.labs.loc.gov/), a dataset of images drawn from the Library of Congress Chronicling America collection (chroniclingamerica.loc.gov/).
\n\n\n\n\n[The Newspaper Navigator dataset] consists of extracted visual content for 16,358,041 historic newspaper pages in Chronicling America. The visual content was identified using an object detection model trained on annotations of World War 1-era Chronicling America pages, including annotations made by volunteers as part of the Beyond Words crowdsourcing project.
\n\n\n
One of these categories is 'maps'. In the original training data for Newspaper Navigator, there were relatively few labelled examples of maps. The predictions for maps have an Average Precision of 69.5%, and 34 images in the validation data.
\n\nThis dataset contains a sample of these images which have been predicted as 'maps'. It also includes additional labels which indicate whether the predicted map image is a 'map' or 'not a map'.
\n\nThe data is organised as follows:
\n\n