commonmeta-ruby 3.5.5 → 3.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +16 -5
- data/lib/commonmeta/readers/crossref_xml_reader.rb +1 -1
- data/lib/commonmeta/utils.rb +6 -6
- data/lib/commonmeta/version.rb +1 -1
- data/spec/cli_spec.rb +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref/default.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref/to_bibtex.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref/to_crossref_xml.yml +25 -25
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref/to_datacite.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref/to_schema_org.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref_xml/default.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref_xml/to_bibtex.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref_xml/to_crossref_xml.yml +7 -59
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref_xml/to_datacite.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref_xml/to_schema_org.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/crossref/default.yml +24 -24
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/crossref/to_bibtex.yml +24 -24
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/crossref/to_citation.yml +24 -24
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/crossref/to_crossref_xml.yml +24 -24
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/crossref/to_datacite.yml +24 -24
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/crossref/to_jats.yml +24 -24
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/crossref/to_schema_org.yml +24 -24
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/datacite/default.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/datacite/to_bibtex.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/datacite/to_citation.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/datacite/to_datacite.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/datacite/to_jats.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/datacite/to_schema_org.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/schema_org/default.yml +479 -946
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/schema_org/to_crossref_xml.yml +957 -1891
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/schema_org/to_datacite.yml +479 -946
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_from_id/schema_org/to_schema_org.yml +481 -950
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/encode/by_blog.yml +5540 -968
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/encode/by_blog_unknown_blog_id.yml +22 -29
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/encode/by_id.yml +25 -39
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/encode/by_id_unknown_uuid.yml +18 -28
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/find_from_format_by_id/crossref.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/find_from_format_by_id/datacite.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/find_from_format_by_id/jalc.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/find_from_format_by_id/kisti.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/find_from_format_by_id/medra.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/find_from_format_by_id/op.yml +7 -7
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/json_feed/json_feed_blog_id.yml +19 -90
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/json_feed/json_feed_by_blog.yml +5578 -246
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/json_feed/json_feed_not_indexed.yml +13 -2201
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/json_feed/json_feed_unregistered.yml +176 -72
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/change_metadata_as_datacite_xml/with_data_citation.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/doi_registration_agency/crossref.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/doi_registration_agency/datacite.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/doi_registration_agency/jalc.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/doi_registration_agency/kisti.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/doi_registration_agency/medra.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/doi_registration_agency/not_found.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/doi_registration_agency/op.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/find_from_format_by_ID/crossref.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/find_from_format_by_ID/crossref_doi_not_url.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/find_from_format_by_ID/datacite.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/find_from_format_by_ID/datacite_doi_http.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/find_from_format_by_ID/unknown_DOI_registration_agency.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_blog_id_for_json_feed_item_id/by_blog_post_id.yml +27 -105
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_blog_id_for_json_feed_item_id/not_found.yml +20 -27
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_cff_metadata/cff-converter-python.yml +51 -25
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_cff_metadata/ruby-cff.yml +12 -12
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_cff_metadata/ruby-cff_repository_url.yml +9 -9
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_codemeta_metadata/maremma.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_codemeta_metadata/metadata_reports.yml +11 -11
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/DOI_with_ORCID_ID.yml +78 -78
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/DOI_with_SICI_DOI.yml +76 -76
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/DOI_with_data_citation.yml +35 -35
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/JaLC.yml +162 -162
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/KISTI.yml +131 -131
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/OP.yml +75 -75
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/affiliation_is_space.yml +76 -76
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/another_book.yml +113 -113
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/another_book_chapter.yml +74 -74
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/article_id_as_page_number.yml +77 -77
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/author_literal.yml +84 -84
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/book.yml +77 -77
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/book_chapter.yml +75 -75
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/book_chapter_with_RDF_for_container.yml +73 -73
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/book_oup.yml +72 -72
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/component.yml +94 -94
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/dataset.yml +104 -104
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/dataset_usda.yml +136 -136
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/date_in_future.yml +80 -80
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/dissertation.yml +103 -103
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/empty_given_name.yml +75 -75
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/invalid_date.yml +77 -77
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/journal_article.yml +76 -76
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/journal_article_original_language_title.yml +73 -73
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/journal_article_with.yml +128 -210
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/journal_article_with_RDF_for_container.yml +74 -74
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/journal_article_with_funding.yml +76 -76
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/journal_issue.yml +72 -72
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/mEDRA.yml +72 -72
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/markup.yml +81 -81
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/missing_contributor.yml +71 -71
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/multiple_issn.yml +75 -75
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/multiple_titles.yml +71 -71
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/multiple_titles_with_missing.yml +573 -573
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/not_found_error.yml +65 -65
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/peer_review.yml +77 -77
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/posted_content.yml +74 -74
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/posted_content_copernicus.yml +76 -76
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/report_osti.yml +120 -120
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/vor_with_url.yml +78 -78
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/yet_another_book.yml +74 -74
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/yet_another_book_chapter.yml +73 -73
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_raw/journal_article.yml +59 -59
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_datacite_metadata/SoftwareSourceCode.yml +4 -4
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_datacite_metadata/dissertation.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_datacite_metadata/funding_references.yml +15 -15
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_datacite_metadata/subject_scheme.yml +120 -120
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_doi_prefix_for_blog/by_blog_id.yml +5540 -555
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_doi_prefix_for_blog/by_blog_post_id.yml +31 -42
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_doi_prefix_for_blog/by_blog_post_id_specific_prefix.yml +25 -39
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed/by_blog_id.yml +5540 -247
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed/not_indexed_posts.yml +14 -26
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed/unregistered_posts.yml +176 -72
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/archived_wordpress_post.yml +27 -95
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/blog_post_with_non-url_id.yml +28 -106
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/blogger_post.yml +21 -65
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_author_name_suffix.yml +20 -208
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_doi.yml +26 -97
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_institutional_author.yml +24 -55
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_organizational_author.yml +27 -70
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_related_identifiers.yml +41 -143
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_related_identifiers_and_funding.yml +54 -132
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_related_identifiers_and_link_to_peer-reviewed_article.yml +304 -818
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_without_doi.yml +24 -169
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/jekyll_post.yml +24 -63
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/jekyll_post_with_anonymous_author.yml +25 -40
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/substack_post_with_broken_reference.yml +278 -591
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/syldavia_gazette_post_with_references.yml +59 -101
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/upstream_post_with_references.yml +135 -331
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/wordpress_post.yml +24 -134
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/wordpress_post_with_many_references.yml +578 -2967
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/wordpress_post_with_references.yml +44 -205
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/wordpress_post_with_tracking_code_on_url.yml +26 -160
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_one_author/affiliation_is_space.yml +21 -21
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_one_author/has_familyName.yml +15 -15
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_one_author/has_name_in_display-order_with_ORCID.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_one_author/name_with_affiliation_crossref.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_one_author/only_familyName_and_givenName.yml +66 -61
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_schema_org_metadata/BlogPosting.yml +145 -146
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_schema_org_metadata/BlogPosting_with_new_DOI.yml +149 -150
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_schema_org_metadata/get_schema_org_metadata_front_matter/BlogPosting.yml +114 -115
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_schema_org_metadata/harvard_dataverse.yml +300 -289
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_schema_org_metadata/pangaea.yml +66 -61
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_schema_org_metadata/upstream_blog.yml +64 -57
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_schema_org_metadata/zenodo.yml +27 -24
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/handle_input/DOI_RA_not_Crossref_or_DataCite.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/handle_input/unknown_DOI_prefix.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/json_schema_errors/is_valid.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/BlogPosting.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/Dataset.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/authors_with_affiliations.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/climate_data.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/from_schema_org.yml +145 -146
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/keywords_subject_scheme.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/maremma.yml +12 -12
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/text.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/with_data_citation.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_bibtex/with_pages.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_cff/Collection_of_Jupyter_notebooks.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_cff/SoftwareSourceCode_Zenodo.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_cff/SoftwareSourceCode_also_Zenodo.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_cff/ruby-cff.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_citation/Dataset.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_citation/Journal_article.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_citation/Journal_article_vancouver_style.yml +21 -21
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_citation/Missing_author.yml +15 -15
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_citation/interactive_resource_without_dates.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_citation/software_w/version.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_codemeta/SoftwareSourceCode_DataCite.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_codemeta/SoftwareSourceCode_DataCite_check_codemeta_v2.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_commonmeta/with_data_citation.yml +12 -12
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/another_schema_org_from_front-matter.yml +32 -32
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/journal_article.yml +5 -5
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/journal_article_from_datacite.yml +5 -5
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/journal_article_plos.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_anonymous_author.yml +25 -40
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_doi.yml +24 -134
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_organizational_author.yml +27 -70
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_relations.yml +41 -143
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_relations_and_funding.yml +55 -133
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_upstream_blog.yml +21 -224
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_with_references.yml +134 -330
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/posted_content.yml +19 -19
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/schema_org_from_another_science_blog.yml +9 -9
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/schema_org_from_front_matter.yml +92 -91
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/schema_org_from_upstream_blog.yml +6 -6
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/Another_dataset.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/BlogPosting.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/BlogPosting_schema_org.yml +146 -147
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/Dataset.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/container_title.yml +16 -21
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/interactive_resource_without_dates.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/journal_article.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/keywords_subject_scheme.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/maremma.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/missing_creator.yml +15 -15
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/multiple_abstracts.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/organization_author.yml +22 -22
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/software.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/software_w/version.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/with_only_first_page.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csl/with_pages.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csv/climate_data.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csv/maremma.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csv/text.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csv/with_data_citation.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_csv/with_pages.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_datacite/dissertation.yml +20 -20
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_datacite/from_schema_org.yml +146 -147
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_datacite/journal_article.yml +22 -22
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_datacite/maremma.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_datacite/with_ORCID_ID.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_datacite/with_data_citation.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/Dataset_in_schema_4_0.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/Text_pass-thru.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/book_chapter.yml +15 -15
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/from_schema_org.yml +146 -147
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/interactive_resource_without_dates.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/maremma.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/with_ORCID_ID.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/with_data_citation.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_jats_xml/with_editor.yml +17 -17
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_ris/BlogPosting.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_ris/BlogPosting_schema_org.yml +145 -146
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_ris/Dataset.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_ris/alternate_name.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_ris/journal_article.yml +9 -9
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_ris/keywords_with_subject_scheme.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_ris/maremma.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_ris/with_pages.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/Another_Schema_org_JSON.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/Funding.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/Funding_OpenAIRE.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/Schema_org_JSON.yml +8 -8
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/Schema_org_JSON_Cyark.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/alternate_identifiers.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/data_catalog.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/geo_location_box.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/interactive_resource_without_dates.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/journal_article.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/maremma_schema_org_JSON.yml +11 -11
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/series_information.yml +17 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/subject_scheme.yml +15 -15
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_schema_org/subject_scheme_multiple_keywords.yml +13 -13
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_turtle/BlogPosting.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_turtle/Dataset.yml +10 -10
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_turtle/journal_article.yml +16 -16
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_turtle/with_pages.yml +16 -16
- data/spec/readers/cff_reader_spec.rb +2 -20
- data/spec/readers/crossref_reader_spec.rb +10 -16
- data/spec/readers/crossref_xml_reader_spec.rb +61 -64
- data/spec/readers/json_feed_reader_spec.rb +56 -56
- data/spec/readers/schema_org_reader_spec.rb +1 -1
- data/spec/utils_spec.rb +1 -1
- data/spec/writers/crossref_xml_writer_spec.rb +9 -8
- data/spec/writers/csv_writer_spec.rb +1 -1
- data/spec/writers/ris_writer_spec.rb +2 -2
- metadata +2 -11
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/convert_file/crossref_xml/to_crossref_xml_refresh.yml +0 -107
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/doi_prefix/doi_prefix_by_blog.yml +0 -997
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/doi_prefix/doi_prefix_by_uuid.yml +0 -256
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/encode/by_uuid.yml +0 -256
- data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/encode/by_uuid_unknown_uuid.yml +0 -49
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_crossref_metadata/missing_creator.yml +0 -307
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_doi_prefix_for_blog/by_blog_post_uuid.yml +0 -136
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_doi_prefix_for_blog/by_blog_post_uuid_specific_prefix.yml +0 -256
- data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/book_oup.yml +0 -107
@@ -1,256 +0,0 @@
|
|
1
|
-
---
|
2
|
-
http_interactions:
|
3
|
-
- request:
|
4
|
-
method: get
|
5
|
-
uri: https://rogue-scholar.org/api/posts/2b22bbba-bcba-4072-94cc-3f88442fff88
|
6
|
-
body:
|
7
|
-
encoding: UTF-8
|
8
|
-
string: ''
|
9
|
-
headers:
|
10
|
-
Connection:
|
11
|
-
- close
|
12
|
-
Host:
|
13
|
-
- rogue-scholar.org
|
14
|
-
User-Agent:
|
15
|
-
- http.rb/5.1.1
|
16
|
-
response:
|
17
|
-
status:
|
18
|
-
code: 200
|
19
|
-
message: OK
|
20
|
-
headers:
|
21
|
-
Age:
|
22
|
-
- '0'
|
23
|
-
Cache-Control:
|
24
|
-
- public, max-age=0, must-revalidate
|
25
|
-
Content-Length:
|
26
|
-
- '17762'
|
27
|
-
Content-Type:
|
28
|
-
- application/json; charset=utf-8
|
29
|
-
Date:
|
30
|
-
- Sun, 18 Jun 2023 06:01:21 GMT
|
31
|
-
Etag:
|
32
|
-
- '"rm8wu4t2aydoe"'
|
33
|
-
Server:
|
34
|
-
- Vercel
|
35
|
-
Strict-Transport-Security:
|
36
|
-
- max-age=63072000
|
37
|
-
X-Matched-Path:
|
38
|
-
- "/api/posts/[slug]"
|
39
|
-
X-Vercel-Cache:
|
40
|
-
- MISS
|
41
|
-
X-Vercel-Id:
|
42
|
-
- fra1::iad1::6w82h-1687068080550-7c14323d7dbd
|
43
|
-
Connection:
|
44
|
-
- close
|
45
|
-
body:
|
46
|
-
encoding: UTF-8
|
47
|
-
string: '{"id":"https://doi.org/10.54900/6p6re-xyj61","uuid":"2b22bbba-bcba-4072-94cc-3f88442fff88","url":"https://upstream.force11.org/an-initial-scholarly-ai-taxonomy/","title":"An
|
48
|
-
Initial Scholarly AI Taxonomy","summary":"Although advances in artificial
|
49
|
-
intelligence (AI)1 have been unfolding for over decades, the progress in the
|
50
|
-
last six months has come faster than anyone expected. The public release of
|
51
|
-
ChatGPT in November 2022, in particular, has opened up new possibilities and
|
52
|
-
heightened awareness of AI''s potential role in various aspects of our work
|
53
|
-
and life.It follows that in the context of the publishing industry, AI also
|
54
|
-
holds the promise of transforming multiple facets of the publishing process2.
|
55
|
-
In this...","date_published":"2023-04-11T08:00:34Z","date_modified":"2023-04-11T15:29:38Z","date_indexed":"1970-01-01T00:00:00+00:00","authors":[{"url":null,"name":"Adam
|
56
|
-
Hyde"},{"url":"https://orcid.org/0000-0002-7378-2408","name":"John Chodacki"},{"url":null,"name":"Paul
|
57
|
-
Shannon"}],"image":"https://upstream.force11.org/content/images/2023/04/1-1.png","content_html":"
|
58
|
-
<!--kg-card-begin: html--><p class=''u-drop-cap-small''>Although advances
|
59
|
-
in artificial intelligence (AI)<sup>1</sup> have been unfolding for over decades,
|
60
|
-
the progress in the last six months has come faster than anyone expected.
|
61
|
-
The public release of ChatGPT in November 2022, in particular, has opened
|
62
|
-
up new possibilities and heightened awareness of AI''s potential role in various
|
63
|
-
aspects of our work and life.</p><!--kg-card-end: html--><!--kg-card-begin:
|
64
|
-
html--><p>It follows that in the context of the publishing industry, AI also
|
65
|
-
holds the promise of transforming multiple facets of the publishing process<sup>2</sup>.
|
66
|
-
In this blog post, we begin the development of a rough taxonomy for understanding
|
67
|
-
how and where AI can and/or should play a role in a publisher’s workflow.</p><!--kg-card-end:
|
68
|
-
html--><p>We intend to iterate on this taxonomy (for now, we will use the
|
69
|
-
working title ‘Scholarly AI Taxonomy’).</p><h2 id=\"scholarly-ai-taxonomy\">Scholarly
|
70
|
-
AI Taxonomy</h2><p>To kickstart discussions on AI''s potential impact on publishing
|
71
|
-
workflows, we present our initial categorization of the \"Scholarly AI Taxonomy.\"
|
72
|
-
This taxonomy outlines seven key roles that AI could potentially play in a
|
73
|
-
scholarly publishing workflow:</p><ol><li><strong>Extract</strong>: Identify
|
74
|
-
and isolate specific entities or data points within the content.</li><li><strong>Validate</strong>:
|
75
|
-
Verify the accuracy and reliability of the information.</li><li><strong>Generate</strong>:
|
76
|
-
Produce new content or ideas, such as text or images.</li><li><strong>Analyse</strong>:
|
77
|
-
Examine patterns, relationships, or trends within the information.</li><li><strong>Reformat</strong>:
|
78
|
-
Modify and adjust information to fit specific formats or presentation styles.</li><li><strong>Discover</strong>:
|
79
|
-
Search for and locate relevant information or connections.</li><li><strong>Translate</strong>:
|
80
|
-
Convert information from one language or form to another.</li></ol><p>The
|
81
|
-
above is the first pass at a taxonomy. To flesh out these further, we have
|
82
|
-
provided examples to illustrate each category further. </p><p>We thoroughly
|
83
|
-
recognise that some of the examples below, when further examined, may be miscategorized.
|
84
|
-
Further, we recognise that some examples could be illustrations of several
|
85
|
-
of these categories at play at once and don’t sit easily within just one of
|
86
|
-
the items listed. We also acknowledge that the categories themselves will
|
87
|
-
need thorough discussion and revision going forward. However, we hope that
|
88
|
-
this initial taxonomy can play a role in helping the community understand
|
89
|
-
what AI could mean for publishing processes.</p><p>Also note, in the examples
|
90
|
-
we are not making any assertions about the accuracy of AI when performing
|
91
|
-
these tasks. There are a lot of discussions already on whether the current
|
92
|
-
state of AI tools can do the following activities <em>well</em>. We are not
|
93
|
-
debating that aspect of the community discussion; that is for publishers and
|
94
|
-
technologists to explore further as the technology progresses and as we all
|
95
|
-
gain experience using these tools. </p><p>These categories are only proposed
|
96
|
-
as a way of understanding the <em>types of contributions</em> AI tools can
|
97
|
-
make. That being said, some of the below examples are more provocative than
|
98
|
-
others in an attempt to help the reader examine what they think <em>and feel</em>
|
99
|
-
about these possibilities.</p><h2 id=\"initial-categorization\">Initial categorization</h2><p>Our
|
100
|
-
initial seven categories are detailed further below.</p><h3 id=\"1-extractidentify-and-isolate-specific-entities-or-data-points-within-the-content\">1.
|
101
|
-
Extract - <em>Identify and isolate specific entities or data points within
|
102
|
-
the content</em></h3><p>In the extraction stage, AI-powered tools can significantly
|
103
|
-
streamline the process of identifying and extracting relevant information
|
104
|
-
from content and datasets. However, an over-reliance on AI for this task can
|
105
|
-
lead to errors if the models are not well-tuned or lack the necessary context
|
106
|
-
to identify entities accurately. Some speculative examples:</p><ol><li>Identifying
|
107
|
-
author names and affiliations from a submitted manuscript to pre-fill forms
|
108
|
-
and save time during submission while increasing the accuracy of the input.</li><li>Extracting
|
109
|
-
key terms and phrases for indexing purposes.</li><li>Isolating figures and
|
110
|
-
tables from a research article for separate processing.</li><li>Extracting
|
111
|
-
metadata, such as title, abstract, and keywords, from a document.</li><li>Identifying
|
112
|
-
citations within a text for reference management.</li></ol><h3 id=\"2-validateverify-the-accuracy-and-reliability-of-the-information\">2.
|
113
|
-
Validate - <em>Verify the accuracy and reliability of the information</em></h3><p>AI-based
|
114
|
-
systems can validate information by cross-referencing data against reliable
|
115
|
-
sources or expected structures, ensuring content conformity, accuracy and/or
|
116
|
-
credibility. While this can reduce human error, it is essential to maintain
|
117
|
-
a level of human oversight, as AI models may not always detect nuances in
|
118
|
-
language or identify reliable sources. Some examples:</p><ol><li>Cross-referencing
|
119
|
-
citations to ensure accuracy and proper formatting.</li><li>Verifying author
|
120
|
-
affiliations against an established database.</li><li>Ensuring proper image
|
121
|
-
attribution and permissions.</li><li>Checking factual information in an article
|
122
|
-
against trusted sources.</li><li>Validating claims made in a scientific paper
|
123
|
-
against previous studies.</li></ol><h3 id=\"3-generateproduce-new-content-or-ideas-such-as-text-or-images\">3.
|
124
|
-
Generate - <em>Produce new content or ideas, such as text or images</em></h3><p>AI
|
125
|
-
can create high-quality text and images, saving time and effort for authors
|
126
|
-
and editors. However, the content generated by AI may contain factual inaccuracies,
|
127
|
-
lack creativity, or inadvertently reproduce biases present in the training
|
128
|
-
data, necessitating human intervention to ensure accuracy, quality, originality,
|
129
|
-
and adherence to ethical guidelines. Some examples:</p><ol><li>Generating
|
130
|
-
social media content (e.g., summarising longer text to a tweetable length)
|
131
|
-
or promotional content for a new publication.</li><li>Creating keyword lists
|
132
|
-
for search engine optimization (SEO).</li><li>Automatically generating an
|
133
|
-
abstract or summary of a manuscript, particularly a plain language summary
|
134
|
-
pitched at a certain audience.</li><li>Creating a list of suggested article
|
135
|
-
titles based on the content and target audience.</li><li>Producing visually
|
136
|
-
engaging charts or graphs from raw data.</li></ol><h3 id=\"4-analyseexamine-patterns-relationships-or-trends-within-the-information\">4.
|
137
|
-
Analyse - <em>Examine patterns, relationships, or trends within the information</em></h3><p>AI-driven
|
138
|
-
data analytics tools can help publishers extract valuable insights from their
|
139
|
-
content, identifying patterns and trends to optimize content strategy. While
|
140
|
-
AI can provide essential information, over-reliance on AI analytics may lead
|
141
|
-
to overlooking important context or misinterpreting data, requiring human
|
142
|
-
analysts to interpret findings accurately. Some examples:</p><ol><li>Analyse
|
143
|
-
an image to create accessible text descriptions.</li><li>Determining the sentiment
|
144
|
-
of reviews.</li><li>Identifying trending topics in a specific field to guide
|
145
|
-
editorial direction.</li><li>Analyzing the readability level of a manuscript.</li><li>Discovering
|
146
|
-
patterns in citation networks to identify influential articles and authors.</li></ol><h3
|
147
|
-
id=\"5-reformatmodify-and-adjust-information-to-fit-specific-formats-or-presentation-styles\">5.
|
148
|
-
Reformat - <em>Modify and adjust information to fit specific formats or presentation
|
149
|
-
styles</em></h3><p>AI can reformat content for specific media channels or
|
150
|
-
alternative structures, enhancing user experience and accessibility. However,
|
151
|
-
AI-generated formatting may not always be ideal or adhere to specific style
|
152
|
-
guidelines, requiring human editors to fine-tune the formatting. Some examples:</p><ol><li>Formatting
|
153
|
-
content to comply with a specific style guide.</li><li>Adapting a long-form
|
154
|
-
article for a shorter, mobile-friendly version.</li><li>Converting a manuscript
|
155
|
-
into XML or converting datasets to open formats.</li><li>Rearranging content
|
156
|
-
to fit different print and digital formats.</li><li>Adjusting images and graphics
|
157
|
-
for optimal display across various devices.</li></ol><h3 id=\"6-discoversearch-for-and-locate-relevant-information-or-connections\">6.
|
158
|
-
Discover - <em>Search for and locate relevant information or connections</em></h3><p>AI
|
159
|
-
can efficiently find and link information about a subject, streamlining the
|
160
|
-
research process. However, AI-driven information discovery may yield irrelevant,
|
161
|
-
incorrect, or outdated results, necessitating human verification and filtering
|
162
|
-
to ensure accuracy and usefulness. Some examples:</p><ol><li>Finding relevant
|
163
|
-
articles within a publisher’s corpus to recommend for further reading.</li><li>Identifying
|
164
|
-
potential reviewers for a submitted manuscript based on their expertise.</li><li>Discovering
|
165
|
-
trending topics for a call for papers.</li><li>Locating similar works to provide
|
166
|
-
context for a piece of content.</li><li>Searching for related images or multimedia
|
167
|
-
to accompany a text.</li></ol><h3 id=\"7-translateconvert-information-from-one-language-or-form-to-another\">7.
|
168
|
-
Translate - <em>Convert information from one language or form to another</em></h3><p>AI
|
169
|
-
can quickly translate languages and sentiments, making content more accessible
|
170
|
-
and understandable to diverse audiences. However, AI translations can sometimes
|
171
|
-
be inaccurate or lose nuances in meaning, especially when dealing with idiomatic
|
172
|
-
expressions or cultural context, necessitating the involvement of human translators
|
173
|
-
for sensitive or complex content. Some examples:</p><ol><li>Translating a
|
174
|
-
research article or book into another language.</li><li>Converting scientific
|
175
|
-
jargon into more accessible language for a popular science article.</li><li>Adapting
|
176
|
-
a text''s cultural references to be more understandable for a global readership.</li><li>Translating
|
177
|
-
the sentiment of a text.</li><li>Converting spoken language into written transcripts
|
178
|
-
(or vice versa) for interviews or podcasts.</li></ol><h2 id=\"balancing-ai-and-human-intervention-in-publishing-workflows\">Balancing
|
179
|
-
AI and Human Intervention in Publishing Workflows</h2><p>There is potential
|
180
|
-
for AI to benefit publishing workflows. Still, it''s crucial to identify where
|
181
|
-
AI should play a role and when human intervention is required to check and
|
182
|
-
validate outcomes of assisted technology. In many ways, this is no different
|
183
|
-
to how publishing works today. If there is one thing publishers do well, and
|
184
|
-
sometimes to exaggerated fidelity, it is quality assurance.</p><p>However,
|
185
|
-
AI tools offer several new dimensions which can bring machine assistance into
|
186
|
-
many more parts of the process at a much larger scale. This, together with
|
187
|
-
the feeling we have that AI is, in fact, in some ways ‘doing work previously
|
188
|
-
considered to be the sole realm of the sentient’ and the need for people and
|
189
|
-
AI machines to ‘learn together’ so those outcomes can improve, means there
|
190
|
-
is both factual and emotional requirements to scope, monitor, and check these
|
191
|
-
outcomes.</p><p>Consequently, workflow platforms must be designed with interfaces
|
192
|
-
allowing seamless ‘Human QA’ at appropriate points in the process. These interfaces
|
193
|
-
should enable publishers to review, edit, and approve AI-generated content
|
194
|
-
or insights, ensuring that the final product meets the required standards
|
195
|
-
and ethical guidelines. Where possible, the ‘Human QA’ should feed back into
|
196
|
-
the AI processes to improve future outcomes; this also needs to be considered
|
197
|
-
by tool builders.</p><p>To accommodate this ''Human QA'', new types of interfaces
|
198
|
-
will need to be developed in publishing tools. These interfaces should facilitate
|
199
|
-
easy interaction between human users and AI-generated content, allowing for
|
200
|
-
necessary reviews and modifications. For instance, a journal workflow platform
|
201
|
-
might offer a feature where users are asked to ''greenlight'' a pre-selected
|
202
|
-
option from a drop-down menu (e.g., institutional affiliation), generated
|
203
|
-
by AI. This way, researchers and editors can quickly validate AI-generated
|
204
|
-
suggestions while providing feedback to improve the AI''s performance over
|
205
|
-
time. Integrating such interfaces not only ensures that the content adheres
|
206
|
-
to the desired quality standards and ethical principles but also expedites
|
207
|
-
the publishing process, making it more efficient.</p><h2 id=\"the-speed-of-trust\">The
|
208
|
-
Speed of Trust</h2><p>Trust plays a large role in this process. As we learn
|
209
|
-
more about the fidelity and accuracy of these systems and confront what AI
|
210
|
-
processes can and can’t do well to date, we will need to move forward with
|
211
|
-
building AI into workflows ''at the speed of trust.''</p><p>Adopting a \"speed
|
212
|
-
of trust\" approach means being cautious yet open to AI''s potential in transforming
|
213
|
-
publishing workflows. It involves engaging in honest conversations about AI''s
|
214
|
-
capabilities and addressing concerns, all while striking a balance between
|
215
|
-
innovation and desirable community standards. As we navigate this delicate
|
216
|
-
balance, we create an environment where AI technology can grow and adapt to
|
217
|
-
better serve the publishing community.</p><p>For example, as a start, when
|
218
|
-
integrating AI into publishing workflows, we believe it is essential to provide
|
219
|
-
an ‘opt-in’ and transparent approach to AI contributions. Publishers and authors
|
220
|
-
should be informed about the extent of AI involvement and its limitations,
|
221
|
-
and presented with interfaces allowing them to make informed decisions about
|
222
|
-
when and how AI will be used. This transparent ‘opt-in’ approach helps build
|
223
|
-
trust, allows us to iterate forward as we gain more experience, and sets the
|
224
|
-
stage for discussions and practices regarding ethical AI integration in publishing
|
225
|
-
workflows.</p><h2 id=\"conclusion\">Conclusion</h2><p>The potential of AI
|
226
|
-
in publishing workflows is immense, and we find ourselves at a time when the
|
227
|
-
technology has taken a significant step forward. But it''s essential to approach
|
228
|
-
its integration with a balanced perspective. We can harness the power of AI
|
229
|
-
while adhering to ethical standards and delivering high-quality content by
|
230
|
-
considering both the benefits and drawbacks of AI, identifying areas for human
|
231
|
-
intervention, maintaining transparency, and evolving our understanding of
|
232
|
-
AI contributions.</p><p>This initial taxonomy outlined in this article can
|
233
|
-
serve as a starting point for understanding how AI can contribute to publishing
|
234
|
-
workflows. By quantifying AI contributions in this way, we can also discuss
|
235
|
-
the ethical boundaries of AI-assisted workflows more clearly and help publishers
|
236
|
-
make informed decisions about AI integration.</p><p>By adopting a thoughtful
|
237
|
-
strategy, the combined strengths of AI and human expertise can drive significant
|
238
|
-
advancements and innovation within the publishing industry.</p><hr><!--kg-card-begin:
|
239
|
-
html--><p class=''u-drop-cap-small''><sup>1</sup> It''s worth noting that
|
240
|
-
we use the term AI here, but we are actually referring to large language models
|
241
|
-
(LLMs); AI serves as useful shorthand since it''s the common term used in
|
242
|
-
our community. As we all gain more experience, being more accurate about how
|
243
|
-
we use terms like AI and LLM will become increasingly important. A Large Language
|
244
|
-
Model (LLM) can be described as a sophisticated text processor. It''s an advanced
|
245
|
-
machine learning model designed to process, generate, and understand natural
|
246
|
-
language text.</p><!--kg-card-end: html--><!--kg-card-begin: html--><p class=''u-drop-cap-small''><sup>2</sup>
|
247
|
-
By publishing, we are referring to both traditional journal-focused publishing
|
248
|
-
models as well as emergent publishing models such as preprints, protocols/methods,
|
249
|
-
micropubs, data, etc.</p>\n<!--kg-card-end: html--><p><em>Many thanks to Ben
|
250
|
-
Whitmore, Ryan Dix-Peek, and Nokome Bentley for the discussions that lead
|
251
|
-
to this taxonomy at our recent Coko Summit. This article was written with
|
252
|
-
the assistance of GPT4.</em></p> ","tags":["Thought Pieces"],"language":"en","references":[],"blog_id":"pm0p222","blog":{"id":"pm0p222","title":"Upstream","description":"The
|
253
|
-
community blog for all things Open Research.","language":"en","favicon":"https://upstream.force11.org/favicon.png","feed_url":"https://upstream.force11.org/atom/","home_page_url":"https://upstream.force11.org","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T07:23:49+00:00","indexed_at":"2023-01-13","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Ghost
|
254
|
-
5.25","category":"Humanities","prefix":"10.54900","modified_at":"2023-06-06T08:00:49+00:00","version":"https://jsonfeed.org/version/1.1","backlog":true,"authors":null}}'
|
255
|
-
recorded_at: Sun, 18 Jun 2023 06:01:21 GMT
|
256
|
-
recorded_with: VCR 6.1.0
|
@@ -1,256 +0,0 @@
|
|
1
|
-
---
|
2
|
-
http_interactions:
|
3
|
-
- request:
|
4
|
-
method: get
|
5
|
-
uri: https://rogue-scholar.org/api/posts/2b22bbba-bcba-4072-94cc-3f88442fff88
|
6
|
-
body:
|
7
|
-
encoding: UTF-8
|
8
|
-
string: ''
|
9
|
-
headers:
|
10
|
-
Connection:
|
11
|
-
- close
|
12
|
-
Host:
|
13
|
-
- rogue-scholar.org
|
14
|
-
User-Agent:
|
15
|
-
- http.rb/5.1.1
|
16
|
-
response:
|
17
|
-
status:
|
18
|
-
code: 200
|
19
|
-
message: OK
|
20
|
-
headers:
|
21
|
-
Age:
|
22
|
-
- '0'
|
23
|
-
Cache-Control:
|
24
|
-
- public, max-age=0, must-revalidate
|
25
|
-
Content-Length:
|
26
|
-
- '17762'
|
27
|
-
Content-Type:
|
28
|
-
- application/json; charset=utf-8
|
29
|
-
Date:
|
30
|
-
- Sun, 18 Jun 2023 06:11:58 GMT
|
31
|
-
Etag:
|
32
|
-
- '"rm8wu4t2aydoe"'
|
33
|
-
Server:
|
34
|
-
- Vercel
|
35
|
-
Strict-Transport-Security:
|
36
|
-
- max-age=63072000
|
37
|
-
X-Matched-Path:
|
38
|
-
- "/api/posts/[slug]"
|
39
|
-
X-Vercel-Cache:
|
40
|
-
- MISS
|
41
|
-
X-Vercel-Id:
|
42
|
-
- fra1::iad1::4td2d-1687068717934-af1351764f24
|
43
|
-
Connection:
|
44
|
-
- close
|
45
|
-
body:
|
46
|
-
encoding: UTF-8
|
47
|
-
string: '{"id":"https://doi.org/10.54900/6p6re-xyj61","uuid":"2b22bbba-bcba-4072-94cc-3f88442fff88","url":"https://upstream.force11.org/an-initial-scholarly-ai-taxonomy/","title":"An
|
48
|
-
Initial Scholarly AI Taxonomy","summary":"Although advances in artificial
|
49
|
-
intelligence (AI)1 have been unfolding for over decades, the progress in the
|
50
|
-
last six months has come faster than anyone expected. The public release of
|
51
|
-
ChatGPT in November 2022, in particular, has opened up new possibilities and
|
52
|
-
heightened awareness of AI''s potential role in various aspects of our work
|
53
|
-
and life.It follows that in the context of the publishing industry, AI also
|
54
|
-
holds the promise of transforming multiple facets of the publishing process2.
|
55
|
-
In this...","date_published":"2023-04-11T08:00:34Z","date_modified":"2023-04-11T15:29:38Z","date_indexed":"1970-01-01T00:00:00+00:00","authors":[{"url":null,"name":"Adam
|
56
|
-
Hyde"},{"url":"https://orcid.org/0000-0002-7378-2408","name":"John Chodacki"},{"url":null,"name":"Paul
|
57
|
-
Shannon"}],"image":"https://upstream.force11.org/content/images/2023/04/1-1.png","content_html":"
|
58
|
-
<!--kg-card-begin: html--><p class=''u-drop-cap-small''>Although advances
|
59
|
-
in artificial intelligence (AI)<sup>1</sup> have been unfolding for over decades,
|
60
|
-
the progress in the last six months has come faster than anyone expected.
|
61
|
-
The public release of ChatGPT in November 2022, in particular, has opened
|
62
|
-
up new possibilities and heightened awareness of AI''s potential role in various
|
63
|
-
aspects of our work and life.</p><!--kg-card-end: html--><!--kg-card-begin:
|
64
|
-
html--><p>It follows that in the context of the publishing industry, AI also
|
65
|
-
holds the promise of transforming multiple facets of the publishing process<sup>2</sup>.
|
66
|
-
In this blog post, we begin the development of a rough taxonomy for understanding
|
67
|
-
how and where AI can and/or should play a role in a publisher’s workflow.</p><!--kg-card-end:
|
68
|
-
html--><p>We intend to iterate on this taxonomy (for now, we will use the
|
69
|
-
working title ‘Scholarly AI Taxonomy’).</p><h2 id=\"scholarly-ai-taxonomy\">Scholarly
|
70
|
-
AI Taxonomy</h2><p>To kickstart discussions on AI''s potential impact on publishing
|
71
|
-
workflows, we present our initial categorization of the \"Scholarly AI Taxonomy.\"
|
72
|
-
This taxonomy outlines seven key roles that AI could potentially play in a
|
73
|
-
scholarly publishing workflow:</p><ol><li><strong>Extract</strong>: Identify
|
74
|
-
and isolate specific entities or data points within the content.</li><li><strong>Validate</strong>:
|
75
|
-
Verify the accuracy and reliability of the information.</li><li><strong>Generate</strong>:
|
76
|
-
Produce new content or ideas, such as text or images.</li><li><strong>Analyse</strong>:
|
77
|
-
Examine patterns, relationships, or trends within the information.</li><li><strong>Reformat</strong>:
|
78
|
-
Modify and adjust information to fit specific formats or presentation styles.</li><li><strong>Discover</strong>:
|
79
|
-
Search for and locate relevant information or connections.</li><li><strong>Translate</strong>:
|
80
|
-
Convert information from one language or form to another.</li></ol><p>The
|
81
|
-
above is the first pass at a taxonomy. To flesh out these further, we have
|
82
|
-
provided examples to illustrate each category further. </p><p>We thoroughly
|
83
|
-
recognise that some of the examples below, when further examined, may be miscategorized.
|
84
|
-
Further, we recognise that some examples could be illustrations of several
|
85
|
-
of these categories at play at once and don’t sit easily within just one of
|
86
|
-
the items listed. We also acknowledge that the categories themselves will
|
87
|
-
need thorough discussion and revision going forward. However, we hope that
|
88
|
-
this initial taxonomy can play a role in helping the community understand
|
89
|
-
what AI could mean for publishing processes.</p><p>Also note, in the examples
|
90
|
-
we are not making any assertions about the accuracy of AI when performing
|
91
|
-
these tasks. There are a lot of discussions already on whether the current
|
92
|
-
state of AI tools can do the following activities <em>well</em>. We are not
|
93
|
-
debating that aspect of the community discussion; that is for publishers and
|
94
|
-
technologists to explore further as the technology progresses and as we all
|
95
|
-
gain experience using these tools. </p><p>These categories are only proposed
|
96
|
-
as a way of understanding the <em>types of contributions</em> AI tools can
|
97
|
-
make. That being said, some of the below examples are more provocative than
|
98
|
-
others in an attempt to help the reader examine what they think <em>and feel</em>
|
99
|
-
about these possibilities.</p><h2 id=\"initial-categorization\">Initial categorization</h2><p>Our
|
100
|
-
initial seven categories are detailed further below.</p><h3 id=\"1-extractidentify-and-isolate-specific-entities-or-data-points-within-the-content\">1.
|
101
|
-
Extract - <em>Identify and isolate specific entities or data points within
|
102
|
-
the content</em></h3><p>In the extraction stage, AI-powered tools can significantly
|
103
|
-
streamline the process of identifying and extracting relevant information
|
104
|
-
from content and datasets. However, an over-reliance on AI for this task can
|
105
|
-
lead to errors if the models are not well-tuned or lack the necessary context
|
106
|
-
to identify entities accurately. Some speculative examples:</p><ol><li>Identifying
|
107
|
-
author names and affiliations from a submitted manuscript to pre-fill forms
|
108
|
-
and save time during submission while increasing the accuracy of the input.</li><li>Extracting
|
109
|
-
key terms and phrases for indexing purposes.</li><li>Isolating figures and
|
110
|
-
tables from a research article for separate processing.</li><li>Extracting
|
111
|
-
metadata, such as title, abstract, and keywords, from a document.</li><li>Identifying
|
112
|
-
citations within a text for reference management.</li></ol><h3 id=\"2-validateverify-the-accuracy-and-reliability-of-the-information\">2.
|
113
|
-
Validate - <em>Verify the accuracy and reliability of the information</em></h3><p>AI-based
|
114
|
-
systems can validate information by cross-referencing data against reliable
|
115
|
-
sources or expected structures, ensuring content conformity, accuracy and/or
|
116
|
-
credibility. While this can reduce human error, it is essential to maintain
|
117
|
-
a level of human oversight, as AI models may not always detect nuances in
|
118
|
-
language or identify reliable sources. Some examples:</p><ol><li>Cross-referencing
|
119
|
-
citations to ensure accuracy and proper formatting.</li><li>Verifying author
|
120
|
-
affiliations against an established database.</li><li>Ensuring proper image
|
121
|
-
attribution and permissions.</li><li>Checking factual information in an article
|
122
|
-
against trusted sources.</li><li>Validating claims made in a scientific paper
|
123
|
-
against previous studies.</li></ol><h3 id=\"3-generateproduce-new-content-or-ideas-such-as-text-or-images\">3.
|
124
|
-
Generate - <em>Produce new content or ideas, such as text or images</em></h3><p>AI
|
125
|
-
can create high-quality text and images, saving time and effort for authors
|
126
|
-
and editors. However, the content generated by AI may contain factual inaccuracies,
|
127
|
-
lack creativity, or inadvertently reproduce biases present in the training
|
128
|
-
data, necessitating human intervention to ensure accuracy, quality, originality,
|
129
|
-
and adherence to ethical guidelines. Some examples:</p><ol><li>Generating
|
130
|
-
social media content (e.g., summarising longer text to a tweetable length)
|
131
|
-
or promotional content for a new publication.</li><li>Creating keyword lists
|
132
|
-
for search engine optimization (SEO).</li><li>Automatically generating an
|
133
|
-
abstract or summary of a manuscript, particularly a plain language summary
|
134
|
-
pitched at a certain audience.</li><li>Creating a list of suggested article
|
135
|
-
titles based on the content and target audience.</li><li>Producing visually
|
136
|
-
engaging charts or graphs from raw data.</li></ol><h3 id=\"4-analyseexamine-patterns-relationships-or-trends-within-the-information\">4.
|
137
|
-
Analyse - <em>Examine patterns, relationships, or trends within the information</em></h3><p>AI-driven
|
138
|
-
data analytics tools can help publishers extract valuable insights from their
|
139
|
-
content, identifying patterns and trends to optimize content strategy. While
|
140
|
-
AI can provide essential information, over-reliance on AI analytics may lead
|
141
|
-
to overlooking important context or misinterpreting data, requiring human
|
142
|
-
analysts to interpret findings accurately. Some examples:</p><ol><li>Analyse
|
143
|
-
an image to create accessible text descriptions.</li><li>Determining the sentiment
|
144
|
-
of reviews.</li><li>Identifying trending topics in a specific field to guide
|
145
|
-
editorial direction.</li><li>Analyzing the readability level of a manuscript.</li><li>Discovering
|
146
|
-
patterns in citation networks to identify influential articles and authors.</li></ol><h3
|
147
|
-
id=\"5-reformatmodify-and-adjust-information-to-fit-specific-formats-or-presentation-styles\">5.
|
148
|
-
Reformat - <em>Modify and adjust information to fit specific formats or presentation
|
149
|
-
styles</em></h3><p>AI can reformat content for specific media channels or
|
150
|
-
alternative structures, enhancing user experience and accessibility. However,
|
151
|
-
AI-generated formatting may not always be ideal or adhere to specific style
|
152
|
-
guidelines, requiring human editors to fine-tune the formatting. Some examples:</p><ol><li>Formatting
|
153
|
-
content to comply with a specific style guide.</li><li>Adapting a long-form
|
154
|
-
article for a shorter, mobile-friendly version.</li><li>Converting a manuscript
|
155
|
-
into XML or converting datasets to open formats.</li><li>Rearranging content
|
156
|
-
to fit different print and digital formats.</li><li>Adjusting images and graphics
|
157
|
-
for optimal display across various devices.</li></ol><h3 id=\"6-discoversearch-for-and-locate-relevant-information-or-connections\">6.
|
158
|
-
Discover - <em>Search for and locate relevant information or connections</em></h3><p>AI
|
159
|
-
can efficiently find and link information about a subject, streamlining the
|
160
|
-
research process. However, AI-driven information discovery may yield irrelevant,
|
161
|
-
incorrect, or outdated results, necessitating human verification and filtering
|
162
|
-
to ensure accuracy and usefulness. Some examples:</p><ol><li>Finding relevant
|
163
|
-
articles within a publisher’s corpus to recommend for further reading.</li><li>Identifying
|
164
|
-
potential reviewers for a submitted manuscript based on their expertise.</li><li>Discovering
|
165
|
-
trending topics for a call for papers.</li><li>Locating similar works to provide
|
166
|
-
context for a piece of content.</li><li>Searching for related images or multimedia
|
167
|
-
to accompany a text.</li></ol><h3 id=\"7-translateconvert-information-from-one-language-or-form-to-another\">7.
|
168
|
-
Translate - <em>Convert information from one language or form to another</em></h3><p>AI
|
169
|
-
can quickly translate languages and sentiments, making content more accessible
|
170
|
-
and understandable to diverse audiences. However, AI translations can sometimes
|
171
|
-
be inaccurate or lose nuances in meaning, especially when dealing with idiomatic
|
172
|
-
expressions or cultural context, necessitating the involvement of human translators
|
173
|
-
for sensitive or complex content. Some examples:</p><ol><li>Translating a
|
174
|
-
research article or book into another language.</li><li>Converting scientific
|
175
|
-
jargon into more accessible language for a popular science article.</li><li>Adapting
|
176
|
-
a text''s cultural references to be more understandable for a global readership.</li><li>Translating
|
177
|
-
the sentiment of a text.</li><li>Converting spoken language into written transcripts
|
178
|
-
(or vice versa) for interviews or podcasts.</li></ol><h2 id=\"balancing-ai-and-human-intervention-in-publishing-workflows\">Balancing
|
179
|
-
AI and Human Intervention in Publishing Workflows</h2><p>There is potential
|
180
|
-
for AI to benefit publishing workflows. Still, it''s crucial to identify where
|
181
|
-
AI should play a role and when human intervention is required to check and
|
182
|
-
validate outcomes of assisted technology. In many ways, this is no different
|
183
|
-
to how publishing works today. If there is one thing publishers do well, and
|
184
|
-
sometimes to exaggerated fidelity, it is quality assurance.</p><p>However,
|
185
|
-
AI tools offer several new dimensions which can bring machine assistance into
|
186
|
-
many more parts of the process at a much larger scale. This, together with
|
187
|
-
the feeling we have that AI is, in fact, in some ways ‘doing work previously
|
188
|
-
considered to be the sole realm of the sentient’ and the need for people and
|
189
|
-
AI machines to ‘learn together’ so those outcomes can improve, means there
|
190
|
-
is both factual and emotional requirements to scope, monitor, and check these
|
191
|
-
outcomes.</p><p>Consequently, workflow platforms must be designed with interfaces
|
192
|
-
allowing seamless ‘Human QA’ at appropriate points in the process. These interfaces
|
193
|
-
should enable publishers to review, edit, and approve AI-generated content
|
194
|
-
or insights, ensuring that the final product meets the required standards
|
195
|
-
and ethical guidelines. Where possible, the ‘Human QA’ should feed back into
|
196
|
-
the AI processes to improve future outcomes; this also needs to be considered
|
197
|
-
by tool builders.</p><p>To accommodate this ''Human QA'', new types of interfaces
|
198
|
-
will need to be developed in publishing tools. These interfaces should facilitate
|
199
|
-
easy interaction between human users and AI-generated content, allowing for
|
200
|
-
necessary reviews and modifications. For instance, a journal workflow platform
|
201
|
-
might offer a feature where users are asked to ''greenlight'' a pre-selected
|
202
|
-
option from a drop-down menu (e.g., institutional affiliation), generated
|
203
|
-
by AI. This way, researchers and editors can quickly validate AI-generated
|
204
|
-
suggestions while providing feedback to improve the AI''s performance over
|
205
|
-
time. Integrating such interfaces not only ensures that the content adheres
|
206
|
-
to the desired quality standards and ethical principles but also expedites
|
207
|
-
the publishing process, making it more efficient.</p><h2 id=\"the-speed-of-trust\">The
|
208
|
-
Speed of Trust</h2><p>Trust plays a large role in this process. As we learn
|
209
|
-
more about the fidelity and accuracy of these systems and confront what AI
|
210
|
-
processes can and can’t do well to date, we will need to move forward with
|
211
|
-
building AI into workflows ''at the speed of trust.''</p><p>Adopting a \"speed
|
212
|
-
of trust\" approach means being cautious yet open to AI''s potential in transforming
|
213
|
-
publishing workflows. It involves engaging in honest conversations about AI''s
|
214
|
-
capabilities and addressing concerns, all while striking a balance between
|
215
|
-
innovation and desirable community standards. As we navigate this delicate
|
216
|
-
balance, we create an environment where AI technology can grow and adapt to
|
217
|
-
better serve the publishing community.</p><p>For example, as a start, when
|
218
|
-
integrating AI into publishing workflows, we believe it is essential to provide
|
219
|
-
an ‘opt-in’ and transparent approach to AI contributions. Publishers and authors
|
220
|
-
should be informed about the extent of AI involvement and its limitations,
|
221
|
-
and presented with interfaces allowing them to make informed decisions about
|
222
|
-
when and how AI will be used. This transparent ‘opt-in’ approach helps build
|
223
|
-
trust, allows us to iterate forward as we gain more experience, and sets the
|
224
|
-
stage for discussions and practices regarding ethical AI integration in publishing
|
225
|
-
workflows.</p><h2 id=\"conclusion\">Conclusion</h2><p>The potential of AI
|
226
|
-
in publishing workflows is immense, and we find ourselves at a time when the
|
227
|
-
technology has taken a significant step forward. But it''s essential to approach
|
228
|
-
its integration with a balanced perspective. We can harness the power of AI
|
229
|
-
while adhering to ethical standards and delivering high-quality content by
|
230
|
-
considering both the benefits and drawbacks of AI, identifying areas for human
|
231
|
-
intervention, maintaining transparency, and evolving our understanding of
|
232
|
-
AI contributions.</p><p>This initial taxonomy outlined in this article can
|
233
|
-
serve as a starting point for understanding how AI can contribute to publishing
|
234
|
-
workflows. By quantifying AI contributions in this way, we can also discuss
|
235
|
-
the ethical boundaries of AI-assisted workflows more clearly and help publishers
|
236
|
-
make informed decisions about AI integration.</p><p>By adopting a thoughtful
|
237
|
-
strategy, the combined strengths of AI and human expertise can drive significant
|
238
|
-
advancements and innovation within the publishing industry.</p><hr><!--kg-card-begin:
|
239
|
-
html--><p class=''u-drop-cap-small''><sup>1</sup> It''s worth noting that
|
240
|
-
we use the term AI here, but we are actually referring to large language models
|
241
|
-
(LLMs); AI serves as useful shorthand since it''s the common term used in
|
242
|
-
our community. As we all gain more experience, being more accurate about how
|
243
|
-
we use terms like AI and LLM will become increasingly important. A Large Language
|
244
|
-
Model (LLM) can be described as a sophisticated text processor. It''s an advanced
|
245
|
-
machine learning model designed to process, generate, and understand natural
|
246
|
-
language text.</p><!--kg-card-end: html--><!--kg-card-begin: html--><p class=''u-drop-cap-small''><sup>2</sup>
|
247
|
-
By publishing, we are referring to both traditional journal-focused publishing
|
248
|
-
models as well as emergent publishing models such as preprints, protocols/methods,
|
249
|
-
micropubs, data, etc.</p>\n<!--kg-card-end: html--><p><em>Many thanks to Ben
|
250
|
-
Whitmore, Ryan Dix-Peek, and Nokome Bentley for the discussions that lead
|
251
|
-
to this taxonomy at our recent Coko Summit. This article was written with
|
252
|
-
the assistance of GPT4.</em></p> ","tags":["Thought Pieces"],"language":"en","references":[],"blog_id":"pm0p222","blog":{"id":"pm0p222","title":"Upstream","description":"The
|
253
|
-
community blog for all things Open Research.","language":"en","favicon":"https://upstream.force11.org/favicon.png","feed_url":"https://upstream.force11.org/atom/","home_page_url":"https://upstream.force11.org","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T07:23:49+00:00","indexed_at":"2023-01-13","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Ghost
|
254
|
-
5.25","category":"Humanities","prefix":"10.54900","modified_at":"2023-06-06T08:00:49+00:00","version":"https://jsonfeed.org/version/1.1","backlog":true,"authors":null}}'
|
255
|
-
recorded_at: Sun, 18 Jun 2023 06:11:58 GMT
|
256
|
-
recorded_with: VCR 6.1.0
|
@@ -1,49 +0,0 @@
|
|
1
|
-
---
|
2
|
-
http_interactions:
|
3
|
-
- request:
|
4
|
-
method: get
|
5
|
-
uri: https://rogue-scholar.org/api/posts/2b22bbba-bcba-4072-94cc-3f88442
|
6
|
-
body:
|
7
|
-
encoding: UTF-8
|
8
|
-
string: ''
|
9
|
-
headers:
|
10
|
-
Connection:
|
11
|
-
- close
|
12
|
-
Host:
|
13
|
-
- rogue-scholar.org
|
14
|
-
User-Agent:
|
15
|
-
- http.rb/5.1.1
|
16
|
-
response:
|
17
|
-
status:
|
18
|
-
code: 200
|
19
|
-
message: OK
|
20
|
-
headers:
|
21
|
-
Age:
|
22
|
-
- '0'
|
23
|
-
Cache-Control:
|
24
|
-
- public, max-age=0, must-revalidate
|
25
|
-
Content-Length:
|
26
|
-
- '4'
|
27
|
-
Content-Type:
|
28
|
-
- application/json; charset=utf-8
|
29
|
-
Date:
|
30
|
-
- Sun, 18 Jun 2023 07:50:45 GMT
|
31
|
-
Etag:
|
32
|
-
- '"wm6yxsynvh4"'
|
33
|
-
Server:
|
34
|
-
- Vercel
|
35
|
-
Strict-Transport-Security:
|
36
|
-
- max-age=63072000
|
37
|
-
X-Matched-Path:
|
38
|
-
- "/api/posts/[slug]"
|
39
|
-
X-Vercel-Cache:
|
40
|
-
- MISS
|
41
|
-
X-Vercel-Id:
|
42
|
-
- fra1::iad1::vcxmh-1687074645282-662f2f07ee79
|
43
|
-
Connection:
|
44
|
-
- close
|
45
|
-
body:
|
46
|
-
encoding: UTF-8
|
47
|
-
string: 'null'
|
48
|
-
recorded_at: Sun, 18 Jun 2023 07:50:45 GMT
|
49
|
-
recorded_with: VCR 6.1.0
|