kausalflow/lightkone / components/citation-key/versions/1/examples.jsonl · raw

{"input": {"drafts": [{"title": "Improving neural networks by preventing co-adaptation", "authors": ["Hinton, Geoffrey"], "year": 2012}]}, "output": {"keys": ["Hinton2012-in"]}, "note": "surname, year, first letters of the first two long words"}
{"input": {"drafts": [{"title": "Attention is all you need", "authors": ["Vaswani, Ashish"], "year": 2017}]}, "output": {"keys": ["Vaswani2017-an"]}, "note": "short words are skipped: attention, need"}
{"input": {"drafts": [{"title": "Über formal unentscheidbare Sätze", "authors": ["Gödel, Kurt"], "year": 1931}]}, "output": {"keys": ["Godel1931-fu"]}, "note": "accents decompose in the surname but vanish from the title"}
{"input": {"drafts": [{"title": "Deep learning", "authors": ["LeCun, Yann"], "year": 2015}], "taken": ["LeCun2015-dl"]}, "output": {"keys": ["LeCun2015-dl2"]}, "note": "a taken key counts up from 2"}
{"input": {"drafts": [{"title": "Deep learning", "authors": ["LeCun, Yann"], "year": 2015}], "taken": ["LeCun2015-dl", "LeCun2015-dl2", "LeCun2015-dl3"]}, "output": {"keys": ["LeCun2015-dl4"]}, "note": "first free number"}
{"input": {"drafts": [{"title": "Deep learning", "authors": ["LeCun, Yann"], "year": 2015}, {"title": "Deep learning", "authors": ["LeCun, Yann"], "year": 2015}, {"title": "Deep learning", "authors": ["LeCun, Yann"], "year": 2015}]}, "output": {"keys": ["LeCun2015-dl", "LeCun2015-dl2", "LeCun2015-dl3"]}, "note": "drafts in one batch take keys from each other"}
{"input": {"drafts": [{"title": "Imported", "authors": ["Doe, Jane"], "year": 2020, "key": "Doe2020-im"}, {"title": "Imported again", "authors": ["Doe, Jane"], "year": 2020, "key": "Doe2020-im"}]}, "output": {"keys": ["Doe2020-im", "Doe2020-ia"]}, "note": "an arriving key is kept unless taken, then a new key is made"}
{"input": {"drafts": [{"title": "Kept key", "authors": [], "key": "mykey"}], "taken": ["mykey"]}, "output": {"keys": ["Anon-kk"]}, "note": "a taken arriving key is replaced"}
{"input": {"drafts": [{"title": "Empty key", "authors": ["Smith, J"], "year": 2001, "key": ""}]}, "output": {"keys": ["Smith2001-ee"]}, "note": "an empty key is no key"}
{"input": {"drafts": [{"title": "No authors here at all", "authors": []}]}, "output": {"keys": ["Anon-ah"]}, "note": "no authors and no year: Anon"}
{"input": {"drafts": [{"title": "Title", "authors": ["李, 雷"], "year": 2019}]}, "output": {"keys": ["Anon2019-tt"]}, "note": "a surname with no ASCII letters becomes Anon"}
{"input": {"drafts": [{"title": "On it", "authors": ["Plato"], "year": 1}]}, "output": {"keys": ["Plato1-xx"]}, "note": "no comma: the whole name is the surname; no long words: xx"}
{"input": {"drafts": [{"title": "Theory of games", "authors": ["von Neumann, John", "Morgenstern, Oskar"], "year": 1944}]}, "output": {"keys": ["VonNeumann1944-tg"]}, "note": "only the first author counts; the first letter is upper-cased"}
{"input": {"drafts": [{"title": "A study", "authors": ["O'Neil, Cathy"], "year": 2016}]}, "output": {"keys": ["ONeil2016-ss"]}, "note": "punctuation in surnames is dropped; one long word gives its letter twice"}
{"input": {"drafts": [{"title": "X-ray crystallography of DNA's double-helix", "authors": ["Franklin, Rosalind"], "year": 1953}]}, "output": {"keys": ["Franklin1953-xc"]}, "note": "hyphens and apostrophes are removed before splitting"}
{"input": {"drafts": [{"title": "Nets", "authors": ["Łukasiewicz, Jan"], "year": 1920}]}, "output": {"keys": ["Ukasiewicz1920-nn"]}, "note": "Ł has no decomposition, so it is dropped"}
{"input": {"drafts": [{"title": "Year zero", "authors": ["Zed, A"], "year": 0}]}, "output": {"keys": ["Zed0-yz"]}, "note": "year 0 is still written"}
{"input": {"drafts": [{"title": "Two  spaces  between", "authors": ["Ng, Andrew"], "year": 2000}]}, "output": {"keys": ["Ng2000-sb"]}, "note": "double spaces make empty words, which are skipped"}
{"input": {"drafts": [{"title": "Research", "authors": ["Smith, J"], "year": 2010}, {"title": "Research", "authors": ["Smith, K"], "year": 2010}], "taken": ["Smith2010-rr"]}, "output": {"keys": ["Smith2010-rr2", "Smith2010-rr3"]}, "note": "the second gets 3 after the first takes 2"}