kausalflow/lightkone / components/search-query/versions/1/examples.jsonl · raw

{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": ""}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "empty query: every paper outside the trash, newest added first; equal times keep input order"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "   "}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "whitespace only is the empty query"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "attention"}, "output": {"ids": ["vaswani17", "nodate"]}, "note": "words rank by relevance under the default sort: title 5, author 4, rest 1"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "attention"}, "output": {"ids": ["vaswani17", "nodate"]}, "note": "sort=added with words means relevance"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "year", "query": "attention"}, "output": {"ids": ["vaswani17", "nodate"]}, "note": "an explicit sort keeps its order; missing year sorts as 0"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "networks"}, "output": {"ids": ["hinton12", "vaswani17", "cafe"]}, "note": "title hits outrank hits in abstract or notes"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "neural networks"}, "output": {"ids": ["hinton12", "vaswani17"]}, "note": "every word must match; scores add up"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "\"neural networks\""}, "output": {"ids": ["hinton12", "vaswani17"]}, "note": "a quoted phrase is one word"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "\"networks by\""}, "output": {"ids": ["hinton12"]}, "note": "a phrase matches across words within a field"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "\"hinton, geoffrey ; srivastava\""}, "output": {"ids": ["hinton12"]}, "note": "authors are joined with ' ; '"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "\"dropout hinton2012\""}, "output": {"ids": ["hinton12"]}, "note": "the rest text joins non-empty fields with single spaces: tags, then key"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "cafe"}, "output": {"ids": ["cafe"]}, "note": "accents fold away"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "CAFÉ"}, "output": {"ids": ["cafe"]}, "note": "case and accents fold away in the query too"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "naive"}, "output": {"ids": ["cafe"]}, "note": "naïveté in the title and naive in notes"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "godel"}, "output": {"ids": ["godel31"]}, "note": "author text is folded: Gödel"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "uber"}, "output": {"ids": ["godel31"]}, "note": "Über in a title"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "hinton"}, "output": {"ids": ["hinton12"]}, "note": "author hit"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "hinton2012"}, "output": {"ids": ["hinton12"]}, "note": "the citation key is in the rest text"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "10.1103"}, "output": {"ids": ["wilson74"]}, "note": "doi is in the rest text"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "1706.03762"}, "output": {"ids": ["vaswani17"]}, "note": "arxiv id is in the rest text"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "re:search"}, "output": {"ids": ["godel31"]}, "note": "an unknown field is an ordinary word, colon included"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "foo:bar"}, "output": {"ids": []}, "note": "unknown field that matches nothing"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "\"attention"}, "output": {"ids": []}, "note": "an unmatched quote is part of the word"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "zzz"}, "output": {"ids": []}, "note": "no match"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:ml"}, "output": {"ids": ["vaswani17", "hinton12"]}, "note": "tag filter; the trashed paper with the tag is hidden"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:ML"}, "output": {"ids": ["vaswani17", "hinton12"]}, "note": "tag values fold"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "TAG:ml"}, "output": {"ids": ["vaswani17", "hinton12"]}, "note": "field names are case-insensitive"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:\"to read\""}, "output": {"ids": ["vaswani17"]}, "note": "quoted tag with a space, folded"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:to"}, "output": {"ids": []}, "note": "a tag must match whole, not as a substring"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:cafe"}, "output": {"ids": ["cafe"]}, "note": "tag value with accent folding"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:ml tag:cnn"}, "output": {"ids": []}, "note": "all tags must match"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:\"\""}, "output": {"ids": []}, "note": "an empty tag value matches no paper here"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "author:hinton"}, "output": {"ids": ["hinton12"]}, "note": "author substring"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "author:\"n, g\""}, "output": {"ids": ["hinton12"]}, "note": "author value is a substring of the joined, folded author text"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "author:zoe"}, "output": {"ids": ["cafe"]}, "note": "folded author"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "author:noam author:niki"}, "output": {"ids": ["vaswani17"]}, "note": "every author filter must match"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:2017"}, "output": {"ids": ["vaswani17"]}, "note": "exact year"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:1900-1975"}, "output": {"ids": ["wilson74", "godel31", "noether18"]}, "note": "inclusive range"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:2020-2010"}, "output": {"ids": []}, "note": "a reversed range matches nothing"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:1974 year:2017"}, "output": {"ids": ["vaswani17"]}, "note": "only the last year filter counts"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:2017 year:1900-2020"}, "output": {"ids": ["vaswani17", "hinton12", "wilson74", "godel31", "noether18", "emptytrash"]}, "note": "only the last year filter counts, whichever form it has"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:1900-1950 year:1974"}, "output": {"ids": ["wilson74"]}, "note": "a later exact year replaces an earlier range"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "in:Physics"}, "output": {"ids": ["wilson74", "noether18"]}, "note": "a folder includes its subfolders"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "in:physics/qft/"}, "output": {"ids": ["wilson74"]}, "note": "folder names fold and trailing slashes are ignored"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "in:Phys"}, "output": {"ids": []}, "note": "a folder is not matched by prefix of its name"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "in:\"cafe/ebauches\""}, "output": {"ids": ["cafe"]}, "note": "folders fold accents"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "in:ML in:ML/Regularization"}, "output": {"ids": ["hinton12"]}, "note": "all folder filters must hold"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "has:pdf"}, "output": {"ids": ["vaswani17", "godel31", "noether18"]}, "note": "a PDF in storage or a file from another manager"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "no:pdf"}, "output": {"ids": ["nodate", "hinton12", "wilson74", "noether18", "cafe", "emptytrash"]}, "note": "no:pdf ignores the other manager's file"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "has:abstract"}, "output": {"ids": ["vaswani17", "noether18"]}, "note": "an empty abstract is absent"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "no:abstract"}, "output": {"ids": ["nodate", "hinton12", "wilson74", "godel31", "cafe", "emptytrash"]}, "note": "opposite of has:abstract"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "has:arxiv no:pdf"}, "output": {"ids": ["hinton12"]}, "note": "filters combine"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "has:notes"}, "output": {"ids": ["godel31", "cafe"]}, "note": "notes present"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "no:notes"}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "noether18", "emptytrash"]}, "note": "empty notes count as absent"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "has:PDF"}, "output": {"ids": ["vaswani17", "godel31", "noether18"]}, "note": "has: values are lower-cased"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "has:wings"}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "unknown has: value is ignored"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "is:starred"}, "output": {"ids": ["hinton12"]}, "note": "starred papers outside the trash"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "is:recent"}, "output": {"ids": ["hinton12", "vaswani17", "wilson74"]}, "note": "opened papers, latest opened first, then newest added"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "is:recent attention"}, "output": {"ids": ["vaswani17"]}, "note": "is:recent orders by opened even with words"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "year", "query": "is:recent"}, "output": {"ids": ["vaswani17", "hinton12", "wilson74"]}, "note": "an explicit sort overrides"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "is:trash"}, "output": {"ids": ["lecun98", "binned"]}, "note": "only trashed papers; an empty trashed field is not trashed"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "is:trash attention"}, "output": {"ids": ["binned"]}, "note": "words within the trash"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "is:trash is:starred"}, "output": {"ids": ["binned"]}, "note": "is: filters combine"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "is:sleepy"}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "unknown is: value is ignored"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "year", "query": ""}, "output": {"ids": ["cafe", "emptytrash", "vaswani17", "hinton12", "wilson74", "godel31", "noether18", "nodate"]}, "note": "year sort, missing years last"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "opened", "query": ""}, "output": {"ids": ["hinton12", "vaswani17", "wilson74", "nodate", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "opened sort; never-opened papers last by newest added"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "relevance", "query": ""}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "relevance with no words: newest added first"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "physics classics"}, "output": {"ids": ["noether18"]}, "note": "words can match tags"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "relevance", "query": "ml attention"}, "output": {"ids": ["vaswani17"]}, "note": "words can match in different fields"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "physics"}, "output": {"ids": ["wilson74", "noether18"]}, "note": "equal scores fall back to newest added, not input order"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:physics confinement"}, "output": {"ids": ["wilson74"]}, "note": "filter plus word"}
{"input": {"papers": {"$fixture": "titles.json"}, "sort": "title", "query": ""}, "output": {"ids": ["t25", "t26", "t11", "t13", "t12", "t9", "t10", "t24", "t23", "t2", "t1", "t4", "t3", "t5", "t8", "t6", "t7", "t0", "t19", "t18", "t21", "t15", "t14", "t17", "t16", "t20", "t22"]}, "note": "title sort follows Unicode collation: letters, then accents, then case, lower case first; punctuation before digits before letters"}
{"input": {"papers": {"$fixture": "titles.json"}, "sort": "title", "query": "apple"}, "output": {"ids": ["t2", "t1", "t4", "t3", "t5", "t8", "t6", "t7"]}, "note": "title sort with a word filter"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:2017 year:abc"}, "output": {"ids": ["vaswani17"]}, "note": "a year: term that is not a number does not count; the earlier one stays"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:abc"}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "a year: term that is not a number filters nothing"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:2017-"}, "output": {"ids": ["vaswani17"]}, "note": "year:2017- means 2017"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:-2017"}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "year:-2017 does not count"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:0"}, "output": {"ids": ["vaswani17", "nodate", "hinton12", "wilson74", "godel31", "noether18", "cafe", "emptytrash"]}, "note": "year:0 does not count"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:1990-2020-1900"}, "output": {"ids": ["vaswani17", "hinton12", "emptytrash"]}, "note": "parts after the second are ignored"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:2020-1990"}, "output": {"ids": []}, "note": "a reversed range matches nothing"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "year:1990-x"}, "output": {"ids": []}, "note": "a second part that is not a number means the first year only"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "author:"}, "output": {"ids": []}, "note": "a filter with nothing after the colon is an ordinary word, which matches nothing here"}
{"input": {"papers": {"$fixture": "library.json"}, "sort": "added", "query": "tag:"}, "output": {"ids": []}, "note": "the same for any field: tag: is the word tag:"}
{"input": {"papers": [{"id": "a", "title": "bar baz", "added": "2024-01-01T00:00:00.000Z"}, {"id": "b", "title": "o:\"bar baz\"", "added": "2024-01-02T00:00:00.000Z"}], "sort": "added", "query": "o:\"bar baz\""}, "output": {"ids": ["b"]}, "note": "an unknown field with a quoted value is one word, quotes included"}