kausalflow/lightkone / components/tidy/versions/1/examples.jsonl · raw

{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "10.1000/X"}, {"id": "b", "title": "Different title", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "https://doi.org/10.1000/x"}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "same DOI, written differently"}
{"input": {"papers": [{"id": "a", "title": "One", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "arxiv": "1207.0580"}, {"id": "b", "title": "Two", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "arxiv": "arXiv:1207.0580v3"}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "same arXiv id with prefix and version"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Improving Neural Networks, by Preventing Co-Adaptation!", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "long titles match after dropping case and punctuation"}
{"input": {"papers": [{"id": "a", "title": "Deep learning", "authors": ["LeCun, Yann"], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Deep Learning", "authors": ["LeCun, Y."], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "c", "title": "Deep learning", "authors": ["Goodfellow, Ian"], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "short titles also need the same first author"}
{"input": {"papers": [{"id": "a", "title": "Nets", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Nets", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "a four-letter title is short: it matches with the same first author, here none on both"}
{"input": {"papers": [{"id": "a", "title": "The", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "The", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": []}, "note": "titles of 3 or fewer letters never match"}
{"input": {"papers": [{"id": "a", "title": "Über formal unentscheidbare Sätze", "authors": ["Gödel, Kurt"], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Uber formal unentscheidbare Satze", "authors": ["Godel, K"], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "accents are decomposed before comparing"}
{"input": {"papers": [{"id": "a", "title": "First", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "10.1/a"}, {"id": "b", "title": "Second", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "10.1/a", "arxiv": "1706.03762"}, {"id": "c", "title": "Third", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "arxiv": "1706.03762v2"}]}, "output": {"groups": [{"ids": ["a", "b", "c"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z", "arxiv": "1706.03762"}}]}, "note": "duplicates of duplicates form one group"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "trashed": "2024-06-01T00:00:00.000Z"}, {"id": "c", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "trashed": ""}]}, "output": {"groups": [{"ids": ["a", "c"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "trashed papers are ignored; an empty trashed is not trashed"}
{"input": {"papers": [{"id": "a", "title": "Alpha", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "  "}, {"id": "b", "title": "Beta", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": " "}]}, "output": {"groups": []}, "note": "DOIs that are only whitespace give no key, so these two do not match"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-02-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "c", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-03-01T00:00:00.000Z", "tags": [], "notes": "mine"}]}, "output": {"groups": [{"ids": ["a", "b", "c"], "keep": "c", "patch": {"tags": [], "folders": [], "notes": "mine", "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "keeper: notes beat age"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "notes": "n"}, {"id": "b", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-05-01T00:00:00.000Z", "tags": [], "pdf": "papers/b.pdf"}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "b", "patch": {"tags": [], "folders": [], "notes": "n", "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "keeper: a PDF beats notes"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-02-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "b", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "keeper: the oldest"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "keeper: library order breaks ties"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": ["ml"], "folders": ["ML"], "notes": " read twice ", "fields": {"pages": "1", "volume": "2"}}, {"id": "b", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": ["dropout", "ml"], "folders": ["Archive"], "notes": "read twice", "starred": true, "venue": "arXiv", "year": 2012, "fields": {"pages": "9", "note": "x"}, "abstract": "We...", "url": "https://arxiv.org/abs/1207.0580", "opened": "2024-05-01T00:00:00.000Z"}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": ["ml", "dropout"], "folders": ["ML", "Archive"], "notes": "read twice", "starred": true, "fields": {"pages": "1", "note": "x", "volume": "2"}, "added": "2024-01-01T00:00:00.000Z", "abstract": "We...", "url": "https://arxiv.org/abs/1207.0580", "venue": "arXiv", "year": 2012, "opened": "2024-05-01T00:00:00.000Z"}}]}, "note": "the keeper gains tags, folders, star, missing fields; equal notes once"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "notes": "first"}, {"id": "b", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "notes": "second", "venue": "V1", "fields": {"k": "b"}}, {"id": "c", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "notes": "third", "venue": "V2", "fields": {"k": "c", "z": "c"}}]}, "output": {"groups": [{"ids": ["a", "b", "c"], "keep": "a", "patch": {"tags": [], "folders": [], "notes": "first\n\nsecond\n\nthird", "fields": {"k": "b", "z": "c"}, "added": "2024-01-01T00:00:00.000Z", "venue": "V1"}}]}, "note": "notes join with a blank line; the first other with a value wins"}
{"input": {"papers": [{"id": "a", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "venue": "", "year": null}, {"id": "b", "title": "Improving neural networks by preventing co-adaptation", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "venue": "Kept venue", "year": 2012}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z", "venue": "Kept venue", "year": 2012}}]}, "note": "an empty value on the keeper is filled"}
{"input": {"papers": [{"id": "a", "title": "Attention is all you need", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "10.1/a"}, {"id": "b", "title": "Something else", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "10.1/b"}, {"id": "c", "title": "Attention Is All You Need", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "10.1/c"}, {"id": "d", "title": "Something Else Entirely here", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "arxiv": "1"}, {"id": "e", "title": "Something else entirely here!", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": [{"ids": ["a", "c"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}, {"ids": ["d", "e"], "keep": "d", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "two groups, in the order of their first paper"}
{"input": {"papers": [{"id": "a", "title": "Unique", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}, {"id": "b", "title": "Other one", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": []}]}, "output": {"groups": []}, "note": "no duplicates"}
{"input": {"papers": []}, "output": {"groups": []}, "note": "an empty library"}
{"input": {"papers": [{"id": "a", "title": "Same", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "doi.org/10.1/a"}, {"id": "b", "title": "Different", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "10.1/a"}]}, "output": {"groups": []}, "note": "a doi.org/ prefix without http is not removed"}
{"input": {"papers": [{"id": "a", "title": "Alpha paper", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "https://doi.org/", "arxiv": " "}, {"id": "b", "title": "Beta paper", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "http://dx.doi.org/", "arxiv": "\t"}, {"id": "c", "title": "Gamma paper", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "arxiv": "arXiv:"}, {"id": "d", "title": "Delta paper", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "arxiv": "arxiv:"}]}, "output": {"groups": []}, "note": "a doi that is only the doi.org prefix, or an arXiv id that is only spaces or the arXiv: prefix, gives no key"}
{"input": {"papers": [{"id": "a", "title": "Alpha paper", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": " 10.1000/X "}, {"id": "b", "title": "Beta paper", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": "https://doi.org/10.1000/x"}, {"id": "c", "title": "Gamma paper", "authors": [], "added": "2024-01-01T00:00:00.000Z", "tags": [], "doi": " "}]}, "output": {"groups": [{"ids": ["a", "b"], "keep": "a", "patch": {"tags": [], "folders": [], "fields": {}, "added": "2024-01-01T00:00:00.000Z"}}]}, "note": "a real DOI still matches after trimming and removing the prefix; the blank one stays out"}