{ "_id": "6ad21e3852d5a3be2dfeea5f", "Package": "alethiaR", "Title": "Match and Deduplicate Messy Entity Names Against a Reference\nList", "Version": "0.1.0", "Authors@R": "person(\"Saket\", \"Choudhary\",\nemail = \"saketc@iitb.ac.in\",\nrole = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0001-5202-7633\"))", "Description": "Aligns messy entity strings against a reference list using\neither string similarity or language-model embeddings.", "License": "MIT + file LICENSE", "Encoding": "UTF-8", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "RoxygenNote": "8.0.0", "URL": "https://alethia.saketlab.org/cli/R,\nhttps://github.com/saketlab/alethia", "BugReports": "https://github.com/saketlab/alethia/issues", "Repository": "https://saketlab.r-universe.dev", "Date/Publication": "2026-10-03 23:00:57 UTC", "RemoteUrl": "https://github.com/saketlab/alethia", "RemoteRef": "main", "RemoteSha": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "RemoteSubdir": "R", "NeedsCompilation": "no", "Packaged": { "Date": "2026-10-16 12:43:07 UTC", "User": "root" }, "Author": "Saket Choudhary [aut, cre] (ORCID:\n)", "Maintainer": "Saket Choudhary ", "_user": "saketlab", "_type": "src", "_file": "alethiaR_0.1.0.tar.gz", "_fileid": "https://r2.ropensci.org/1fdd228d3ba9624b35253c6146b49eab5826c11bf4ba04864837f4eca868110e", "_filesize": 212498, "_sha256": "1fdd228d3ba9624b35253c6146b49eab5826c11bf4ba04864837f4eca868110e", "_expires": "2027-01-24T12:53:10.000Z", "_created": "2026-10-16T12:43:07.000Z", "_published": "2026-10-16T12:53:12.638Z", "_buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 116978026058, "time": 137, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "12045874253" }, { "job": 116978025853, "time": 107, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12046817208" }, { "job": 116978025832, "time": 90, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "12046144075" }, { "job": 116978025741, "time": 94, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "12046957698" }, { "job": 116976915601, "time": 165, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "12046517656" }, { "job": 116978025682, "time": 91, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "12047102048" }, { "job": 116978026822, "time": 86, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "12046378177" }, { "job": 116978025783, "time": 90, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "12047052375" }, { "job": 116978025894, "time": 85, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12046133532" } ], "_upstream": "https://github.com/saketlab/alethia", "_commit": { "id": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "author": "Saket Choudhary ", "committer": "Saket Choudhary ", "message": "Add logo\n", "time": 1791068457 }, "_maintainer": { "name": "Saket Choudhary", "email": "saketc@iitb.ac.in", "login": "saketkc", "orcid": "0000-0001-5202-7633", "twitter": "@saketkc", "description": "", "uuid": 682153 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "stats", "role": "Imports" }, { "package": "stringdist", "version": ">= 0.9.10", "role": "Imports" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "jsonlite", "role": "Suggests" }, { "package": "igraph", "role": "Suggests" }, { "package": "onnxr", "role": "Suggests" }, { "package": "tok", "role": "Suggests" }, { "package": "hfhub", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "saketlab", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-35", "n": 12 }, { "week": "2026-36", "n": 1 }, { "week": "2026-40", "n": 4 } ], "_tags": [], "_topics": [ "entity-matching", "fuzzy-matching", "llms", "messy-data" ], "_stars": 3, "_contributors": [ { "user": "saketkc", "count": 51, "uuid": 682153 } ], "_userbio": { "uuid": 204561227, "type": "organization", "name": "Saket Lab", "followers": 19 }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/alethiaR" }, "_devurl": "https://github.com/saketlab/alethia", "_pkgdown": "https://alethia.saketlab.org/cli/R", "_searchresults": 3, "_rbuild": "4.6.1", "_assets": [ "extra/alethiaR.html", "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/readme.html", "extra/readme.md", "LICENSE" ], "_cranurl": false, "_exports": [ "alethia", "alethia_split", "alignment_loss", "apply_threshold", "as_embedder", "assess_models", "centered_separability", "cluster_entities", "cluster_records", "DEFAULT_METRIC_WEIGHTS", "DEFAULT_THRESHOLD", "encode", "get_embedding_backend", "hubness", "intrinsic_dimensionality", "l2_normalize", "match_by_embeddings", "match_by_strings", "mutual_nn_edges", "mutual_nn_rate", "n_clusters", "onnx_available", "onnx_embedder", "positive_pair_rank", "RANK_DECIMALS", "reference_separability", "retrieval_margin", "set_embedding_backend", "token_sort", "token_sort_ratio", "true_accuracy", "uniformity_loss", "use_onnx_backend" ], "_help": [ { "page": "alethia", "title": "Align messy entity strings against a reference list", "topics": [ "alethia" ] }, { "page": "alethia_split", "title": "Match composite entries by splitting them on a separator first", "topics": [ "alethia_split" ] }, { "page": "alignment_loss", "title": "Alignment loss", "concept": [ "assess metrics" ], "topics": [ "alignment_loss" ] }, { "page": "apply_threshold", "title": "Blank out matches scoring below a threshold", "topics": [ "apply_threshold" ] }, { "page": "as_embedder", "title": "Coerce a model specification into an embedder", "topics": [ "as_embedder" ] }, { "page": "assess_models", "title": "Score candidate embedding models on your own data, without labels", "topics": [ "assess_models", "DEFAULT_METRIC_WEIGHTS" ] }, { "page": "assess-metrics", "title": "Label-free geometric metrics for an embedding set", "topics": [ "assess-metrics" ] }, { "page": "centered_separability", "title": "Anisotropy-corrected separability", "concept": [ "assess metrics" ], "topics": [ "centered_separability" ] }, { "page": "cluster_entities", "title": "Group entity strings into clusters of duplicates", "topics": [ "cluster_entities" ] }, { "page": "cluster_records", "title": "Cluster membership as a tidy data frame", "topics": [ "cluster_records" ] }, { "page": "DEFAULT_THRESHOLD", "title": "Default minimum cosine similarity for embedding backends", "topics": [ "DEFAULT_THRESHOLD" ] }, { "page": "encode", "title": "Encode text with an embedder", "topics": [ "encode" ] }, { "page": "hubness", "title": "Hubness", "concept": [ "assess metrics" ], "topics": [ "hubness" ] }, { "page": "intrinsic_dimensionality", "title": "Intrinsic dimensionality", "concept": [ "assess metrics" ], "topics": [ "intrinsic_dimensionality" ] }, { "page": "l2_normalize", "title": "Row-wise L2 normalisation", "topics": [ "l2_normalize" ] }, { "page": "match_by_embeddings", "title": "Match queries to references by embedding cosine similarity", "topics": [ "match_by_embeddings" ] }, { "page": "match_by_strings", "title": "Match strings against a reference list by token-sort similarity", "topics": [ "match_by_strings" ] }, { "page": "mutual_nn_edges", "title": "Candidate merge edges from mutual nearest neighbours", "topics": [ "mutual_nn_edges" ] }, { "page": "mutual_nn_rate", "title": "Mutual nearest-neighbour rate", "concept": [ "assess metrics" ], "topics": [ "mutual_nn_rate" ] }, { "page": "n_clusters", "title": "Number of clusters found", "topics": [ "n_clusters" ] }, { "page": "onnx_available", "title": "Is the local ONNX stack ready to use?", "topics": [ "onnx_available" ] }, { "page": "onnx_embedder", "title": "Build an embedder backed by a local ONNX model", "topics": [ "onnx_embedder" ] }, { "page": "positive_pair_rank", "title": "Positive-pair rank", "concept": [ "assess metrics" ], "topics": [ "positive_pair_rank" ] }, { "page": "RANK_DECIMALS", "title": "Decimal places similarities are rounded to before any ranking decision", "topics": [ "RANK_DECIMALS" ] }, { "page": "reference_separability", "title": "Reference-set separability", "concept": [ "assess metrics" ], "topics": [ "reference_separability" ] }, { "page": "retrieval_margin", "title": "Retrieval margin", "concept": [ "assess metrics" ], "topics": [ "retrieval_margin" ] }, { "page": "set_embedding_backend", "title": "Register a backend that turns model names into embedding functions", "topics": [ "get_embedding_backend", "set_embedding_backend" ] }, { "page": "token_sort", "title": "Normalise a string by sorting its whitespace-separated tokens", "topics": [ "token_sort" ] }, { "page": "token_sort_ratio", "title": "Token-sort similarity ratio", "topics": [ "token_sort_ratio" ] }, { "page": "true_accuracy", "title": "Top-1 accuracy and MRR of an embedder against ground truth", "topics": [ "true_accuracy" ] }, { "page": "uniformity_loss", "title": "Uniformity loss", "concept": [ "assess metrics" ], "topics": [ "uniformity_loss" ] }, { "page": "use_onnx_backend", "title": "Resolve bare model names through the local ONNX runtime", "topics": [ "use_onnx_backend" ] } ], "_readme": "https://github.com/saketlab/alethia/raw/main/R/README.md", "_rundeps": [ "stringdist" ], "_vignettes": [ { "source": "quickstart.Rmd", "filename": "quickstart.html", "title": "Quickstart", "engine": "knitr::rmarkdown", "headings": [ "Install", "Match against a reference list", "Match on meaning", "Choose a model without labels", "Cluster without a reference list" ], "created": "2026-08-26 21:50:47", "modified": "2026-08-26 22:16:38", "commits": 2 } ], "_score": 3.653212513775344, "_indexed": true, "_nocasepkg": "alethiar", "_universes": [ "saketlab", "saketkc" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.0", "date": "2026-10-16T12:45:31.000Z", "distro": "resolute", "commit": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "fileid": "https://r2.ropensci.org/b4d1c41c31c429a937374a1b441215bd4e9c53016dd7fa243a3a0e54789de357", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435" }, { "r": "4.6.1", "os": "linux", "version": "0.1.0", "date": "2026-10-16T12:45:08.000Z", "distro": "resolute", "commit": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "fileid": "https://r2.ropensci.org/74a15052a371c680f039cbcf73386006ce8faf361a1746f0e7118e339c4916ae", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435" }, { "r": "4.5.3", "os": "mac", "version": "0.1.0", "date": "2026-10-16T12:52:46.000Z", "commit": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "fileid": "https://r2.ropensci.org/fa3be2c90674c0f3b78da05cec19631b39ae6fc05afdf84564a6d37988af9c01", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435" }, { "r": "4.6.1", "os": "mac", "version": "0.1.0", "date": "2026-10-16T12:47:26.000Z", "commit": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "fileid": "https://r2.ropensci.org/a96a0ec4b09998fa7e9fff84924729c69b050a5970c8ce06d7eaed2f23c00527", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.0", "date": "2026-10-16T12:45:07.000Z", "commit": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "fileid": "https://r2.ropensci.org/370251ad6ccad0a7e840823d066f50d1be5b47c3e2a8e6069ef3c63e88f8adcd", "status": "success", "buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435" }, { "r": "4.7.0", "os": "win", "version": "0.1.0", "date": "2026-10-16T12:44:28.000Z", "commit": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "fileid": "https://r2.ropensci.org/749a33a50979b5988a06297c398fb214de398beff32e9b9f16bc9f09f18aca16", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435" }, { "r": "4.5.3", "os": "win", "version": "0.1.0", "date": "2026-10-16T12:44:34.000Z", "commit": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "fileid": "https://r2.ropensci.org/898416784904e124a9e88ad937e663633b10ff5d98c7b6252e3800cece5aa61c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435" }, { "r": "4.6.1", "os": "win", "version": "0.1.0", "date": "2026-10-16T12:44:26.000Z", "commit": "7d3f46a4b4918a2fc8d1d1284a7ee60c20e9acd1", "fileid": "https://r2.ropensci.org/5c9a3584d36f0848dc5db0a317b97220c0967e7d5e73fd3082cd6a7cbc2c2906", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/saketlab/actions/runs/38902164435" } ] }