{ "title": "A research analysis plan you can inspect", "context": "ScientiaHub Original Study — self-initiated demonstration.", "status": "This is an original, prospective methods demonstration. No dataset has been downloaded for analysis, synthesised or analysed. The before and after passages are original illustrations, not client manuscripts. Documentation facts are attributed to their sources. No empirical findings, publication outcomes or staff credentials are claimed.", "sourceFacts": [ { "id": "C01", "claim": "The simplified penguins table is documented as 344 rows and eight variables.", "sourceId": "S02", "locator": "Format opening statement.", "locations": [ "DEC-01" ], "type": "source-fact" }, { "id": "C02", "claim": "The maintainers distinguish the simplified penguins table from penguins_raw.", "sourceId": "S03", "locator": "About the data and the displayed examples of the two datasets.", "locations": [ "DEC-01", "slide-02" ], "type": "source-fact" }, { "id": "C03", "claim": "The package site displays 0.1.1 while its Citation example names 0.1.0.", "sourceId": "S03", "locator": "Site version header and Citation example.", "locations": [ "DEC-01", "S03" ], "type": "source-fact" }, { "id": "C04", "claim": "The simplified variable dictionary contains no individual identifier.", "sourceId": "S02", "locator": "Complete eight-variable Format list.", "locations": [ "DEC-02", "ED-02", "slide-02" ], "type": "source-fact" }, { "id": "C05", "claim": "The original field methods describe sampling adult pairs at nests and different island sampling arrangements across species.", "sourceId": "S01", "locator": "Materials and Methods, Field methods: nest selection and capture of both adults at the selected nests.", "locations": [ "DEC-02", "slide-02" ], "type": "source-fact" }, { "id": "C06", "claim": "body_mass_g is documented as integer body mass in grams.", "sourceId": "S02", "locator": "Format, body_mass_g.", "locations": [ "DEC-03", "dictionary" ], "type": "source-fact" }, { "id": "C07", "claim": "The original study reports scale tolerances of ±25 g or ±50 g depending on the instrument.", "sourceId": "S01", "locator": "Materials and Methods, Field methods: 5 kg and 10 kg Pesola scales.", "locations": [ "DEC-03" ], "type": "source-fact" }, { "id": "C08", "claim": "The dictionary lists the species, island, measurement-unit and recorded-sex definitions reproduced in the working dictionary.", "sourceId": "S02", "locator": "Format: species, island, bill_length_mm, bill_depth_mm, flipper_length_mm and sex.", "locations": [ "dictionary" ], "type": "source-fact" }, { "id": "C09", "claim": "The documented integer study-year codes are 2007, 2008 and 2009.", "sourceId": "S02", "locator": "Format, year.", "locations": [ "DEC-07", "dictionary", "slide-04" ], "type": "source-fact" }, { "id": "C10", "claim": "The original article describes austral summer field seasons of 2007/08, 2008/09 and 2009/10.", "sourceId": "S01", "locator": "Materials and Methods, Field methods, opening paragraph.", "locations": [ "DEC-07" ], "type": "source-fact" }, { "id": "C11", "claim": "Broman and Woo recommend maintaining a data dictionary and separating source data from calculations.", "sourceId": "S04", "locator": "Create a data dictionary; No calculations in the raw data files.", "locations": [ "DEC-08", "slide-06" ], "type": "source-fact" }, { "id": "C12", "claim": "The package maintainers describe the data as CC0 and provide additional data-use guidance.", "sourceId": "S03", "locator": "License and Additional data use information.", "locations": [ "S03" ], "type": "source-fact" } ], "sources": [ { "id": "S01", "title": "Gorman, Williams and Fraser: Ecological Sexual Dimorphism and Environmental Variability within a Community of Antarctic Penguins", "url": "https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0090081", "publicationOrVersion": "PLOS ONE, 2014, 9(3), e90081. DOI: 10.1371/journal.pone.0090081.", "accessedAt": "2026-09-11", "locator": "Materials and Methods: Field methods, Statistical methods and Data management.", "rights": "Original article cited through concise attributed paraphrase. No article figure or substantial passage is reproduced. Citation does not imply endorsement." }, { "id": "S02", "title": "Palmer Penguins: Size measurements for adult foraging penguins near Palmer Station", "url": "https://allisonhorst.github.io/palmerpenguins/reference/penguins.html", "publicationOrVersion": "Maintainers' penguins reference page. Site header displays package version 0.1.1; this does not identify a downloaded analysis file.", "accessedAt": "2026-09-11", "locator": "Description, Format and Source, including all eight variable definitions.", "rights": "Variable definitions and format facts attributed to the maintainers. No dataset is redistributed or analysed in this demonstration." }, { "id": "S03", "title": "Horst, Hill and Gorman: palmerpenguins R data package", "url": "https://allisonhorst.github.io/palmerpenguins/", "publicationOrVersion": "Project page displays 0.1.1. Its Citation example names package version 0.1.0; these statements are retained separately.", "accessedAt": "2026-09-11", "locator": "About the data, License, Citation and Additional data use information.", "rights": "Maintainers describe the data as CC0 and also provide scholarly-use guidance. This folio cites documentation without redistributing data or reusing the penguin artwork. No author affiliation or endorsement is implied." }, { "id": "S04", "title": "Broman and Woo: Data organization in spreadsheets", "url": "https://kbroman.org/Paper_DataOrg/manuscript.html", "publicationOrVersion": "Author-hosted manuscript as accessed. The web copy is cited without asserting a separately pinned document release.", "accessedAt": "2026-09-11", "locator": "Be consistent; Create a data dictionary; No calculations in the raw data files.", "rights": "Concise attributed discussion of organisational recommendations. No table, figure or substantial manuscript passage is reproduced." } ], "originalMethodologicalDecisions": [ { "id": "DEC-01", "title": "Dataset identity", "choice": "Freeze an identified analysis file before execution.", "rationale": "A documentation page and a dataset release identify different objects. The file checksum and citation must refer to the actual input.", "sourceIds": [ "S02", "S03" ], "editorialAnnotation": "ED-01", "slide": "slide-02" }, { "id": "DEC-02", "title": "Record identity", "choice": "Use imported rows as working records without assuming individual independence.", "rationale": "The simplified dictionary lacks an individual identifier. Equal measurements alone do not establish duplicate records.", "sourceIds": [ "S01", "S02" ], "editorialAnnotation": "ED-02", "slide": "slide-02" }, { "id": "DEC-03", "title": "Mass and precision", "choice": "Retain grams, resolve invalid values and round only for display.", "rationale": "Stored units, field measurement tolerance and the chosen display precision have distinct meanings.", "sourceIds": [ "S01", "S02" ], "editorialAnnotation": "ED-03", "slide": "slide-04" }, { "id": "DEC-04", "title": "Variable-specific eligibility", "choice": "Retain missing body mass in N and do not delete a primary record because another measurement or secondary grouping value is missing.", "rationale": "Eligibility follows the stated question. Missing grouping values remain visible in their applicable audit groups.", "sourceIds": [ "S02" ], "editorialAnnotation": "ED-04", "slide": "slide-05" }, { "id": "DEC-05", "title": "Denominators", "choice": "Report eligible N, observed n and missing N−n with explicit empty-case labels.", "rationale": "Readers need to distinguish the archive covered by a group from the measurements contributing to its mean.", "sourceIds": [], "editorialAnnotation": "ED-05", "slide": "slide-03" }, { "id": "DEC-06", "title": "Stratification and pooling", "choice": "Use separate sex and year tables within species and pool through raw valid records or observed-count weights.", "rationale": "Unweighted subgroup means can change the contribution of individual records. Reconciled totals reveal unintended filters.", "sourceIds": [], "editorialAnnotation": "ED-06", "slide": "slide-04" }, { "id": "DEC-07", "title": "Year and season", "choice": "Retain recorded year codes until a season mapping is verified.", "rationale": "The dictionary's codes and the article's field-season descriptions must not be treated as an audited row-level mapping.", "sourceIds": [ "S01", "S02" ], "editorialAnnotation": "ED-07", "slide": "slide-04" }, { "id": "DEC-08", "title": "Interpretation limits", "choice": "Keep interpretation descriptive and reserve execution for a separately reviewed stage.", "rationale": "A finished protocol does not establish computed findings, population effects or successful replication.", "sourceIds": [ "S01", "S04" ], "editorialAnnotation": "ED-08", "slide": "slide-06" } ], "originalIllustrativePassages": { "before": [ { "id": "B1", "sentences": [ "We will use the Palmer Penguins data from the current package website, citing the paper and the package as the source of the analysis file.", "Every row will represent an independent penguin, and rows with identical measurements will be removed as duplicate observations.", "The analysis will compare body mass among species and describe differences across the other recorded characteristics.", "A single cleaned table will provide the basis for the report and presentation so that readers receive a consistent account." ] }, { "id": "B2", "sentences": [ "Body mass is recorded in grams, so displaying the mean to the nearest gram will preserve the accuracy of the measurements.", "Records with any missing value will be excluded before analysis, giving all comparisons the same complete sample.", "The remaining measurements will be treated as suitable for calculation without a separate record of unusual entries.", "This approach will keep the methods brief and avoid presenting different eligibility rules for related tables." ] }, { "id": "B3", "sentences": [ "We will calculate the percentage of missing masses by dividing the number of missing entries by the number of observed masses.", "Overall species means will be obtained by averaging the means for the recorded sex groups.", "The tables will show these means alongside a sample size, with empty numerical cells entered as zero for consistency.", "Comparisons will use the displayed rounded values, and the same values will appear in the conference slides." ] }, { "id": "B4", "sentences": [ "The year values will be relabelled as the corresponding breeding seasons, and changes between these periods will describe temporal patterns.", "Differences in the summary means will establish which species are heavier in the population and whether those differences vary over time.", "The final discussion will connect the observed patterns to the ecological account in the original paper.", "A short methods slide will summarise the cleaning procedure before the audience sees the comparisons." ] } ], "after": [ { "id": "A1", "sentences": [ "Before execution, we will resolve query Q01 by identifying the analysis release and file checksum, while keeping the original article and package documentation as separate references.", "Imported rows will be working records without assuming that they represent unique individuals or statistically independent observations, and equal measurements will not trigger automatic deletion.", "The proposed analysis will describe archived body-mass records by species, with separate secondary groupings by recorded sex and year.", "No analysis has yet been executed." ] }, { "id": "A2", "sentences": [ "Mass will remain in grams, with full calculation precision and means rounded half-up to the nearest gram for display, without implying one-gram measurement accuracy.", "The primary species summary will retain records with missing body mass in its eligible count and will not exclude records because unrelated fields are missing.", "Missing species will enter an unassigned audit count, while missing sex or year will enter its applicable 'not recorded' group.", "Unexpected nonmissing codes and invalid masses will require resolution before dependent summaries proceed." ] }, { "id": "A3", "sentences": [ "For each group, N will count eligible records, n will count observed valid masses, and missing percentage will equal 100 × (N−n) / N when N exceeds zero.", "Species means will use valid raw records or equivalent observed-count weighting across disjoint strata, retaining full precision until display.", "For N=0, missing percentage will be 'not applicable', and for n=0, mean mass will be 'not estimable'.", "When N is positive and n is zero, missingness will be 100%, and secondary counts will reconcile to their primary species totals." ] }, { "id": "A4", "sentences": [ "Stored year codes will remain categorical labels unless source evidence resolves the breeding-season mapping in query Q03.", "Interpretation will remain descriptive of the selected archive, without significance tests, confidence intervals, population effects or claims of temporal change.", "Counts will remain integers, and missing percentages will use one decimal place with half-up rounding only at display.", "The report and talk will retain the protocol's prospective status, unresolved identity query Q02 and explicit distinction between source facts and proposed calculations." ] } ] }, "editorialAnnotations": [ { "id": "ED-01", "before": "B1.1", "after": "A1.1", "change": "Replace a changing website reference with an identified input and separate bibliographic records.", "rationale": "A reader needs to distinguish the analysed bytes from documentation and from the original article. The edit leaves file identity prospective rather than implying completed verification.", "decisionId": "DEC-01", "sourceIds": [ "S02", "S03" ], "disposition": "Protocol wording adopted. Q01 remains open before analysis." }, { "id": "ED-02", "before": "B1.2", "after": "A1.2", "change": "Remove the unsupported independence claim and automatic measurement-based deduplication.", "rationale": "The simplified table does not supply an individual identifier. A tracking row number cannot establish biological identity, and equal measurements can be legitimate separate records.", "decisionId": "DEC-02", "sourceIds": [ "S01", "S02" ], "disposition": "Protocol wording adopted. Q02 remains open for any later individual-level analysis." }, { "id": "ED-03", "before": "B2.1", "after": "A2.1", "change": "Separate measurement units from display precision and state the rounding rule.", "rationale": "Reporting an integer mean does not preserve or improve instrument accuracy. Calculations retain full precision, with a consistent project-specific display convention.", "decisionId": "DEC-03", "sourceIds": [ "S01", "S02" ], "disposition": "Adopted as a reporting decision. No instrument-level accuracy claim retained." }, { "id": "ED-04", "before": "B2.2", "after": "A2.2", "change": "Replace blanket complete-case deletion with eligibility for the stated outcome.", "rationale": "A missing sex value need not discard an observed mass from a species summary. The following sentence in the edited passage separately accounts for missing species and missing secondary grouping values.", "decisionId": "DEC-04", "sourceIds": [ "S02" ], "disposition": "Adopted for this descriptive protocol. No claim that missingness is random or unbiased." }, { "id": "ED-05", "before": "B3.1", "after": "A3.1", "change": "Use eligible records as the missingness denominator and distinguish N from n.", "rationale": "Dividing missing entries by observed entries answers a different question and can misrepresent the missing share. The accompanying sentences state the zero-denominator cases explicitly.", "decisionId": "DEC-05", "sourceIds": [], "disposition": "Adopted as the calculation specification. No numerical result computed." }, { "id": "ED-06", "before": "B3.2", "after": "A3.2", "change": "Replace an unweighted mean of subgroup means with equivalent record-weighted aggregation.", "rationale": "Each observed mass must contribute once to its species mean. Full-precision aggregation and count reconciliation prevent display rounding or omitted audit groups from altering the calculation.", "decisionId": "DEC-06", "sourceIds": [], "disposition": "Adopted as an original aggregation rule, not attributed as a published finding." }, { "id": "ED-07", "before": "B4.1", "after": "A4.1", "change": "Retain source year codes and make season relabelling conditional on evidence.", "rationale": "The dictionary and article describe time at different levels. Similar labels do not establish a verified mapping for each record, nor a population trend.", "decisionId": "DEC-07", "sourceIds": [ "S01", "S02" ], "disposition": "Conditional wording adopted. Q03 remains open." }, { "id": "ED-08", "before": "B4.2", "after": "A4.2", "change": "Replace population and temporal conclusions with the commissioned descriptive scope.", "rationale": "The proposed tables concern an archived sample. Neither the planned calculations nor this unexecuted demonstration establish inferential or ecological conclusions.", "decisionId": "DEC-08", "sourceIds": [ "S01" ], "disposition": "Adopted. Any inferential extension would require a new question, design review and analysis plan." } ], "unresolvedQueries": [ { "id": "Q01", "question": "Which release and exact data file would the commissioned analysis use?", "why": "The documentation page, citation example and future input file need separate identities. Record the selected file's retrieval details and checksum before execution.", "status": "Open. No analysis file has been retrieved in this demonstration." }, { "id": "Q02", "question": "If individual-level interpretation is required, what source evidence establishes identity and relevant sampling relationships?", "why": "A simplified row index is a tracking key. It does not resolve biological identity, pair or nest relationships, or possible repeated observations.", "status": "Open for an individual-level extension. The current protocol remains descriptive of records." }, { "id": "Q03", "question": "What evidence would justify mapping the stored year codes to breeding-season labels?", "why": "Relabelling needs an auditable mapping rather than an assumption based on similar numbers.", "status": "Open. Stored codes remain unchanged in the proposed tables." } ], "analysisExecuted": false, "datasetDownloadedForAnalysis": false, "syntheticDatasetUsed": false, "calculationPolicy": { "N": "Eligible records in each group, including ordinary missing body mass after invalid-value issues are resolved", "n": "Records with valid observed body_mass_g", "missing": "N − n", "missingPercentage": "100 × (N − n) / N if N > 0; not applicable if N = 0", "mean": "Sum of valid observed body_mass_g / n if n > 0; not estimable if n = 0", "display": "Integer counts; mean to one gram; percentages to one decimal place; round-half-up for nonnegative derived values; retain full precision internally", "results": null }, "language": { "interface": "English", "editorialConvention": "British English", "serviceOutputLanguages": [ "English", "German", "French", "Italian", "Russian", "Chinese", "Portuguese", "Spanish", "Japanese" ] } }