Package index • LLMRcontent

All functions

archive_appendix(): Draft the reproducibility appendix
archive_build(): Build a replication archive from an LLMR audit log
archive_check(): Verify an archive's integrity and (optionally) a result's completeness
archive_current(): Archive the currently active audit log
archive_diff(): Compare two archives
archive_read(): Read an archive from a directory
archive_redact(): Redact an archive's content while keeping its hash tree
archive_replay(): Replay archived responses offline
archive_seal(): Seal an archive under a root hash
archive_verify(): Re-verify archived calls against the live providers
archive_write(): Write an archive to a directory
as_tibble(<archive>): Convert an archive manifest to a tibble
as_tibble(<audit>): Coerce an audit to a tibble
as_tibble(<audit_placebo>): Coerce an audit placebo to a tibble
as_tibble(<gold_correction>): Coerce a gold correction to a tibble
as_tibble(<protocol_tuning>): Coerce protocol tuning results to a tibble
audit_add_models(): Add the model arm of the grid
audit_add_perturbations(): Add measurement perturbations
audit_add_prompts(): Add prompt paraphrases
audit_curve(): The specification curve
audit_fragility(): How small a measurement change flips the conclusion?
audit_placebo(): Placebo tests for the measurement pipeline
audit_plan(): Declare a measurement-robustness audit
audit_report(): Draft the robustness appendix
audit_run(): Run the audit grid
audit_stability(): Stability of the estimate across the grid
audit_units(): The unit-level trail behind an audit
cb_category(): Define one category of a codebook
code_corpus(): Code a corpus with a locked protocol
codebook(): Create a codebook
codebook_hash(): Content hash of a codebook
codebook_labels(): Labels defined by a codebook
coder_agreement(): Agreement among coders or replicates
coding_report(): Draft the methods text and validation summary
diagnostics(<archive>): Machine-readable archive diagnostics
diagnostics.audit(): Audit diagnostics through LLMR's shared generic
diagnostics(<gold_correction>): Gold-correction diagnostics
diagnostics(<protocol_validation>): Protocol-validation diagnostics
export_caqdas(): Export coded data for CAQDAS software
sign_flip() threshold_flip(): Conclusion-flip rules for the fragility index
format_codebook(): Render a codebook as prompt text
gold_correct(): Correct corpus prevalences with the gold-set audit
gold_ledger(): The evaluation ledger of a sealed gold set
gold_set(): Build a gold-standard set with split provenance and a sealed test split
gold_size(): Plan the size of a gold set
gold_split(): Rows of a gold set belonging to one split
install_gui_deps(): Install the LLMRcontent GUI's suggested packages
parse_label(): Default parser: match the reply to a codebook label
protocol(): Assemble a coding protocol
protocol_lock(): Lock a protocol
report(<archive>): Draft an archive report through the shared LLMR generic
report.audit(): Report an audit through LLMR's shared generic
report(<protocol_validation>): Report a protocol validation through the LLMR generic
reset(<archive_replayer>): Reset an archive replayer to its initial position
run_content_studio(): Launch the LLMRcontent Shiny GUI
tune_protocol(): Tune candidate protocols on the development split
validate_protocol(): Validate a locked protocol on the sealed test split
verifiability_horizon(): The verifiability horizon of an archive