survey-data-table — workgraph

Metadata

Status	done
Assigned	`agent-665`
Agent identity	`3184716484e6f0ea08bb13539daf07686ee79d440505f1fdf2de0357707034c3`
Created	2026-05-05T04:13:14.890719778+00:00
Started	2026-05-05T04:27:34.601257069+00:00
Completed	2026-05-05T04:31:55.045267582+00:00
Tags	`paper-prep,survey`, `eval-scheduled`
Eval score	0.95
└ blocking impact	0.97
└ completeness	0.97
└ coordination overhead	0.97
└ correctness	0.97
└ downstream usability	0.93
└ efficiency	0.90
└ intent fidelity	0.85
└ style adherence	0.95

Description

CONTEXT: Nature manuscript prep. Many CSV/TSV/RData files exist — synthesis architect needs to know which can be turned into figures or feed extended-data tables. TASK: Find ALL tabular data files under project root: *.csv, *.tsv, *.RData, *.rds, *.parquet, *.bed, *.gff, *.txt that look like tables. For each (or representative groups for very repetitive sets), produce a row: PATH | SHAPE (rows × cols, sample if large) | TOPIC | LIKELY USE (main-fig / extended-data table / SI / supporting / not-useful) | NOTES. Group by topic. Add a short 'opportunities' section: tables whose contents would make a strong extended-data table or stat-test summary if not already plotted. DO use: find, head/wc on csv files for quick inspection. Skip into binaries. For RData files, list their inferred contents from filename if you cannot inspect. OUTPUT: paper_prep/surveys/SURVEY_DATA_inventory.md (table grouped by topic + opportunities section). ACCEPTANCE: File exists, ≥80% of tabular files cataloged, opportunities section present.

CONTEXT: Nature manuscript prep. Many CSV/TSV/RData files exist — synthesis architect needs to know which can be turned into figures or feed extended-data tables.
TASK: Find ALL tabular data files under project root: *.csv, *.tsv, *.RData, *.rds, *.parquet, *.bed, *.gff, *.txt that look like tables. For each (or representative groups for very repetitive sets), produce a row: PATH | SHAPE (rows × cols, sample if large) | TOPIC | LIKELY USE (main-fig / extended-data table / SI / supporting / not-useful) | NOTES. Group by topic. Add a short 'opportunities' section: tables whose contents would make a strong extended-data table or stat-test summary if not already plotted.
DO use: find, head/wc on csv files for quick inspection. Skip into binaries. For RData files, list their inferred contents from filename if you cannot inspect.
OUTPUT: paper_prep/surveys/SURVEY_DATA_inventory.md (table grouped by topic + opportunities section).
ACCEPTANCE: File exists, ≥80% of tabular files cataloged, opportunities section present.

Depends on

done .assign-survey-data-table

Required by

Log

2026-05-05T04:13:14.870164636+00:00 Task paused
2026-05-05T04:24:47.240825940+00:00 Task resumed
2026-05-05T04:27:34.601260695+00:00 Spawned by coordinator --executor claude --model opus
2026-05-05T04:28:04.199967043+00:00 Starting survey of tabular data files. Will catalog .csv/.tsv/.RData/.rds/.parquet/.bed/.gff/.txt under repo root.
2026-05-05T04:30:40.931099938+00:00 Cataloged 46/46 tabular files (100%). Grouped by 7 topics; opportunities section lists 7 EXT/SI candidates. Output: paper_prep/surveys/SURVEY_DATA_inventory.md
2026-05-05T04:31:41.746983981+00:00 Committed 8bcdb3b and pushed wg/agent-665/survey-data-table to origin.
2026-05-05T04:31:55.045271940+00:00 Task pending eval (agent reported done; awaiting `.evaluate-*` to score)
2026-05-05T04:35:32.496562760+00:00 PendingEval → Done (evaluator passed; downstream unblocks)