{
 "command": "23_chronology.py --agg /mnt/user-data/uploads/topic modeling/sep6/ab_spelling_out/runs_Qwen_Qwen3-Embedding-0.6B_masked_hdb10/topics_B_s42/aggregate --sheet /mnt/user-data/uploads/topic modeling/sep6/ab_spelling_out/runs_Qwen_Qwen3-Embedding-0.6B_masked_hdb10/topics_B_s42/topic_sheet.csv --chunk-meta /mnt/user-data/uploads/topic modeling/sep6/ab_spelling_out/chunks_w500/chunk_meta.csv --deep /mnt/user-data/uploads/Clustering Character Archetypes/early-modern-drama-character-clustering/data/DEEP_data.csv --company-dir company --out chron_out",
 "python": "3.11.15",
 "numpy": "2.4.4",
 "matplotlib": "3.10.9",
 "params": {
  "genres": [
   "comedy",
   "tragedy",
   "history"
  ],
  "use": [
   "included"
  ],
  "n_topics": 53,
  "top_works": 3,
  "heat_topics_max": 15,
  "heat_topic_rule": "max-min of decade means across decades with >=10 works, else overall genre mean",
  "decade_rule": "floor(year/10)*10",
  "display_rule": "<5 blank, 5-9 sparse, >=10 shown"
 },
 "inputs_sha256": {
  "work_topic_share.csv": "58f3fb62671405594111a52b180a4ca4b030f65d34847732c84b80ef29925270",
  "config.json": "72d339d258cdbb85730e11547e10a6d9b71490b65ab9445ad816f96bdb7a461a",
  "topic_sheet.csv": "fc4239342dc826ec807140304dd4250ee9fb41d57cd324dde94e02c1ea08e663",
  "chunk_meta.csv": "66d9f0c44b5a8e70cda76ea3844458754a717cea6a026baa71922f8e4aaf430f",
  "company_fields_by_work.csv": "acde66f5e6127faf871556eb48b6fdb1d53cd4b28aa5dd18ff166bb0c794ba2b",
  "DEEP_data.csv": "2222542869afce6a59c27211cf1d7efe5ebd7b46c144180c84a6c44dbadffbee"
 },
 "run": "topics_B_s42"
}