books/gu-zhenren/diag/rootcause_auto.json

612 lines
No EOL
11 KiB
JSON

{
"summary": {
"n_chunks": 54,
"avg_similarity_draft_final": 0.971,
"median_similarity": 0.978,
"chunks_sim_ge_0.85 (editor near-passive)": 54,
"chunks_sim_ge_0.95 (editor barely touched)": 45,
"avg_len_ratio_final_draft": 0.992,
"clerical_markers_draft_total": 12,
"clerical_markers_final_total": 12,
"clerical_reduced_by_editor": 0,
"hyphen_dialogue_final_total": 0,
"em_dialogue_final_total": 237,
"cjk_residue_final_total": 4
},
"per_chunk": [
{
"chunk": "1/2",
"chapter": 1,
"sim": 0.981,
"len_ratio": 0.989,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "1/3",
"chapter": 1,
"sim": 1.0,
"len_ratio": 1.0,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "1/4",
"chapter": 1,
"sim": 0.968,
"len_ratio": 1.0,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "1/5",
"chapter": 1,
"sim": 0.988,
"len_ratio": 0.997,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 14,
"cjk_final": 0
},
{
"chunk": "2/0",
"chapter": 2,
"sim": 0.979,
"len_ratio": 1.002,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "2/1",
"chapter": 2,
"sim": 0.936,
"len_ratio": 0.983,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 2,
"cjk_final": 0
},
{
"chunk": "3/0",
"chapter": 3,
"sim": 0.963,
"len_ratio": 0.976,
"cler_draft": 1,
"cler_final": 1,
"hyphen_dlg_final": 0,
"em_dlg_final": 9,
"cjk_final": 0
},
{
"chunk": "3/1",
"chapter": 3,
"sim": 0.944,
"len_ratio": 0.989,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "4/0",
"chapter": 4,
"sim": 0.975,
"len_ratio": 0.994,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 9,
"cjk_final": 0
},
{
"chunk": "4/1",
"chapter": 4,
"sim": 0.967,
"len_ratio": 1.013,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "5/0",
"chapter": 5,
"sim": 0.979,
"len_ratio": 0.99,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "5/1",
"chapter": 5,
"sim": 0.994,
"len_ratio": 0.996,
"cler_draft": 1,
"cler_final": 1,
"hyphen_dlg_final": 0,
"em_dlg_final": 2,
"cjk_final": 0
},
{
"chunk": "6/0",
"chapter": 6,
"sim": 0.977,
"len_ratio": 0.992,
"cler_draft": 3,
"cler_final": 3,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "6/1",
"chapter": 6,
"sim": 0.972,
"len_ratio": 1.01,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 9,
"cjk_final": 0
},
{
"chunk": "7/0",
"chapter": 7,
"sim": 0.993,
"len_ratio": 1.0,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "7/1",
"chapter": 7,
"sim": 0.995,
"len_ratio": 0.999,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 1,
"cjk_final": 0
},
{
"chunk": "8/0",
"chapter": 8,
"sim": 0.984,
"len_ratio": 0.983,
"cler_draft": 3,
"cler_final": 3,
"hyphen_dlg_final": 0,
"em_dlg_final": 7,
"cjk_final": 0
},
{
"chunk": "8/1",
"chapter": 8,
"sim": 0.97,
"len_ratio": 0.998,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "9/0",
"chapter": 9,
"sim": 0.953,
"len_ratio": 0.982,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 5,
"cjk_final": 0
},
{
"chunk": "9/1",
"chapter": 9,
"sim": 0.963,
"len_ratio": 0.98,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 6,
"cjk_final": 0
},
{
"chunk": "10/0",
"chapter": 10,
"sim": 0.993,
"len_ratio": 0.997,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 1,
"cjk_final": 0
},
{
"chunk": "11/0",
"chapter": 11,
"sim": 0.984,
"len_ratio": 0.995,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 7,
"cjk_final": 0
},
{
"chunk": "11/1",
"chapter": 11,
"sim": 0.97,
"len_ratio": 0.985,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 5,
"cjk_final": 0
},
{
"chunk": "12/0",
"chapter": 12,
"sim": 0.937,
"len_ratio": 0.992,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 20,
"cjk_final": 0
},
{
"chunk": "12/1",
"chapter": 12,
"sim": 0.978,
"len_ratio": 0.995,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 10,
"cjk_final": 0
},
{
"chunk": "13/0",
"chapter": 13,
"sim": 0.998,
"len_ratio": 1.0,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "13/1",
"chapter": 13,
"sim": 0.984,
"len_ratio": 0.994,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "14/0",
"chapter": 14,
"sim": 0.983,
"len_ratio": 0.997,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 1,
"cjk_final": 0
},
{
"chunk": "14/1",
"chapter": 14,
"sim": 0.979,
"len_ratio": 0.987,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "15/0",
"chapter": 15,
"sim": 0.969,
"len_ratio": 0.998,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "15/1",
"chapter": 15,
"sim": 0.981,
"len_ratio": 0.987,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 11,
"cjk_final": 0
},
{
"chunk": "16/0",
"chapter": 16,
"sim": 0.998,
"len_ratio": 0.997,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 5,
"cjk_final": 0
},
{
"chunk": "16/1",
"chapter": 16,
"sim": 0.947,
"len_ratio": 0.984,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "17/0",
"chapter": 17,
"sim": 0.978,
"len_ratio": 0.995,
"cler_draft": 1,
"cler_final": 1,
"hyphen_dlg_final": 0,
"em_dlg_final": 4,
"cjk_final": 0
},
{
"chunk": "17/1",
"chapter": 17,
"sim": 0.979,
"len_ratio": 0.995,
"cler_draft": 2,
"cler_final": 2,
"hyphen_dlg_final": 0,
"em_dlg_final": 1,
"cjk_final": 0
},
{
"chunk": "18/0",
"chapter": 18,
"sim": 0.969,
"len_ratio": 0.995,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 16,
"cjk_final": 4
},
{
"chunk": "18/1",
"chapter": 18,
"sim": 0.965,
"len_ratio": 0.983,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 16,
"cjk_final": 0
},
{
"chunk": "18/2",
"chapter": 18,
"sim": 0.971,
"len_ratio": 0.991,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "19/0",
"chapter": 19,
"sim": 0.969,
"len_ratio": 1.008,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "19/1",
"chapter": 19,
"sim": 0.937,
"len_ratio": 0.984,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "20/0",
"chapter": 20,
"sim": 0.982,
"len_ratio": 0.99,
"cler_draft": 1,
"cler_final": 1,
"hyphen_dlg_final": 0,
"em_dlg_final": 6,
"cjk_final": 0
},
{
"chunk": "20/1",
"chapter": 20,
"sim": 0.946,
"len_ratio": 0.983,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 16,
"cjk_final": 0
},
{
"chunk": "21/0",
"chapter": 21,
"sim": 0.993,
"len_ratio": 0.999,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "21/1",
"chapter": 21,
"sim": 0.992,
"len_ratio": 1.0,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 11,
"cjk_final": 0
},
{
"chunk": "22/0",
"chapter": 22,
"sim": 0.972,
"len_ratio": 0.974,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "22/1",
"chapter": 22,
"sim": 0.97,
"len_ratio": 0.998,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 11,
"cjk_final": 0
},
{
"chunk": "22/2",
"chapter": 22,
"sim": 0.938,
"len_ratio": 1.0,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "23/0",
"chapter": 23,
"sim": 0.986,
"len_ratio": 0.989,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 17,
"cjk_final": 0
},
{
"chunk": "23/1",
"chapter": 23,
"sim": 0.991,
"len_ratio": 0.993,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 4,
"cjk_final": 0
},
{
"chunk": "23/2",
"chapter": 23,
"sim": 0.855,
"len_ratio": 0.959,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "24/0",
"chapter": 24,
"sim": 0.995,
"len_ratio": 0.994,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 7,
"cjk_final": 0
},
{
"chunk": "24/1",
"chapter": 24,
"sim": 0.974,
"len_ratio": 0.997,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "25/0",
"chapter": 25,
"sim": 0.978,
"len_ratio": 0.992,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 0,
"cjk_final": 0
},
{
"chunk": "25/1",
"chapter": 25,
"sim": 0.913,
"len_ratio": 0.989,
"cler_draft": 0,
"cler_final": 0,
"hyphen_dlg_final": 0,
"em_dlg_final": 4,
"cjk_final": 0
}
]
}