Renumber the pipeline substeps to match the paper (5-1 becomes 5a)

prompts/ and runs/ move by git mv; zero padding dropped; the
arbitration and LLM-merge rows in the cost ledger carry no new
name -- their step column reads 已廢棄 with the original name
kept in a new last column.  Archived meta.json files and past
decision-log entries keep the names they were written with.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

runs/5c-synthesize/run1/meta.json

@@ -0,0 +1,25 @@
+{
+  "script_version": "run_llm.py 3.1.0",
+  "model": "claude-fable-5",
+  "temperature": null,
+  "thinking": null,
+  "max_tokens": 32000,
+  "prompt_path": "../prompts/05-03-synthesize.md",
+  "prompt_sha256": "90ed14f43153fd8184929e80315d660ca8516466bffa857e669bb2985829a365",
+  "input_path": "instance/llm-input-synthesize.jsonl",
+  "input_sha256": "2beb94a3643a6fe63e86664f0936fe411f180fed0cd520fb16571dd2f9a9408e",
+  "item_count": 1,
+  "dry_run": false,
+  "started_at": "2026-08-15T14:43:50+08:00",
+  "batch": {
+    "batch_id": "msgbatch_01XbNQb1SFrUxhk2ZWF7epPA",
+    "submitted_at": "2026-08-15T14:43:53+08:00",
+    "ended_at": "2026-08-15T06:46:50.472954+00:00"
+  },
+  "usage": {
+    "cache_creation_input_tokens": 0,
+    "cache_read_input_tokens": 0,
+    "input_tokens": 103888,
+    "output_tokens": 9982
+  }
+}

runs/5c-synthesize/run1/prompt.md

@@ -0,0 +1,41 @@
+You are inducing the recurring patterns in how the problems
+appear across the consolidated reading reports of many songs.
+
+Input: a JSON object keyed by song ID (such as "song-11"),
+each value the consolidated reading report of that song; a
+report of 「無」 means no problem was found for that song.
+
+{
+  "song-11": "consolidated report ...",
+  "song-95": "無"
+}
+
+The reports come from feminist-perspective readings of each
+song's lyrics; every item carries verbatim quotes and a
+convergence mark, and the trailing 「僅單獨提及」 line of a
+report holds the scattered findings of a single reading --
+take them into account when inducing the patterns, but draw
+the representative quotes from the main lists only.
+
+Task: induce the patterns -- the recurring forms in which
+the problems appear and operate -- across the reports.
+
+Rules:
+
+- A pattern describes how a problem works in the lyrics:
+  what is coupled with what, who speaks, how the mechanism
+  runs.  It is not a category for filing problems, and not
+  every problem needs to belong to one; a pattern may also
+  cut across several kinds of problems.
+- Induce the patterns from the report contents; never
+  introduce a problem or knowledge absent from the reports;
+  the number of patterns follows the material, with nothing
+  preset.
+- For every pattern: a name, a paragraph describing the form
+  and how it operates, and two or three representative
+  quotes, each with its song ID.
+- Describe and induce only; never evaluate severity, never
+  make recommendations.
+
+Output: Traditional Chinese (Taiwan usage).  One section per
+pattern; output nothing else.

runs/5c-synthesize/run2/meta.json

@@ -0,0 +1,25 @@
+{
+  "script_version": "run_llm.py 3.1.0",
+  "model": "claude-fable-5",
+  "temperature": null,
+  "thinking": null,
+  "max_tokens": 32000,
+  "prompt_path": "../prompts/05-03-synthesize.md",
+  "prompt_sha256": "90ed14f43153fd8184929e80315d660ca8516466bffa857e669bb2985829a365",
+  "input_path": "instance/llm-input-synthesize-male.jsonl",
+  "input_sha256": "aa0848e7a33e1c579ff3edfc60f3df8c62d15ef2e1464dfc20b4f5acd8ee9a17",
+  "item_count": 1,
+  "dry_run": false,
+  "started_at": "2026-08-15T17:12:34+08:00",
+  "batch": {
+    "batch_id": "msgbatch_01FKqq8U6m5HLLsx7KpQES26",
+    "submitted_at": "2026-08-15T17:12:35+08:00",
+    "ended_at": "2026-08-15T09:15:03.223864+00:00"
+  },
+  "usage": {
+    "cache_creation_input_tokens": 0,
+    "cache_read_input_tokens": 0,
+    "input_tokens": 13573,
+    "output_tokens": 6883
+  }
+}

runs/5c-synthesize/run2/prompt.md

@@ -0,0 +1,41 @@
+You are inducing the recurring patterns in how the problems
+appear across the consolidated reading reports of many songs.
+
+Input: a JSON object keyed by song ID (such as "song-11"),
+each value the consolidated reading report of that song; a
+report of 「無」 means no problem was found for that song.
+
+{
+  "song-11": "consolidated report ...",
+  "song-95": "無"
+}
+
+The reports come from feminist-perspective readings of each
+song's lyrics; every item carries verbatim quotes and a
+convergence mark, and the trailing 「僅單獨提及」 line of a
+report holds the scattered findings of a single reading --
+take them into account when inducing the patterns, but draw
+the representative quotes from the main lists only.
+
+Task: induce the patterns -- the recurring forms in which
+the problems appear and operate -- across the reports.
+
+Rules:
+
+- A pattern describes how a problem works in the lyrics:
+  what is coupled with what, who speaks, how the mechanism
+  runs.  It is not a category for filing problems, and not
+  every problem needs to belong to one; a pattern may also
+  cut across several kinds of problems.
+- Induce the patterns from the report contents; never
+  introduce a problem or knowledge absent from the reports;
+  the number of patterns follows the material, with nothing
+  preset.
+- For every pattern: a name, a paragraph describing the form
+  and how it operates, and two or three representative
+  quotes, each with its song ID.
+- Describe and induce only; never evaluate severity, never
+  make recommendations.
+
+Output: Traditional Chinese (Taiwan usage).  One section per
+pattern; output nothing else.

runs/5c-synthesize/run3/meta.json

@@ -0,0 +1,25 @@
+{
+  "script_version": "run_llm.py 3.1.0",
+  "model": "claude-fable-5",
+  "temperature": null,
+  "thinking": null,
+  "max_tokens": 32000,
+  "prompt_path": "../prompts/05-03-synthesize.md",
+  "prompt_sha256": "90ed14f43153fd8184929e80315d660ca8516466bffa857e669bb2985829a365",
+  "input_path": "instance/llm-input-synthesize-female.jsonl",
+  "input_sha256": "e63c401dfce3dd3de1969afda2b2db46a55e2ac57c70eb2b4259b12f564c01f2",
+  "item_count": 1,
+  "dry_run": false,
+  "started_at": "2026-08-15T17:15:39+08:00",
+  "batch": {
+    "batch_id": "msgbatch_017tfhiRTnaxqCp6YFyoivsu",
+    "submitted_at": "2026-08-15T17:15:39+08:00",
+    "ended_at": "2026-08-15T09:19:21.041833+00:00"
+  },
+  "usage": {
+    "cache_creation_input_tokens": 0,
+    "cache_read_input_tokens": 0,
+    "input_tokens": 60727,
+    "output_tokens": 8519
+  }
+}

runs/5c-synthesize/run3/prompt.md

@@ -0,0 +1,41 @@
+You are inducing the recurring patterns in how the problems
+appear across the consolidated reading reports of many songs.
+
+Input: a JSON object keyed by song ID (such as "song-11"),
+each value the consolidated reading report of that song; a
+report of 「無」 means no problem was found for that song.
+
+{
+  "song-11": "consolidated report ...",
+  "song-95": "無"
+}
+
+The reports come from feminist-perspective readings of each
+song's lyrics; every item carries verbatim quotes and a
+convergence mark, and the trailing 「僅單獨提及」 line of a
+report holds the scattered findings of a single reading --
+take them into account when inducing the patterns, but draw
+the representative quotes from the main lists only.
+
+Task: induce the patterns -- the recurring forms in which
+the problems appear and operate -- across the reports.
+
+Rules:
+
+- A pattern describes how a problem works in the lyrics:
+  what is coupled with what, who speaks, how the mechanism
+  runs.  It is not a category for filing problems, and not
+  every problem needs to belong to one; a pattern may also
+  cut across several kinds of problems.
+- Induce the patterns from the report contents; never
+  introduce a problem or knowledge absent from the reports;
+  the number of patterns follows the material, with nothing
+  preset.
+- For every pattern: a name, a paragraph describing the form
+  and how it operates, and two or three representative
+  quotes, each with its song ID.
+- Describe and induce only; never evaluate severity, never
+  make recommendations.
+
+Output: Traditional Chinese (Taiwan usage).  One section per
+pattern; output nothing else.

runs/5c-synthesize/run4/meta.json

@@ -0,0 +1,25 @@
+{
+  "script_version": "run_llm.py 3.1.0",
+  "model": "claude-fable-5",
+  "temperature": null,
+  "thinking": null,
+  "max_tokens": 32000,
+  "prompt_path": "../prompts/05-03-synthesize.md",
+  "prompt_sha256": "90ed14f43153fd8184929e80315d660ca8516466bffa857e669bb2985829a365",
+  "input_path": "instance/llm-input-synthesize-mixed.jsonl",
+  "input_sha256": "9ac673b3f44f139028a9bab34dbbc0e1c325282450d126efabcb35d61b7c663a",
+  "item_count": 1,
+  "dry_run": false,
+  "started_at": "2026-08-15T17:19:43+08:00",
+  "batch": {
+    "batch_id": "msgbatch_01SNjTLiNPEba4LW2tcUAcTJ",
+    "submitted_at": "2026-08-15T17:19:43+08:00",
+    "ended_at": "2026-08-15T09:23:39.172965+00:00"
+  },
+  "usage": {
+    "cache_creation_input_tokens": 0,
+    "cache_read_input_tokens": 0,
+    "input_tokens": 29958,
+    "output_tokens": 9793
+  }
+}

runs/5c-synthesize/run4/prompt.md

@@ -0,0 +1,41 @@
+You are inducing the recurring patterns in how the problems
+appear across the consolidated reading reports of many songs.
+
+Input: a JSON object keyed by song ID (such as "song-11"),
+each value the consolidated reading report of that song; a
+report of 「無」 means no problem was found for that song.
+
+{
+  "song-11": "consolidated report ...",
+  "song-95": "無"
+}
+
+The reports come from feminist-perspective readings of each
+song's lyrics; every item carries verbatim quotes and a
+convergence mark, and the trailing 「僅單獨提及」 line of a
+report holds the scattered findings of a single reading --
+take them into account when inducing the patterns, but draw
+the representative quotes from the main lists only.
+
+Task: induce the patterns -- the recurring forms in which
+the problems appear and operate -- across the reports.
+
+Rules:
+
+- A pattern describes how a problem works in the lyrics:
+  what is coupled with what, who speaks, how the mechanism
+  runs.  It is not a category for filing problems, and not
+  every problem needs to belong to one; a pattern may also
+  cut across several kinds of problems.
+- Induce the patterns from the report contents; never
+  introduce a problem or knowledge absent from the reports;
+  the number of patterns follows the material, with nothing
+  preset.
+- For every pattern: a name, a paragraph describing the form
+  and how it operates, and two or three representative
+  quotes, each with its song ID.
+- Describe and induce only; never evaluate severity, never
+  make recommendations.
+
+Output: Traditional Chinese (Taiwan usage).  One section per
+pattern; output nothing else.