simonkoson/tps-dashboard
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ai-labeling: Prompt 1 v0.1 + ground-truth v0.4.0(20期) + MiMo首轮跑批

Browse Source 
- Prompt 1 v0.1: 4分类字段(题材/装备域/场景/技术)判别prompt，含5示例+边界规则+换装测试
- ground-truth v0.4.0: 10→20期扩展，ep编号重映射(旧ep3-15→新ep001-020)，4分类字段全填(制片人逐期审定)
- 文稿升级: 旧10期删除，新20期md文件(doco子项目清洗产出)替换
- 脚本升级: ep编号2位→3位，ALL_EPISODES扩至1-20，summarize classification比对逻辑实现
- MiMo首轮结果: 题材75%/装备域70%/场景95%/技术70%/全对40%，需迭代Prompt
- 质量标杆: 加入PPT+Excel样板文件(example/)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
simonkoson
2026-06-24 19:22:13 +08:00
parent 30931d4446
commit d8057b07e9
37 changed files with 3647 additions and 1508 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ai-labeling/benchmark-set/ground-truth.json
+228 -17
View File
@@ -1,20 +1,231 @@
{
"version": "v0.3.0",
"locked_at": "2026-06-11",
"locked_by": "制片人刘通 + Opus 复议(二次审定)",
"fields_covered": ["narrative_structure", "opening_hook"],
"fields_reserved": ["program_format", "equipment_domain", "scene_tags", "tech_tags"],
"changelog": "v0.1→v0.2: ep10(射速决定论)严格命中性能阶梯主线、ep15(空中坚盾)符合层级承接到体系困局递进,两期从并列结构改为主线演进。ep05/ep13/ep14 经讨论后维持并列结构(共同原因: 段内有承接但全片骨架为并列,已写入 Prompt v0.2 示例 4/5 作为反例教学)。v0.2.1: ep12 三家独立模型一致判并列结构,经制片人复读稿确认后改为并列结构。v0.3.0: 为 Prompt 1 预留 4 个分类字段位置(program_format/equipment_domain/scene_tags/tech_tags),枚举值待定,暂填 null/[]。未改动现有 narrative_structure/opening_hook 标注结果。v0.3.0补丁: equipment_domain 从 null 改为 []，对齐 v2 快照"多选"定义。",
"version": "v0.4.0",
"locked_at": "2026-06-24",
"locked_by": "制片人刘通 + Opus 顾问(逐期审定)",
"fields_covered": ["narrative_structure", "opening_hook", "program_format", "equipment_domain", "scene_tags", "tech_tags"],
"fields_reserved": [],
"changelog": "v0.1→v0.2: ep10/ep15 从并列改主线演进。v0.2→v0.2.1: ep12 经三家模型独立一致+制片人复审改为并列结构。v0.2.1→v0.3.0: 预留4分类字段骨架(null/[])。v0.3.0→v0.4.0: 期号重映射(旧ep3-15→新ep001-020按播出日期排序)，从10期扩展至20期，4分类字段(program_format/equipment_domain/scene_tags/tech_tags)全部填入，制片人逐期审定。新增10期暂无narrative_structure/opening_hook标注(待Prompt 2/3跑批后补)。",
"ep_number_migration": "v0.3.0旧编号→v0.4.0新编号: ep15→001, ep4→002, ep13→003, 新增→004, ep3→005, ep5→006, 新增→007, ep7→008, 新增→009, ep10→010, ep11→011, ep12→012, ep14→013, 新增→014, 新增→015, 新增→016, 新增→017, 新增→018, 新增→019, 新增→020",
"episodes": [
{"ep": 3, "title": "硅基大脑", "share": 0.85, "narrative_structure": "并列结构", "opening_hook": "中", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 4, "title": "潜艇仿生", "share": 0.92, "narrative_structure": "主线演进", "opening_hook": "强", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 5, "title": "舰证不凡", "share": 0.72, "narrative_structure": "并列结构", "opening_hook": "中", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 7, "title": "马年军事图鉴", "share": 0.95, "narrative_structure": "并列结构", "opening_hook": "强", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 10, "title": "射速决定论", "share": 0.703, "narrative_structure": "主线演进", "opening_hook": "弱", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 11, "title": "空战颠覆者", "share": 0.859, "narrative_structure": "主线演进", "opening_hook": "中", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 12, "title": "逆袭战局", "share": 0.85, "narrative_structure": "并列结构", "opening_hook": "强", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 13, "title": "长短智慧", "share": 0.533, "narrative_structure": "并列结构", "opening_hook": "中", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 14, "title": "X-76 飞行器", "share": 0.873, "narrative_structure": "并列结构", "opening_hook": "中", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []},
{"ep": 15, "title": "空中坚盾", "share": 0.875, "narrative_structure": "主线演进", "opening_hook": "强", "program_format": null, "equipment_domain": [], "scene_tags": [], "tech_tags": []}
{
"ep": 1,
"title": "防空反导大对决",
"share": 0.875,
"narrative_structure": "主线演进",
"opening_hook": "强",
"program_format": "装备深解",
"equipment_domain": ["导弹与反导"],
"scene_tags": ["热点跟进"],
"tech_tags": []
},
{
"ep": 2,
"title": "潜艇仿生",
"share": 0.92,
"narrative_structure": "主线演进",
"opening_hook": "强",
"program_format": "装备深解",
"equipment_domain": ["海军舰船"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 3,
"title": "枪械小尺寸大讲究",
"share": 0.533,
"narrative_structure": "并列结构",
"opening_hook": "中",
"program_format": "横切类比",
"equipment_domain": ["轻武器"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 4,
"title": "枪王对决",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "人物牵引",
"equipment_domain": ["轻武器"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 5,
"title": "硅基大脑",
"share": 0.85,
"narrative_structure": "并列结构",
"opening_hook": "中",
"program_format": "前沿科技",
"equipment_domain": ["航空航天", "陆战装备"],
"scene_tags": [],
"tech_tags": ["智能化", "有人无人协同"]
},
{
"ep": 6,
"title": "舰证不凡",
"share": 0.72,
"narrative_structure": "并列结构",
"opening_hook": "中",
"program_format": "横切类比",
"equipment_domain": ["海军舰船"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 7,
"title": "大国巨舰反差",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "横切类比",
"equipment_domain": ["海军舰船"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 8,
"title": "马年军事图鉴",
"share": 0.95,
"narrative_structure": "并列结构",
"opening_hook": "强",
"program_format": "横切类比",
"equipment_domain": ["海军舰船", "航空航天", "陆战装备"],
"scene_tags": ["节点策划"],
"tech_tags": []
},
{
"ep": 9,
"title": "重金造神器",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "横切类比",
"equipment_domain": ["海军舰船", "陆战装备", "航空航天", "跨域"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 10,
"title": "射速决定论",
"share": 0.703,
"narrative_structure": "主线演进",
"opening_hook": "弱",
"program_format": "横切类比",
"equipment_domain": ["轻武器"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 11,
"title": "空战演进",
"share": 0.859,
"narrative_structure": "主线演进",
"opening_hook": "中",
"program_format": "历史纵深",
"equipment_domain": ["航空航天"],
"scene_tags": [],
"tech_tags": ["无人作战"]
},
{
"ep": 12,
"title": "逆袭战局",
"share": 0.85,
"narrative_structure": "并列结构",
"opening_hook": "强",
"program_format": "横切类比",
"equipment_domain": ["航空航天", "陆战装备"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 13,
"title": "X-76飞行器",
"share": 0.873,
"narrative_structure": "并列结构",
"opening_hook": "中",
"program_format": "装备深解",
"equipment_domain": ["航空航天"],
"scene_tags": ["装备首发"],
"tech_tags": []
},
{
"ep": 14,
"title": "启程远航",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "装备深解",
"equipment_domain": ["海军舰船"],
"scene_tags": ["节点策划"],
"tech_tags": []
},
{
"ep": 15,
"title": "舰炮暴力美学",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "历史纵深",
"equipment_domain": ["海军舰船"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 16,
"title": "无人舰艇",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "前沿科技",
"equipment_domain": ["海军舰船"],
"scene_tags": [],
"tech_tags": ["无人作战"]
},
{
"ep": 17,
"title": "逆袭的鸭翼",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "横切类比",
"equipment_domain": ["航空航天"],
"scene_tags": ["装备首发"],
"tech_tags": []
},
{
"ep": 18,
"title": "机枪双雄",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "人物牵引",
"equipment_domain": ["轻武器"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 19,
"title": "玩具总动员",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "横切类比",
"equipment_domain": ["陆战装备", "航空航天", "海军舰船", "跨域"],
"scene_tags": [],
"tech_tags": []
},
{
"ep": 20,
"title": "武器颜值洼地",
"share": null,
"narrative_structure": null,
"opening_hook": null,
"program_format": "横切类比",
"equipment_domain": ["航空航天", "海军舰船"],
"scene_tags": [],
"tech_tags": []
}
]
}
}