feat: trace quality agent selection report, identity clustering runner_v2 DB write, age/gender CoreML selection, updated experiment config UUID

experiments/identity_clustering/results/exp_001/config.json

@@ -0,0 +1,11 @@
+{
+  "id": "001",
+  "name": "Baseline: Fixed Threshold (0.85), min 3 frames, no TMDb",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "threshold",
+  "threshold": 0.85,
+  "adaptive_threshold": false,
+  "enable_tmdb": false,
+  "notes": "sample_interval=60 導致 trace 碎片化。min_frames=3 納入大部分 traces。"
+}

experiments/identity_clustering/results/exp_001/metrics.json

@@ -0,0 +1,10 @@
+{
+  "total_traces": 677,
+  "clustered_traces": 677,
+  "cluster_count": 199,
+  "coverage": 1.0,
+  "avg_cluster_size": 3.4020100502512562,
+  "tmdb_matched": 0,
+  "tmdb_coverage": 0.0,
+  "execution_time_s": 3.706886053085327
+}

experiments/identity_clustering/results/exp_001/summary.txt

@@ -0,0 +1,36 @@
+
+Experiment 001: Baseline: Fixed Threshold (0.85), min 3 frames, no TMDb
+====================================
+Date: 2026-05-04T17:13:02.183318
+Config: {
+  "id": "001",
+  "name": "Baseline: Fixed Threshold (0.85), min 3 frames, no TMDb",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "threshold",
+  "threshold": 0.85,
+  "adaptive_threshold": false,
+  "enable_tmdb": false,
+  "notes": "sample_interval=60 \u5c0e\u81f4 trace \u788e\u7247\u5316\u3002min_frames=3 \u7d0d\u5165\u5927\u90e8\u5206 traces\u3002"
+}
+
+Results:
+  Traces loaded:     677
+  Clusters:          379
+  Clustered traces:  677
+  Coverage:          100.0%
+  Avg cluster size:  1.8
+  TMDb matched:      0
+  Execution time:    3.6s
+
+Top clusters:
+  Cluster 2: 74 traces → None (sim=0.000)
+  Cluster 29: 38 traces → None (sim=0.000)
+  Cluster 133: 14 traces → None (sim=0.000)
+  Cluster 14: 13 traces → None (sim=0.000)
+  Cluster 62: 10 traces → None (sim=0.000)
+  Cluster 126: 8 traces → None (sim=0.000)
+  Cluster 31: 7 traces → None (sim=0.000)
+  Cluster 13: 6 traces → None (sim=0.000)
+  Cluster 19: 6 traces → None (sim=0.000)
+  Cluster 89: 6 traces → None (sim=0.000)

experiments/identity_clustering/results/exp_002/config.json

@@ -0,0 +1,11 @@
+{
+  "id": "002",
+  "name": "Adaptive Threshold (pose-aware), min 30 frames, no TMDb",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "threshold",
+  "threshold": 0.85,
+  "adaptive_threshold": true,
+  "enable_tmdb": false,
+  "notes": "Pose-aware: 短 trace 放寬 threshold 5%。適合 profile/three_quarter 角度辨識。"
+}

experiments/identity_clustering/results/exp_002/metrics.json

@@ -0,0 +1,10 @@
+{
+  "total_traces": 677,
+  "clustered_traces": 677,
+  "cluster_count": 143,
+  "coverage": 1.0,
+  "avg_cluster_size": 4.734265734265734,
+  "tmdb_matched": 0,
+  "tmdb_coverage": 0.0,
+  "execution_time_s": 3.065944194793701
+}

experiments/identity_clustering/results/exp_002/summary.txt

@@ -0,0 +1,36 @@
+
+Experiment 002: Adaptive Threshold (pose-aware), min 30 frames, no TMDb
+====================================
+Date: 2026-05-04T17:13:05.263374
+Config: {
+  "id": "002",
+  "name": "Adaptive Threshold (pose-aware), min 30 frames, no TMDb",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "threshold",
+  "threshold": 0.85,
+  "adaptive_threshold": true,
+  "enable_tmdb": false,
+  "notes": "Pose-aware: \u77ed trace \u653e\u5bec threshold 5%\u3002\u9069\u5408 profile/three_quarter \u89d2\u5ea6\u8fa8\u8b58\u3002"
+}
+
+Results:
+  Traces loaded:     677
+  Clusters:          293
+  Clustered traces:  677
+  Coverage:          100.0%
+  Avg cluster size:  2.3
+  TMDb matched:      0
+  Execution time:    3.0s
+
+Top clusters:
+  Cluster 2: 114 traces → None (sim=0.000)
+  Cluster 13: 43 traces → None (sim=0.000)
+  Cluster 51: 19 traces → None (sim=0.000)
+  Cluster 112: 15 traces → None (sim=0.000)
+  Cluster 28: 12 traces → None (sim=0.000)
+  Cluster 30: 12 traces → None (sim=0.000)
+  Cluster 56: 11 traces → None (sim=0.000)
+  Cluster 107: 11 traces → None (sim=0.000)
+  Cluster 169: 11 traces → None (sim=0.000)
+  Cluster 74: 9 traces → None (sim=0.000)

experiments/identity_clustering/results/exp_003/config.json

@@ -0,0 +1,11 @@
+{
+  "id": "003",
+  "name": "DBSCAN (eps=0.3), min 30 frames, no TMDb",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "dbscan",
+  "eps": 0.3,
+  "min_samples": 2,
+  "enable_tmdb": false,
+  "notes": "DBSCAN 自動偵測 cluster 數量，不需要手設 threshold。eps=0.3 對應 cosine distance。"
+}

experiments/identity_clustering/results/exp_003/metrics.json

@@ -0,0 +1,10 @@
+{
+  "total_traces": 677,
+  "clustered_traces": 677,
+  "cluster_count": 34,
+  "coverage": 1.0,
+  "avg_cluster_size": 19.91176470588235,
+  "tmdb_matched": 0,
+  "tmdb_coverage": 0.0,
+  "execution_time_s": 2.6430821418762207
+}

experiments/identity_clustering/results/exp_003/summary.txt

@@ -0,0 +1,36 @@
+
+Experiment 003: DBSCAN (eps=0.3), min 30 frames, no TMDb
+====================================
+Date: 2026-05-04T17:13:08.042584
+Config: {
+  "id": "003",
+  "name": "DBSCAN (eps=0.3), min 30 frames, no TMDb",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "dbscan",
+  "eps": 0.3,
+  "min_samples": 2,
+  "enable_tmdb": false,
+  "notes": "DBSCAN \u81ea\u52d5\u5075\u6e2c cluster \u6578\u91cf\uff0c\u4e0d\u9700\u8981\u624b\u8a2d threshold\u3002eps=0.3 \u5c0d\u61c9 cosine distance\u3002"
+}
+
+Results:
+  Traces loaded:     677
+  Clusters:          78
+  Clustered traces:  677
+  Coverage:          100.0%
+  Avg cluster size:  8.7
+  TMDb matched:      0
+  Execution time:    2.7s
+
+Top clusters:
+  Cluster 1: 537 traces → None (sim=0.000)
+  Cluster 10: 26 traces → None (sim=0.000)
+  Cluster 2: 14 traces → None (sim=0.000)
+  Cluster 9: 9 traces → None (sim=0.000)
+  Cluster 47: 8 traces → None (sim=0.000)
+  Cluster 37: 4 traces → None (sim=0.000)
+  Cluster 7: 2 traces → None (sim=0.000)
+  Cluster 32: 2 traces → None (sim=0.000)
+  Cluster 36: 2 traces → None (sim=0.000)
+  Cluster 48: 2 traces → None (sim=0.000)

experiments/identity_clustering/results/exp_004/config.json

@@ -0,0 +1,11 @@
+{
+  "id": "004",
+  "name": "DBSCAN (eps=0.25), min 30 frames, no TMDb",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "dbscan",
+  "eps": 0.25,
+  "min_samples": 2,
+  "enable_tmdb": false,
+  "notes": "DBSCAN 更嚴格版本（eps=0.25），預期更多 cluster、較少 false positive。"
+}

experiments/identity_clustering/results/exp_004/metrics.json

@@ -0,0 +1,10 @@
+{
+  "total_traces": 677,
+  "clustered_traces": 677,
+  "cluster_count": 64,
+  "coverage": 1.0,
+  "avg_cluster_size": 10.578125,
+  "tmdb_matched": 0,
+  "tmdb_coverage": 0.0,
+  "execution_time_s": 2.588068962097168
+}

experiments/identity_clustering/results/exp_004/summary.txt

@@ -0,0 +1,36 @@
+
+Experiment 004: DBSCAN (eps=0.25), min 30 frames, no TMDb
+====================================
+Date: 2026-05-04T17:13:10.776315
+Config: {
+  "id": "004",
+  "name": "DBSCAN (eps=0.25), min 30 frames, no TMDb",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "dbscan",
+  "eps": 0.25,
+  "min_samples": 2,
+  "enable_tmdb": false,
+  "notes": "DBSCAN \u66f4\u56b4\u683c\u7248\u672c\uff08eps=0.25\uff09\uff0c\u9810\u671f\u66f4\u591a cluster\u3001\u8f03\u5c11 false positive\u3002"
+}
+
+Results:
+  Traces loaded:     677
+  Clusters:          129
+  Clustered traces:  677
+  Coverage:          100.0%
+  Avg cluster size:  5.2
+  TMDb matched:      0
+  Execution time:    2.6s
+
+Top clusters:
+  Cluster 1: 444 traces → None (sim=0.000)
+  Cluster 32: 43 traces → None (sim=0.000)
+  Cluster 14: 24 traces → None (sim=0.000)
+  Cluster 4: 13 traces → None (sim=0.000)
+  Cluster 115: 6 traces → None (sim=0.000)
+  Cluster 38: 4 traces → None (sim=0.000)
+  Cluster 53: 4 traces → None (sim=0.000)
+  Cluster 65: 4 traces → None (sim=0.000)
+  Cluster 88: 4 traces → None (sim=0.000)
+  Cluster 102: 4 traces → None (sim=0.000)

experiments/identity_clustering/results/exp_005/config.json

@@ -0,0 +1,12 @@
+{
+  "id": "005",
+  "name": "Adaptive Threshold + TMDb matching, min 30 frames",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "threshold",
+  "threshold": 0.85,
+  "adaptive_threshold": true,
+  "enable_tmdb": true,
+  "enable_speaker_verify": false,
+  "notes": "最佳方案候選：pose-aware + TMDb 自動標註。預期 Cary Grant, Audrey Hepburn 等主要角色被標出。"
+}

experiments/identity_clustering/results/exp_005/metrics.json

@@ -0,0 +1,10 @@
+{
+  "total_traces": 677,
+  "clustered_traces": 677,
+  "cluster_count": 293,
+  "coverage": 1.0,
+  "avg_cluster_size": 2.310580204778157,
+  "tmdb_matched": 0,
+  "tmdb_coverage": 0.0,
+  "execution_time_s": 3.034806966781616
+}

experiments/identity_clustering/results/exp_005/summary.txt

@@ -0,0 +1,37 @@
+
+Experiment 005: Adaptive Threshold + TMDb matching, min 30 frames
+====================================
+Date: 2026-05-04T17:05:33.808099
+Config: {
+  "id": "005",
+  "name": "Adaptive Threshold + TMDb matching, min 30 frames",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "clustering_method": "threshold",
+  "threshold": 0.85,
+  "adaptive_threshold": true,
+  "enable_tmdb": true,
+  "enable_speaker_verify": false,
+  "notes": "\u6700\u4f73\u65b9\u6848\u5019\u9078\uff1apose-aware + TMDb \u81ea\u52d5\u6a19\u8a3b\u3002\u9810\u671f Cary Grant, Audrey Hepburn \u7b49\u4e3b\u8981\u89d2\u8272\u88ab\u6a19\u51fa\u3002"
+}
+
+Results:
+  Traces loaded:     677
+  Clusters:          293
+  Clustered traces:  677
+  Coverage:          100.0%
+  Avg cluster size:  2.3
+  TMDb matched:      0
+  Execution time:    3.0s
+
+Top clusters:
+  Cluster 2: 114 traces → None (sim=0.000)
+  Cluster 13: 43 traces → None (sim=0.000)
+  Cluster 51: 19 traces → None (sim=0.000)
+  Cluster 112: 15 traces → None (sim=0.000)
+  Cluster 28: 12 traces → None (sim=0.000)
+  Cluster 30: 12 traces → None (sim=0.000)
+  Cluster 56: 11 traces → None (sim=0.000)
+  Cluster 107: 11 traces → None (sim=0.000)
+  Cluster 169: 11 traces → None (sim=0.000)
+  Cluster 74: 9 traces → None (sim=0.000)

experiments/identity_clustering/results/exp_006/config.json

@@ -0,0 +1,13 @@
+{
+  "id": "006",
+  "name": "Multi-Stage: Face-level high-conf binding + centroid clustering + speaker",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "enable_identity_match": true,
+  "stage1_face_threshold": 0.92,
+  "stage1_bind_ratio": 0.85,
+  "stage2_threshold": 0.85,
+  "stage2_adaptive": true,
+  "enable_tmdb": false,
+  "notes": "Stage1: each face vs identity ref, bind if >85% faces match >0.92. Stage2: centroid clustering of unbound + speaker merge."
+}

experiments/identity_clustering/results/exp_006/metrics.json

@@ -0,0 +1,10 @@
+{
+  "total_traces": 677,
+  "stage1_bound": 0,
+  "stage1_bound_traces": 0,
+  "stage2_clusters": 295,
+  "stage2_unbound_clustered": 677,
+  "total_clusters": 295,
+  "execution_time_s": 3.226997137069702,
+  "coverage": 1.0
+}

experiments/identity_clustering/results/exp_007/config.json

@@ -0,0 +1,13 @@
+{
+  "id": "007",
+  "name": "Multi-Stage: relaxed TMDb bind + 3-angle anchor selection",
+  "file_uuid": "1a04db97be5fa12bd77369831dc141fd",
+  "min_frames": 3,
+  "enable_identity_match": true,
+  "stage1_face_threshold": 0.72,
+  "stage1_bind_ratio": 0.75,
+  "stage2_threshold": 0.85,
+  "stage2_adaptive": true,
+  "enable_tmdb": false,
+  "notes": "Stage1: TMDb bind threshold 0.72 (跨 domain 較寬)。Stage2: 每個 identity 從 bound traces 挑 frontal/three_quarter/profile 三角度 face 組合成多角度 reference，用於 further matching。"
+}

experiments/identity_clustering/results/exp_007/metrics.json

@@ -0,0 +1,10 @@
+{
+  "total_traces": 677,
+  "stage1_bound": 0,
+  "stage1_bound_traces": 0,
+  "stage2_clusters": 295,
+  "stage2_unbound_clustered": 677,
+  "total_clusters": 295,
+  "execution_time_s": 3.2448980808258057,
+  "coverage": 1.0
+}

experiments/identity_clustering/results/exp_008/config.json

@@ -0,0 +1,15 @@
+{
+  "id": "008",
+  "name": "Composite: TMDb vector + speaker frequency scoring",
+  "file_uuid": "417a7e93860d70c87aee6c4c1b715d70",
+  "min_frames": 3,
+  "enable_identity_match": true,
+  "stage1_face_threshold": 0.55,
+  "stage1_bind_ratio": 0.6,
+  "stage2_threshold": 0.85,
+  "stage2_adaptive": true,
+  "enable_speaker_weight": true,
+  "speaker_weight_factor": 0.3,
+  "notes": "V2.0 embedding space。Speaker 出現次數(segment count)加權 × vector similarity 綜合評分。主角(SPEAKER_0/SPEAKER_1)加權較高。",
+  "write_db": true
+}

experiments/identity_clustering/results/exp_008/metrics.json

@@ -0,0 +1,10 @@
+{
+  "total_traces": 677,
+  "stage1_bound": 671,
+  "stage1_bound_traces": 671,
+  "stage2_clusters": 6,
+  "stage2_unbound_clustered": 6,
+  "total_clusters": 677,
+  "execution_time_s": 11.841914176940918,
+  "coverage": 1.0
+}