2026:Rhythm Game Chart Generation Results - Revision history

Junyan at 22:15, 12 October 2026

2026-10-12T22:15:32Z

Ziyunliu: /* Expert Evaluation Results */

2026-10-11T17:08:34Z

‎Expert Evaluation Results

Ziyunliu: /* Expert Evaluation Results */

2026-10-11T17:03:56Z

‎Expert Evaluation Results

Ziyunliu: /* Expert Evaluation Results */

2026-10-11T16:47:57Z

‎Expert Evaluation Results

Ziyunliu: /* Overall Results */

2026-10-11T16:43:32Z

‎Overall Results

Ziyunliu: /* Overall Results */

2026-10-11T16:43:05Z

‎Overall Results

Ziyunliu: /* Expert Evaluation Results */

2026-10-11T16:00:39Z

‎Expert Evaluation Results

Ziyunliu: /* Expert Evaluation Results */

2026-10-11T15:59:39Z

‎Expert Evaluation Results

Ziyunliu: /* Expert Evaluation Results */

2026-10-11T15:52:49Z

‎Expert Evaluation Results

Ziyunliu: /* Expert Evaluation Results */

2026-10-11T14:56:05Z

‎Expert Evaluation Results

@@ Line 10: / Line 10: @@
 | DOSU
 | DOSU: DIFFICULTY-CONDITIONED ON-GRID SEQUENCE UNMASKING FOR OSU!TAIKO CHART GENERATION
+| [http://futuremirex.com/portal/wp-content/uploads/2026/rhythm-game-chart-generation/DOSU.pdf PDF]
 | Junyoung Koh, Hao-Wen Dong
 |-
 | FumenLab
 | FUMENLAB: PLAN-CONDITIONED JOINT GENERATION AND REFINEMENT OF OSU!TAIKO CHARTS
+| [http://futuremirex.com/portal/wp-content/uploads/2026/rhythm-game-chart-generation/FumenLab.pdf PDF]
 | Ryo Mitoma
 |-
 | HiTaiko
 | HiTaiko: Hierarchical osu!Taiko Chart Generation via Metrical Candidate Selection
+| [http://futuremirex.com/portal/wp-content/uploads/2026/rhythm-game-chart-generation/HiTaiko.pdf PDF]
 | Sungjung Park
 |-
 | MALer
 | RHYTHM GAME CHART GENERATION WITH PRE-TRAINED MUSIC TRANSCRIPTION MODEL
+| [http://futuremirex.com/portal/wp-content/uploads/2026/rhythm-game-chart-generation/MALer.pdf PDF]
 | Sojeong An, Chris Donahue, Dasaem Jeong
 |}

@@ Line 539: / Line 539: @@
 | Missing sections, timing errors and inconsistent musical logic undermined the spread. Muzukashii was reportedly the hardest tier, while easier difficulties contained unexplained breaks. Inner Oni’s awkward fast bursts did not resolve the overall lack of musical coverage.
 |}
 == Community Evaluation Results ==

@@ Line 341: / Line 341: @@
 osu!taiko mappers evaluated submissions across 5 songs: '''Silver Bullet''', '''A fight in Tunisia''', '''YUBIKIRI-GENMAN''', '''Something Fun''', and '''closer to you'''. Each judge was assigned 3 songs based on their familiarity and interest of the songs, and each song was evaluated by 3 judges. For every assigned song, judges assessed submissions from all 4 models on 4 categories (Musical Representation, Creativity, Gameplay, and Human-Likeness) using an integer scale from 1 to 10.
 We follow [https://osu.ppy.sh/wiki/en/Contests/Monthly_Beatmapping_Contest Monthly Beatmapping Contest] and adopt '''within-song normalization''' for per-song report. For each category, judge X's final score = (judge X's raw score - judge X's average raw score) / judge X's standard deviation within that song, and a submission's score is the sum of each judge's final score.
-==== Silver Bullet ====
+=== Silver Bullet ===
 {| class="wikitable"
@@ Line 385: / Line 383: @@
 |}
-==== A fight in Tunisia ====
+=== A fight in Tunisia ===
 {| class="wikitable"
@@ Line 424: / Line 422: @@
 |}
-==== YUBIKIRI-GENMAN ====
+=== YUBIKIRI-GENMAN ===
 {| class="wikitable"
@@ Line 464: / Line 462: @@
 ''Musical Representation scores for FumenLab and HiTaiko round to the same value; HiTaiko has the higher unrounded score.''
-==== Something Fun ====
+=== Something Fun ===
 {| class="wikitable"
@@ Line 503: / Line 501: @@
 |}
-==== closer to you ====
+=== closer to you ===
 {| class="wikitable"
@@ Line 540: / Line 538: @@
 | −3.9903
 | Missing sections, timing errors and inconsistent musical logic undermined the spread. Muzukashii was reportedly the hardest tier, while easier difficulties contained unexplained breaks. Inner Oni’s awkward fast bursts did not resolve the overall lack of musical coverage.
 |}

@@ Line 341: / Line 341: @@
 osu!taiko mappers evaluated submissions across 5 songs: '''Silver Bullet''', '''A fight in Tunisia''', '''YUBIKIRI-GENMAN''', '''Something Fun''', and '''closer to you'''. Each judge was assigned 3 songs based on their familiarity and interest of the songs, and each song was evaluated by 3 judges. For every assigned song, judges assessed submissions from all 4 models on 4 categories (Musical Representation, Creativity, Gameplay, and Human-Likeness) using an integer scale from 1 to 10.
 We follow [https://osu.ppy.sh/wiki/en/Contests/Monthly_Beatmapping_Contest Monthly Beatmapping Contest] and adopt '''within-song normalization''' for per-song report. For each category, judge X's final score = (judge X's raw score - judge X's average raw score) / judge X's standard deviation within that song, and a submission's score is the sum of each judge's final score.
-=== Silver Bullet ===
+==== Silver Bullet ====
 {| class="wikitable"
@@ Line 383: / Line 385: @@
 |}
-=== A fight in Tunisia ===
+==== A fight in Tunisia ====
 {| class="wikitable"
@@ Line 422: / Line 424: @@
 |}
-=== YUBIKIRI-GENMAN ===
+==== YUBIKIRI-GENMAN ====
 {| class="wikitable"
@@ Line 462: / Line 464: @@
 ''Musical Representation scores for FumenLab and HiTaiko round to the same value; HiTaiko has the higher unrounded score.''
-=== Something Fun ===
+==== Something Fun ====
 {| class="wikitable"
@@ Line 501: / Line 503: @@
 |}
-=== closer to you ===
+==== closer to you ====
 {| class="wikitable"

@@ Line 542: / Line 542: @@
 === Overall Results ===
-The tables below summarize performance across all 5 songs using 2 normalization methods: within-song normalization and across-song normalization. Overall scores are the equally weighted mean of the 5 per-song scores. '''Combined Quality includes Musical Representation, Creativity, and Gameplay; Human-Likeness is evaluated separately.'''
+The tables below summarize performance across all 5 songs using 2 normalization methods: '''within-song normalization''' and '''across-song normalization'''. Overall scores are the equally weighted mean of the 5 per-song scores. '''Combined Quality includes Musical Representation, Creativity, and Gameplay; Human-Likeness is evaluated separately.'''
 ==== Within-song Normalization ====

← Older revision		Revision as of 15:59, 11 October 2026
Line 541:		Line 541:

	The tables below summarize performance across all 5 songs using 2 normalization methods: within-song normalization and across-song normalization. Overall scores are the equally weighted mean of the 5 per-song scores. Combined Quality includes Musical Representation, Creativity, and Gameplay; Human-Likeness is evaluated separately.		The tables below summarize performance across all 5 songs using 2 normalization methods: within-song normalization and across-song normalization. Overall scores are the equally weighted mean of the 5 per-song scores. Combined Quality includes Musical Representation, Creativity, and Gameplay; Human-Likeness is evaluated separately.
		+
		+	==== Within-song Normalization ====
		+
		+	{\| class="wikitable"
		+	! Model
		+	! Musical Representation
		+	! Creativity
		+	! Gameplay
		+	! Combined Quality
		+	! Human-Likeness
		+	\|-
		+	\| DOSU
		+	\| −1.8850
		+	\| −1.5620
		+	\| −0.4957
		+	\| −1.9416
		+	\| −1.6278
		+	\|-
		+	\| FumenLab
		+	\| '''1.4122'''
		+	\| '''1.4761'''
		+	\| 0.6217
		+	\| '''1.2576'''
		+	\| 0.8437
		+	\|-
		+	\| HiTaiko
		+	\| 1.0530
		+	\| −0.2570
		+	\| '''1.1337'''
		+	\| 1.1165
		+	\| '''2.4409'''
		+	\|-
		+	\| MALer
		+	\| −0.5802
		+	\| 0.3429
		+	\| −1.2597
		+	\| −0.4325
		+	\| −1.6567
		+	\|}
		+
		+	==== Across-song Normalization ====
		+
		+	{\| class="wikitable"
		+	! Model
		+	! Musical Representation
		+	! Creativity
		+	! Gameplay
		+	! Combined Quality
		+	! Human-Likeness
		+	\|-
		+	\| DOSU
		+	\| −1.8592
		+	\| −1.3766
		+	\| −0.6081
		+	\| −1.4305
		+	\| −1.5213
		+	\|-
		+	\| FumenLab
		+	\| '''1.4946'''
		+	\| '''1.5760'''
		+	\| '''0.8282'''
		+	\| '''1.5429'''
		+	\| 0.8177
		+	\|-
		+	\| HiTaiko
		+	\| 0.7580
		+	\| −0.4161
		+	\| 0.7907
		+	\| 0.3365
		+	\| '''1.9699'''
		+	\|-
		+	\| MALer
		+	\| −0.3934
		+	\| 0.2167
		+	\| −1.0107
		+	\| −0.4489
		+	\| −1.2663
		+	\|}

	== Community Evaluation Results ==		== Community Evaluation Results ==

@@ Line 340: / Line 340: @@
 == Expert Evaluation Results ==
-osu!taiko mappers evaluated submissions across 5 songs: '''Silver Bullet''', '''A fight in Tunisia''', '''YUBIKIRI-GENMAN''', '''Something Fun''', and '''closer to you'''. Each judge was assigned 3 songs based on their familiarity and interest of the songs, and each song was evaluated by 3 judges. For every assigned song, judges assessed submissions from all 4 models on 4 categories (Musical Representation, Creativity, Gameplay, and Human-Likeness) using an integer scale from 1 to 10. We follow [https://osu.ppy.sh/wiki/en/Contests/Monthly_Beatmapping_Contest Monthly Beatmapping Contest] and adopt '''within-song normalization''' for per-song report. For each category, judge X's final score = (judge X's raw score - judge X's average raw score) / judge X's standard deviation within that song, and a submission's score is the sum of each judge's final score.
+osu!taiko mappers evaluated submissions across 5 songs: '''Silver Bullet''', '''A fight in Tunisia''', '''YUBIKIRI-GENMAN''', '''Something Fun''', and '''closer to you'''. Each judge was assigned 3 songs based on their familiarity and interest of the songs, and each song was evaluated by 3 judges. For every assigned song, judges assessed submissions from all 4 models on 4 categories (Musical Representation, Creativity, Gameplay, and Human-Likeness) using an integer scale from 1 to 10.
 === Silver Bullet ===