Datasets:

DJLougen
/

Acta

conversations listlengths 2 14	source stringclasses 5 values	quality_score float64 0.55 1	semantic_diversity float64 0.35 0.93	lexical_diversity float64 0.3 0.91	verb_diversity float64 0.29 1
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.900243	0.546584	0.4	0.75
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.783205	0.411905	0.320611	0.480769
[ { "content": "You are a senior software engineer capable of understanding and fixing complex bugs, implementing new features, and refactoring code. You have access to tools for reading, writing, and testing code.", "role": "assistant" }, { "content": "Fix issue getmoto__moto.694ce1f4.pr_5134", "...	flamefox_agentic	0.7625	0.916667	0.864865	1
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.878615	0.508621	0.385475	0.634615
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.858583	0.469208	0.376448	0.612903
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.810525	0.443396	0.356108	0.588235
[ { "content": "You are a senior software engineer capable of understanding and fixing complex bugs, implementing new features, and refactoring code. You have access to tools for reading, writing, and testing code.", "role": "assistant" }, { "content": "Fix issue pandas-dev__pandas.95280573.pr_57488",...	flamefox_agentic	0.7625	0.932331	0.905923	1
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.874035	0.484919	0.398714	0.596491
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.887547	0.515406	0.400735	0.55
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.83406	0.380952	0.313324	0.508772
[ { "content": "You are a senior software engineer capable of understanding and fixing complex bugs, implementing new features, and refactoring code. You have access to tools for reading, writing, and testing code.", "role": "assistant" }, { "content": "Fix issue Project-MONAI__MONAI.a09c1f08.pr_4728"...	flamefox_agentic	0.7625	0.92	0.868421	1
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.756894	0.36755	0.301038	0.526316
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.828657	0.37886	0.301997	0.408759
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.92544	0.569492	0.43913	0.764706
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.870593	0.43131	0.352201	0.526316
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.810356	0.412389	0.315068	0.596154
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.90358	0.476773	0.387312	0.45
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.891079	0.515244	0.409736	0.585366
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.893839	0.453846	0.386842	0.625
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.897102	0.475	0.372964	0.666667
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.759982	0.375712	0.300254	0.54717
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.905373	0.482517	0.385809	0.465116
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.860153	0.411268	0.346979	0.452381
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.857175	0.411765	0.339015	0.588235
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.825863	0.463801	0.373199	0.72973
[ { "content": "You are a senior software engineer capable of understanding and fixing complex bugs, implementing new features, and refactoring code. You have access to tools for reading, writing, and testing code.", "role": "assistant" }, { "content": "Fix issue seperman__deepdiff.ed252022.lm_rewrite...	flamefox_agentic	0.7625	0.916667	0.864865	1
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.788381	0.368976	0.305352	0.375
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.918361	0.513196	0.386322	0.595238
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.888964	0.452962	0.375576	0.633333
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.923551	0.485981	0.427646	0.575758
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.929233	0.508121	0.41879	0.571429
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.759672	0.375	0.300221	0.484848
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_reasoning	0.880826	0.510417	0.38913	0.72
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.814594	0.414873	0.323077	0.390805
[ { "content": "You are a senior software engineer capable of understanding and fixing complex bugs, implementing new features, and refactoring code. You have access to tools for reading, writing, and testing code.", "role": "assistant" }, { "content": "Fix issue cantools__cantools.0c6a7871.combine_mo...	flamefox_agentic	0.7625	0.608108	0.521739	0.9
[ { "content": "You are a senior software engineer capable of understanding and fixing complex bugs, implementing new features, and refactoring code. You have access to tools for reading, writing, and testing code.", "role": "assistant" }, { "content": "Fix issue kayak__pypika.1c9646f0.lm_rewrite__kih...	flamefox_agentic	0.7625	0.6	0.540541	0.909091
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.884499	0.447761	0.36983	0.72
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	hermes_multiturn	0.871173	0.430876	0.354103	0.574468
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.820982	0.414179	0.339768	0.458333
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.857114	0.432596	0.317164	0.693878
[ { "content": "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </th...	flamefox_agentic	0.838589	0.447837	0.348726	0.552632

End of preview. Expand in Data Studio

Acta

Acta (Latin: "acts, deeds, records") - A premium curated sample of high-quality agentic tool-use conversations, filtered using an 8-factor quality model based on statistical correlation analysis of diversity metrics.

Overview

This public sample contains 5,000 conversations from the full 37K Acta dataset. It was created by analyzing 5 major agentic datasets (FlameFox, Hermes Reasoning, Hermes Multi-turn, Smolagents, SWE Agent) and applying evidence-based quality filters to maximize training signal density.

Key Statistics:

Train: 4,500 samples
Validation: 500 samples
Avg semantic diversity: 0.53
Avg lexical diversity: 0.47
Sources: 5 datasets harmonized

The 8-Factor Quality Model

Each sample was scored using 8 factors weighted by their correlation with training quality:

Factor	Weight	Threshold	Rationale
Lexical Diversity	0.25	>=0.35	unique_words / total_words (r=+0.967 with quality)
Semantic Diversity	0.20	>=0.40	content richness excluding stopwords (r=+0.947)
Verb Uniqueness	0.15	>=0.01	unique_verbs / total_verbs (r=+0.852)
Turn Efficiency	0.15	2-12 turns	Optimal conversation length (longer = repetitive)
Tool Pattern Novelty	0.10	-	Penalty for over-represented tool sequences
Reasoning Density	0.08	-	Thinking blocks per assistant turn
Role Balance	0.05	-	User/assistant turn ratio
Content Brevity	0.02	-	Information density (shorter = denser signal)

Source Distribution

Source	Samples	Avg Quality	Characteristics
FlameFox Agentic	~2,600	0.819	Highest diversity, balanced tools
Hermes Reasoning	~1,400	0.598	Good semantic diversity
Hermes Multi-turn	~450	0.534	Multi-turn, deduplicated
Smolagents Code	~70	0.592	Low redundancy
SWE Agent GLM	~20	0.433	Shortest, least repetitive traces

Usage

from datasets import load_dataset

# Load the curated sample
dataset = load_dataset("DJLougen/Acta")

# Access quality metrics
sample = dataset["train"][0]
print(sample["quality_score"])  # 0.0 - 1.0
print(sample["semantic_diversity"])  # 0.546
print(sample["lexical_diversity"])  # 0.400

Key Findings

Quality ≠ Quantity - 37K curated samples > 200K raw samples
Lexical diversity is the strongest quality predictor (r=+0.967)
More content ≠ better signal - SWE Agent has 5x more text but 3x lower quality
4-10 turns optimal - longer conversations become repetitive (r=-0.982)
Tool redundancy is rampant - some patterns repeat 3000+ times in raw data

Citation

@dataset{acta_2026,
  title = {Acta: A Quality-Curated Agentic Tool-Use Dataset},
  author = {Lougen, Daniel},
  year = {2026},
  url = {https://huggingface.co/datasets/DJLougen/Acta}
}

License

Apache 2.0

Acknowledgments

Source datasets:

Full 37K proprietary dataset: DJLougen/Acta-Proprietary

Downloads last month: 36