Pith Number

pith:RFZR3QBS

pith:2023:RFZR3QBSBPJSZTMJWL5BRKQE7Z

not attested not anchored not stored refs resolved

AI Alignment: A Comprehensive Survey

Aidan O'Gara, Borong Zhang, Boyuan Chen, Brian Tse, Donghai Hong, Fanzhi Zeng, Hantao Lou, Hua Xu, Jiaming Ji, Jiayi Zhou, Jie Fu, Juntao Dai, Kaile Wang, Kwan Yee Ng, Lukas Vierling, Song-Chun Zhu, Stephen McAleer, Tianyi Qiu, Wen Gao, Xuehai Pan, Yaodong Yang, Yawen Duan, Yike Guo, Yizhou Wang, Zhaowei Zhang, Zhonghao He

AI alignment research can be structured around four principles and split into forward training versus backward assurance.

arxiv:2310.19852 v6 · 2023-10-30 · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{RFZR3QBSBPJSZTMJWL5BRKQE7Z}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We identify four principles as the key objectives of AI alignment: Robustness, Interpretability, Controllability, and Ethicality (RICE). Guided by these four principles, we outline the landscape of current alignment research and decompose them into two key components: forward alignment and backward alignment.

C2weakest assumption

That the four RICE principles comprehensively capture the essential objectives of AI alignment and that the forward/backward decomposition provides a useful, largely non-overlapping categorization of the existing literature.

C3one line summary

The paper surveys AI alignment by proposing the RICE principles and categorizing research into forward training-based alignment and backward assurance and governance approaches.

References

18 extracted · 18 resolved · 4 Pith anchors

[1] Rui Zheng, Wei Shen, Yuan Hua, Wenbin Lai, Shihan Dou, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Haoran Huang, Tao Gui, Qi Zhang, and Xuanjing Huang. 2024. Improving generalization of alignment with human pr 2024

[2] Stephan Zheng, Yang Song, Thomas Leung, and Ian Goodfellow. 2016. Improving the robustness of deep neural networks via stability training. In Proceedings of the ieee conference on computer vision and 2016

[3] Revisiting the Importance of Individual Units in CNNs via Ablation 2018 · arXiv:1806.02891

[4] Chunting Zhou, Pengfei Liu, Puxin Xu, Srinivasan Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, et al. 2024. Lima: Less is more for alignment.Advances in Neural Information Proce 2024

[5] Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, and Chen Change Loy. 2022. Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 2022

Formal links

2 machine-checked theorem links

Cited by

30 papers in Pith

The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems

Proof-of-Learning with Incentive Security

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

Revisiting Robustness for LLM Safety Alignment via Selective Geometry Control

MoralityGym: A Benchmark for Evaluating Hierarchical Moral Alignment in Sequential Decision-Making Agents

Receipt and verification

First computed	2026-05-17T23:38:13.826924Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

89731dc0320bd32ccd89b2fa18aa04fe7d12472eb6034ce52229d7b01d876ede

Aliases

arxiv: 2310.19852 · arxiv_version: 2310.19852v6 · doi: 10.48550/arxiv.2310.19852 · pith_short_12: RFZR3QBSBPJS · pith_short_16: RFZR3QBSBPJSZTMJ · pith_short_8: RFZR3QBS

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/RFZR3QBSBPJSZTMJWL5BRKQE7Z \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 89731dc0320bd32ccd89b2fa18aa04fe7d12472eb6034ce52229d7b01d876ede

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "71a187f0c4ce7bfd2c1937bf3c1f3edbe4d30a000688c961a7f23470d31deaa0",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2023-10-30T15:52:15Z",
    "title_canon_sha256": "cdaea1ef56d9f162173f93e128895eccd8b87d13027ab82760ec2de0f01c0492"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2310.19852",
    "kind": "arxiv",
    "version": 6
  }
}