pith. machine review for the scientific record. sign in
Pith Number

pith:CSY654CR

pith:2025:CSY654CRWD64OIPFZ2LWXPSWC2
not attested not anchored not stored refs resolved

Phi-4-reasoning Technical Report

Ahmed Awadallah, Arindam Mitra, Besmira Nushi, Caio C\'esar Teodoro Mendes, Dimitris Papailiopoulos, Guoqing Zheng, Gustavo de Rosa, Harkirat Behl, Lingjiao Chen, Marah Abdin, Mojan Javaheripi, Neel Joshi, Olli Saarikivi, Piero Kauffmann, Safoora Yousefi, Sahaj Agarwal, Shital Shah, Suriya Gunasekar, Vaishnavi Shrivastava, Vibhav Vineet, Vidhisha Balachandran, Yash Lara, Yue Wu

A 14-billion parameter model trained on curated teachable prompts and o3-mini demonstrations reaches performance levels of much larger reasoning systems.

arxiv:2504.21318 v1 · 2025-04-30 · cs.AI · cs.CL

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open

Claims

C1strongest claim

Across a wide range of reasoning tasks, both models outperform significantly larger open-weight models such as DeepSeek-R1-Distill-Llama-70B model and approach the performance levels of full DeepSeek-R1 model.

C2weakest assumption

That the performance improvements stem primarily from the curated 'teachable' prompts and o3-mini demonstrations rather than from undisclosed details of the base Phi-4 model, evaluation choices, or overlap with the teacher model's training data.

C3one line summary

A 14B reasoning model trained via supervised fine-tuning on selected prompts and o3-mini traces, plus outcome RL, outperforms larger open models like DeepSeek-R1-Distill-Llama-70B on math, coding, planning and related benchmarks.

References

64 extracted · 64 resolved · 20 Pith anchors

[1] Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone 2024 · arXiv:2404.14219
[2] Phi-4 Technical Report 2024 · arXiv:2412.08905
[3] KITAB: evaluating llms on constraint satisfaction for information retrieval 2024
[4] AIME. Aime 83-24. https://huggingface.co/datasets/lchen001/AIME1983_2024, 2024. Accessed: 2025- 03-17 2024
[5] AIME. Aime 2025. https://huggingface.co/datasets/lchen001/AIME2025, 2025. Accessed: 2025-03-17 2025

Formal links

2 machine-checked theorem links

Cited by

19 papers in Pith

Receipt and verification
First computed2026-05-17T23:38:15.236139Z
Builderpith-number-builder-2026-05-17-v1
SignaturePith Ed25519 (pith-v1-2026-05) · public key
Schemapith-number/v1.0

Canonical hash

14b1eef051b0fdc721e5ce976bbe56168c5f4b9b3db39f240432fa7349969614

Aliases

arxiv: 2504.21318 · arxiv_version: 2504.21318v1 · doi: 10.48550/arxiv.2504.21318
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CSY654CRWD64OIPFZ2LWXPSWC2 \
  | 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: 14b1eef051b0fdc721e5ce976bbe56168c5f4b9b3db39f240432fa7349969614
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "34014de1e10e2d80b34c097e7349a5a05a3af62c4f55a5452f4ea11ba606fe0f",
    "cross_cats_sorted": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-04-30T05:05:09Z",
    "title_canon_sha256": "88aed280d7a9e33a84ea4a72eb25e0c5b88ae04d91c643a83976bc6cae82e7f8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2504.21318",
    "kind": "arxiv",
    "version": 1
  }
}