Pith Number

pith:I345H75Q

pith:2017:I345H75Q2A5BN6ZUDPV3VWAOUC

not attested not anchored not stored refs resolved

Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

Caiming Xiong, Richard Socher, Victor Zhong

Seq2SQL translates natural language questions into SQL queries by combining structured generation with reinforcement learning rewards from database executions, reaching 59.4 percent execution accuracy.

arxiv:1709.00103 v7 · 2017-08-31 · cs.CL · 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{I345H75Q2A5BN6ZUDPV3VWAOUC}

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

By applying policy-based reinforcement learning with a query execution environment to WikiSQL, our model Seq2SQL outperforms attentional sequence to sequence models, improving execution accuracy from 35.9% to 59.4% and logical form accuracy from 23.4% to 48.3%.

C2weakest assumption

That rewards obtained by executing generated queries on the database provide a sufficiently dense and stable training signal for the policy, especially for the unordered components of SQL.

C3one line summary

Seq2SQL uses deep learning plus reinforcement learning to generate SQL from natural language, reaching 59.4% execution accuracy on the new WikiSQL dataset of 80k examples.

References

43 extracted · 43 resolved · 1 Pith anchors

[1] I. Androutsopoulos, G.D. Ritchie, and P. Thanisch. Natural language interfaces to databases - an introduction. 1995 1995

[2] Yoav Artzi and Luke S. Zettlemoyer. Bootstrapping semantic parsers from conversations. In EMNLP, 2011 2011

[3] Yoav Artzi and Luke S. Zettlemoyer. Weakly supervised learning of semantic parsers for mapping instructions to actions. TACL, 1: 0 49--62, 2013 2013

[4] A new database on the structure and development of the financial sector 2000

[5] Le, Mohammad Norouzi, and Samy Bengio 2017

Cited by

61 papers in Pith

Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows

ChartWalker: Benchmarking the Cross-Chart RAG Task with Hierarchical Knowledge Graphs

The Table Says Otherwise: Testing LLMs with Counterfactual Relational Data

Text2DSL: LLM-Based Code Generation for Domain-Specific Languages

Strategic Decision Support for AI Agents

Receipt and verification

First computed	2026-07-04T22:19:56.633883Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

46f9d3ffb0d03a16fb341bebbad80ea0a47b4062b97061407c38783053958c4b

Aliases

arxiv: 1709.00103 · arxiv_version: 1709.00103v7 · doi: 10.48550/arxiv.1709.00103 · pith_short_12: I345H75Q2A5B · pith_short_16: I345H75Q2A5BN6ZU · pith_short_8: I345H75Q

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/I345H75Q2A5BN6ZUDPV3VWAOUC \
  | 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: 46f9d3ffb0d03a16fb341bebbad80ea0a47b4062b97061407c38783053958c4b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "634462eb8ea9f932ce45f70ef44f9c4918af5f660aadc44e312a5c09d7767d75",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2017-08-31T23:12:15Z",
    "title_canon_sha256": "1a5ccd4fc7bdb0c7f10e9cb3ff6460df4ab865e742bccf6b281a0bf23dd02796"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1709.00103",
    "kind": "arxiv",
    "version": 7
  }
}