REVIEW 6 cited by
Efficient Code Embeddings from Code Generation Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Efficient Code Embeddings from Code Generation Models
read the original abstract
jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages. It makes innovative use of an autoregressive backbone pre-trained on both text and code, generating embeddings via last-token pooling. We outline the training recipe and demonstrate state-of-the-art performance despite the relatively small size of the models, validating this approach to code embedding model construction.
Forward citations
Cited by 6 Pith papers
-
CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding
CORE-Bench is a benchmark for code retrieval in agentic coding settings, built from curated tasks and SWE-bench instances, showing performance drops and gains from fine-tuning.
-
CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding
Existing embedding models drop sharply from traditional code search to requirement-driven repository retrieval, while in-domain PR fine-tuning substantially improves Level-2/3 performance on CORE-Bench.
-
Can LLMs Deobfuscate Binary Code? A Systematic Analysis of Large Language Models into Pseudocode Deobfuscation
LLM deobfuscation of binaries to pseudocode depends more on reasoning ability and task-specific fine-tuning than on model size, with reasoning models showing robustness across ISAs and obfuscation levels on the new Bi...
-
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents
A per-commit multi-view repository-index system with incremental updates that match independent rebuilds at 8.7x/25.4x median speedups, and context policies that cut agent trajectory tokens 50-87% while holding locali...
-
Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents
A 427-sample workflow-grounded benchmark finds complementary strengths across lexical, structural, and embedding retrieval for coding-agent context acquisition, with large residual miss rates and a selective-abstentio...
-
MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation
MARS² integrates multi-agent collaboration with tree-structured search in RL to boost code generation by increasing exploratory diversity and using path-level group advantages for credit assignment.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.