What is recorded here?
Mined hard negatives from an approximate nearest-neighbor index of the corpus while a parallel inferencer periodically re-encoded documents and refreshed the index from newer training checkpoints.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Asynchronous refresh permits stale negatives and incurs re-encoding/index costs; it does not exactly eliminate every train-test distribution gap. Uses inherited encoders, nearest-neighbor search and contrastive losses. Source speedups depend on baselines and workload, not unconditional100x acceleration.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Lee Xiong; Chenyan Xiong; Ye Li; Kwok-Fung Tang; Jialin Liu; Paul Bennett; Junaid Ahmed; Arnold Overwijk
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
ANCE: asynchronously refreshed corpus negatives for dense retrieval
Mined hard negatives from an approximate nearest-neighbor index of the corpus while a parallel inferencer periodically re-encoded documents and refreshed the index from newer training checkpoints.
Scientific scope
Asynchronous refresh permits stale negatives and incurs re-encoding/index costs; it does not exactly eliminate every train-test distribution gap. Uses inherited encoders, nearest-neighbor search and contrastive losses. Source speedups depend on baselines and workload, not unconditional100x acceleration.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Lee Xiong; Chenyan Xiong; Ye Li; Kwok-Fung Tang; Jialin Liu; Paul Bennett; Junaid Ahmed; Arnold Overwijk
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.