PulseAugur
EN
LIVE 22:09:39
ENTITY Gavel

Gavel

PulseAugur coverage of Gavel — every cluster mentioning Gavel across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
2
6 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
5 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 7 TOTAL
  1. TOOL · CL_357782 ·

    New LLM-based system reconstructs clinical timelines with source-grounded adjudication

    Researchers have developed a new method for reconstructing clinical timelines from patient records, preserving unique identifiers for each event and its source. This approach aims to clarify the chronology of symptoms, …

  2. RESEARCH · CL_312648 ·

    New benchmark VerifierBench highlights AI agent verifier generation flaws · 3 sources tracked

    Researchers have introduced VerifierBench, a new benchmark designed to evaluate how well AI agents can generate executable verifiers for their own outputs. The benchmark includes 222 tasks across various domains, with n…

  3. TOOL · CL_254134 ·

    New GAVEL protocol uses LLMs to adjudicate clinical timeline discrepancies

    Researchers have developed GAVEL, a novel LLM judge protocol designed to compare clinical timelines extracted from case reports against the original reports themselves. This system aims to identify and adjudicate discre…

  4. RESEARCH · CL_252665 ·

    New LLM agent skill routing methods improve efficiency and diversity

    Researchers have developed new methods for LLM agents to select and utilize external skills more effectively. One approach, Gavel, uses a frozen LLM to elicit native skill routing by training only two linear maps, which…

  5. RESEARCH · CL_113543 ·

    Canadian lawyer fined $31K for AI fake citations; Relativity acquires Gavel

    A Canadian tribunal has ordered a lawyer to pay a substantial fine of $31,150 for using AI-generated fake case citations. In parallel, Relativity has acquired Gavel, a company specializing in AI-powered document automat…

  6. RESEARCH · CL_108136 ·

    New benchmarks and models advance image change captioning and segmentation

    Researchers are developing new methods for image change captioning and segmentation, aiming to improve the accuracy and detail of descriptions for paired images. Several new frameworks and benchmarks are being introduce…

  7. RESEARCH · CL_11754 ·

    GAVEL framework introduces rule-based AI safety via activation monitoring

    Researchers have introduced GAVEL, a novel framework for enhancing AI safety through rule-based activation monitoring. This approach models LLM activations as fine-grained "cognitive elements" that can be composed into …