Pith. sign in

Researcher Evidence Record

Saurav Kadavath

This bounded record lists 14 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.CL, cs.LG, cs.AI work dated 2019 to 2023. The record describes sources and coverage; it makes no judgment about the person.

Compiled coverage vector

Measured lane counts only. Not a trust score or person verdict.

Identity 2 canonical identity row plus typed public identifiers Pith papers 14 attributed paper rows in the Pith corpus, itemized below Imported works 0 imported works beyond the paper ledger Current reviews 8 of 14 papers carrying a current Pith review; presence, not outcome Sourced citations 12 of 14 works with a source-named citation count Coauthors 50 distinct coauthors across shared paper rows
Enumerated paper scope: 5 fields (cs.CL, cs.LG, cs.AI, +2 more) · 2019-2023 sources: authors, author_identifiers · paper_authors · author_works · current_verdicts · cited_works

A sourced case file for attributed work. It is neither a profile score nor a verdict about this researcher.

Attributed works

A bounded ledger from the Pith paper and imported-work queries. Counts and source confidence stay with each work.

  1. 2023 Pith paper

    Specific versus General Principles for Constitutional AI

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 5 pith inbound references from cited_work_pith_inbound_counts
  2. 2023 Pith paper

    Measuring Faithfulness in Chain-of-Thought Reasoning

    cs.AI provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    20
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 147 pith inbound references from cited_work_pith_inbound_counts
  3. 2023 Pith paper

    The Capacity for Moral Self-Correction in Large Language Models

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    31
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 15 pith inbound references from cited_work_pith_inbound_counts
  4. 2022 Pith paper

    Discovering Language Model Behaviors with Model-Written Evaluations

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    10
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 44 pith inbound references from cited_work_pith_inbound_counts
  5. 2022 Pith paper

    Constitutional AI: Harmlessness from AI Feedback

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 531 pith inbound references from cited_work_pith_inbound_counts
  6. 2022 Pith paper

    DeepChrome 2.0: Investigating and Improving Architectures, Visualizations, & Experiments

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  7. 2022 Pith paper

    Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 147 pith inbound references from cited_work_pith_inbound_counts
  8. 2022 Pith paper

    Language Models (Mostly) Know What They Know

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 323 pith inbound references from cited_work_pith_inbound_counts
  9. 2022 Pith paper

    Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    12
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 479 pith inbound references from cited_work_pith_inbound_counts
  10. 2021 Pith paper

    Pretraining & Reinforcement Learning: Sharpening the Axe Before Cutting the Tree

    cs.LG provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  11. 2021 Pith paper

    Measuring Coding Challenge Competence With APPS

    cs.SE provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 76 pith inbound references from cited_work_pith_inbound_counts
  12. 2021 Pith paper

    Measuring Mathematical Problem Solving With the MATH Dataset

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 462 pith inbound references from cited_work_pith_inbound_counts
  13. 2020 Pith paper

    The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization

    cs.CV provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  14. 2019 Pith paper

    Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

    cs.LG provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Saurav Kadavath
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts

Evidence apparatus

The machinery behind this record. Every lane states whether Pith measured it, did not query it, could not reach it, or withheld it.

LaneStateObservedBoundary and source
identity Measured 2 Canonical identity row plus public typed identifiers.
source=authors, author_identifiers
papers Measured 14 of 14 bounded rows Rows attributed to this author UUID in the Pith corpus.
source=paper_authors
works Measured zero 0 of 0 bounded rows Imported works not duplicated by the paper ledger.
source=author_works
reviews Measured 8 of 14 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 12 of 14 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 50 of 14 bounded rows Shared-work edges from admitted paper rows.
source=paper_authors
account Unavailable No public count of 1 bounded rows Account metadata is separate from corpus evidence.
source=users.author_id
Public identity sources
  • name variant
    Saurav Kadavath     backfill
    confidence 0.6

identity history

Enumerated research scope

Fields and dates come only from enumerated, non-disputed Pith paper rows. They do not claim career completeness.

  • cs.CL7 rows
  • cs.LG4 rows
  • cs.AI1 rows
  • cs.CV1 rows
  • cs.SE1 rows
  • 20191 rows
  • 20201 rows
  • 20213 rows
  • 20226 rows
  • 20233 rows
Shared-work index
Record scope

The work queries are bounded. Missing rows may mean measured zero, an unavailable source, a query that did not run, or private data that Pith withheld. The lane table keeps those cases separate.

Paper findings remain attached to papers. They do not become findings about this researcher.