Pith. sign in

Researcher Evidence Record

Zihang Xiang

This bounded record lists 12 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.LG, cs.CR work dated 2023 to 2025. 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.

Enumerated paper scope: 2 fields (cs.LG, cs.CR) · 2023-2025 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. 2025 Pith paper

    Tight Privacy Audit in One Run

    cs.CR provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 2 pith inbound references from cited_work_pith_inbound_counts
  2. 2025 Pith paper

    Beyond Ordinary Lipschitz Constraints: Differentially Private Stochastic Optimization with Tsybakov Noise Condition

    cs.LG provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  3. 2025 Pith paper

    FlashDP: Private Training Large Language Models with Efficient DP-SGD

    cs.LG provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  4. 2025 Pith paper

    Differentially Private Sparse Linear Regression with Heavy-tailed Responses

    cs.LG provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 1 pith inbound references from cited_work_pith_inbound_counts
  5. 2025 Pith paper

    Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness

    cs.LG provisional current review present

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    No source count is attached to this work row.
  6. 2025 Pith paper

    Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    4
    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. 2025 Pith paper

    Towards User-level Private Reinforcement Learning with Human Feedback

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    5
    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
  8. 2025 Pith paper

    Privacy Audit as Bits Transmission: (Im)possibilities for Audit by One Run

    cs.CR provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    1
    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
  9. 2024 Pith paper

    Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Approximate Unlearning Completeness

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    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
  10. 2024 Pith paper

    Revisiting Differentially Private Hyper-parameter Tuning

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    Author position
    1
    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
  11. 2023 Pith paper

    Differentially Private Non-convex Learning for Multi-layer Neural Networks

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    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
  12. 2023 Pith paper

    Practical Differentially Private and Byzantine-resilient Federated Learning

    cs.LG provisional measured, no current review

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Zihang Xiang
    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.

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 12 of 12 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 5 of 12 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 7 of 12 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 24 of 12 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
    Zihang Xiang
    backfill
    confidence 0.6
Enumerated research scope

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

  • cs.LG10 rows
  • cs.CR2 rows
  • 20232 rows
  • 20242 rows
  • 20258 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.