Pith. sign in

Researcher Evidence Record

Songyang Gao

This bounded record lists 33 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.CL, cs.AI, cs.LG work dated 2022 to 2026. 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 33 attributed paper rows in the Pith corpus, itemized below Imported works 0 imported works beyond the paper ledger Current reviews 6 of 33 papers carrying a current Pith review; presence, not outcome Sourced citations 18 of 33 works with a source-named citation count Coauthors 50 distinct coauthors across shared paper rows
Enumerated paper scope: 4 fields (cs.CL, cs.AI, cs.LG, +1 more) · 2022-2026 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. 2026 Pith paper

    Group Entropy-Controlled Policy Optimization

    cs.CL provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  2. 2026 Pith paper

    ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning

    cs.AI provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  3. 2026 Pith paper

    Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation

    cs.CL provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Songyang Gao
    Author position
    1
    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. 2026 Pith paper

    EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    backfill
    Printed name
    Songyang Gao
    Author position
    7
    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

    Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving

    cs.CL provisional current review present

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    2
    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

    CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 4 pith inbound references from cited_work_pith_inbound_counts
  7. 2025 Pith paper

    Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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
  8. 2025 Pith paper

    A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 6 pith inbound references from cited_work_pith_inbound_counts
  9. 2025 Pith paper

    Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 3 pith inbound references from cited_work_pith_inbound_counts
  10. 2024 Pith paper

    Are Your LLMs Capable of Stable Reasoning?

    cs.AI provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    6
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 6 pith inbound references from cited_work_pith_inbound_counts
  11. 2024 Pith paper

    Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    2
    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.
  12. 2024 Pith paper

    AgentGym: Evolving Large Language Model-based Agents across Diverse Environments

    cs.AI provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    11
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 9 pith inbound references from cited_work_pith_inbound_counts
  13. 2024 Pith paper

    Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 4 pith inbound references from cited_work_pith_inbound_counts
  14. 2024 Pith paper

    The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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
  15. 2024 Pith paper

    EasyJailbreak: A Unified Framework for Jailbreaking 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
    Songyang Gao
    Author position
    12
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 9 pith inbound references from cited_work_pith_inbound_counts
  16. 2024 Pith paper

    ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 3 pith inbound references from cited_work_pith_inbound_counts
  17. 2024 Pith paper

    Navigating the OverKill in Large Language Models

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  18. 2024 Pith paper

    Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  19. 2024 Pith paper

    RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    3
    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.
  20. 2024 Pith paper

    Secrets of RLHF in Large Language Models Part II: Reward Modeling

    cs.AI provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    11
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 22 pith inbound references from cited_work_pith_inbound_counts
  21. 2024 Pith paper

    ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 3 pith inbound references from cited_work_pith_inbound_counts
  22. 2023 Pith paper

    LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 12 pith inbound references from cited_work_pith_inbound_counts
  23. 2023 Pith paper

    RealBehavior: A Framework for Faithfully Characterizing Foundation Models' Human-like Behavior Mechanisms

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  24. 2023 Pith paper

    TRACE: A Comprehensive Benchmark for Continual Learning 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
    Songyang Gao
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 18 pith inbound references from cited_work_pith_inbound_counts
  25. 2023 Pith paper

    Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Tasks

    cs.SD provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    2
    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.
  26. 2023 Pith paper

    Secrets of RLHF in Large Language Models Part I: PPO

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 22 pith inbound references from cited_work_pith_inbound_counts
  27. 2023 Pith paper

    On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  28. 2023 Pith paper

    DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  29. 2023 Pith paper

    Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 4 pith inbound references from cited_work_pith_inbound_counts
  30. 2023 Pith paper

    Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 3 pith inbound references from cited_work_pith_inbound_counts
  31. 2023 Pith paper

    CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  32. 2022 Pith paper

    Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Songyang Gao
    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.
  33. 2022 Pith paper

    Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective

    cs.CL provisional measured, no current review

    paper paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    SongYang Gao
    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.

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 33 of 33 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 6 of 33 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 18 of 33 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 50 of 33 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
    Songyang Gao     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.CL27 rows
  • cs.AI4 rows
  • cs.LG1 rows
  • cs.SD1 rows
  • 20222 rows
  • 202310 rows
  • 202412 rows
  • 20255 rows
  • 20264 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.