pith. sign in

arxiv: 1907.09745 · v1 · pith:LP73FQXUnew · submitted 2019-07-23 · 💻 cs.CY

Computing Lens for Exploring the Historical People's Social Network

Junjie Huang , Tiejian Luo This is my paper

Pith reviewed 2026-05-24 17:12 UTC · model grok-4.3

classification 💻 cs.CY
keywords social network analysishistorical figuressigned graphsgroup partition algorithmdigital humanitiesChina Biographical Databasepower rankingalliance detection
0
0 comments X

The pith

A signed graph model and custom partition algorithm extract power rankings and alliance camps from historical biographical records.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents a computational framework that models relationships among ancient figures as a signed graph, with edges indicating positive or negative ties, then applies a novel algorithm to divide the graph into camps and rank influence levels. This targets the problem of manually analyzing massive historical literature by using the China Biographical Database as input. The authors test the approach on a case study and report that the resulting partitions and rankings align with established historical facts and expert interpretations. If the method works as described, it offers social scientists a faster way to surface relationship structures from large digitized archives without exhaustive reading.

Core claim

The signed graph representation of historical relationships, processed by a novel group partition algorithm, yields power rankings and camp divisions on the CBDB dataset that are consistent with facts reported in the literature and with viewpoints held by social scientists.

What carries the argument

Signed graph model paired with a novel group partition algorithm that identifies camps and computes power rankings from biographical edge data.

If this is right

  • Social scientists gain a repeatable procedure for mapping influence networks across large biographical collections.
  • The outputs can serve as quantitative checks against qualitative historical narratives.
  • The same pipeline can be rerun on updated or expanded versions of the database to track changes in detected structures.
  • Results consistent with expert views support using the framework as an initial screen before deeper manual investigation.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the partitions hold up, the method could flag previously under-examined figures whose connections only become visible at scale.
  • The approach might transfer to other signed-network domains such as modern political or organizational conflict data.
  • Repeated application across different dynasties or regions could reveal recurring patterns in how alliance structures form or dissolve.

Load-bearing premise

The signed graph encoding and partition algorithm produce divisions and rankings that reflect actual historical relationships rather than artifacts of how the data was recorded or how the algorithm was designed.

What would settle it

Finding a well-documented historical case in which the algorithm's output camps or power order directly contradict primary-source evidence that was not used to build the graph.

Figures

Figures reproduced from arXiv: 1907.09745 by Junjie Huang, Tiejian Luo.

Figure 1
Figure 1. Figure 1: Logarithmic plot of the degree distribution showing that the degree distribution in the networks follows a power law. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 3
Figure 3. Figure 3: Wang Anshi (1021-1086) as the focus, the relationship between [PITH_FULL_IMAGE:figures/full_fig_p003_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: CLHPSoNet Workflow is showed in the Figure. It includes signed graph modeling, subgraph extraction, computing and visualize. The final output [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Input: People(Su Shi , Wang Anshi, Ouyang Xiu, Zeng Gong, Su [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 7
Figure 7. Figure 7: The Partition between Eight Great Prose Masters of Song [PITH_FULL_IMAGE:figures/full_fig_p006_7.png] view at source ↗
read the original abstract

A typical social research topic is to figure out the influential people's relationship and its weights. It is very tedious for social scientists to solve those problems by studying massive literature. Digital humanities bring a new way to a social subject. In this paper, we propose a framework for social scientists to find out ancient figures' power and their camp. The core of our framework consists of signed graph model and novel group partition algorithm. We validate and verify our solution by China Biographical Database Project (CBDB) dataset. The analytic results on a case study demonstrate the effectiveness of our framework, which gets information that consists with the literature's facts and social scientists' viewpoints.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript proposes a framework for social network analysis in historical contexts that combines a signed graph model with a novel group partition algorithm. The goal is to identify influential figures' power and camps from biographical data. The framework is applied to the China Biographical Database Project (CBDB) and its effectiveness is asserted via a case study whose outputs are described as consistent with established historical facts and social scientists' viewpoints.

Significance. If the signed-graph encoding and partition algorithm can be shown through quantitative means to recover genuine historical structures, the work would supply a scalable computational aid for digital humanities, allowing social scientists to extract relational insights from large biographical corpora without exhaustive manual review. The choice of signed graphs is appropriate for modeling positive and negative ties, but the current evidence does not yet establish this utility.

major comments (2)
  1. [Abstract] Abstract: The claim that analytic results on a case study demonstrate effectiveness rests solely on post-hoc qualitative consistency with literature and viewpoints, without any description of the signed-graph construction procedure, the novel partition algorithm, quantitative metrics, error analysis, or comparison to baselines. This is load-bearing for the central claim that the method produces partitions and power rankings that faithfully reflect historical relationships rather than encoding or algorithmic artifacts.
  2. [Case study] Case study validation: The only support offered is that results 'consist with' known facts; no independent ground-truth set, inter-annotator agreement on edge signs, or blinded evaluation is described. Because edge signs must be inferred from non-relational biographical fields, discretionary choices in encoding could drive the observed consistency, and this must be addressed for the central claim to hold.
minor comments (1)
  1. [Abstract] The phrasing 'gets information that consists with the literature's facts' is grammatically incorrect and should read 'produces information that is consistent with the literature's facts'.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive report. We address each major comment below and commit to revisions that strengthen the description of methods and validation approach without overstating the current evidence.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claim that analytic results on a case study demonstrate effectiveness rests solely on post-hoc qualitative consistency with literature and viewpoints, without any description of the signed-graph construction procedure, the novel partition algorithm, quantitative metrics, error analysis, or comparison to baselines. This is load-bearing for the central claim that the method produces partitions and power rankings that faithfully reflect historical relationships rather than encoding or algorithmic artifacts.

    Authors: The abstract is intentionally concise and does not detail the signed-graph construction or partition algorithm; those appear in the Methods section of the full manuscript. We agree that the abstract should summarize the procedures and will revise it to include a brief description of both. The validation remains qualitative, as no quantitative metrics, error analysis, or baselines are present in the work. We will add an explicit limitations paragraph acknowledging this and the risk that results could reflect modeling choices rather than historical structure. revision: yes

  2. Referee: [Case study] Case study validation: The only support offered is that results 'consist with' known facts; no independent ground-truth set, inter-annotator agreement on edge signs, or blinded evaluation is described. Because edge signs must be inferred from non-relational biographical fields, discretionary choices in encoding could drive the observed consistency, and this must be addressed for the central claim to hold.

    Authors: We agree that the case-study support is limited to qualitative consistency with known historical facts and that no ground-truth set, inter-annotator agreement, or blinded evaluation is provided. Edge signs are inferred from non-relational fields in CBDB, introducing possible discretionary choices. In revision we will expand the case-study section with an explicit account of the inference rules used for positive/negative edges and a discussion of how those choices could affect outcomes. We cannot retroactively create an independent ground-truth corpus, but the added transparency will allow readers to assess the risk of encoding artifacts. revision: partial

Circularity Check

0 steps flagged

No circularity detected; framework proposal lacks any derivation chain or equations.

full rationale

The paper proposes a signed-graph framework plus a novel partition algorithm, then validates it via qualitative consistency of one case study with existing literature. No equations, parameter fits, predictions, or derivation steps are described in the provided text. The central claim therefore does not reduce to its own inputs by construction, self-citation, or renaming; it is a computational method whose correctness is asserted by external (literary) agreement rather than internal equivalence. This is the normal non-circular outcome for a methods paper without a mathematical derivation.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Abstract-only review prevents full ledger construction. The framework rests on the unstated assumption that biographical records can be reliably encoded as signed edges without systematic bias.

axioms (1)
  • domain assumption Signed graph model accurately captures historical relationships from biographical text
    Core modeling choice stated in abstract as the basis of the framework.

pith-pipeline@v0.9.0 · 5626 in / 896 out tokens · 17327 ms · 2026-05-24T17:12:12.056813+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

25 extracted references · 25 canonical work pages · 2 internal anchors

  1. [1]

    Su shi’s association with wang anshi,

    L. Naichang, “Su shi’s association with wang anshi,” Journal of North- east Normal University: a Philosophy and Social Science Edition , no. 3, pp. 45–51, 1981

    work page 1981

  2. [2]

    The friendship between ouyang xiu and wang anshi,

    G. Yongxin, “The friendship between ouyang xiu and wang anshi,” Literary heritage, vol. 5, p. 016, 2001

    work page 2001

  3. [3]

    Sharing weal and woe and supporting each other - on friendship between su shi and wang gong,

    Y . Shihua and Z. Guangyu, “Sharing weal and woe and supporting each other - on friendship between su shi and wang gong,” Journal of Jiangsu University of Science and Technology (Social Science Edition) , vol. 13, no. 2, pp. 50–58, 2013

    work page 2013

  4. [4]

    Chro-ring: a time-oriented visual approach to represent writer’s history,

    Y . Zhu, J. Yu, and J. Wu, “Chro-ring: a time-oriented visual approach to represent writer’s history,” The Visual Computer , vol. 32, no. 9, pp. 1133–1149, 2016

    work page 2016

  5. [5]

    The china biographical database user’s guide,

    M. A. Fuller, “The china biographical database user’s guide,” 2015

    work page 2015

  6. [6]

    Tracking Words in Chinese Poetry of Tang and Song Dynasties with the China Biographical Database

    C.-L. Liu and K.-F. Luo, “Tracking words in chinese poetry of tang and song dynasties with the china biographical database,” arXiv preprint arXiv:1611.06320, 2016

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  7. [7]

    Flexible Computing Services for Comparisons and Analyses of Classical Chinese Poetry

    C.-L. Liu, “Flexible computing services for comparisons and analyses of classical chinese poetry,” arXiv preprint arXiv:1709.05729 , 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  8. [8]

    An investigation of the digitization of chinese genealogical records,

    X. Guo, “An investigation of the digitization of chinese genealogical records,” Taiwan University of Information Network and Multimedia Institute Dissertation, pp. 1–40, 2016

    work page 2016

  9. [9]

    Development of a text retrieval and mining system for taiwanese historical people,

    S.-H. Sie, H.-R. Ke, and S.-B. Chang, “Development of a text retrieval and mining system for taiwanese historical people,” in Pacific Neighbor- hood Consortium Annual Conference and Joint Meetings (PNC), 2017 . IEEE, 2017, pp. 56–62

    work page 2017

  10. [10]

    Signed networks in social media,

    J. Leskovec, D. Huttenlocher, and J. Kleinberg, “Signed networks in social media,” in Proceedings of the SIGCHI conference on human factors in computing systems . ACM, 2010, pp. 1361–1370

    work page 2010

  11. [11]

    Attitudes and cognitive organization,

    F. Heider, “Attitudes and cognitive organization,” The Journal of psy- chology, vol. 21, no. 1, pp. 107–112, 1946

    work page 1946

  12. [12]

    Easley and J

    D. Easley and J. Kleinberg, Networks, crowds, and markets: Reasoning about a highly connected world . Cambridge University Press, 2010

    work page 2010

  13. [13]

    An ils algorithm to evaluate structural balance in signed social networks,

    M. Levorato, L. Drummond, Y . Frota, and R. Figueiredo, “An ils algorithm to evaluate structural balance in signed social networks,” in Proceedings of the 30th Annual ACM Symposium on Applied Computing. ACM, 2015, pp. 1117–1122

    work page 2015

  14. [14]

    Local balancing influences global structure in social networks,

    A. Srinivasan, “Local balancing influences global structure in social networks,” Proceedings of the National Academy of Sciences , vol. 108, no. 5, pp. 1751–1752, 2011

    work page 2011

  15. [15]

    A partitioning approach to structural balance,

    P. Doreian and A. Mrvar, “A partitioning approach to structural balance,” Social networks, vol. 18, no. 2, pp. 149–168, 1996

    work page 1996

  16. [16]

    Partitioning signed social networks,

    ——, “Partitioning signed social networks,” Social Networks , vol. 31, no. 1, pp. 1–11, 2009

    work page 2009

  17. [17]

    Community detection in networks with positive and negative links,

    V . A. Traag and J. Bruggeman, “Community detection in networks with positive and negative links,”Physical Review E, vol. 80, no. 3, p. 036115, 2009

    work page 2009

  18. [18]

    Signed network embedding in social media,

    S. Wang, J. Tang, C. Aggarwal, Y . Chang, and H. Liu, “Signed network embedding in social media,” in Proceedings of the 2017 SIAM International Conference on Data Mining . SIAM, 2017, pp. 327–335

    work page 2017

  19. [19]

    node2vec: Scalable feature learning for networks,

    A. Grover and J. Leskovec, “node2vec: Scalable feature learning for networks,” in Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining . ACM, 2016, pp. 855–864

    work page 2016

  20. [20]

    Visualizing data using t-sne,

    L. v. d. Maaten and G. Hinton, “Visualizing data using t-sne,” Journal of machine learning research , vol. 9, no. Nov, pp. 2579–2605, 2008

    work page 2008

  21. [21]

    Deepwalk: Online learning of social representations,

    B. Perozzi, R. Al-Rfou, and S. Skiena, “Deepwalk: Online learning of social representations,” in Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining . ACM, 2014, pp. 701–710

    work page 2014

  22. [22]

    Gener- alizations of the clustering coefficient to weighted complex networks,

    J. Saram ¨aki, M. Kivel ¨a, J.-P. Onnela, K. Kaski, and J. Kertesz, “Gener- alizations of the clustering coefficient to weighted complex networks,” Physical Review E , vol. 75, no. 2, p. 027105, 2007

    work page 2007

  23. [23]

    A social network analysis of twitter: Mapping the digital humanities community,

    M. Grandjean, “A social network analysis of twitter: Mapping the digital humanities community,” Cogent Arts & Humanities , vol. 3, no. 1, p. 1171458, 2016

    work page 2016

  24. [24]

    Wasserman and K

    S. Wasserman and K. Faust, Social network analysis: Methods and applications. Cambridge university press, 1994, vol. 8

    work page 1994

  25. [25]

    Community structure in social and biological networks,

    M. Girvan and M. E. Newman, “Community structure in social and biological networks,” Proceedings of the national academy of sciences , vol. 99, no. 12, pp. 7821–7826, 2002

    work page 2002