Where Do Your Citations Come From? Citation-Constellation: A Free, Open-Source, No-Code, and Auditable Tool for Citation Network Decomposition with Complementary BARON and HEROCON Scores
Authors: Mahbub Ul Alam
Organizations: SciLifeLab Data Centre, Uppsala University, Sweden
Standard citation metrics treat all citations as equal, obscuring the social and structural pathways through which scholarly influence propagates. I introduce Citation-Constellation, a freely available no-code tool for citation network analysis with two complementary bibliometric scores that decompose a researcher's citation profile by network proximity between citing and cited authors. BARON (Boundary-Anchored Research Outreach Network score) is a strict binary metric counting only citations from outside the detected collaborative network. HEROCON (Holistic Equilibrated Research Outreach CONstellation score) applies graduated weights assigning partial credit to in-group citations based on relationship proximity. The gap between scores serves as a diagnostic of inner-circle dependence. An extended abstract with full details appears in the paper. The tool implements this through a phased architecture: (1) self-citation analysis, (2) co-authorship graph traversal, (3) temporal institutional affiliation matching via ROR, and (4) AI-agent-driven venue governance extraction using a local LLM. Phases 1-3 are fully operational; Phase 4 is under development. Key design choices include ORCID-validated author identity resolution, an UNKNOWN classification for citations with insufficient metadata, and comprehensive audit trails documenting every classification decision. A no-code web interface enables researchers to compute scores without programming, installation, or registration. I present these scores as structural diagnostics, not quality indicators. BARON and HEROCON describe where in the social graph citations originate. They should not be used for hiring, promotion, or funding decisions. HEROCON weights are experimental and require empirical calibration.
Figures & tables
Figure 1
Flag
Description
--export results.json
Export summary to JSON
--trajectory or -t
Show cumulative career trajectory by year
--since 2010
Only include works from 2010 onward
--depth 1|2|3
Co-author graph depth (default 2)
--herocon-weights file.json
Custom HEROCON weight configuration
--confirm or -c
Review ORCID-flagged works interactively before scoring
Table 1: Common flags for command-line interface
Component
Purpose
Link
Citation-Constellation
BARON & HEROCON scoring
No-Code Tool | Code
Citation-Pulsar-Helm
LLM inference on Kubernetes
Code
Citation-Astrolabe
Venue governance database
Code
Table 2: The Citation-Cosmograph ecosystem on GitHub.
Phase
Detection Layers
Classes
BARON
HEROCON
1
Self-citation
2
High
—
2
+ Co-author network
4
Moderate
Moderate-High
3
+ Affiliation matching
7
Lower
Moderate
Table 3: Score progression across phases
Figure 1: Ethical notice displayed at the top of every analysis output.
Figure 2: Score panel in both interfaces.
Figure 3: Classification breakdown donut chart.
Figure 4: Co-author network graph (overview).
Figure 5: Co-author network graph (detail).
Figure 6: Classification summary in both interfaces.
Figure 7: Career trajectory chart in both interfaces.
Figure 8: Full citation table from the audit trail.
Figure 9: Comparison table.
Figure 10: BARON trajectory comparison.
Figure 11: HEROCON trajectory comparison.
Figure 12: Individual reports within the comparison view.
Very low credit; strongest proximity without co-authorship
3b
Same institution, different dept
0
0.4
Moderate credit; cross-departmental
3c
Same parent organization
0
0.7
High credit; tenuous institutional link
Table 4: Conceptualizing scoring for a researcher’s citation profile as concentric network layers.
Figure 14: Phased implementation architecture. Phases 1–3 are complete and available via CLI and web interface. Phase 4 (venue governance via local LLM) is under development. Phase 5 (field normalization) is planned.
Tool
Primary Function
Per-Citation Decomposition
Network Scoring
Free & Open
Audit Trail
VOSviewer
Field-level network visualization
No
No
Yes (free)
No
CiteSpace
Research front detection & trends
No
No
Yes (free)
No
Bibliometrix
Comprehensive science mapping (R)
No
No
Yes (open-source)
No
Connected Papers
Literature discovery from seed paper
No
No
Freemium
No
ResearchRabbit
Citation/co-authorship exploration
No
No
Yes (free)
No
Litmaps
Citation timeline & monitoring
No
No
Freemium
No
Table 5: Comparison of bibliometric tools.
Figure 15: Development roadmap. Phase 4 introduces venue governance detection via a three-tool ecosystem (Pulsar, Astrolabe, Constellation). Phase 5 adds field normalization and comparative analytics. Phase 6 focuses on empirical validation and multi-source data fusion.