InterSci-Grad: researcher-controlled graduate planning and literature workflows
InterSci-Grad documents graduate research planning from question selection and literature matrices to experiment cards and supervisor discussions. Its literature workflow keeps interpretation with the researcher and requires checking references and data; experiment cards specify controls, stopping criteria and failure evidence. This is intended L2 research planning and synthesis support, not automated study execution or demonstrated academic benefit.
L2Research workflow (workflow level, not a quality rating) Source: Repository-documented Outcome: Not empirically evaluated here
Research applicability
Pinned core skill, graduate playbook and integrity guidance document substantive research assistance with source/evidence distinctions and author checks. Recommend bounded intended planning/literature process; examples and reported tests are not empirical outcomes.
Getting started
Editorial untested suggestion: read pinned primary documentation; define an appropriate non-sensitive task and researcher verification before separately considering execution.
Maintenance
Dated source snapshot only; present availability, maintenance and version parity require separate checks.
License
Source visibility is not reuse clearance; source/model/data licenses and rights require separate checking.
Workflow & human oversight
Scope: Source-described intended research-use process only; not observed execution, research quality or demonstrated outcomes Human control: Skill excludes replacing user decisions; integrity guidance conditions AI literature matrices on user checking. Sources/data are author-verified and supervisor/institutional rules retain authority. No actual human editorial review of this packet implied. Stage connections: Researcher-directed literature selection and source checking feed synthesis/gap definition and proposed study planning. Seven menu modes do not by themselves prove autonomous end-to-end research execution. Stopping: Playbook offers a ten-paper novelty-saturation reading heuristic and asks experiment cards to set count/time stops and failure criteria. These are guidance, not validated stopping policies or executed trials. Missing evidence: No live host/model integration, underlying example-citation validation, graduate outcomes or author-reported test runs independently checked.
Workflow level is not an evidence score; higher is not better evidence.
Approach
- Suggest scoped research options, structure literature reading/matrices and proposed experiment plans, support supervisor/reviewer communication
Outcomes (as reported by the originating team)
Documented method or intended capability; no empirical research benefit established by this review.
Limitations
- Examples use demonstrative topics/data/results; source claim of real references was not independently checked. - Reported165tests and162offlinepass/3skip are documentation claims; no tests executed or results adopted as research benefit. - Core no-API-key claim concerns skill/tool dependencies and does not guarantee free/credential-free model hosting. - Fixed reading-time/percentage/saturation numbers are source heuristics, not empirically validated general research rules. - No school/venue acceptance, novelty, publication or degree outcome promised. - AI editorial review only; no human editorial verification claimed.
Reproducibility
AI editorial source review only. No candidate code, model, agent, experiment or reported outcome independently executed or reproduced.
Adoption requirements
Editorial suggestions, untested: inspect selected module rights, source/version, environment and private-data boundaries before separately authorised adoption. This pass installs or invokes nothing.
Comments
No comments yet.
Add a comment
Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.