multi-stage-cascade-extraction
Skill1 starsChanged 3 months agoApache-2.0View on GitHub
Run a multi-stage extraction cascade (mention detection, document-level coreference clustering, optional saliency judgment, N-ary relation/triple extraction) directly over a paper's full text — covers SciERC, SciREX, and NLP Contribution Graph. Use this whenever cross-sentence or document-level entity/relation extraction is needed (e.g. SciREX-style Task-Dataset-Metric-Score tuples); do NOT use unit-classification for this, since these methods reason over the whole document's mentions, not independently-classified sentence units.
In this repository34 other files it gives its agents.
- acu-nugget-recallSkill
- argumentative-zoningSkill
- atomic-unit-matchingSkill
- atomic-unit-recall-aggregateSkill
- atomic-unit-writingSkill
- claim-label-predictionSkill
- claim-writingSkill
- domain-level-judgmentSkill
- dual-column-self-checkSkill
- engineering-config-gradingSkill
- first-pass-skimSkill
- keshav-three-passSkill
- paper-fetchSkill
- qalmriSkill
- qalmri-worksheetSkill
- qasper-evidence-qaSkill
- quality-appraisal-checklistSkill
- question-framingSkill
- rationale-selectionSkill
- reforms-gradingSkill
- reporting-standard-checklistSkill
- reproducibility-third-party-verificationSkill
- research-question-appraisalSkill
- rhetorical-structure-qualitySkill
- second-pass-graspSkill
- signalling-question-answeringSkill
- star-awardingSkill
- study-design-tool-gateSkill
- sum-threshold-scoringSkill
- template-slot-fillingSkill
- third-pass-deep-readSkill
- unit-classificationSkill
- unit-segmentationSkill
- worst-case-lookupSkill
The file
Files
Multi-Stage Cascade Extraction
Mention detection → coreference clustering → [saliency] → relation extraction, all stages consuming the full prior stage's output. Covers SciERC/SciREX/NLP-Contribution-Graph — three methods with different stage counts but the same "consume-the-full-prior-layer" structure (graph correction S6: merged under the unifying rule "same action-sequence length → mergeable via parameterization").
Execution
Subagent — spawned via spawn-agent skill.
Why Direct From paper-fetch, Not Through unit-segmentation
This cascade discovers its own mention spans over the whole document rather than consuming pre-segmented sentence/clause units — sentence-level segmentation is the wrong granularity for a method whose relations are 99% cross-sentence (SciREX's own reported figure). This is a deliberate graph choice, not an oversight — see spec §5's flagged note before "fixing" this dependency.
Errors Compound Stage-Over-Stage
NLP Contribution Graph's own reported consistency figures fall from stage to stage (67.92% → 41.82% → 22.31%) — this is the shared risk profile of this whole method family, not specific to one method. Producing every stage's intermediate output (not just the final relations) is what makes this compounding visible and debuggable.
<!-- BEGIN available-tables (generated) -->Available SOPs
| SOP | When to use |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. |
<!-- END available-tables (generated) -->Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.