Lint report · stored run
Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
0errors
0warnings
0info
25claims read
139numbers extracted
56references
How well we read this paper
1 observation
These are notes about our reading of the paper, not about the paper. They affect how much weight the findings below can carry.
Note 1
- compile-warning semantic extraction: dropped 5 items whose quote was not found in the paper
Some checks could not run
- RL002 reported nothing, and it could not reach OpenAlex — so its silence here is not evidence that this paper is clean.
- RL003 reported nothing, and it could not reach OpenAlex — so its silence here is not evidence that this paper is clean.
Everything else on this page was computed from the paper itself and is unaffected. This is a limit of this run, not a finding about the paper.
Compiler extraction log (1)
semantic extraction: dropped 5 items whose quote was not found in the paper
No findings on this paper.
That is a result, not a failure. The compiler read the paper without errors, and no rule found something it could prove with evidence — this product would rather say nothing than say something vague.
Read the extraction notes above before taking this as a clean bill of health: they say which checks were working with incomplete information.
Rule notes (31)
RL001 funnel arithmetic: sentences_with_from=0 endpoint_pairs=0 claims_compared=0 emitted=0 [dropped: not-a-measurement=0] <- no 'from A to B' sentence reached this check
RL001 funnel delta-column: structured_tables=2 with_exactly_one_delta_column=0 rows_checked=0 emitted=0
RL001 funnel cross-location: quant=139 prose=35 prose_with_metric=1 prose_with_dataset=0 prose_with_metric_and_dataset=0 distinct_buckets=0 emitted=0 [dropped: not-a-measurement=7 not-in-quote=0]
RL001 funnel identifier-drift: settings_checked=2 sections_stating_one_value=0 emitted=0
RL002 citation entailment: attempted 18 of 54 ranked cited claims (117 in-text markers from 56 bibliography entries); 3 cited works could not be identified, 4 had no retrievable text, 0 model quotes failed verbatim verification, 0 were topically unrelated to the retrieved text.
RL002 candidate ranking (why the top 18 were chosen): [6] [introduction, absolutist wording]; [10] [introduction, names an artefact (Agent Skills), unusable title (identity fragile)]; [11] [introduction, names an artefact (Scientific Agent Skills), unusable title (identity fragile)]; [7] [introduction, names an artefact (ARRIVE)]; [8] [introduction, names an artefact (MIQE)]; [18] [introduction, title/sentence overlap near zero, unusable title (identity fragile)]; [1] [introduction, title/sentence overlap near zero]; [5] [introduction, title/sentence overlap near zero]
RL002 label distribution over 11 classified citations: SUPPORTED=11
RL002 base-rate self-check: not tripped (0/11 = 0% NOT_SUPPORTED, threshold 40%).
RL002 attribution check (case B): 9 candidates name an artefact, 4 of them made the top-N and were checked against their cited source
RL002: 4 citations skipped because the sentence reports this paper's own results (the citation there is a comparison pointer, not evidence for the sentence)
RL002: 2 markers skipped because the claim is jointly attributed to several works
RL002: 4 enumerated-citation sentences skipped (they cite >=3 works, so the claim is about the set and cannot be refuted by any single cited work)
RL002: 3 duplicate candidates dropped (same reference and claim, or the same artefact attributed twice)
RL002: 3 cited works unresolvable (first 3: [{"key": "[10]", "title": "Agent skills specification", "why": "bibliography title unusable for identity verification"}, {"key": "[11]", "title": "Scientific agent skills", "why": "bibliography title unusable for identity verification"}, {"key": "[18]", "title": "Ziru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang, Botao Yu, Yifei Li, Zeyi Liao, Chen Wei, Zitong Lu, Vis", "why": "bibli)
RL003: 2 queries -> 100 unique works (arXiv search 50, category listings 0, scholarly graph 50 [crossref 50], 0 graph works matched to an arXiv id); source errors during retrieval: arXiv 0, graph 0
RL003: parsed the reference list of 1/3 comparable papers (2 unreadable) — that is the PeerUsage denominator
RL003: could read the reference list of only 1 comparable papers (need 4) — peer usage unavailable, no findings
RL004 funnel: components=11 contribution_backed=1 candidates=0 ablations_found=0 matched_by_ablation=0 unmatched=0 experiments=4
RL004 component M1 'skill directory': excluded:not-a-claimed-contribution
RL004 component M2 'SKILL.md': covered (filtered earlier)
RL004 component M3 'name, description, license, compatibility, allowed-tools and metadata': excluded:not-a-claimed-contribution
RL004 component M4 'references/ for additional documentation, scripts/ for code, and assets/ for templates and static resources': excluded:not-a-claimed-contribution
RL004 component M5 'progressive disclosure': excluded:not-a-claimed-contribution
RL004 component M6 'three-tier disclosure model': excluded:not-a-claimed-contribution
RL004 component M7 'cross-references': excluded:evaluation-infrastructure-or-packaging
RL004 component M8 'bag of lower-cased alphanumeric tokens that are at least 3 characters long': covered (filtered earlier)
RL004 component M9 '500-line limit on instruction files': excluded:not-a-claimed-contribution
RL004 component M10 'throwaway environment per skill': excluded:not-a-claimed-contribution
RL004 component M11 'tests outside the shipped directory': excluded:not-a-claimed-contribution
RL004 funnel: ranked=0 emitted=0 suppressed_by_cap=0 dropped_unverified_quote=0
RL005: repository read, but the paper states no comparable hyperparameter
Reading the report as data
This page is a rendering of the report the pipeline wrote. The JSON below
is the stored artefact, unedited — the same document
research-lint --format json produces.
loading…