Run AI Content Detection

AI Content Detection, powered by Pangram AI Detection, scores how much of each submission's text looks AI-generated — a screening signal for a track's submissions. (Looking for AI-generated technical reviews of submissions instead? That's AI Review.)

How It Works

1. Confirm the charge — The confirmation dialog shows the estimated cost before anything runs
2. Run in the background — PaperFox extracts each submission's text and sends it to Pangram
3. Review results — Per-submission verdicts, composition scores, and in-app evidence showing the flagged passages

---

Credits and Pricing

Detection costs 20 credits per 1,000 words, pay-as-you-go: each submission is charged from its actual length as it's analyzed — a typical 9,000-word submission costs about 180 credits, a short submission costs less.

• The service card shows the rate; the confirmation dialog shows the estimated cost — an exact per-submission figure from the submission's measured word count for a single-submission run, an approximate total for Run All
• Submissions are charged one at a time, as each is analyzed — you're never charged for a submission that wasn't analyzed
• Unchanged submissions are free — if a submission's text is identical to a previous run, the earlier result is reused at no charge. A submission whose current text already has a result can't be re-run at all (its Re-run button is disabled — there's nothing new to analyze)
• If your balance runs out mid-run, analysis stops automatically — already-analyzed submissions keep their results, the rest are marked "insufficient credits," and running again after a top-up picks up exactly where it stopped (the analyzed submissions reuse for free)
• Submissions that fail on the provider's side after being charged are refunded automatically
• Starting a run requires enough balance for at least one typical submission

---

Running Detection

1. Go to Conferences in the sidebar, then click on your conference
2. Navigate to your track and under Submission Management, click "AI Content Detection"

3. Click "Run All" on the service card — or click "Run" / "Re-run" on any individual submission's row to analyze just that submission

4. The confirmation dialog shows the estimated cost — an exact figure from the submission's measured word count for a single submission, an approximate total for Run All — and reminds you that submission text is sent to the external provider. Confirm to start

The analysis runs in the background with a progress bar — a typical track finishes in under a minute. You can keep working or cancel the run; cancelling refunds any submissions that weren't analyzed, while submissions that already finished keep their results and their charges.

Multiple File Fields

If your submission form has more than one file upload field (for example a manuscript plus an appendix), a Submission field selector appears above the service cards — pick which field's upload gets analyzed. Submissions without an upload in the selected field are skipped, never billed. Forms with a single file field need no configuration.

Multi-Phase Tracks

If your track has more than one phase, a Phase selector appears above the service cards. The run analyzes each submission's latest version in the selected phase; submissions with no version in that phase are not included. Single-phase tracks hide the selector.

---

Reviewing Results

The Submissions list on each service card shows every submission in scope with its latest result — single-submission re-runs simply refresh that submission's row. On large tracks, use the search box (title, author, or submission ID) and the result filter next to it (All / AI / Mixed / Human / Skipped / Not analyzed, with live counts) to narrow the list; the two combine. Verdicts:

Each analyzed row also shows:

• Composition bar — how much of the text looks AI-generated (red), AI-assisted (amber), and human (green); hover for exact percentages
• Evidence — click the magnifier icon to see the full composition breakdown and the flagged passages
• Version badge — if the submission has been revised since the run, the row shows which version was analyzed so you know the result may be outdated
• Skipped / Failed — submissions without a PDF, with unreadable files, or stopped by an empty balance; failed-after-charge submissions are refunded automatically

Viewing Evidence

Click the magnifier icon on any analyzed row to see the submission's full composition and exactly which passages were flagged, each with its own label, score, and confidence level. Long passages are collapsed — click "Show full passage" to expand:

Submissions with a Human verdict have no flagged passages — the evidence panel simply confirms nothing was flagged.

Re-running the service refreshes results for submissions that changed and reuses earlier results for submissions that didn't — you're only billed for what's actually re-analyzed. Only one run per service can be active on a track at a time.