Detectors

Milestones

• A milestone reached

  Notes the first time the channel crosses a round-number views, watch-time, or subscriber threshold. Useful early on, when each milestone is itself a signal that the catalog is building.

  Can fire from

  seedling stage

  Sample threshold

  First crossing of a threshold; no minimum.

  Last matched Jun 13, 2026 · 9 matches since Jun 5, 2026

• An emerging signal

  A catch-all slot for early-channel signals — first views, first impressions, first non-zero traffic from a given source, and other directional findings that often precede a clearer pattern.

  Can fire from

  seedling stage

  Sample threshold

  Typically two to three days of non-zero data.

  Last matched Jun 13, 2026 · 113 matches since May 31, 2026

Trajectory and outliers

• A video tracking off the channel norm

  Compares a video's view trajectory against the channel's percentile bands at the same days-since-publish. Marks videos sitting clearly above or below where similarly-aged videos usually land.

  Can fire from

  sprouting stage

  Sample threshold

  At least 20 prior videos at comparable ages for the band.

  Last matched Jun 13, 2026 · 24 matches since Jun 3, 2026

• Views accelerating

  Picks up videos whose recent daily views are accelerating against their own decay curve. Acceleration is rare and tends to be short-lived; the detector flags the window, not a forecast.

  Can fire from

  growing stage

  Sample threshold

  Seven days of non-zero daily views.

  Last matched Jun 13, 2026 · 36 matches since Jun 3, 2026

Discovery and traffic sources

• A traffic source proportion shifting

  Tracks per-video changes in the share of views coming from each traffic source. A shift usually shows up when YouTube starts surfacing a video through a different surface than it did at first.

  Can fire from

  sprouting stage

  Sample threshold

  At least a 7-day window with non-zero daily impressions.

  Not yet fired on this channel

• Browse / Homepage opening up

  Names the first date the channel's Browse / Homepage surface delivered at least 100 impressions across the catalog combined. Channel-scope milestone — once it lands, the channel has passed the gate for the rest of its life. The detector keeps the milestone in foreground for fourteen days, then goes quiet.

  Can fire from

  seedling stage

  Sample threshold

  First channel-wide day at or above 100 Browse impressions.

  Not yet fired on this channel

• Browse / Homepage going quiet

  Marks at least seven consecutive days of zero channel-wide Browse impressions after an earlier active stretch. Channel-scope. Names the quiet window without claiming a cause — Browse pauses commonly follow a Suggested-driven phase or a topic rotation, and tend to lift again on the channel's own schedule.

  Can fire from

  sprouting stage

  Sample threshold

  Seven or more consecutive zero-impression Browse days plus at least one earlier active day.

  Not yet fired on this channel

• YouTube Search reaching the channel

  Names the first date the YouTube Search surface delivered at least five views across the catalog combined. Channel-scope milestone. Search behaves differently from Browse and Suggested — it requires viewers to come looking for something the catalog matches — so the first sustained Search hit usually reads as an inflection separate from algorithmic discovery.

  Can fire from

  seedling stage

  Sample threshold

  First channel-wide day at or above five Search views.

  Not yet fired on this channel

• Suggested Videos lifting

  Fires when channel-wide Suggested Videos impressions held at or above twice their prior seven-day median for at least two consecutive days. Channel-scope. Often shows up when an adjacent video on YouTube currently sends viewers in; the detector names the lift without claiming which video.

  Can fire from

  sprouting stage

  Sample threshold

  Seven prior Suggested-impression days plus two consecutive at or above twice that median.

  Not yet fired on this channel

• Suggested Videos cliff

  Fires when the latest day's channel-wide Suggested Videos impressions sit at half or less of the higher of the prior two days, with that prior level at or above fifty impressions. Channel-scope. Most Suggested cliffs typically follow a fading link from a now-cooled adjacent video; the detector names the drop without claiming a cause.

  Can fire from

  sprouting stage

  Sample threshold

  Three or more Suggested-impression days, with the prior two-day max at or above fifty.

  Not yet fired on this channel

• Single-source-dominated day

  Names the most recent day inside the trailing fourteen on which one traffic source delivered eighty percent or more of channel-wide views. Channel-scope. Marks a single-surface day — useful for distinguishing a short-lived pulse from a steady mix and for matching it with what was happening on the catalog that day.

  Can fire from

  sprouting stage

  Sample threshold

  At least ten total channel-wide views on the picked day, with one source at or above eighty percent.

  Not yet fired on this channel

• Top-country flipping week-over-week

  Compares the rolling seven-day top viewer country against the prior seven-day top. Fires only when the rank-one country changes between the two windows and each window cleared the fifty-view floor. Channel-scope. Often surfaces when a single video reached a different surface than the catalog's usual mix — though country shifts also occur for many other reasons.

  Can fire from

  sprouting stage

  Sample threshold

  Two consecutive seven-day windows each carrying at least fifty channel-wide views.

  Not yet fired on this channel

• First External-source views

  Per-video milestone — emits one insight per video that received its first External-source views on the channel's earliest first-external date, when that date falls within the trailing seven days. External views typically arrive from links off YouTube (social posts, embeds, blog mentions); the matching timeline event is generated separately by the public-DB build.

  Can fire from

  seedling stage

  Sample threshold

  One non-zero External-views day on the earliest first-external date in the catalog.

  Not yet fired on this channel

• Channel-wide top traffic source flipping

  Compares the channel's top traffic source in two consecutive seven-day windows. Fires when the rank-one source changes — for example, Browse moving ahead of Suggested across the channel. A genuine shift in how the catalog as a whole is reaching new viewers, not a per-video signal.

  Can fire from

  sprouting stage

  Sample threshold

  Two consecutive seven-day windows each carrying non-zero traffic.

  Not yet fired on this channel

• Per-source typical days-to-activation

  Channel-scope summary of the per-source p25/median/p75 days-to-activation band — the typical age range a video must reach before each traffic source first sends views. Surfaces the gap between fast-activating surfaces (Suggested usually shows up within days) and slow-activating ones (Search and External commonly lag by weeks or months) on this channel's own history.

  Can fire from

  sprouting stage

  Sample threshold

  At least five videos with activation dates for the named source.

  Not yet fired on this channel

• A specific video's source activation outside the channel's band

  Per-video flag — fires when a video's days-to-activation on a given source land outside the channel's p25-to-p75 band (with a two-day buffer). Often the most concrete way to call out a video that reached a surface unusually early or unusually late compared with the channel's typical pace on that surface.

  Can fire from

  sprouting stage

  Sample threshold

  Channel needs at least five videos with activation dates for the named source.

  Not yet fired on this channel

• First impressions on a video

  Marks the first day a video received non-zero impressions on a given surface. Often arrives later than the first views.

  Can fire from

  sprouting stage

  Sample threshold

  First non-zero impression day.

  Not yet fired on this channel

• A video drawing most traffic from one source

  A single video whose source-HHI sits well above the channel's typical mix. Often shows up when one surface — Suggested, Browse, or External — carries the bulk of the views while other sources stay quiet.

  Can fire from

  sprouting stage

  Sample threshold

  At least five videos with non-null source HHI on the channel; the video needs 14+ tracked days and 50+ views.

  Not yet fired on this channel

• Source mix widening

  Trailing 14-day slope of the channel's source-diversity score is rising. Typically a sign that views are spreading across more surfaces over time rather than concentrating on one or two.

  Can fire from

  sprouting stage

  Sample threshold

  Ten or more reporting days with a non-null diversity slope.

  Not yet fired on this channel

• Source mix narrowing

  Trailing 14-day slope of the channel's source-diversity score is falling. Usually means one or two surfaces are carrying a larger share of recent views than they did two weeks earlier.

  Can fire from

  sprouting stage

  Sample threshold

  Ten or more reporting days with a non-null diversity slope.

  Not yet fired on this channel

• A source going quiet on a video

  A specific video-and-source pair where the source sent at least 20 views in a 14-day prior window then sent zero across the last seven days. Often shows up when a feed-driven surface stops surfacing the video; can also reflect the natural tail of a short-lived spike.

  Can fire from

  sprouting stage

  Sample threshold

  The video must be at least 30 days old; the prior window needs 20+ views from the source.

  Not yet fired on this channel

• A gap in watch time per view across sources

  Ranks the channel's traffic sources by average watch minutes per view and names the best-vs-worst gap. Viewers arriving from different surfaces often watch for very different lengths — this names which surface tends to send the longest-watching audience on this channel.

  Can fire from

  seedling stage

  Sample threshold

  At least two sources with five or more views each and a positive watch-per-view rate; best/worst ratio at least 1.5x.

  Not yet fired on this channel

• A gap in subs-per-view across sources

  Per-source subscribers gained per 1,000 views, comparing the best- and worst-performing surface on the channel. Per-source subs are estimated by proportionally allocating channel-level subs to each source's view share — treat the rate as a modeled share, not a measured count.

  Can fire from

  sprouting stage

  Sample threshold

  At least two sources with 200+ views; total allocated subs at least 50; best/worst ratio at least 2x.

  Not yet fired on this channel

• A previously-quiet organic source firing again on a video

  Per-(video, organic-source) pair where the source delivered non-zero views recently after a stretch of zero views. Lifts the resumed source name into the foreground so the per-video page can describe what surface picked back up. The detector is observational — it doesn't claim YouTube intentionally resurfaced anything, only that the source went quiet and came back.

  Can fire from

  sprouting stage

  Sample threshold

  At least 14 prior quiet days followed by at least 3 active days with combined views above the channel median.

  Not yet fired on this channel

• A video drawing most views from a single country

  Per-video reading — fires when one country accounts for at least 60% of a video's lifetime views AND that country's average watch percentage on the video sits below the channel's typical retention on that country. The combined gate keeps a high-share country reading from firing on videos the country is also engaging well with.

  Can fire from

  sprouting stage

  Sample threshold

  At least 100 lifetime views on the video and a non-null channel-country retention baseline.

  Not yet fired on this channel

Trajectory and outliers

• A video's view-curve deviating from its peer norm

  The default outlier shape behind trajectory_outlier — fires when a video's daily view counts deviate from the channel's age-normalized peer percentile band by at least the configured threshold. Magnitude scales with the absolute percent deviation, capped so a wildly above-norm video doesn't crowd out the rest of the catalog's findings.

  Can fire from

  sprouting stage

  Sample threshold

  At least five peer videos with the same days-since-publish slice for the channel norm.

  Not yet fired on this channel

• A week-over-week step up

  A clear step up in weekly views compared to the prior week, beyond what the channel's own variability usually produces.

  Can fire from

  sprouting stage

  Sample threshold

  Two complete prior weeks for the comparison.

  Not yet fired on this channel

• Day-one numbers predicting longer-run reach

  Tests how strongly day-one views correlate with day-30 totals across the channel. The strength of that correlation reflects how much the channel's reach is set early versus built over time.

  Can fire from

  growing stage

  Sample threshold

  At least 30 videos with both day-1 and day-30 data.

  Not yet fired on this channel

• Cross-video outlier

  Flags videos whose totals sit far above or below the channel's overall average — a coarse marker for which videos defined the catalog.

  Can fire from

  growing stage

  Sample threshold

  At least 10 videos in the catalog.

  Not yet fired on this channel

• A live video sitting outside the channel's day-N cone for its age

  Per-video reading on videos ≤ 30 days old. Compares the day-N reading against the channel's per-(age, peer) trajectory cone; fires when the day's views sit above p75 or below p25 of the cone for that age. The percentile is observational and rests on the channel's own history at that age — not a forecast of where the video lands. Decay-fit annotations attach when an R² ≥ 0.7 model is available.

  Can fire from

  sprouting stage

  Sample threshold

  At least 5 peer videos in the channel cone at the same age, with the day's per-day views above zero.

  Not yet fired on this channel

• Retention and engagement ranking high relative to view mass

  Per-video quality-to-reach gap. Fires when retention and engagement-rate percentiles both sit well above the video's view-rank percentile across the channel — the typical pattern is a video that holds attention well but hasn't reached many people. The framing is observational; many things can produce the gap (topic, thumbnail, timing, audience mismatch) and the detector does not claim which.

  Can fire from

  sprouting stage

  Sample threshold

  At least 10 videos with non-null retention and engagement data.

  Not yet fired on this channel

• A per-metric trajectory consistent across videos

  Pearson-based per-metric trend across the catalog when newer videos consistently sit higher or lower than older ones on a single axis (click rate, average watch time, subscribers per view, engagement rate). The detector names the metric and direction; the cause sits outside the data.

  Can fire from

  growing stage

  Sample threshold

  At least 10 videos with non-null values on the metric.

  Not yet fired on this channel

• A title pattern correlating with click rate on this channel

  Splits the catalog by title format — questions, numbers, length tier, and structural features — and notes the format whose median click rate sits highest among groups with at least three videos.

  Can fire from

  growing stage

  Sample threshold

  At least 10 videos with non-null click rate and the relevant title flag populated.

  Not yet fired on this channel

Per-video lifecycle

• This video's arc

  Reads the shape of a video's view curve and labels its current phase: early-burst, slow-burn, second-wind, or decline. Most videos pass through several phases over their life.

  Can fire from

  sprouting stage

  Sample threshold

  At least 14 days of post-publish data.

  Not yet fired on this channel

• A video gone quiet

  Marks videos that were once active but have received little or no traffic recently. Most videos eventually pass through this state.

  Can fire from

  sprouting stage

  Sample threshold

  At least 14 prior days of zero or near-zero views.

  Not yet fired on this channel

• Impressions without views

  Flags videos that are still being shown to viewers but rarely clicked into. The pattern usually reads as YouTube continuing to test the video's surfaces.

  Can fire from

  sprouting stage

  Sample threshold

  At least 1,000 trailing-window impressions.

  Not yet fired on this channel

• Days from publish to peak

  Records the day on which each video reached its highest daily-view total, and compares the spread across the catalog.

  Can fire from

  sprouting stage

  Sample threshold

  At least 3 videos with 10+ lifetime views and 7+ days of tracking each.

  Not yet fired on this channel

• Older videos vs newer videos

  Splits the catalog by publish date and compares the older half to the newer half on click rate and average watch time. The gap describes how the channel's typical numbers have shifted over time — it doesn't attribute that shift to any single cause.

  Can fire from

  sprouting stage

  Sample threshold

  At least six videos across both halves, with non-null values on at least two per side.

  Not yet fired on this channel

• Click rate rising late in life

  Notes videos whose click rate rose well after publish — sometimes after a thumbnail change, sometimes alongside a fresh push from YouTube's surfaces.

  Can fire from

  growing stage

  Sample threshold

  At least 1,000 impressions in each comparison window.

  Not yet fired on this channel

• Watch time rising late in life

  Notes videos whose average watch time rose well after publish, against the channel's typical decay.

  Can fire from

  growing stage

  Sample threshold

  At least 14 days of post-publish data with non-zero AVD.

  Not yet fired on this channel

• Trend across recent debuts

  Looks across the most recent batch of newly-published videos for a shared early-life pattern — a coarse marker for whether new videos are landing differently than older ones.

  Can fire from

  growing stage

  Sample threshold

  At least three recent debuts in the trailing window.

  Not yet fired on this channel

• Channel trend, week over week

  Compares the channel's last seven days against the seven before — and against the channel's first seven days — across views, times-shown, engagement, and traffic-source spread. Names the window-over-window movement as an observation; it does not grade the direction.

  Can fire from

  sprouting stage

  Sample threshold

  At least seven days in each window, above a per-metric magnitude floor.

  Not yet fired on this channel

• Trend across recent videos

  Compares the last five videos against the previous five — and against the channel's first five — on day-1 and day-7 views, plus the newest video against the one published before it. A coarse read of whether recent videos are landing differently than earlier ones.

  Can fire from

  sprouting stage

  Sample threshold

  At least three videos in each window, above a magnitude floor.

  Not yet fired on this channel

• A video launched in a weak channel phase performing under the channel median

  Per-video reading. Compares a video's day-7 views against the channel's lifetime day-7 median, but only on videos launched during a week the channel was running below its trailing 28-day baseline. The framing names the launch context so the reading doesn't penalize the video for circumstances outside its own metrics.

  Can fire from

  sprouting stage

  Sample threshold

  At least 30 day-7 views on the video and a non-null channel day-7 median.

  Not yet fired on this channel

Engagement

• Two metrics that usually move together pulling apart

  Per-video cross-axis divergence. Names videos where two correlated engagement readings sit far apart — most often a high click rate paired with low retention, or strong retention paired with a quiet click rate. The V13 build runs this against the channel-internal CTR / retention medians; pre-V13 fixtures fall back to a percentile-rank pass that also covers views-per-day vs engagement-rate.

  Can fire from

  growing stage

  Sample threshold

  At least three videos with 50+ views and 100+ impressions to compare against; eight or more reads as high confidence.

  Not yet fired on this channel

• A video drawing more engagement per view than the rest of the channel

  Combined likes + comments + shares divided by views, per video. Fires when a video's ratio runs at least 2x the channel's median ratio AND lands in the top quartile of the channel's distribution. Names the single metric — comments, likes, or shares — whose per-view rate ran furthest above the channel's own typical pace, so the card stays concrete.

  Can fire from

  sprouting stage

  Sample threshold

  Channel needs five or more videos with 10+ views; the spotlight video needs 10+ views and a channel-internal median ratio above zero.

  Not yet fired on this channel

• Comments-per-view well above the channel's band

  Per-video comments per 100 views, against the channel's own median comments-per-100-views. Fires when the video runs at least three times the channel median, with at least three absolute comments to keep small-sample noise out. Comments are the highest-friction engagement event — a viewer typically has to type something — and an outsized rate often traces back to the topic landing somewhere the channel's typical content does not.

  Can fire from

  sprouting stage

  Sample threshold

  Channel needs five or more videos with 100+ views and a non-zero median comments rate; the spotlight video needs three or more comments.

  Not yet fired on this channel

• A trailing-3-day jump in shares on a video

  Sums a video's shares across the last three reporting days and compares the total against three days of the channel's typical per-video share rate. Fires when the recent total clears both an absolute floor of three shares and twice the channel's typical pace. Sharing tends to be lumpy — one off-platform mention can show up as a clear pulse — so the multiplier gate sits well above day-to-day drift.

  Can fire from

  sprouting stage

  Sample threshold

  Channel needs five or more public videos and a non-zero median per-video share rate; the spotlight video needs three or more shares in the trailing three days.

  Not yet fired on this channel

• Subscribe rate and reach moving in opposite directions

  Channel-scope. Compares the trailing-28-day slope of the per-day subscribe rate (subs gained / trailing-7-day views) to the slope of trailing-7-day views itself. Two shapes can fire: audience quality improving (sub-rate climbing while reach holds roughly flat) and volume without depth (sub-rate easing while reach climbs). Both are framed as observation in opposite directions — neither is graded as good or bad.

  Can fire from

  sprouting stage

  Sample threshold

  21 or more non-null days inside the trailing 28-day window with both subscribe and view data.

  Not yet fired on this channel

• Subscribers stepping up on a routine view day

  Names the most-recent day inside the trailing 14-day window where the channel gained at least three net subscribers AND that day's views sat at or below the 14-day median. Subscriber gains usually correlate with view spikes; a sub event on a routine view day is shape-distinct, and often (though not always) traces back to attention reaching the channel through a surface that doesn't show up in the view count — search, an off-platform link, a memory of a prior watch.

  Can fire from

  sprouting stage

  Sample threshold

  14 or more days of channel-daily rows ending at the latest reporting date.

  Not yet fired on this channel

• Subscribers lost in the trailing two weeks

  Sums subs lost across the last 14 channel-daily rows. Fires when the total clears a small floor — the prose stays observation-only and never claims a cause. Per-video subscriber-loss days are tracked separately in the timeline and surface in per-video Eras sections.

  Can fire from

  seedling stage

  Sample threshold

  At least seven days of channel-level subscriber data; at least three subscribers lost in the window.

  Not yet fired on this channel

• Audience replacing itself faster than its trailing weeks

  Compares the latest week's audience replacement rate against the median of the prior eight week-ending readings. A clear lift means viewers who watched recently are mostly new faces rather than repeat returners. The replacement signal lives next to a persistence reading — together they describe how much of each week's audience is the same audience.

  Can fire from

  growing stage

  Sample threshold

  At least eight prior week-ending rows for the baseline.

  Not yet fired on this channel

• Channel attribution share trending up

  Sums views YouTube couldn't attribute to a specific traffic source across the trailing seven days, against total views in the same window. Fires when the share clears 15%. YouTube's reporting always carries some unattributed share — the gate is set well above the typical baseline so a fire usually corresponds to a reporting-system shift rather than channel behavior.

  Can fire from

  seedling stage

  Sample threshold

  Seven trailing channel-daily rows with non-null attribution data.

  Not yet fired on this channel

• Per-video attribution share well above baseline

  Reads a video's lifetime unattributed impressions against its lifetime total impressions. Fires when the share is above 20% and the video has at least 5,000 lifetime impressions. The certainty stays at trust-language tier — the reading is informative about YouTube's reporting, not about the video.

  Can fire from

  seedling stage

  Sample threshold

  At least 5,000 lifetime impressions on the video.

  Not yet fired on this channel

Channel shape

• Lifetime distribution of views across the catalog

  Classifies the catalog's lifetime view distribution into hit-driven, balanced, long-tail, or flat. Hit-driven means the top video alone carries at least 40% of channel views; balanced is between 20% and 40%; long-tail is below 20% on the top but at least 70% on the top five combined; flat is below 20% on the top and below 50% on the top five. The detector stays quiet in the gap between long-tail and flat where neither label fits cleanly.

  Can fire from

  sprouting stage

  Sample threshold

  At least five videos with at least ten views each.

  Not yet fired on this channel

• Channel's 5-dimensional state vector outside its 90-day envelope

  Builds a state vector per date from weighted CTR, average view duration, top-video share over the trailing 7 days, source diversity, and quiet-inventory share. Computes Mahalanobis distance against the trailing 90-day distribution; fires when the distance stays above 2.5 across the latest two days. When the covariance can't be inverted, falls back to a per-component z-score path and notes the method on the evidence row.

  Can fire from

  growing stage

  Sample threshold

  At least 90 baseline days plus 2 sustained candidate days.

  Not yet fired on this channel

• Recent publishing gap notably longer than the channel's median

  Finds the longest gap between two consecutive public-release dates inside the last 30 days. Fires when that gap is at least two times the channel's lifetime median inter-publish gap and at least seven absolute days. Prefers first_public_at when populated and falls back to published_at — the fallback is disclosed on the evidence row so the prose can hedge accordingly.

  Can fire from

  seedling stage

  Sample threshold

  At least 10 public videos lifetime, at least 3 distinct publish dates.

  Not yet fired on this channel

• How often this channel publishes

  Classifies the publishing rhythm into a median-gap bucket — daily, near-daily, twice-weekly, weekly, biweekly, monthly, or irregular. Two special cases override the buckets: when five or more videos share one public-release date and every one of them carries first_public_at, the pattern reads as burst-launch; when first_public_at is missing on the cluster, the pattern reads as schema-ambiguous because batch-launch can't be told apart from an upload-date artifact.

  Can fire from

  seedling stage

  Sample threshold

  At least five videos with public-release dates on or before the latest reporting date.

  Not yet fired on this channel

• Recent 7-day publish count diverging from the prior 7-day count

  Compares public-release counts in the trailing 7 days against the 7 days immediately before. Fires when the ratio is at least 2 (speedup) or at most 0.5 (slowdown) with an absolute difference of at least one video. A two-video floor on the prior window keeps 0-to-N or 1-to-N transitions from reading as infinite speedups — channels routinely sit quiet for a week and post once, and that is not a cadence shift.

  Can fire from

  seedling stage

  Sample threshold

  At least 5 videos overall, at least 2 in the 7-to-14-day prior window.

  Not yet fired on this channel

• One or two weekdays consistently outperforming the rest

  Tracks per-weekday median daily views against the overall daily median. Fires when one or two weekdays sit at least 1.5 times the overall median and the leading weekday is itself elevated in at least three distinct calendar weeks. The one-or-two cap keeps the card honest — four-of-seven weekdays running higher reads as noise, not a recurring rhythm. Pattern only; the detector does not name a cause.

  Can fire from

  seedling stage

  Sample threshold

  At least 21 days of data across at least 3 full calendar weeks; overall daily-view median at least 20.

  Not yet fired on this channel

• The catalog shape shifting

  Detects when channel-wide patterns (concentration, cadence, source mix) moved enough to read as a phase change rather than week-to-week noise.

  Can fire from

  growing stage

  Sample threshold

  At least 90 days of channel-daily data.

  Not yet fired on this channel

• A metric outside its usual range

  A channel-level metric (CTR, watch time, daily views) that recently moved outside its typical range. The detector marks the day window; the cause usually isn't readable from the data alone.

  Can fire from

  sprouting stage

  Sample threshold

  At least 28 days of prior data for the baseline.

  Not yet fired on this channel

• How retention distributes across the catalog

  Splits the catalog into retention tiers and notes how the distribution shifted over time — a slower-moving signal than per-video retention.

  Can fire from

  sprouting stage

  Sample threshold

  At least 10 videos with retention data.

  Not yet fired on this channel

• Share of the catalog that went the past week without views

  Reads the trailing-7-day share of public videos that received no views, against a maturity-scaled threshold (sprouting 0.50, growing 0.30, established 0.15). Quiet weeks are common as a catalog grows — recent videos and a few favorites usually carry most of the surface — so the gate is set wider for younger catalogs and tightens as the channel matures.

  Can fire from

  sprouting stage

  Sample threshold

  At least four public videos live on the date.

  Not yet fired on this channel

• Top-video and quiet-inventory shares trending up together

  Reads the trailing 14-day OLS slopes of two channel-shape axes: the share of views carried by the single top video, and the share of public videos that received no views. Fires when both 10-day mean slopes clear 0.005 share-points per day upward AND the latest top-video 7-day share is at least 0.30. The dual gate keeps a brief concentration spike on a single upload from reading as a trend on its own — the catalog has to be meaningfully concentrated at the latest reading too.

  Can fire from

  growing stage

  Sample threshold

  At least ten trailing channel-daily rows with paired slope readings.

  Not yet fired on this channel

• Share of videos below a view threshold

  Counts how many public videos sit below a maturity-scaled view threshold (seedling 10, sprouting 100, growing and established 500). Stays quiet when every video clears the threshold and when no video clears it — the in-between case is the descriptive one. The framing is observational context rather than a high-signal alert, and the magnitude caps low so it rarely outranks more specific per-video findings.

  Can fire from

  seedling stage

  Sample threshold

  At least five public videos in the catalog.

  Not yet fired on this channel

• Share of fitted videos projected quiet within 30 days

  Counts how many videos with a fitted decay model carry a predicted quiet date inside the next thirty days, against the total fitted catalog. Fires when the share clears 30 percent. The model itself only fits on videos that have at least three days of post-publish data, so the detector inherits that floor naturally; seedling channels stay gated out because the catalog is rarely deep enough for the share to read as anything more than noise.

  Can fire from

  sprouting stage

  Sample threshold

  At least five videos with a fitted decay-model row.

  Not yet fired on this channel

• A video projected quiet within two weeks

  Reads the per-video decay-model row and fires when the goodness-of-fit R-squared is at least 0.70 and the predicted quiet date sits within the next fourteen days. Magnitude rises as the date approaches. One insight per qualifying video — the detector emits per-video rather than rolling up, so the page can name the specific videos rather than describing the catalog in aggregate.

  Can fire from

  sprouting stage

  Sample threshold

  At least three days of post-publish data on the video with R-squared at least 0.70.

  Not yet fired on this channel

• Before / after a title or thumbnail change

  Compares click rate across the windows before and after a title or thumbnail change. The detector reports the difference; it makes no claim about whether the change caused it.

  Can fire from

  sprouting stage

  Sample threshold

  At least 1,000 impressions in each window.

  Not yet fired on this channel

• How a title or thumbnail change reshuffled traffic sources

  Compares the per-source traffic mix across before/after windows of a title or thumbnail change. Useful because click rate alone hides which surfaces moved.

  Can fire from

  sprouting stage

  Sample threshold

  At least 1,000 impressions in each window.

  Not yet fired on this channel

• How often a video was iterated on

  Counts the number of title or thumbnail changes a video has received and notes outliers against the catalog's typical iteration intensity.

  Can fire from

  sprouting stage

  Sample threshold

  At least three iterations on the video.

  Not yet fired on this channel

• Whether iterations moved the metric

  For each title or thumbnail change, compares the metric in the prior window against the new window. The result is observation, not advice — the same change can read positive on one video and negative on another.

  Can fire from

  sprouting stage

  Sample threshold

  At least 1,000 impressions in each window.

  Not yet fired on this channel

• How fast YouTube is testing a video

  Notes per-video impression rates that read as YouTube's ongoing impression-testing pattern — high impressions paired with click rates that haven't settled yet.

  Can fire from

  sprouting stage

  Sample threshold

  At least 1,000 trailing impressions.

  Not yet fired on this channel