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.

  Activates:

  seedling

  Sample-size threshold:

  First crossing of a threshold; no minimum.

  Last fired Apr 28, 2026 · 30 total fires since Apr 11, 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.

  Activates:

  seedling

  Sample-size threshold:

  Typically two to three days of non-zero data.

  Last fired Apr 28, 2026 · 408 total fires since Apr 9, 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.

  Activates:

  sprouting

  Sample-size threshold:

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

  Last fired Apr 28, 2026 · 15 total fires since Apr 17, 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.

  Activates:

  sprouting

  Sample-size threshold:

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

  Last fired Apr 28, 2026 · 95 total fires since Apr 12, 2026

Channel shape

• How the catalog distributes

  A family of channel-level findings about the shape of the catalog — how concentrated views are across videos, how steady the publishing cadence has been, where the channel sits in its own arc.

  Activates:

  seedling

  Sample-size threshold:

  At least three published videos.

  Last fired Apr 28, 2026 · 20 total fires since Apr 9, 2026

Discovery and traffic sources

• Browse traffic opening up

  First sustained day-over-day rise in Browse views for a video that previously had little or none. Often the earliest sign that the home-feed surface is showing the video to new viewers.

  Activates:

  seedling

  Sample-size threshold:

  Three or more consecutive days of rising Browse views.

  Not yet fired on this channel

• Browse traffic tapering

  A clear taper in Browse views after a sustained run. Most videos see Browse traffic taper at some point; the detector marks when the taper is sharp enough to read as a phase change.

  Activates:

  sprouting

  Sample-size threshold:

  Three or more consecutive days of falling Browse views.

  Not yet fired on this channel

• Search picking up

  First sustained Search-traffic emergence on a video that previously had none. Search arrival usually trails Browse and Suggested by weeks or months.

  Activates:

  seedling

  Sample-size threshold:

  Three or more days of non-zero Search views.

  Not yet fired on this channel

• Suggested-Videos surge

  A multi-day jump in Suggested-Videos views beyond the channel's typical level. Usually means another video on YouTube is currently sending viewers in.

  Activates:

  sprouting

  Sample-size threshold:

  At least three days above the channel's recent Suggested baseline.

  Not yet fired on this channel

• Suggested-Videos cliff

  A sharp drop in Suggested-Videos views after a stretch of higher activity. Typically reflects a fading link from another video that had been driving traffic.

  Activates:

  sprouting

  Sample-size threshold:

  Drop spanning at least three days vs the prior baseline.

  Not yet fired on this channel

• A single-day, single-source spike

  A one-day spike that came almost entirely from one traffic source. Marks a short-lived pulse — useful for distinguishing real momentum from a one-off mention.

  Activates:

  sprouting

  Sample-size threshold:

  At least 70% of the spike-day views from a single source.

  Not yet fired on this channel

• A traffic-source order flipping

  Notes when the top traffic source for a video changes — for example, Browse falling behind Suggested, or Search overtaking External. A genuine shift in how the video reaches new viewers.

  Activates:

  sprouting

  Sample-size threshold:

  Two windows of seven or more days each.

  Not yet fired on this channel

• Order in which sources activated

  The chronological sequence in which each traffic source first delivered non-zero views to a video. The pattern often differs across videos in surprising ways.

  Activates:

  sprouting

  Sample-size threshold:

  At least two distinct sources activated at different dates.

  Not yet fired on this channel

• Source activations linked across videos

  Looks for cases where a traffic source first activates on multiple videos within a short window — a hint that YouTube began surfacing the channel through that source as a whole.

  Activates:

  sprouting

  Sample-size threshold:

  Three or more videos with first-activation dates within 14 days.

  Not yet fired on this channel

• Views concentrated on the channel page

  Marks videos whose views came mostly from the channel page rather than from algorithmic surfaces — a signal that traffic depended on viewers who already knew the channel.

  Activates:

  sprouting

  Sample-size threshold:

  At least 50% of views from the Channel-page surface.

  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.

  Activates:

  sprouting

  Sample-size threshold:

  First non-zero impression day.

  Not yet fired on this channel

• How first-impression patterns line up across videos

  Looks across videos for shared first-impression patterns — for example, a tendency for Search impressions to arrive at a similar age across the catalog.

  Activates:

  sprouting

  Sample-size threshold:

  At least three videos with first-impression dates.

  Not yet fired on this channel

• A country mix flipping

  Notes when the leading viewer country for a video changed across two trailing windows — a coarse signal that the audience reached a different geography.

  Activates:

  sprouting

  Sample-size threshold:

  Two windows of seven or more days each.

  Not yet fired on this channel

Trajectory and outliers

• 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.

  Activates:

  growing

  Sample-size threshold:

  Seven days of non-zero daily views.

  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.

  Activates:

  sprouting

  Sample-size 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.

  Activates:

  growing

  Sample-size 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.

  Activates:

  growing

  Sample-size threshold:

  At least 10 videos in the catalog.

  Not yet fired on this channel

• Multiple videos catching at once

  Notes windows where several videos accelerated simultaneously — usually a sign of a channel-wide surface change rather than per-video momentum.

  Activates:

  sprouting

  Sample-size threshold:

  Three or more videos with concurrent non-zero acceleration.

  Not yet fired on this channel

• A publish cohort outperforming

  Compares groups of videos published in the same window and marks cohorts that outperformed the channel's median — useful for pulling apart the effect of timing from the videos themselves.

  Activates:

  sprouting

  Sample-size threshold:

  Cohorts of at least three videos.

  Not yet fired on this channel

• A quiet stretch warming up

  Detects when channel-wide algorithmic traffic resumed after a quiet stretch. The detector marks the window; it does not claim cause.

  Activates:

  sprouting

  Sample-size threshold:

  At least seven prior quiet days followed by a sustained increase.

  Not yet fired on this channel

• A drop into a quiet stretch

  Detects when channel-wide algorithmic traffic cooled into a quiet stretch. Often follows a prior surge.

  Activates:

  sprouting

  Sample-size threshold:

  At least seven days below the prior baseline.

  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.

  Activates:

  sprouting

  Sample-size threshold:

  At least 14 days of post-publish data.

  Not yet fired on this channel

• A video finding a second life

  Picks up a video that had gone quiet and then resumed receiving non-zero views from an organic source — sometimes weeks or months after the initial run.

  Activates:

  sprouting

  Sample-size threshold:

  At least seven quiet days followed by sustained resumption.

  Not yet fired on this channel

• A video re-emerging across sources

  Like organic re-emergence, but tracks resumption across any traffic source. The detector marks the resumption; the underlying cause is rarely visible from the data alone.

  Activates:

  sprouting

  Sample-size threshold:

  At least seven quiet days followed by a sustained return.

  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.

  Activates:

  sprouting

  Sample-size 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.

  Activates:

  sprouting

  Sample-size 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.

  Activates:

  sprouting

  Sample-size threshold:

  At least 14 days of post-publish data per video.

  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.

  Activates:

  growing

  Sample-size 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.

  Activates:

  growing

  Sample-size 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.

  Activates:

  growing

  Sample-size threshold:

  At least three recent debuts in the trailing window.

  Not yet fired on this channel

Engagement

• Engagement diverging from views

  Looks for videos where engagement metrics (likes, comments, retention) disagree with raw view totals — videos that performed well on one axis but not the other.

  Activates:

  growing

  Sample-size threshold:

  At least 10 videos in the catalog.

  Not yet fired on this channel

• An engagement ratio standing out

  Per-video divergence between correlated engagement metrics — for example, a high comments-per-view rate on a video with otherwise typical retention.

  Activates:

  sprouting

  Sample-size threshold:

  At least 100 views and 10 engagements on the video.

  Not yet fired on this channel

• Engagement arriving ahead of views

  When likes or comments rise before views catch up, the pattern can indicate a small audience reacting strongly before a wider surface picks the video up.

  Activates:

  growing

  Sample-size threshold:

  Two trailing windows of seven or more days.

  Not yet fired on this channel

• Comment counts well above the norm

  Marks videos with comments-per-view well above the channel's typical band. Often the topic, not the production, is what drove the conversation.

  Activates:

  sprouting

  Sample-size threshold:

  At least 100 views on the video.

  Not yet fired on this channel

• A share spike

  A trailing-window jump in shares for a video. Sharing tends to be lumpy — one social channel mention can show up as a clear pulse.

  Activates:

  sprouting

  Sample-size threshold:

  At least 10 shares in the spike window.

  Not yet fired on this channel

• Subscribe rate versus view rate

  Compares a video's subscribers-gained-per-view to the channel's median. A high ratio suggests the video reached viewers who were ready to subscribe; a low ratio, viewers passing through.

  Activates:

  sprouting

  Sample-size threshold:

  At least 500 views on the video.

  Not yet fired on this channel

• Subscribers gained without a view spike

  Days when subscriptions stepped up without a corresponding view spike. The pattern usually traces back to off-platform attention rather than algorithmic surfacing.

  Activates:

  sprouting

  Sample-size threshold:

  At least seven days of channel-level subscriber data.

  Not yet fired on this channel

• A change in who is watching

  Tracks shifts in the viewer mix — for example, retention rising while subscribe rate fell, suggesting the same content is reaching a different audience.

  Activates:

  sprouting

  Sample-size threshold:

  Two trailing windows of seven days each.

  Not yet fired on this channel

• Two metrics decoupling

  Marks windows when two metrics that usually move together (impressions and views, or views and watch time) drifted apart for an extended stretch.

  Activates:

  sprouting

  Sample-size threshold:

  At least 14 days in each trailing window.

  Not yet fired on this channel

Channel shape

• 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.

  Activates:

  growing

  Sample-size threshold:

  At least 90 days of channel-daily data.

  Not yet fired on this channel

• A phase transition

  When several channel-shape signals lined up at once — often cadence, concentration, and source mix moving in the same window — the detector marks it as a transition rather than a single event.

  Activates:

  sprouting

  Sample-size threshold:

  Two or more concurrent shape signals.

  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.

  Activates:

  sprouting

  Sample-size 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.

  Activates:

  sprouting

  Sample-size threshold:

  At least 10 videos with retention data.

  Not yet fired on this channel

• Adjacent-video correlation

  Looks for cases where two videos published close together moved together in views, often through Suggested-Videos linking them.

  Activates:

  sprouting

  Sample-size threshold:

  Two videos with overlapping non-zero windows.

  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.

  Activates:

  sprouting

  Sample-size 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.

  Activates:

  sprouting

  Sample-size 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.

  Activates:

  sprouting

  Sample-size 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.

  Activates:

  sprouting

  Sample-size 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.

  Activates:

  sprouting

  Sample-size threshold:

  At least 1,000 trailing impressions.

  Not yet fired on this channel