?

Layout: UMAP(centroids, cosine). Each channel = mean of its bge-large chunk embeddings. Move the sliders to change connectivity; Louvain is pre-baked per top-k.

— pick a channel — A Quality ExistenceAdams FallAm I DrivingAndrea with the BangsAphrael PilotsonBrett AndresBrian of College StationCassidy van der KampChad Matthew AlvinChannel UCiJmdXTb76iCharlie's Little CornerChris HowardChristian BaxterClimbing Mt SophiaCorner CitizenEin Sof - Infinite ReflectionsEmily RajehEolson-helperEric SeitzEthan CaugheyEverett Vroon (EJV)EzrafaturechiFinding IdeasFree RilianFrom Whom All Blessings FlowGrail CountryGrey HamiltonGrizwald GrimHow to Understand the WorldJohn VervaekeJonathan DumeerJonathan PageauJordan B PetersonJordan HallJoseph LambrechtJustinsmorningcoffeeK Joseph RivetKale ZeldenLucas VosLuke ThompsonMarc JacksonMark D ParkerMark SMary KochanmcmosavMore ChristNeal DaedalusNechama GluckNickolas ShermanNuance ForumOG RosePaul AnleitnerPaul Rene NicholsPaul VanderKlayPresident FoxmanRafekelleyRandos UnitedRandos United 2Rebel WisdomRestoring MeaningRigel Windsong ThurstonRightinchristRon CoppermanSartori StudiosSecular KoranismShoulder SerfSkankensteinStrange TheologyThe AnadromistThe Chris ShowThe Meaning Codethe plebistocratThe Young LeviteTheCommonToadTheScrollersPodcastTransfiguredUpCycleClubWavesofobsession

Semantic Citations

sem: ? · cite: ? · comms: ?

Gravity (repulsion): -500 Central pull: 0.05 Spring length: 80 Spring strength: 0.02 Damping: 0.9 Avoid overlap: 0.4

Pipeline

1. Source: ~22K primary YouTube video transcripts (Canary ASR preferred, YouTube auto-captions fallback) for channels listed in channels.yml.
2. Chunking: each transcript split into ~400-token sentence-aware chunks. ~32 chunks/video.
3. Embedding: each chunk encoded with BAAI/bge-large-en-v1.5 (1024-d, fp16). Stored in Qdrant collection tlc-graph-research.
4. Channel centroid: L2-normalized mean of a channel's chunk embeddings.
5. Distinctive direction (key step): centroid − corpus-mean direction, renormalized. Removes the shared "long-form intellectual English" baseline so cosines spread from a tight 0.85–0.99 band into roughly −0.3 → +0.9.
6. Cosine similarity on the distinctive centroids → the matrix used everywhere downstream.
7. k-NN graph: each node keeps its top-K most-similar neighbors as edges.
8. Communities: Louvain on the weighted k-NN graph, pre-baked for every k ∈ {2..15}.
9. Layout: UMAP(centroids, cosine, n_neighbors=10, min_dist=0.20) → 2D positions.
10. Cluster labels: per-cluster TF-IDF (unigrams + bigrams, stopword-filtered) over each member channel's concatenated chunk text.
11. Citation edges (overlay): aggregated from Elasticsearch internal_references. A → B counts how many of A's video descriptions link to one of B's videos. Channel-level, directional.

Inspector columns

• sim — pairwise cosine on the distinctive centroids. Positive = aligned content direction. ~0 = generic. Negative = anti-aligned. Typical range −0.3 → +0.9.
• z — how many σ this neighbor's similarity is above the mean of the selected channel's similarity row. >1σ noteworthy, >2σ strong, ≥3σ a standout. Says "unusually close for this channel", beyond the global baseline of "everyone's close-ish."
• Δ-next — gap in similarity to the next-ranked neighbor. A large gap is a cliff: the listed neighbor is qualitatively more similar than whoever's next. >0.02 meaningful; >0.05 a strong break.

Controls

• top-k neighbors: how many edges per node (Louvain runs separately for each k).
• edge floor: only render semantic edges with sim ≥ floor.
• Semantic / Citations: toggle each edge layer.
• citation count [min..max]: filter the citation overlay to a band.
• citation pull / semantic pull: when Physics is on, edges become springs whose rest length shortens with citation count / similarity. 0 = that layer doesn't contribute to physics.
• Gravity (repulsion): Barnes-Hut all-pairs repulsion. More negative = nodes push each other harder; communities separate.
• UMAP Reset: snap nodes back to original UMAP positions.
• De-overlap: short burst of collision-only physics to nudge overlapping nodes apart with minimal layout disruption.

Caveats

• Dense embedders compress within-domain similarity. All TLC channels are long-form intellectual English. The distinctive-direction step is what makes relative comparisons read; trust orderings, z-scores, and gaps more than raw cosine magnitudes.
• Channel size affects centroid noise. Large channels (PVK ~113K chunks) have very smooth centroids; small channels (<200 chunks) are noisier and may sit slightly oddly.
• Citation overlay is incomplete. ~2K reference target videos didn't resolve to any channel in our index; another ~4K reference channels weren't in channels.yml and were dropped.