Results for “downtrend”

Trains, evaluates, and runs inference for Mask Auto-Label (MAL) weakly-supervised segmentation models using ViT-MAE backbones with minimal point or box annotations.

DEPRECATED in v5.6.0 — see joint-multi-tf-v560 skill. Documents the v5.2.0 dual-model approach (train separate 15Min/1Hour models, combine via weighted voting). Still relevant for: (1) loading legacy v5.5.0 dual models, (2) understanding the historical aggregation layer, (3) resampling pattern via origin='start'.

Produce displace/team/ghost talk tracks for the incumbent on a recompete pursuit. Use when user wants competitive angles saved to the pursuit vault; optional multi-turn LLM for customer-facing phrasing.

OWL v5.2 — Pure contrarian. One scanner, one thesis: the crowd is wrong. Monitors crowding across top 30 assets (funding extremity, OI concentration, SM tilt). When crowding persists 4+ hours AND exhaustion signals fire (volume declining, price stalling, RSI divergence), enters AGAINST the crowd to ride the liquidation unwind. 1-2 trades per day max. Re-crowding exit: if the crowd comes back, thesis is dead, exit immediately. DSL High Water Mode (mandatory). The patient predator. v5.2: funding floor lowered from 20% to 12% so the five-factor scoring model actually runs. Added observability logging (top 3 crowding scores per scan cycle).

Track performance across sessions and reduce scaffolding as competence grows. Makes fading visible — the learner knows when scaffolds are removed and why. Use for sustained learning engagement where independence is the goal.

Fix HOLD bias in RL reward function. Trigger when: (1) model learns to always HOLD, (2) trade rate is too low (<10%), (3) slippage penalty exceeds typical price moves.