Each child directory is an immutable result record. Exact metrics, protocol, raw console output and caveats live in that directory; this page only routes readers to the right comparison.

Result record	Question answered
`easycom_omni_floor_screen_2026-09-16/`	Whether G+A, pooled-V, or current-frame F1 improve raw boundaries and provisional semantic opportunities over EgoSpeak
`easycom_egospeak_three_level_eval_2026-09-16/`	How dense forecasting, raw boundary anticipation, and provisional opportunity-conditioned ENTRY/YIELD differ for the EgoSpeak baseline
easycom_oracle_pooled_wearer_audit_2026-09-10/	Fixed-four-epoch three-seed oracle test results and the limited wearer gains of historical pooled AV
`easycom_open_stream_vs_causal_prefix_2026-08-19/`	How prepared-media open-stream and causal-prefix features compare
`easycom_open_stream_8s_vs_20s_2026-08-23/`	Frozen open-stream context-length comparison
`easycom_sparse_supervision_vs_lora_2026-08-24/`	Sparse supervision versus LoRA comparison
`easycom_omni_lora_sparse_epoch2_2026-08-24/`	Sparse epoch-2 LoRA result and provenance
`easycom_frozen_3b_8s_last4_learned_mix_2026-08-26/`	Learned last-four-layer mixture ablation
`easycom_loss_structure_4ep_2026-08-26/`	LSTR-MCE versus independent BCE versus four-state CE
`easycom_transition_auxiliary_4ep_2026-08-27/`	Supervised transition head and expected-reward objectives
`easycom_encoder_only_1s_4ep_2026-08-28/`	Encoder-only A/V/AV versus global-Thinker local-feature baselines
`easycom_track_gru_residual_4ep_2026-09-07/`	Matched pooled/anonymous-track-GRU screen and near-zero residual-gate diagnosis
`easycom_oracle_information_4ep_2026-09-07/`	Causal aggregate/per-person oracle information value and identity-continuity control

Interpretation rules

Do not compare full-timeline and causal-valid metrics without naming the protocol.
A single seed is preliminary even when its absolute improvement is large.
Framewise mAP is retained for EgoSpeak comparability; it does not prove correct floor-entry/yield behavior.
G+A+V > G+A does not prove visual speaker grounding unless correct visual alignment also beats wrong-person/time-shift controls.
Historical transition-auxiliary results concern generic label changes, not the new scenario-conditioned wearer entry/yield objective.

Required contents for a new result record

results/<dataset>_<question>_<date>/
  README.md       # hypothesis, command/config, split, seeds, interpretation
  summary.json    # machine-readable aggregate and provenance
  metrics.csv     # when a tabular comparison exists
  raw_console.txt # optional but recommended

Never overwrite a dated record with a new protocol. Create another directory and link the relationship from both READMEs.