| S-16 | done | S-16 — Trajectories are content-hashed per (game, lock, release); issuance is frozen with the existing |
| S-11 | done | S-11 — Kickoffs (with the 2024 rule era), punts, returns, blocks, and field goals by kicker rating × di |
| T-02 | done | T-02 — Regularised adjusted plus-minus at the play grain: a sparse design matrix (players on field × ro |
| X-02 | done | X-02 — Add `form_off`, `form_def` (leave-one-play-out EPA in this game) to `LATENT`; fit the distributi |
| X-04 | done | X-04 — Simulation-based calibration of a small vector of logit offsets against drive and game moments f |
| B-03 | done | B-03 — Personnel grouping (11/12/21…) given state and roster. This selects the on-field set from A-05. |
| T-05 | done | T-05 — Weekly state-space update per player-skill: process noise by age and position, a shock term on r |
| X-05 | done | X-05 — Key numbers: the mass at 3, 6, 7, 10, 14 and 17 on margin, and at 37, 41, 44, 47 and 51 on total |
| X-06 | done | X-06 — The column-by-column real-against-simulated feature diff that found the 3.2-sd `games_seen` shif |
| B-05 | done | B-05 — Box count, rushers, man/zone, shell, given state, offensive personnel and DC. These are the W-00 |
| B-06 | done | B-06 — Who gets the ball. Run: carrier among on-field backs and QB (designed or scramble). Pass: a mult |
| S-17 | done | S-17 — Any team-season against any team-season, retired players included. The north star's first demand |
| S-18 | done | S-18 — Whole seasons and playoffs. Ratings evolve between simulated weeks and injuries accrue through A |
| S-19 | done | S-19 — Compile the boosters (treelite or lleaves, or Numba lookup tables) if S-14 misses its budget. | |
| T-08 | done | T-08 — Every rating family is scored on what it adds to the kernel and logged to the ledger. | — |
| S-15 | done | S-15 — The compiler: margin, total, moneyline, team totals, alt lines, any prop, fantasy points under a |
| S-14 | done | S-14 — The rollout, vectorised across trajectories and the slate, with **player attribution**: every pl |
| T-09 | done | T-09 — Shrinkage audit DONE: five families, each with a held-out comparison |
| B-02 | done | B-02 — Action model v2, replacing `train_action.py`: P(action \| state, personnel, unit ratings, QB, we |
| X-01 | done | X-01 — **First thing built.** k-step rollouts from real states (k = 1, 2, 4, 8, 16, to end of drive); d |
| S-08 | done | S-08 — Early stopping on a validation season, not an inference cap at 60 rounds. 115 integer yard bins. |
| T-01 | done | T-01 — The role of every player on every play: passer, carrier, target, route runner, pass blocker, run |
| S-12 | done | S-12 — Interception and fumble returns, defensive TDs, recovery. This replaces the additive 2.18 pts/te |
| S-09 | done | S-09 — A learned penalty model: type, yards and automatic first down, by crew (C-07) and team disciplin |
| X-03 | done | X-03 — Density-ratio classifier (real states against simulated); reweight the transition fits to the si |
| T-03 | done | T-03 — Directly measured component skills with shrinkage, from NGS, PFR advanced, FTN and pbp (the comp |
| T-06 | done | T-06 — The lineup → unit function: a learned map from the on-field players' vectors to the unit quantit |
| S-13 | done | S-13 — Rule-exact overtime by era. | 61% of overtime games finish on 3, as in history. |
| S-10 | done | S-10 — Semi-Markov durations: the elapsed-time *distribution* per play type, state, tempo and coach, in |
| B-04 | done | B-04 — Go/punt/kick by coach. The late-and-close policy is its own model: kneel-downs, playing for the |
| B-07 | done | B-07 — A play-caller effect has to survive a change of team and quarterback, or it is a team effect in |
| T-07 | done | T-07 — From the tracking releases: speed, acceleration, separation at throw, get-off, closing speed. Th |
| T-04 | done | T-04 — Priors for players with little history: draft pick (the only B-hypothesis that ever paid, B13/B4 |
| B-01 | done | B-01 — Head coach, play-caller, OC and DC per team-week, as-of. `coordinators.csv` exists; fix `games_r |
| S-06 | done | S-06 — Calibration measured: held-out reliability FAILS |