28 Sep 2026 · 2:44 PM MTUpdated…
Accuracy, transcripts, allowance

Status

Executive reports

Each executive owns and dates their own account. The movement panel below tracks acceptance, reviewed delivery and execution evidence by source time.

Codex report

Updated Sep 28, 12:23 PM MT
61.5%Complete · 16/26 assigned
+3Recorded progress · last 6h
3 accepted · 0 reopened

9 partial · 0 queued for dispatch · 10 assigned awaiting dispatch · 0 fresh task/run markers; markers show reported work, not accepted outcomes. Audit findings and leadership packages are separate scopes; some address related gaps. 6h = recorded acceptances minus reopenings; partial stays open. All 47 IDs and evidence ↗

How measured

Changes come from dated canonical source verdict history. First-recorded completions lack a known acceptance time and are excluded. The documented LDR-02 pre-acceptance entry correction is excluded from reopened work.

27 of 47 tracked findings and leadership packages are source-verified complete.

Working on
Close the closed-gate incident repair path, measure storage growth at the next ordinary scorecard refresh, and preserve honest historical input-clock limits while useful products keep running.
Why
A detected failure must reach an owner and a fresh verified repair; a partial control or benchmark cannot count as a repaired product.
Verified progress
One new independent acceptance: CTRL-07 injected missing image and Yahoo cells, routed two findings, then restored both in the real staged renderer through apply-serving; live optimized rank and points remain visible. CTRL-01 and CTRL-02 remain partial because a closed gate blocks the build worker from claiming the related incident. DATA-02 now refuses verified-as-of claims on unknown issuer, lead, walkforward and G4 inputs, but historical clocks and other consumers remain incomplete. OPS-01 safely reuses unchanged cohort reports after unrelated archive growth in focused tests; production growth has not yet been measured. LDR-07 was independently accepted through owner-feedback receipts. No model gain or new live publish is inferred from these controls.
Next
Claude has a tested gate-specific incident dispatch patch proposal and owns implementation plus empty-board missed-grade proof. Verify the first ordinary scorecard refresh for actual reduced writes; retain older reports until reconstruction and references are proved. Continue DATA-02 historical clock acquisition and remaining consumer gates. Accept only completed owner-linked repair receipts.
Contribution to the vision
Convert defects into verified product repairs and durable controls while preserving the useful live product and scientific release gates.
Evidence and receipts

Canonical source-derived accountability: 27/47 in 9ee6c320 (Codex 16/26, Claude 11/21). · CTRL-07 independent staged browser/producer recovery and live optimized-total verification: ops/audits/codex-control-verification-2026-09-28.md; implementation 22210e02. · CTRL-01/02 blocked wrapper finding and isolated tested patch: 80d96ded; Claude owns production fix. · OPS-01 cohort growth control ad6cd554; three independent targeted tests; production growth unmeasured. · DATA-02 d3f1dfe7,79f1fec1,94235f66,b6c17b79; 23 independent issuer/clock/eval checks; historical clocks absent. · LDR-07 independent owner-feedback closure 91b7a088 and Claude review 98459834.

Claude report

Updated Sep 28, 2:13 PM MT
52.4%Complete · 11/21 assigned
+1Recorded progress · last 6h
1 accepted · 0 reopened

10 partial · 0 queued for dispatch · 10 assigned awaiting dispatch · 0 fresh task/run markers; markers show reported work, not accepted outcomes. Audit findings and leadership packages are separate scopes; some address related gaps. 6h = recorded acceptances minus reopenings; partial stays open. All 47 IDs and evidence ↗

How measured

Changes come from dated canonical source verdict history. First-recorded completions lack a known acceptance time and are excluded. The documented LDR-02 pre-acceptance entry correction is excluded from reopened work.

Make Sean's decisions and the employees' work flow through to results he can see.

Working on
Close the remaining unresolved audit and leadership IDs Codex assigned to Claude, each to its written acceptance, while keeping the served product running.
Why
Sean approved 30 items on Friday and 12 never reached a worker because of a selection bug I introduced. Research had produced 69 findings with 0 in the served model. Activity was high and delivered value was not visible.
Verified progress
13:14 → 14:13 MT (2026-09-28): no Claude-owned audit-accountability id closed this hour; canonical accountability holds at 27/47 (Codex 16/26, Claude 11/21) — CTRL-01/CTRL-02 still PARTIAL on the gate-closed worker-claim path, Codex's isolated patch (80d96ded) still unapplied. build-w5 independently reran PW-93 (14:02 MT) and confirmed it is still correctly DEFERRED by the quiet-window guard, with the grind (launchctl com.playerweek.grind) self-polling it every 15 min at zero model cost — nothing left for a session there until the slate quiets. Same unit flagged a board defect, N-10, showing state=done while its own result text says the Tuesday 09-29 04:00 MT acceptance observation hasn't happened yet; routed to shard 2/audit since N-10 is not a Claude-owned id. On the podcast-selection question left open at 13:06: Sean decided to drop historical offseason podcasts entirely, and Codex iterated the isolated protected-runtime patch twice more to match — d2d68527 → 0bd12d43 → fa8a9248 — now scoped to T0/T1/T2 only (digest 433c69ef13c3065553bf2b3008f9fc88d1e6a428b0aa7c247e594d9510903070, allowed_tiers=[0,1,2], 37 feeds; tracker measures T0 5,109 / T1 5,042 / T2 24,401 = 34,552 eligible vs 23,455 T3 excluded). No Claude session has applied it yet, so runtime adoption is still unproven — tracker counts only. Separately, the unrelated news-read incident (INC-231555d84e) self-resolved wont_fix via a 13:37 MT lane-watchdog decision, no action needed. The Yahoo-cookie Keychain ACL regression from browser-fix 84e9fa1c (5 open incidents, INC-136aee5368/9a48274cb1/eb81e3e668/0e86d6a3b4/e16ac1df8d) is still open and still needs Sean's one-time interactive Keychain grant; now ~1h40m old, still under the 3h escalation bar so not sent to ask-sean.py this cycle. Gate OPEN, chain 8/8, board 238/15, plan 127/127, disk free 136Gi/85% used.
Next
A full Claude session should: (1) apply/adapt Codex's fa8a9248 protected podcast-runtime patch onto feeder/Nimo/Mac transcriber — deploy the Nimo worker first so a missing manifest blocks old staged jobs, then feeder/Mac — and return a fresh selection digest confirming zero T3 rows in flight; (2) adapt Codex's isolated CTRL-01/CTRL-02 patch (80d96ded) onto the live incident_ledger.py/build-loop gate so closed-gate incidents can still reach worker claim, add a durable repo test, and send a receipt; (3) decide and act on the browser.py Keychain regression — either get Sean's one-time Keychain grant for chrome-headless-shell, or take Codex's narrower option (c): keep headless Chrome.app for the Yahoo-authenticated producer children specifically while chrome-headless-shell covers the rest — this is blocking 5 live incidents; (4) correct board item N-10's state field back to "next" (or record the Tuesday observation if it already landed); (5) keep working the review queue toward OPS-05/MODEL-03/MODEL-04/R-02/R-03/LDR-02/03/04/06 acceptance with Codex.
Contribution to the vision
A business where Sean decides and sees results. Employees are graded daily on real output, research findings reach the served product only through paired held-out tests, and negative results are kept as learning.
Evidence and receipts

CODE-6 accepted · b598f366 · ACTUAL-3 accepted · 73ec23c0 · UX-04/UX-05 accepted · 329f5ee1 · SURF-02 accepted · ef43c11d · MODEL-03/MODEL-04 role/joint tests, both rejected · 1d272297 · R-03 lane_intake landing, 17/89 qualifying · d79e5853 · CTRL-07 recovery drill, R6 blind spot fixed · 22210e02 · R-02 standing consumption run, 2 candidates rejected · 990ccccf · OPS-05 Drive-receipt identity fix, 6 losses disclosed · d5d48b06 evidence · LDR-07 reviewed and accepted · 98459834/OWNER-20260928-001, canonical accept 91b7a088 · CTRL-07 recovery drill accepted · 22210e02, committed 9ee6c320 · CTRL-02 ledger claim-ceiling fix, 15/15 tests, stays PARTIAL on gate-closed wrapper path · 1d40a90f · playgrain-loop heartbeat tombstone fixed, planted-negative test · b686fff6 · Yahoo daily-sweep empty-render retry fixed, published live · 307aca48c899dc0020a7.json · browser.py Chrome-for-Testing swap 84e9fa1c broke Yahoo cookie decryption fleet-wide (Keychain ACL) · INC-136aee5368/INC-9a48274cb1/INC-eb81e3e668

Build movement

As of Sep 28 · 2:44 PM MDT

Product repairs reach the live screen, then independent review, then owner acceptance. Research becomes a model improvement only after measured release follow-up.

+4Recorded acceptance · 6h4 accepted · 0 reopened
0Reviewed fixes awaiting owner acceptanceRecheck live after six hours
—Active repairs · evidencedTask + run ID with heartbeat ≤15m; dash means unverified
8:44—
9:44—
10:44—
11:444 accepted
12:44—
1:44—

Recorded acceptanceIndependent review pending owner acceptance · Last recorded acceptance 2.4h ago · CTRL-07

Delivered · awaiting acceptance

No current reviewed delivery receipt is awaiting owner acceptance.

Execution evidence

No fresh bounded task and run receipt. Current audit worker execution is unverified.

Latest activity marker: build-w5 · 1m ago · unit 4 — picking an item (shard 5 of 8). A marker does not establish delivery.

1 Antigravity evidence checks · 6h

Latest completed 2.5h ago; 0 observations sent for manager review. These are preparation receipts, not accepted product or model gains.

Source: research/management/capacity/runs.jsonl · latest r20260928T121322-agy-evidence-flash-5b65e2

Waiting for action

OPS-05 · Claude · 23.8h ago

Mismatched audio archive deletion unresolved; repair executor and receipt missing.

Next: Claude assigns a bounded repair and verifies archive behavior without deleting unique material.

Recheck overdue · data/coord/claude-codex.md 17:51 and 18:13 MT
PW-93 · Claude build worker · 21.6h ago

Historical captured_at repair proven in dry run; live-slate write deferred.

Next: Run the confirmed warehouse repair in a quiet non-live-slate window, then verify rows.

Recheck overdue · c4b1564f; data/coord/claude-codex.md 17:06 MT
Canonical audit: 27/47 verified complete; partial work remains open. Recorded acceptance is a source-verdict change, not proof of model gain. All IDs and evidence ↗ · Build plan ↗

Product and machine measures

Forecast performance

Winner accuracy

How often the issued forecast picked the winning team.

Full scorecard
Live · 2026
74.2%
▼ 0.8 pts 7d
31 games · as issued
Held-out · 2024–25
55.9%
▼ 0.2 since Sep 22
544 games · backtest 2024–25 (fit ≤2023)
Live − backtest +18.3 ptsDifferent seasons and sample sizes; this difference is not a model improvement.

Served v1.0 (fit ≤2025), v1.0.1-availability (fit ≤2025), as issued before kickoff · from wk 2

Exactly what the live numbers score
  • 31 games (winner, margin, total) = Wk 2: 16 from v1.0-20260916 · Wk 3: 1 from v1.0-20260916 · Wk 3: 14 from v1.0.1-availability-20260926
  • 736 player-week rows (fantasy points) = Wk 2: 363 from v1.0-20260916 · Wk 3: 36 from v1.0-20260916 · Wk 3: 337 from v1.0.1-availability-20260926
  • Selection: per 2026 game and player-week: the last COMPLETE forecast-refresh run produced before that kickoff; truth: final game score, and player_week_g fantasy points (a player-week with no points row is not scored).
  • The separate served-release card (research/served_scorecard/v1.0.1-availability-20260926.json) scores a different selection, per team-game: latest VERIFIED_ACTIVATED generation activated strictly before kickoff, and scores a player who did not play in a final game as 0: v1.0-20260916 562 settled rows, weeks 2, 3 (not certified); v1.0.1-availability-20260926 366 settled rows, week 3 (certified).
  • Why these are not the consumer S / SB / SQ / SBQ accuracy cards: the served forecast is one pooled SBQ fit, so no served S, SB or SQ rows exist; these live figures mix two frozen releases rather than one release at one cutoff; and they are not yet bound to the per-grain frozen-forecast records those cards require. The arm ablation below is a refit, not the served product.
Measured vs live

Forecast quality

Winner ↑ · error ↓
measuredactualgap
Winner correctn 31
55.9%▼ 0.2 since Sep 22
74.2%▼ 0.8 7d
+18.3
Marginn 31
96.8%· 0.0 since Sep 22
94.7%▲ 1.2 7d
−2.1
Totaln 31
23.3%· 0.0 since Sep 22
25.9%▼ 0.6 7d
+2.6
Team pointsn 62
33.7%· 0.0 since Sep 22
36.8%▼ 5.2 7d
+3.1
Pass yardsn 62
25.0%· 0.0 since Sep 22
19.3%▲ 0.9 7d
−5.7
Rush yardsn 62
32.9%· 0.0 since Sep 22
31.5%· 0.0 7d
−1.4
Fantasy pointsn 736
55.8%· 0.0 since Sep 22
62.7%▼ 3.7 7d
+6.9

Winner = % correct. Other rows: %error = mean |pred − actual| ÷ mean |actual|. Held-out: 2024–25 (fit ≤2023). Live: 2026 as issued. Read Sep 28 · 2:44 PM MT.

With vs without

Feature contribution

Green helps
B hypB liveQ hypQ live
Winner correct
0.0
0.0
−0.4
0.0
Margin
+0.2
+0.4
+0.2
+0.4
Total
−0.1
+0.1
−0.1
+0.1
Team points
0.0
+0.1
0.0
+0.1
Pass yards
−0.1
0.0
−0.1
0.0
Rush yards
0.0
−0.1
0.0
−0.2
Fantasy points
+0.1
−1.5
+0.1
+0.2

B = coaching decisions; Q = injury-report text. Test = backtest 2024–25 (fit ≤2023); live = 2026 wk 1–3 refits. News claims are withheld.

Podcast tracker

Selected current shows: 48 · 48 indexed · 1,052 indexed shows excluded (outside selected current roster). Eligible episodes: 40,184 across T0–T2. Historical offseason excluded: 26,927. Reviewed 2026-09-28T20:17:01.783727Z; review due 2026-10-12.

Top 20 fantasy-football shows from the US Apple Fantasy Sports chart (updated 2026-09-28T13:15:01-07:00, checked 2026-09-28T20:17:01.783727Z): 20/20 RSS indexes captured; 20/20 recent RSS metadata; 20/20 have T0–T2 episodes. Mac queue receipt pending refresh.

Retained shows and selection evidence
  • The Athletic Football Show: A show about the NFL · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 3114 · Deep tactical and roster analysis across the league.
  • NFL Daily with Gregg Rosenthal · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 8195 · NFL Media reporting, news reaction, and all-league game coverage.
  • The Ringer NFL Show · indexed · latest 2026-09-26 · Apple Podcasts US rating count: 4448 · High-reach weekly interpretation and team/storyline context.
  • The Mina Kimes Show featuring Lenny · indexed · latest 2026-09-24 · Apple Podcasts US rating count: 6798 · Distinct film-led and scheme-focused analysis.
  • Yahoo Sports NFL · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 1170 · National reporting and immediate game reaction from Yahoo Sports.
  • Ross Tucker Football Podcast: Daily NFL Podcast · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 2131 · Former-player perspective and daily game analysis.
  • Sharp Football Analysis by Warren Sharp · indexed · latest 2026-09-25 · Apple Podcasts US rating count: 202 · Matchup, strategy, and betting-oriented analysis; lower rating count accepted for distinct quantitative focus.
  • The PFF NFL Podcast · indexed · latest 2026-09-25 · Apple Podcasts US rating count: 1626 · Player-grading and matchup analysis from a separate data provider.
  • Fantasy #3 · Fantasy Footballers - Fantasy Football Podcast · indexed · RSS 1,969 · captured 2026-09-28T20:18:21.596757+00:00 · eligible 1,182 · Mac queue unverified · confirmed audio 11 · latest 2026-09-28 · Apple Podcasts US rating count: 29640 · Leading audience proxy and broad start/sit, injury, and waiver coverage.
  • Fantasy #4 · FantasyPros - Fantasy Football Podcast · indexed · RSS 2,392 · captured 2026-09-28T20:18:22.730163+00:00 · eligible 1,570 · Mac queue unverified · confirmed audio 30 · latest 2026-09-28 · Apple Podcasts US rating count: 10659 · Expert consensus and actionable weekly waiver/ranking coverage.
  • Fantasy #1 · Fantasy Football Today · indexed · RSS 3,053 · captured 2026-09-28T20:18:20.711251+00:00 · eligible 1,840 · Mac queue unverified · confirmed audio 17 · latest 2026-09-28 · Apple Podcasts US rating count: 8106 · Long-running CBS fantasy news and game-by-game reaction.
  • Fantasy Focus Football · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 13453 · Large established audience and ESPN fantasy reaction.
  • Fantasy #2 · The Ringer Fantasy Football Show · indexed · RSS 833 · captured 2026-09-28T20:18:21.231036+00:00 · eligible 558 · Mac queue unverified · confirmed audio 6 · latest 2026-09-28 · Apple Podcasts US rating count: 1741 · Distinct Ringer fantasy slate discussion and recaps.
  • Fantasy #5 · Yahoo Fantasy Forecast with Matt Harmon · indexed · RSS 1,185 · captured 2026-09-28T20:18:23.108664+00:00 · eligible 761 · Mac queue unverified · confirmed audio 10 · latest 2026-09-28 · Apple Podcasts US rating count: 794 · Matt Harmon receiver/usage analysis and Yahoo fantasy reporting.
  • Fantasy #17 · Establish The Run Fantasy Football · indexed · RSS 1,011 · captured 2026-09-28T20:18:32.046909+00:00 · eligible 553 · Mac queue unverified · confirmed audio 7 · latest 2026-09-24 · Apple Podcasts US rating count: 1502 · Projection-driven player valuation and rest-of-season analysis.
  • Fantasy #8 · The Late-Round Fantasy Football Podcast · indexed · RSS 1,338 · captured 2026-09-28T20:18:25.033689+00:00 · eligible 834 · Mac queue unverified · confirmed audio 15 · latest 2026-09-26 · Apple Podcasts US rating count: 3154 · JJ Zachariason’s compact, process-based fantasy analysis.
  • Fantasy #14 · Rotoworld Football Show – Fantasy Football · indexed · RSS 1,389 · captured 2026-09-28T20:18:30.954035+00:00 · eligible 879 · Mac queue unverified · confirmed audio 8 · latest 2026-09-28 · Apple Podcasts US rating count: 1198 · Rotoworld player news and game-by-game fantasy interpretation.
  • Fantasy #18 · Dynasty Nerds Podcast | Dynasty Fantasy Football · indexed · RSS 938 · captured 2026-09-28T20:18:32.465015+00:00 · eligible 541 · Mac queue unverified · confirmed audio 12 · latest 2026-09-25 · Apple Podcasts US rating count: 2047 · Dynasty-specific player trade and long-horizon valuation.
  • The Favorites Sports Betting Podcast · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 1411 · NFL lines, contest discussion, and betting market context.
  • Even Money: NFL Betting Podcast · indexed · latest 2026-09-24 · Apple Podcasts US rating count: 666 · NFL betting and prop perspective from Ross Tucker and Steve Fezzik.
  • The Football Analytics Show by The Power Rank and Ed Feng · indexed · latest 2026-09-25 · Apple Podcasts US rating count: 154 · Independent quantitative football analysis; specialist exception to a high rating-count threshold.
  • 49ers Talk: A San Francisco 49ers Podcast · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 1012 · Established 49ers beat and postgame coverage.
  • PHLY Philadelphia Eagles Podcast · indexed · latest 2026-09-26 · Apple Podcasts US rating count: 587 · Frequent Eagles beat reporting and game previews.
  • Talkin’ Giants (Giants Podcast) · indexed · latest 2026-09-27 · Apple Podcasts US rating count: 2407 · Strong team-audience proxy and detailed Giants postgame analysis.
  • Purple Daily | a Minnesota Vikings podcast · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 1450 · Vikings-specific reporting and reaction with a strong team-audience proxy.
  • Pack-A-Day: Your Daily Packers Podcast · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 894 · Packers-specific daily analysis and roster context.
  • Shout! A football podcast on the Buffalo Bills with Matt Parrino and Ryan Talbot · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 255 · Bills beat reporting; chosen over a second Bills live-talk feed to limit duplication.
  • Browns Film Breakdown · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 529 · Browns film study adds team-level tactical detail.
  • The Vault: A Podcast Covering the Baltimore Ravens · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 347 · Dedicated Ravens reporting and local postgame context.
  • DolphinsTalk.com Daily Podcast · indexed · latest 2026-09-27 · Apple Podcasts US rating count: 551 · Dolphins beat and postgame reaction.
  • The Detroit Lions Podcast · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 522 · Independent Lions game reaction and team context.
  • KC Sports Network: Kansas City Chiefs Podcasts · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 523 · Chiefs-focused reporting and analysis with established team audience.
  • Guilty As Charged: An LA Chargers Podcast · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 280 · Chargers film and postgame perspective.
  • Daily Seahawks Podcast: HB Mornings & Real Hawk Talk · indexed · latest 2026-09-27 · Apple Podcasts US rating count: 757 · Seahawks-specific live reaction and game analysis.
  • Locked On Steelers – Daily Podcast On The Pittsburgh Steelers · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 734 · Selected single Steelers daily for recent activity and strong team audience.
  • Play Like A Jet: New York Jets · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 617 · Established Jets-specific reporting and game reaction.
  • Locked On Broncos - Daily Podcast On The Denver Broncos · indexed · latest 2026-09-28 · Apple Podcasts US rating count: 457 · Selected single Broncos daily for recent activity and established team audience.
  • Fantasy #6 · Yahoo Fantasy Football with Josh & Hayden · indexed · RSS 1,051 · captured 2026-09-28T20:18:23.365787+00:00 · eligible 619 · Mac queue unverified · confirmed audio 8 · latest 2026-09-28 · Apple Podcasts US rating count: 808 · Current Apple US fantasy-football top 20; Yahoo hosts offer distinct waiver and player discussion.
  • Fantasy #7 · Fantasy Football Happy Hour with Matthew Berry · indexed · RSS 43 · captured 2026-09-28T20:18:24.682847+00:00 · eligible 43 · Mac queue unverified · confirmed audio 4 · latest 2026-09-28 · Apple Podcasts US rating count: 852 · Current Apple US fantasy-football top 20; Matthew Berry’s established fantasy coverage.
  • Fantasy #9 · The Audible · indexed · RSS 65 · captured 2026-09-28T20:18:25.751407+00:00 · eligible 65 · Mac queue unverified · confirmed audio 5 · latest 2026-09-28 · Apple Podcasts US rating count: 1867 · Current Apple US fantasy-football top 20; Footballguys analysis and start/sit coverage.
  • Fantasy #10 · Pat Mayo Experience · indexed · RSS 2,287 · captured 2026-09-28T20:18:26.147422+00:00 · eligible 1,317 · Mac queue unverified · confirmed audio 19 · latest 2026-09-28 · Apple Podcasts US rating count: 5242 · Current Apple US fantasy-football top 20; recurring NFL fantasy and DFS episodes share a mixed golf/NFL feed.
  • Fantasy #11 · Fantasy Football Today Beyond the Box Score · indexed · RSS 1,630 · captured 2026-09-28T20:18:29.547492+00:00 · eligible 957 · Mac queue unverified · confirmed audio 9 · latest 2026-09-26 · Apple Podcasts US rating count: 754 · Current Apple US fantasy-football top 20; CBS analytical fantasy extension.
  • Fantasy #12 · Fantasy Football World · indexed · RSS 30 · captured 2026-09-28T20:18:29.761011+00:00 · eligible 30 · Mac queue unverified · confirmed audio 6 · latest 2026-09-28 · Apple Podcasts US rating count: 597 · Current Apple US fantasy-football top 20; recent active fantasy-football coverage despite a short episode history.
  • Fantasy #13 · Harris Fantasy Football Podcast · indexed · RSS 106 · captured 2026-09-28T20:18:30.566348+00:00 · eligible 105 · Mac queue unverified · confirmed audio 4 · latest 2026-09-28 · Apple Podcasts US rating count: 3760 · Current Apple US fantasy-football top 20; film-informed player evaluation.
  • Fantasy #15 · Fantasy Footballers DFS & Betting - Fantasy Football Podcast · indexed · RSS 433 · captured 2026-09-28T20:18:31.206301+00:00 · eligible 319 · Mac queue unverified · confirmed audio 8 · latest 2026-09-25 · Apple Podcasts US rating count: 2028 · Current Apple US fantasy-football top 20; DFS and betting focus of the Footballers network.
  • Fantasy #16 · RotoWire Fantasy Football With Theo Gremminger · indexed · RSS 2,017 · captured 2026-09-28T20:18:31.570499+00:00 · eligible 1,327 · Mac queue unverified · confirmed audio 9 · latest 2026-09-28 · Apple Podcasts US rating count: 302 · Current Apple US fantasy-football top 20; RotoWire fantasy player and market analysis.
  • Fantasy #19 · Fantasy Footballers Dynasty - Fantasy Football Podcast · indexed · RSS 181 · captured 2026-09-28T20:18:32.651130+00:00 · eligible 103 · Mac queue unverified · confirmed audio 0 · latest 2026-09-23 · Apple Podcasts US rating count: 1086 · Current Apple US fantasy-football top 20; dynasty specialization of the Footballers network.
  • Fantasy #20 · Fantasy Football Daily with Brett and Scott · indexed · RSS 1,209 · captured 2026-09-28T20:18:33.062143+00:00 · eligible 695 · Mac queue unverified · confirmed audio 12 · latest 2026-09-28 · Apple Podcasts US rating count: 152 · Current Apple US fantasy-football top 20; Fantasy Points player analysis under the current Brett and Scott title.
T06,144 episodes · 48 feeds
Current season · all publication days
downloaded499 / 6,144 · 8.1%
transcribed200 / 6,144 · 3.3%
5,645 episode states unknown · Nimo receipt incomplete or stale
Open to load feeds.
T15,985 episodes · 44 feeds
Historical in-season · Friday published
downloaded2,411 / 5,985 · 40.3%
transcribed37 / 5,985 · 0.6%
3,574 episode states unknown · Nimo receipt incomplete or stale
Open to load feeds.
T228,055 episodes · 45 feeds
Historical in-season · other days
downloaded2,777 / 28,055 · 9.9%
transcribed41 / 28,055 · 0.1%
25,278 episode states unknown · Nimo receipt incomplete or stale
Open to load feeds.

Indexed 2026-09-28T20:43:52.191082+00:00 · 40,184 eligible episodes · 537,445 known indexed archive episodes (470,334 outside roster; 26,927 historical offseason excluded). Nimo inventory 2026-09-28T02:00:32+00:00 · stale or unavailable · T0 tier policy adoption not yet verified · Selection feeder adoption unverified. Bars count confirmed audio/transcript receipts; absent remote items are unknown when the Nimo inventory is stale. Friday describes publication priority, not download timing.

Research

Findings and adoption

69findings
6adopted
0live in served
27in review
See findings
In served v1.0hypactual
CARD · served v1.0.1-availability-20260926 (certified)
held-out MAE 3.54 [3.47, 3.62] (2024-25, all rostered)
live MAE 3.69 [3.30, 4.11], 366 settled (wk 3, row CI); rookie prior MAE 9.63 (2 settled); K/DEF MAE 5.35 (16 settled); 6,697 rows pending; replay 21,264/21,264 exact + 1,135/1,135 K/DEF+rookie; graded 2026-09-28 05:24 MT
CP-H49 · trailing windows include last game
−0.352 FP MAE
no live A/B
CP-H65 · stop pricing all weeks on wk-1 market
−0.063 FP MAE
no live A/B
CP-H199 · kalman share leak removed
+0.040 FP MAE
no live A/B
CP-H6 · order-independent room sums
−0.006 FP MAE
no live A/B
CP-H43 · pass attempts weighted to recent
−0.071 att MAE
no live A/B
CP-H47 · DEF events from implied total
−0.178 DEF MAE
no live A/B
Adopted findings · live shadow vs servedhypactual
B13 · draft capital on thin history
+0.048 pts RMSE vs BASE (thin)
gain −0.031 MAE, 174 rows, 3 wk [−0.096,+0.008]; backtest −0.011 · not promoted
B41 · draft + contract on thin history
+0.059 pts RMSE vs BASE (thin)
gain −0.025 MAE, 174 rows, 3 wk [−0.074,+0.012]; backtest −0.030 · not promoted
Q-13 · Saturday attention → availability
−0.0030 Brier (P(play))
live shadow scores from week 4; backtest +0.0029 · not promoted
Q-14 · fame adds nothing (a null)
null: −0.005 pts, floor not cleared
nothing to serve
Q-19 · expert file leaks availability (control)
control passed: −0.020 Brier = contaminated
not servable: leak
XD-S07 · empirical null for the batteries
method: null sd 2.22 vs 1.00
not a model feature
R-02 · promoted feature lf_garbage_time_clock_kill_l3 through the served training path
playgrain loop: +0.000568 log-loss delta (play grain, not FP)
gain +0.048 MAE, 372 rows, 2 wk [−0.016,+0.116]; backtest −0.003 · not promoted
H-030 · receiving shares: Poisson + attempts weight (O3 cycle)
−0.0242 FP MAE (D-212, 2025 only)
gain +0.034 MAE, 666 rows, 2 wk [−0.030,+0.104]; backtest +0.008 · not promoted

Σ hyp −0.38 FP MAE (4 rows) · Σ actual no live A/B

Hypotheses: docs/hypotheses.json · review incl. 10 L-07 · fixes: CHANGES-PROPOSED.md

Capacity

Weekly model allowance

Account-wide · projected from the last 24h
Claude28% remainingProjected out Oct 1 · ~3 AM MTRead Sep 28 · 2:37 PM MTHow estimated

11 quota points used over 23.9h within the last 24h; pace may change.

Weekly allowance resets Oct 1 · 9:00 PM MT.

Logged scheduled starts, last 24h: 0

Account-wide allowance; includes work outside Playerweek.

Codex16% remainingProjected out Sep 28 · ~11 PM MTRead Sep 28 · 2:44 PM MTHow estimated

45 quota points used over 24.0h within the last 24h; pace may change.

Weekly allowance resets Oct 3 · 12:15 PM MT.

Logged scheduled starts, last 24h: 0

Account-wide Codex allowance. Direct account-status read; no model request.

Antigravity · Gemini models77.8% remainingNo measurable usage increaseRead Sep 28 · 2:44 PM MTHow estimated

0 quota points used over 0.6h within the last 24h; pace may change.

Weekly allowance resets Oct 1 · 7:29 PM MT.

Logged scheduled starts, last 24h: 56

Shared by Gemini Flash and Pro in Antigravity. Local scheduled starts also have a 15-minute cooldown. Gemini app/web usage is unknown here.

Antigravity · Claude and GPT models89.6% remainingNo measurable usage increaseRead Sep 28 · 2:44 PM MTHow estimated

0 quota points used over 1.4h within the last 24h; pace may change.

Weekly allowance resets Oct 1 · 11:19 PM MT.

Shared by Claude Opus, Claude Sonnet and GPT-OSS in Antigravity; separate from Claude Code and Codex.