{
  "_meta": {
    "session": "v9 session 2026-07-31 — first application of the analytical framework (v9.0) to the X-algorithm domain",
    "method": "Every prediction: positive-event form, 5-gate resolvability check (designated source, observable criterion, granularity match, stranger test, post-registration events only), outside-view anchor (hazard rate or reference class), log-odds evidence ledger (items capped at ±1.0 lo), and a SHADOW BASELINE — the 60-second gut number recorded before the framework number was computed. Shadow vs framework is a live A/B: when each prediction resolves, both arms get a Brier score; persistent lift ≤ 0 means the method is overhead and we say so.",
    "logged_at": "2026-07-31",
    "model": "claude-fable-5",
    "scoring": "Brier per arm on resolution; results published on this page. Registry entries are never silently revised — updates are new entries.",
    "effective_independent_bets": 6,
    "drivers": ["xai-release-cadence", "weights-transparency", "competitor-adoption", "x-api-economics", "engagement-content-correlates", "mini-model-behavior-stability"]
  },
  "predictions": [
    {
      "id": "p1-next-drop",
      "prediction": "A new commit is pushed to github.com/xai-org/x-algorithm (main branch HEAD changes from 0bfc279) between 2026-08-01 and 2026-09-15",
      "confidence": "48%",
      "shadow_baseline": "60%",
      "timeframe": "2026-08-01 → 2026-09-15 23:59 UTC",
      "resolution_source": "github.com/xai-org/x-algorithm commit history (main branch)",
      "resolution_criterion": "HEAD SHA on main differs from 0bfc279 on deadline day. Stranger-testable in one click.",
      "falsification": "HEAD still 0bfc279 on 2026-09-16",
      "sq_change": "CHANGE",
      "driver": "xai-release-cadence",
      "anchor": {"type": "hazard", "value": 0.38, "basis": "k=2 public drops (Jan 20, May 15) over L=192 days -> lambda=0.0104/day; w=46 days; P=1-e^(-0.479)=0.38"},
      "ledger": [
        {"item": "Jul 15 public full-codebase pledge creates pressure to show movement", "lo": 0.4},
        {"item": "stated ~4-week update cadence (broken in practice, but signals intent)", "lo": 0.2},
        {"item": "post-exfiltration security review may freeze releases", "lo": -0.2}
      ],
      "resolved": false, "outcome": null
    },
    {
      "id": "p2-weights-public",
      "prediction": "Numeric production ranking weights (the values the withheld params module supplies to ranking_scorer.rs, or their successor) appear in public code from X/xAI by 2026-12-31",
      "confidence": "14%",
      "shadow_baseline": "15%",
      "timeframe": "2026-07-31 → 2026-12-31 23:59 UTC",
      "resolution_source": "github.com/xai-org (any repo) / official X engineering channels",
      "resolution_criterion": "A public file from X/xAI contains numeric weight values consumed by the production ranking formula (named constants for the engagement heads). Partial (demo/sample constants labeled illustrative) does NOT count.",
      "falsification": "No such file public by deadline",
      "sq_change": "CHANGE",
      "driver": "weights-transparency",
      "anchor": {"type": "reference-class", "value": 0.12, "basis": "(a) Musk public-deadline promises delivered on time and in full: low base rate (~15%; 2022 'open source the algorithm' promise delivered partial, ~11 months late); (b) revealed preference: two 2026 drops each deliberately withheld params"},
      "ledger": [
        {"item": "competitive/regulatory transparency pressure wildcard", "lo": 0.2}
      ],
      "resolved": false, "outcome": null
    },
    {
      "id": "p3-full-codebase-verified",
      "prediction": "X publishes its full codebase publicly WITH a named third party attesting production-matches-GitHub, by 2026-12-31 (the July 15 pledge, delivered as stated)",
      "confidence": "7%",
      "shadow_baseline": "10%",
      "timeframe": "2026-07-31 → 2026-12-31 23:59 UTC",
      "resolution_source": "official X/xAI announcement + the published repo(s)",
      "resolution_criterion": "Both parts required: (1) repo(s) presented as the full X codebase are public; (2) an announcement names a specific third-party verifier of production parity. Stranger reads the announcement and repo landing page only.",
      "falsification": "Either part missing at deadline",
      "sq_change": "CHANGE",
      "driver": "weights-transparency",
      "anchor": {"type": "reference-class", "value": 0.08, "basis": "Musk-deadline reference class as p2, further discounted for the two-part criterion (full publication AND third-party verification)"},
      "ledger": [
        {"item": "coherence: must stay <= p2-weights-public (full verified codebase implies weights)", "lo": 0.0}
      ],
      "resolved": false, "outcome": null
    },
    {
      "id": "p4-competitor-adopts",
      "prediction": "At least one of TweetHunter, Typefully, SuperX, Teract, Pounce, OpenTweet publicly markets a feature as scoring with or running the open-source Phoenix model (naming Phoenix or linking xai-org/x-algorithm in a product/feature description) by 2026-11-01",
      "confidence": "45%",
      "shadow_baseline": "30%",
      "timeframe": "2026-07-31 → 2026-11-01 23:59 UTC",
      "resolution_source": "the six vendors' public marketing pages / product changelogs / official X accounts (archived on resolution day)",
      "resolution_criterion": "An archived public page or post from one of the six that describes a product feature and either uses the name 'Phoenix' for X's model or links the xai-org/x-algorithm repo. Generic 'AI-powered' or 'algorithm-optimized' claims do NOT count.",
      "falsification": "No qualifying page by deadline",
      "sq_change": "CHANGE",
      "driver": "competitor-adoption",
      "anchor": {"type": "hazard-laplace", "value": 0.69, "basis": "k=0 adoption events in 77 days since the runnable release; Laplace (k+1)/(L+2)=0.0127/day; w=92d -> 0.69. Flagged: k=0 makes this anchor weak by construction"},
      "ledger": [
        {"item": "77 days of zero adoption despite a public runnable release = revealed disinterest", "lo": -0.7},
        {"item": "marketing payoff unclear: 'AI-powered' already sells without a 3GB JAX dependency", "lo": -0.3}
      ],
      "note": "Largest shadow-vs-framework divergence in the session (30% vs 45%) — the Laplace anchor on k=0 drags upward. This is the A/B doing its job; resolution will say which arm was right.",
      "resolved": false, "outcome": null
    },
    {
      "id": "p5-api-price-hike",
      "prediction": "X announces a further increase to any per-item API price (per post read/write/lookup or per-content surcharge), effective in 2026, posted on devcommunity.x.com between 2026-08-01 and 2026-12-31",
      "confidence": "79%",
      "shadow_baseline": "75%",
      "timeframe": "2026-08-01 → 2026-12-31 23:59 UTC",
      "resolution_source": "devcommunity.x.com official announcements category",
      "resolution_criterion": "An official announcement post in the window states an increased per-item price (any item) taking effect in 2026. Price restructures that only decrease or hold prices do not count.",
      "falsification": "No qualifying announcement by deadline",
      "sq_change": "SQ",
      "driver": "x-api-economics",
      "anchor": {"type": "hazard", "value": 0.77, "basis": "k=2 pricing increases in 2026 (Feb pay-per-use default, Apr 20 link-post surcharge) over L=211 days -> lambda=0.0095/day; w=153d; P=1-e^(-1.45)=0.77"},
      "ledger": [
        {"item": "continuing revenue pressure; both 2026 changes moved prices up", "lo": 0.1}
      ],
      "resolved": false, "outcome": null
    },
    {
      "id": "p6-replication-questions",
      "prediction": "Rerunning our published scripts (phx_fetch.py + phx_analyze.py, frozen at build commit) on >=300 previously-unfetched sports-corpus posts on or after 2026-08-14 yields median replies for question-mark posts >= 2x the median for non-question posts",
      "confidence": "78%",
      "shadow_baseline": "80%",
      "timeframe": "run window 2026-08-14 → 2026-08-31",
      "resolution_source": "the rerun's lab.json output, published at /api/ on this site (scripts are public; anyone can reproduce)",
      "resolution_criterion": "feature_effects.question_mark: median_replies_with >= 2 x median_replies_without, on n>=300 posts none of which appear in the Jul 31 fetch files",
      "falsification": "ratio < 2x on the qualifying rerun",
      "sq_change": "SQ",
      "driver": "engagement-content-correlates",
      "anchor": {"type": "reference-class", "value": 0.75, "basis": "one prior measurement (4.0 vs 1.0 median on 1,311 posts) with small-integer medians; regression toward the mean expected; 2x threshold leaves headroom"},
      "ledger": [
        {"item": "effect size measured at 4x vs a 2x pass bar", "lo": 0.2}
      ],
      "resolved": false, "outcome": null
    },
    {
      "id": "p7-null-persists",
      "prediction": "CONDITIONAL: IF xai-org publishes a new runnable checkpoint by 2026-12-31 (artifacts our frozen scripts run against with at most path fixes), THEN the within-author backtest on it yields median Spearman <= 0.10",
      "confidence": "80%",
      "shadow_baseline": "75%",
      "timeframe": "resolves when/if the antecedent occurs, else VOID at 2026-12-31",
      "resolution_source": "our frozen phx_score.py + phx_analyze.py output on the new artifacts, published at /api/",
      "resolution_criterion": "within_author_backtest.fav_spearman_median <= 0.10 with >=50 qualifying authors. VOID (not scored) if no qualifying checkpoint ships.",
      "falsification": "median rho > 0.10 on a qualifying run",
      "sq_change": "SQ",
      "driver": "mini-model-behavior-stability",
      "anchor": {"type": "reference-class", "value": 0.78, "basis": "the null replicated across two viewer contexts (warm rho=-0.003, cold rho=+0.008); ID-hash architecture makes post-quality signal structurally hard for a mini distillation"},
      "ledger": [
        {"item": "a larger/longer-trained release could encode more author-conditional signal", "lo": -0.2},
        {"item": "architecture unchanged unless announced otherwise", "lo": 0.3}
      ],
      "resolved": false, "outcome": null
    }
  ]
}