erratum: the eco-chain row published .867 as its solo score; in the ECO ledger .867 is pre_train_chain_read, the LOADED arm read before this stage (a different weight file). This arm alone reads .833 (stop member masked off) and .853 in the pair. Corrected against the ledger in the index, the card and the Space catalog; .867 kept as the named comparator. Card also notes every packaged arm is the wide adapter shape and the narrow certified twins are not packaged.

README.md

@@ -63,7 +63,7 @@ result is.
 | `rules-minted-seed1` | the second seed of the ruled dial; the quietest arm in the package on general text | arm | minted words .647 · unseen .593 · general-text cost .0066 bpb | DIAL | settled (2 seeds, 2026-09-22) |
 | `chain` | reads five if-then rules and writes out every step: 'So Wren is …' five times | arm | chain .867 · general-text cost .003 bpb | E-I (trained with an abstention term, so it composes ungated) | settled (2 seeds) |
 | `chain-plain` | the same step-by-step chain writing, trained without the abstention term: the best chain number in the library, but it writes on off-domain text too | arm | chain .887 | C1 | settled (2 seeds) |
-| `eco-chain` | a loaded chain arm carried through a second training stage beside a fresh turn-end arm, and still detachable | arm | chain .867 solo · .833 with the stop arm masked back on | ECO / L4 | settled (2 seeds) |
+| `eco-chain` | a loaded chain arm carried through a second training stage beside a fresh turn-end arm, and still detachable | arm | alone .833 · in the pair .853 · quiet .0054 bpb (the loaded arm read .867 before this stage) | ECO / L4 | settled (2 seeds) |
 | `stop` | ends its turn cleanly with a blank line instead of rambling on | arm | clean stop .83 (second seed 1.00) | E-I | settled (2 seeds) |
 | `stop-seed1` | the second seed: every probe ends its turn | arm | clean stop 1.00 | E-I | settled (2 seeds) |
 | `eco-stop` | the fresh turn-end arm trained in that second stage, with its own abstention term | arm | turn end .953 in the pair · chat 1.00 | ECO / L4 | settled (2 seeds) |
@@ -199,6 +199,12 @@ state dict is unchanged by any number of mount/detach cycles.
 - The rule-chain arms are a controlled capability on made-up words, not
   general reasoning: they read five if-then rules and either write the
   steps out or answer with the final word.
+- Every packaged arm is the **wide** adapter shape: 32 slots of dimension
+  4 read through a 64-atom address, 8.57M parameters. The certified twins
+  of these same recipes at the narrower 16-atom, dimension-8 shape (a
+  near-identical 8.56M parameters) live on the training repo and are
+  **not** packaged here, so nothing in this table is a comparison
+  between the two shapes.
 - `rules-minted` was trained on the lexicon minted for the **next** craft's
   curriculum; it is packaged here because it is the newest settled arm and
   the same recipe, not because this core saw those words in pretraining.

arms/index.json

@@ -382,17 +382,18 @@
    "family": "chain",
    "status": "settled (2 seeds)",
    "rank": 12,
-   "score": "chain .867 solo · .833 with the stop arm masked back on",
+   "score": "alone .833 · in the pair .853 · quiet .0054 bpb (the loaded arm read .867 before this stage)",
    "measured": {
-    "solo_chain": 0.867,
-    "masked_chain": 0.8333,
+    "alone_chain": 0.8333,
     "pair_chain": 0.8533,
+    "pre_stage_solo_chain": 0.867,
     "general_text_cost_bpb": 0.0054
    },
    "cell": "ECO / L4",
    "examples": [
     "If someone is sook, then they are quen. If someone is quen, then they are harl. If someone is harl, then they are torv. If someone is torv, then they are prin. If someone is prin, then they are mund. Wren is sook. What follows?"
-   ]
+   ],
+   "erratum": "2026-09-22: first published as 'chain .867 solo'; .867 is the ledger's pre_train_chain_read — the loaded arm BEFORE this stage, a different weight file. This arm alone reads .833."
   },
   {
    "id": "stop",
@@ -749,6 +750,9 @@
   "detach": "the core's state dict is unchanged by mount/detach, and the restored logits are bit-identical to the pre-mount fingerprint",
   "when": "2026-09-22",
   "device": "RTX 4090, fp32, greedy",
-  "why": "bit-identical logits under a greedy decode give bit-identical bytes, so the campaign's scores are the package's scores; re-scoring here could only reproduce them"
+  "why": "bit-identical logits under a greedy decode give bit-identical bytes, so the campaign's scores are the package's scores; re-scoring here could only reproduce them",
+  "errata": [
+   "2026-09-22: first published as 'chain .867 solo'; .867 is the ledger's pre_train_chain_read — the loaded arm BEFORE this stage, a different weight file. This arm alone reads .833."
+  ]
  }
 }