You asked
How do I play?
Answered counted as answeredAsked with: Undaunted: Stalingradbg-354570-en-1e
Question closed. Friendships intact.
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live,vps
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 93 ms · ask 6635 ms · total 11575 ms
- single-flight (PR-5)
- queued 4843 ms · generation 6732 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 12, "score": 0.04918, "snippet": "Play takes the form of a series of rounds, during which both players will play cards to move units, attack the opposing forces, and take objectives. Each round consists of three phases: 1. DRAW CARDS 2. DETERMINE INITIATIVE 3. PLAYER TURNS Once the last phase is complete, the round is over and the n", "headingPath": "HOW TO PLAY · DRAW CARDS · DETERMINE INITIATIVE · PLAYER TURNS", "sharpsignalDocId": 702}, {"page": 17, "score": 0.047643, "snippet": "The game continues until one of three things happens: A player achieves their primary objective . OR A player inflicts a Full Rout . OR A player Withdraws . When the game ends, complete the Campaign Step. Do this before you pack away any components. If you are playing a practice game, don't complete", "headingPath": "EXAMPLE TURN · PRIMARY OBJECTIVES · Control Objective Points · STOP READING! · FULL ROUT · WITHDRAW", "sharpsignalDocId": 702}, {"page": 22, "score": 0.045743, "snippet": "1. Confirm the game state: Before playing any game of Undaunted: Stalingrad, always confirm that you and your opponent have the same game state code in your Campaign Record. If the codes are not the same, compare your Campaign Records to determine where a mistake has been made. The number in the gam", "headingPath": "CAMPAIGN SETUP · UNLOCKING AND REPLACING CARDS", "sharpsignalDocId": 702}, {"page": 14, "score": 0.045695, "snippet": "Move the unit's combat counter up to Each tile you move to or through must be scouted or controlled by your side. Move the unit's combat counter up to If any tile you move to or through does not have one of your control markers on it, place a control marker there with its scouted side up. For each c", "headingPath": "Move · Bolster X A · Conceal · Control · Inspire X A", "sharpsignalDocId": 702}, {"page": 26, "score": 0.044904, "snippet": "They are now no longer routed. Command X Draw up to X cards from your deck and add them to your hand. You can play those cards as normal this turn. If your deck runs out before you finish drawing, shuffle your discard pile into a deck and continue drawing. Do not shuffle any cards in your play area ", "headingPath": "", "sharpsignalDocId": 702}, {"page": 18, "score": 0.044557, "snippet": "After every game of Undaunted: Stalingrad, before packing away any components or continuing to the next scenario, both players resolve the Campaign Step in full. The Campaign Step has three phases, which you will always perform in the following order: 2. CASUALTY PHASE 3. UPGRADE PHASE You will trac", "headingPath": "CAMPAIGN STEP · 1. VICTORY PHASE · GAME STATE EXAMPLE", "sharpsignalDocId": 702}, {"page": 30, "score": 0.04329, "snippet": "30 CAMPAIGN RULES GAME END The game continues until one of three things happens: 1. A player achieves their primary objective. 2. A player inflicts a Full Rout. 3. A player Withdraws. When the game ends, complete the Campaign Step. Do this before packing away any components. PRIMARY OBJECTIVES Each ", "headingPath": "", "sharpsignalDocId": 702}, {"page": 3, "score": 0.029828, "snippet": "If this is your first experience with Undaunted, we recommend that you read the Components and Rules for Your First Game sections and then play a practice game. Play the first scenario as normal, but skip the Campaign Step at the end. This will give you a chance to familiarise yourself with the rule", "headingPath": "If you have never played Undaunted before · If you have played Undaunted before · SCALE · ACTIONS · ROUTING · SPAWNING · …", "sharpsignalDocId": 702}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 12, "quote": null, "headingPath": "HOW TO PLAY · DRAW CARDS · DETERMINE INITIATIVE · PLAYER TURNS", "sharpsignalDocId": 702}, {"page": 17, "quote": null, "headingPath": "EXAMPLE TURN · PRIMARY OBJECTIVES · Control Objective Points · STOP READING! · FULL ROUT · WITHDRAW", "sharpsignalDocId": 702}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 702 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 702 boosted
- answered-before recall
-
this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
- answer fence
- passed — letter density 0.92420 of 1504 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 24, 2026 08:26 UTC
retrieval — what the passage search returned
what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.
per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| fused rank | document | heading | page | fused RRF score | snippet chars |
|---|---|---|---|---|---|
| #1 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | HOW TO PLAY · DRAW CARDS · DETERMINE INITIATIVE · PLAYER TURNS | p.12 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | EXAMPLE TURN · PRIMARY OBJECTIVES · Control Objective Points · STOP READING! · FULL ROUT · WITHDRAW | p.17 | 0.047643 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #3 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | CAMPAIGN SETUP · UNLOCKING AND REPLACING CARDS | p.22 | 0.045743 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #4 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | Move · Bolster X A · Conceal · Control · Inspire X A | p.14 | 0.045695 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #5 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | p.26 | 0.044904 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 | |
| #6 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | CAMPAIGN STEP · 1. VICTORY PHASE · GAME STATE EXAMPLE | p.18 | 0.044557 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
| #7 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | p.30 | 0.04329 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 | |
| #8 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | If you have never played Undaunted before · If you have played Undaunted before · SCALE · ACTIONS · ROUTING · SPAWNING · … | p.3 | 0.029828 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | 300 |
what the answerer read — the passages it actually had in front of it
what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.
candidate pool: the answering read scored 47 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.
floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.
arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.
| read at | document | heading | page | fused rank | fused RRF score | carried by | how it got its slot |
|---|---|---|---|---|---|---|---|
| #1 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | HOW TO PLAY · DRAW CARDS · DETERMINE INITIATIVE · PLAYER TURNS | p.12 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | ASSEMBLY AND STORAGE GUIDE · Cards · USING CARD SLEEVES · Tiles | p.4 | #16 | 0.026519 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text | the re-ranker chose it |
| #3 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | p.27 | #10 | 0.029644 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text | the re-ranker chose it | |
| #4 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | EXAMPLE TURN | p.16 | #13 | 0.028175 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text | the re-ranker chose it |
| #5 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | SCENARIO 1 SETUP | p.10 | #17 | 0.026334 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text | the re-ranker chose it |
| #6 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | EXAMPLE TURN · PRIMARY OBJECTIVES · Control Objective Points · STOP READING! · FULL ROUT · WITHDRAW | p.17 | #2 | 0.047643 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | If you have never played Undaunted before · If you have played Undaunted before · SCALE · ACTIONS · ROUTING · SPAWNING · … | p.3 | #8 | 0.029828 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text | the re-ranker chose it |
| #8 | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | p.26 | #5 | 0.044904 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
chosen chunks — what the answer actually cited
token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | HOW TO PLAY · DRAW CARDS · DETERMINE INITIATIVE · PLAYER TURNS | p.12 | no quote on the wire |
| [2] | RULEBOOK Undaunted: Stalingrad — Rulebook (corpus doc 702) | EXAMPLE TURN · PRIMARY OBJECTIVES · Control Objective Points · STOP READING! · FULL ROUT · WITHDRAW | p.17 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 93 ms · first delta 3199 ms · total 11575 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 4843 ms · retrieval 93 ms · ask 6635 ms · gateway work 6732 ms · total 11575 ms
- tokens in (the prompt the answerer read)
- 3858
- tokens out (what the answerer generated)
- 449
- tok/sec
- 130.7 tok/sec — 449 output tokens in 3.435 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 18s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 60h, checked 6s ago)
- answerer node (the seat proxy's own header — this probe, not this ask)
- node1
- stream path
- streamed — the gateway pushed at least one accumulated draft
- watchdog
- first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
- num_ctx · think posture
- both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.
disposition
- outcome
- ANSWERED — Answered
- abstain rationale (n/a — this ruling answered)
- answered — no abstain rationale applies
setup-shape — why the checklist band did or didn't render
- decision
- NOT_SETUP_SHAPED — no setup-shape pattern matched this question
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 635), so "no registered errata card matched" above could never have matched one
Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.