You asked
How do I play?
Answered counted as answeredAsked with: Tower Upbg-393307-en-1e
The table has its answer — dice up.
🔧 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 253 ms · ask 5736 ms · total 5991 ms
- single-flight (PR-5)
- queued 0 ms · generation 5991 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 7, "score": 0.048652, "snippet": "After moving one of your markers, check if they have ALL reached (or passed) the column of stars on your board. If yes, you get to immediately play an extra turn (take a card or start a new building). The 3 objective cards of the game allow you to collect up to three bonus chips ranging from 3M to 7", "headingPath": "EXTRA TURN · OBJECTIVES · GAME END · FINAL SCORE", "sharpsignalDocId": 1245}, {"page": 6, "score": 0.046642, "snippet": "Your black marker 2 steps to the right Take: 1 floor of your choice You're playing Blue. You want to found a black building next to the brown one. There are 2 possible sites ( ). The site marked with a red cross is forbidden as it is adjacent to a pre-existing black building. 1 Place the black floor", "headingPath": "Move:", "sharpsignalDocId": 1245}, {"page": 6, "score": 0.045037, "snippet": "6 The game is played in clockwise order, starting with the 1st player. On your turn, you may take one of the two possible actions: TAKE 1 CARD Choose a card form the Market, discard it in the space provided on the right of the container and gain what is depicted on it. Immediately draw a new card to", "headingPath": "SET UP · TAKE 1 CARD · EXAMPLES · START 1 NEW BUILDING · PLACE 1 ROOF · SCORE · …", "sharpsignalDocId": 1245}, {"page": 5, "score": 0.032787, "snippet": "For your first game, use the Starting ( ) cards and place them face up on the dedicated slots of the board. Once you are familiar with the game, you may take 3 random cards from the 10 available in the game. You only need 3 objective cards for each game. You may return the unused ones in the box. Al", "headingPath": "SET UP", "sharpsignalDocId": 1245}, {"page": 4, "score": 0.031746, "snippet": "1 Place the board in the center of the table. For a 2-players game, fold the board and place the half-board on the back between both players. 2 Place the container with all the roofs sorted out by color next to the board. 3 \u0007 Shuffle all the Materials cards, create a draw pile and place it in the sp", "headingPath": "SET UP", "sharpsignalDocId": 1245}, {"page": 2, "score": 0.03125, "snippet": "Please read this before your first game Front (3-4 players) Back (2 players) The board shows a city downtown divided in 5 areas. The front of the board is used for games with 3 or 4 players, while the half board on the back is only for 2 players. The board displays many square construction sites con", "headingPath": "GAME COMPONENTS · 1 BOARD", "sharpsignalDocId": 1245}, {"page": 2, "score": 0.030622, "snippet": "T he expansion of the city's downtown is in full swing. Y ou are at the head of one of the construction companies mandated for all the skyscrapers: new buildings, juicy bonuses and, if all goes well, all the riches! However, city planning is pretty demanding: each time you start a new building, you ", "headingPath": "CREDITS · Game Design · Project Manager · Product Manager · Illustrations · Graphism and layout · …", "sharpsignalDocId": 1245}, {"page": 8, "score": 0.030303, "snippet": "-With 2 or 3 players, you can tighten the game a bit by placing up to 7 starting floors (draw additional Materials cards and then reshuffle them into the deck). -With 4 players, you may go up to 5 starting floors, but that makes the end game very tight. Be present in 5 connected buildings. Have a ro", "headingPath": "VARIANT", "sharpsignalDocId": 1245}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "SET UP", "sharpsignalDocId": 1245}, {"page": 5, "quote": null, "headingPath": "SET UP", "sharpsignalDocId": 1245}, {"page": 6, "quote": null, "headingPath": "SET UP · TAKE 1 CARD · EXAMPLES · START 1 NEW BUILDING · PLACE 1 ROOF · SCORE · …", "sharpsignalDocId": 1245}, {"page": 8, "quote": null, "headingPath": "OBJECTIVES CARDS · GAME TURN · SCORING · TACTICAL ADVICE · EXTRA TURN · GAME END · …", "sharpsignalDocId": 1245}, {"page": 7, "quote": null, "headingPath": "EXTRA TURN · OBJECTIVES · GAME END · FINAL SCORE", "sharpsignalDocId": 1245}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1245 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1245 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 0.90840 of 3155 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 5, 2026 13:27 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 Tower Up — Rulebook (corpus doc 1245) | EXTRA TURN · OBJECTIVES · GAME END · FINAL SCORE | p.7 | 0.048652 (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 |
| #2 | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | Move: | p.6 | 0.046642 (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 Tower Up — Rulebook (corpus doc 1245) | SET UP · TAKE 1 CARD · EXAMPLES · START 1 NEW BUILDING · PLACE 1 ROOF · SCORE · … | p.6 | 0.045037 (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 Tower Up — Rulebook (corpus doc 1245) | SET UP | p.5 | 0.032787 (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 Tower Up — Rulebook (corpus doc 1245) | SET UP | p.4 | 0.031746 (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 Tower Up — Rulebook (corpus doc 1245) | GAME COMPONENTS · 1 BOARD | p.2 | 0.03125 (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 Tower Up — Rulebook (corpus doc 1245) | CREDITS · Game Design · Project Manager · Product Manager · Illustrations · Graphism and layout · … | p.2 | 0.030622 (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 Tower Up — Rulebook (corpus doc 1245) | VARIANT | p.8 | 0.030303 (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 10 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 Tower Up — Rulebook (corpus doc 1245) | Move: | p.6 | #2 | 0.046642 (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 |
| #2 | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | SET UP | p.4 | #5 | 0.031746 (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 + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | EXTRA TURN · OBJECTIVES · GAME END · FINAL SCORE | p.7 | #1 | 0.048652 (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 |
| #4 | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | GAME COMPONENTS · 1 BOARD | p.2 | #6 | 0.03125 (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 + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | OBJECTIVES CARDS · GAME TURN · SCORING · TACTICAL ADVICE · EXTRA TURN · GAME END · … | p.8 | #9 | 0.029851 (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 + the doc-priority boost arm | the re-ranker chose it |
| #6 | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | VARIANT | p.8 | #8 | 0.030303 (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 + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | SET UP · TAKE 1 CARD · EXAMPLES · START 1 NEW BUILDING · PLACE 1 ROOF · SCORE · … | p.6 | #3 | 0.045037 (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 |
| #8 | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | SET UP | p.5 | #4 | 0.032787 (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 + 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 Tower Up — Rulebook (corpus doc 1245) | SET UP | p.4 | no quote on the wire |
| [2] | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | SET UP | p.5 | no quote on the wire |
| [3] | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | SET UP · TAKE 1 CARD · EXAMPLES · START 1 NEW BUILDING · PLACE 1 ROOF · SCORE · … | p.6 | no quote on the wire |
| [4] | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | OBJECTIVES CARDS · GAME TURN · SCORING · TACTICAL ADVICE · EXTRA TURN · GAME END · … | p.8 | no quote on the wire |
| [5] | RULEBOOK Tower Up — Rulebook (corpus doc 1245) | EXTRA TURN · OBJECTIVES · GAME END · FINAL SCORE | p.7 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 253 ms · first delta 1166 ms · total 5991 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 253 ms · ask 5736 ms · gateway work 5991 ms · total 5991 ms
- tokens in (the prompt the answerer read)
- 2710
- tokens out (what the answerer generated)
- 964
- tok/sec
- 202.4 tok/sec — 964 output tokens in 4.764 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 23s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 2s 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 1175), 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.