You asked
How do I play?
Answered counted as answeredAsked with: RoboRallybg-18-en-1e
So says the rulebook. So plays the table.
🔧 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 215 ms · ask 5085 ms · total 5302 ms
- single-flight (PR-5)
- queued 0 ms · generation 5302 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 2, "score": 0.048387, "snippet": "Beep. Buzz. Clang. SMASH. These are the beautiful sounds of a Saturday-night robot race. HOW TO WIN Play cards to program your robot’s moves through the hazardous factory. Make your way to each of the checkpoints in your chosen course in numerical order. The first player to reach all of the checkpoi", "headingPath": "", "sharpsignalDocId": 629}, {"page": 4, "score": 0.046875, "snippet": "4 ROBO RALLY is played in rounds. Each round is made up of the following three phases: (1) the upgrade phase, (2) the programming phase, and (3) the activation phase. Here's a quick summary of what a round will look like. You'll find a more detailed description of each phase and how to play a full r", "headingPath": "For a two player game, your game set up should look like this. · HOW TO PLAY · Determining Priority", "sharpsignalDocId": 629}, {"page": 2, "score": 0.046486, "snippet": "......................................................................................................................................................................................................3 HOW TO PLAY", "headingPath": "", "sharpsignalDocId": 629}, {"page": 25, "score": 0.046244, "snippet": "You may obtain these special programming cards by installing certain temporary upgrades. When you first receive a special programming card, place it in your discard pile. The card will cycle through your programming deck, and you may play them just as you would any other programming card, by placing", "headingPath": "SPECIAL PROGRAMMING CARDS · ENERGY ROUTINE · WEASEL ROUTINE · SPAM FOLDER · SANDBOX ROUTINE · SPEED ROUTINE · …", "sharpsignalDocId": 629}, {"page": 16, "score": 0.045695, "snippet": "16 On the following pages, you'll find a list of nineteen racing courses. The course descriptions will tell you which boards to use (each board is labeled with a number and a letter) and how to set up board elements. The courses are listed according to the following five difficulty levels. If you're", "headingPath": "VIRUS · RACING COURSES · STARTER COURSE: DIZZY HIGHWAY · BEGINNER · INTERMEDIATE · ADVANCED · …", "sharpsignalDocId": 629}, {"page": 3, "score": 0.045079, "snippet": "Choose a racing course to play. You'll find a complete list of courses starting on page 16. 'Dizzy Highway' is a great course for first-time players. Page 16 of this guide will tell you how to set up the gameboards, priority antenna, checkpoints, reboot tokens, and energy cubes for 'Dizzy Highway.' ", "headingPath": "SET UP · For a two player game, your game set up should look like this.", "sharpsignalDocId": 629}, {"page": 2, "score": 0.044118, "snippet": "All week long, the robots of ROBO RALLY toil over their work. There's no escaping their factory home, so these robots know only one joy: to be the victor in their weekly race of survival and sabotage. Choose a robot, and program it to move, turn, pick up energy, and navigate the trials of the factor", "headingPath": "Beep. Buzz. Clang. SMASH. These are the beautiful sounds of a Saturday-night robot race. · HOW TO WIN · THE FIRST TIME YOU PLAY", "sharpsignalDocId": 629}, {"page": 6, "score": 0.04329, "snippet": "During the programming phase, you'll plan your robot's actions for the round. You'll do this by placing programming cards in each of the five registers on your player mat. Programming cards tell your robot to do things like move, turn, or collect energy. You'll find a complete description of the eig", "headingPath": "The Programming Phase 2 · Programming your robots", "sharpsignalDocId": 629}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "For a two player game, your game set up should look like this. · HOW TO PLAY · Determining Priority", "sharpsignalDocId": 629}, {"page": 10, "quote": null, "headingPath": "", "sharpsignalDocId": 629}, {"page": 2, "quote": null, "headingPath": "", "sharpsignalDocId": 629}, {"page": 2, "quote": null, "headingPath": "Beep. Buzz. Clang. SMASH. These are the beautiful sounds of a Saturday-night robot race. · HOW TO WIN · THE FIRST TIME YOU PLAY", "sharpsignalDocId": 629}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 629 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 629 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 0.93888 of 1129 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 25, 2026 13:30 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 RoboRally — Rulebook (corpus doc 629) | p.2 | 0.048387 (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 RoboRally — Rulebook (corpus doc 629) | For a two player game, your game set up should look like this. · HOW TO PLAY · Determining Priority | p.4 | 0.046875 (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 RoboRally — Rulebook (corpus doc 629) | p.2 | 0.046486 (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)) | 211 | |
| #4 | RULEBOOK RoboRally — Rulebook (corpus doc 629) | SPECIAL PROGRAMMING CARDS · ENERGY ROUTINE · WEASEL ROUTINE · SPAM FOLDER · SANDBOX ROUTINE · SPEED ROUTINE · … | p.25 | 0.046244 (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 RoboRally — Rulebook (corpus doc 629) | VIRUS · RACING COURSES · STARTER COURSE: DIZZY HIGHWAY · BEGINNER · INTERMEDIATE · ADVANCED · … | p.16 | 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 |
| #6 | RULEBOOK RoboRally — Rulebook (corpus doc 629) | SET UP · For a two player game, your game set up should look like this. | p.3 | 0.045079 (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 RoboRally — Rulebook (corpus doc 629) | Beep. Buzz. Clang. SMASH. These are the beautiful sounds of a Saturday-night robot race. · HOW TO WIN · THE FIRST TIME YOU PLAY | p.2 | 0.044118 (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 RoboRally — Rulebook (corpus doc 629) | The Programming Phase 2 · Programming your robots | p.6 | 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 |
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 51 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 RoboRally — Rulebook (corpus doc 629) | p.10 | #12 | 0.028139 (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 | |
| #2 | RULEBOOK RoboRally — Rulebook (corpus doc 629) | p.2 | #1 | 0.048387 (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 | |
| #3 | RULEBOOK RoboRally — Rulebook (corpus doc 629) | BURN RUN · CARD INDEX · TURN RIGHT · U-TURN · POWER UP · MOVE 1, MOVE 2, MOVE 3 · … | p.24 | #9 | 0.029469 (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 RoboRally — Rulebook (corpus doc 629) | p.9 | #16 | 0.025649 (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 RoboRally — Rulebook (corpus doc 629) | Beep. Buzz. Clang. SMASH. These are the beautiful sounds of a Saturday-night robot race. · HOW TO WIN · THE FIRST TIME YOU PLAY | p.2 | #7 | 0.044118 (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 |
| #6 | RULEBOOK RoboRally — Rulebook (corpus doc 629) | SET UP · For a two player game, your game set up should look like this. | p.3 | #6 | 0.045079 (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 RoboRally — Rulebook (corpus doc 629) | For a two player game, your game set up should look like this. · HOW TO PLAY · Determining Priority | p.4 | #2 | 0.046875 (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 RoboRally — Rulebook (corpus doc 629) | SPECIAL PROGRAMMING CARDS · ENERGY ROUTINE · WEASEL ROUTINE · SPAM FOLDER · SANDBOX ROUTINE · SPEED ROUTINE · … | p.25 | #4 | 0.046244 (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 RoboRally — Rulebook (corpus doc 629) | For a two player game, your game set up should look like this. · HOW TO PLAY · Determining Priority | p.4 | no quote on the wire |
| [2] | RULEBOOK RoboRally — Rulebook (corpus doc 629) | p.10 | no quote on the wire | |
| [3] | RULEBOOK RoboRally — Rulebook (corpus doc 629) | p.2 | no quote on the wire | |
| [4] | RULEBOOK RoboRally — Rulebook (corpus doc 629) | Beep. Buzz. Clang. SMASH. These are the beautiful sounds of a Saturday-night robot race. · HOW TO WIN · THE FIRST TIME YOU PLAY | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 215 ms · first delta 3867 ms · total 5302 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 215 ms · ask 5085 ms · gateway work 5302 ms · total 5302 ms
- tokens in (the prompt the answerer read)
- 2772
- tokens out (what the answerer generated)
- 276
- tok/sec
- 199.6 tok/sec — 276 output tokens in 1.383 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 0s 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 562), 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.