You asked
How do I setup the game?
Answered counted as answeredAsked with: Android: Netrunnerbg-124742-en-1e
Rule found, game on.
🔧 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 219 ms · ask 2686 ms · total 2909 ms
- single-flight (PR-5)
- queued 0 ms · generation 2909 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 5, "score": 0.048412, "snippet": "To prepare a game of Android: Netrunner , carefully follow the steps below. Choose Sides: The players decide who will play as the Runner and who will play as the Corporation. Then, each player places his identity card faceup in his play area and takes a corresponding deck. Note: New players should u", "headingPath": "Setup · The Golden Rule · Starter Decks · Corporation: · Runner:", "sharpsignalDocId": 279}, {"page": 6, "score": 0.032258, "snippet": "Each player has a click tracker that he uses to track the number of clicks left that he has to spend on his turn. This is a game aid only and its use is optional. Some cards enter Archives faceup, and some cards enter Archives facedown. Facedown cards in Archives should be oriented horizontally so t", "headingPath": "Click Tracker · Remote Servers · Ice · Heap · Rig", "sharpsignalDocId": 279}, {"page": 13, "score": 0.031746, "snippet": "For [ , the Corporation installs a single agenda, asset, upgrade, or piece of ice from HQ, placing it facedown on the table. Note: When an asset or upgrade is installed, the Corporation can pay its rez cost to rez it at almost any time (see the 'Timing Structures' on pages 32-33). Ice can only be re", "headingPath": "Installing Cards", "sharpsignalDocId": 279}, {"page": 15, "score": 0.03125, "snippet": "For [ , the Runner installs a single program, resource, or piece of hardware faceup in his rig. An installed Runner card is active and does not have to be rezzed like a Corporation card. Note: The Runner's cards are always installed faceup and in a vertical orientation. ProgramsTo install a program,", "headingPath": "Installing Cards · Playing Events · Removing Tags · Making a Run · Triggering [ Abilities", "sharpsignalDocId": 279}, {"page": 13, "score": 0.030769, "snippet": "If the Corporation wants to install an agenda in a remote server that has an asset or an agenda already installed in it, he can install the card but must trash the existing card first as part of the install action. UpgradesAn upgrade can be installed in any server. When an upgrade is installed in a ", "headingPath": "Installing Cards", "sharpsignalDocId": 279}, {"page": 12, "score": 0.030303, "snippet": "In Android: Netrunner, the Corporation and the Runner alternate taking turns. Android: Netrunner is unusual in that the Runner and the Corporation are governed by different rules. Players should familiarize themselves with the rules for both sides. The Corporation always takes the first turn of the ", "headingPath": "Playing the Game · Turn Overview · Corporation's Turn · Rezzed and Unrezzed Cards · 1. Draw Phase", "sharpsignalDocId": 279}, {"page": 36, "score": 0.029851, "snippet": "36 Is ice protecting the server? Approach ice: Continue the run? End Run Is the ice rezzed? Will the Corp rez it? Is there more ice protecting the server? End Run Encounter ice: · Break subroutines. · Unbroken subroutines trigger. Is there more ice protecting the server? Continue the run? YES NO Acc", "headingPath": "www.FantasyFlightgames.com · INITIATE RUN AGAINST SERVER", "sharpsignalDocId": 279}, {"page": 6, "score": 0.029412, "snippet": "In Android: Netrunner , the play areas for the Corporation and the Runner differ significantly from one another. However, both players have a credit pool, identity card, score area, and click tracker. Each player has a credit pool where he keeps the credit tokens he has available to spend. Spent cre", "headingPath": "Play Areas · Credit Pool · Corporation Play Area · Central Servers · Research and Development (R&D)- · Runner Play Area · …", "sharpsignalDocId": 279}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 5, "quote": null, "headingPath": "Setup · The Golden Rule · Starter Decks · Corporation: · Runner:", "sharpsignalDocId": 279}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 279 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 279 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 0.92268 of 970 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Nov 15, 2026 12:08 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 Android: Netrunner — Rulebook (corpus doc 279) | Setup · The Golden Rule · Starter Decks · Corporation: · Runner: | p.5 | 0.048412 (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 Android: Netrunner — Rulebook (corpus doc 279) | Click Tracker · Remote Servers · Ice · Heap · Rig | p.6 | 0.032258 (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 Android: Netrunner — Rulebook (corpus doc 279) | Installing Cards | p.13 | 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 |
| #4 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | Installing Cards · Playing Events · Removing Tags · Making a Run · Triggering [ Abilities | p.15 | 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 |
| #5 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | Installing Cards | p.13 | 0.030769 (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 Android: Netrunner — Rulebook (corpus doc 279) | Playing the Game · Turn Overview · Corporation's Turn · Rezzed and Unrezzed Cards · 1. Draw Phase | p.12 | 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 |
| #7 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | www.FantasyFlightgames.com · INITIATE RUN AGAINST SERVER | p.36 | 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)) | 300 |
| #8 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | Play Areas · Credit Pool · Corporation Play Area · Central Servers · Research and Development (R&D)- · Runner Play Area · … | p.6 | 0.029412 (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 80 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 Android: Netrunner — Rulebook (corpus doc 279) | Setup · The Golden Rule · Starter Decks · Corporation: · Runner: | p.5 | #1 | 0.048412 (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 Android: Netrunner — Rulebook (corpus doc 279) | Installing Cards · Playing Events · Removing Tags · Making a Run · Triggering [ Abilities | p.15 | #4 | 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 |
| #3 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | 2. Discard Phase | p.15 | #30 | 0.011494 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #4 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | Accessing Multiple Cards · Concluding the Run | p.18 | #19 | 0.013158 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #5 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | Playing the Game · Turn Overview · Corporation's Turn · Rezzed and Unrezzed Cards · 1. Draw Phase | p.12 | #6 | 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 |
| #6 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | p.34 | #58 | 0.008475 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it | |
| #7 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | Important Vocabulary | p.5 | #43 | 0.009804 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #8 | RULEBOOK Android: Netrunner — Rulebook (corpus doc 279) | Why deckbuild? | p.24 | #9 | 0.029274 (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 |
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 Android: Netrunner — Rulebook (corpus doc 279) | Setup · The Golden Rule · Starter Decks · Corporation: · Runner: | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 219 ms · first delta 1495 ms · total 2909 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 219 ms · ask 2686 ms · gateway work 2909 ms · total 2909 ms
- tokens in (the prompt the answerer read)
- 2884
- tokens out (what the answerer generated)
- 269
- tok/sec
- 199.1 tok/sec — 269 output tokens in 1.351 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 35s 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 19h, checked 4s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 207), 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.