{
 "title": "Rules note",
 "about": "Every rule idea we talk about goes here, with the exact wording, where it came from, and its status. Status: IDEA = written down, not tested; TESTING; NO EDGE = tested, did not hold; WORKS = held on 2 years (both halves) and beats cost; LIVE = in a bot. Tests run on the 30 days first; the 2 years only when you say so. Nothing here is live unless it says LIVE.",
 "rules": [
  {
   "id": "RN-26",
   "date": "2026-11-15",
   "status": "TESTING",
   "name": "Volume must support the V before a cross buy",
   "from": "User 11/15, RCAT 2025-02-11 buy #3 (11:42 deep-V cross, -2% first): 'has no volume to support the V'. Checked: drop into the V 27.4k sh/min (1.23x normal), rise out of it 13.0k (0.53x day pace), cross bars 1.3k-3.9k.",
   "rule": "For deep-V, re-cross and 2nd-leg cross buys (not opening, breakout or shallow-asleep). A: average volume per minute on the rise (V low to cross) must be at least the average on the drop (60-bar high to V low). B (user's favourite): at the cross bar, volume over the last 15 bars must be at least the day's pace so far (rv_day >= 1.0). If it fails, skip that cross.",
   "open": "Thresholds 1.0x are first settings. Checked at the cross bar, not at the buy bar.",
   "result": "30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on, halves split at Oct 26; random net -0.25 / -0.23; FULL V-cross buys net -0.27 / +0.05). A (rise vol >= drop vol): blocks 469 of 798 V-cross buys; blocked net -0.26 / +0.11 vs kept -0.28 / -0.06 = blocked did better in both halves (hurts) -> NO EDGE. B (15-bar vol >= day pace at cross): blocks 600 of 798 (75%); kept -0.16 / -0.09 vs blocked -0.30 / +0.09 = helps half 1, hurts half 2 (mixed). Kept buys are steadier between halves. By type: deep kept -0.22 / -0.16 vs blocked -0.44 / +0.21 (mixed); re-cross kept +0.10 / +0.08 vs blocked -0.04 / +0.02 (better in both halves, only 17 + 25 kept). FULL with B overall -0.32 / +0.21 vs FULL -0.30 / +0.16 = about the same. RCAT 2025-02-11 11:42 blocked by both. 2-year not run."
  },
  {
   "id": "RN-25",
   "date": "2026-11-15",
   "status": "NO EDGE",
   "name": "Opening buy only if the next bar opens higher than the trigger bar",
   "from": "User 11/15, after the 2-year charts: 'add to the open rules: after the buy signal is triggered, the next open bar has to be higher than the trigger bar to allow the buy'.",
   "rule": "Add-on to RN-18 (opening 9:34-9:59, RUNNING + EMA9 above EMA20 and EMA50 + green trigger bar): buy at the next bar's open only if that open is higher than the trigger bar. If it is not, no buy from this trigger.",
   "open": "'Higher than the trigger bar' = above its CLOSE or above its HIGH? And after a failed check: skip the opening buy that day, or keep looking for the next trigger before 10:00? Testing all four.",
   "result": "30-day test 11/15 (Oct 5 - Nov 13, guards on, halves split at Oct 26; random 9:35-10:00 net -0.18 / -0.00). RN-18 as now: 463 buys, net -0.34 / +0.41. Open > trigger CLOSE: keeps only 163 of 463; kept buys net -0.47 / +0.06, blocked buys -0.27 / +0.60 = the blocked buys did BETTER in both halves (hurts). Open > trigger HIGH: keeps 56; kept -0.58 / +0.54 vs blocked -0.31 / +0.39 = mixed, tiny sample. 'Wait for next trigger' versions: close -0.39 / +0.42, high -0.50 / +0.35 = no better than RN-18 as now. Reading: a higher next open means paying more for the same move. 2-year not run (user to decide)."
  },
  {
   "id": "RN-24",
   "date": "2026-11-15",
   "status": "NO EDGE",
   "name": "Avoid cross buys while the EMAs are compressed",
   "from": "User 11/15, SOUN 2025-04-09 (base 11:30-13:15, then spring + breakout 13:19): 'as long as EMAs are compressed together, avoid buying with the cross; consider the distance at 11:00 as the acceptable gap'.",
   "rule": "Applied 11/15 (user chose A): if EMA9, EMA20 and EMA50 stayed within 1 own candle of each other (highest minus lowest) for all 30 bars before a cross, skip that cross buy; only a breakout (RN-22) can buy out of the base. Opening (RN-18) and RN-22 not affected. Exception (user 11/15): a shallow + asleep cross that waits for RECLAIM (RN-17) still buys.",
   "open": "30 bars and 1 own candle are my first settings (user gave none).",
   "result": "Charts 11/15 (RN-16 off), with the RN-17 exception: 3 buys removed - SOUN 12:36 +2% first, ACHR 14:01 -2% first, UUUU 10:56 neither. APPS 12:17 (+2%, user's mark) and SOUN 13:20 kept. With RN-16 on: only ACHR 14:01 (-2%) removed. Literal 'gap at SOUN 11:00' version (2.8c at the cross) would have blocked all 32 cross buys. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Removes 48 buys: half 1 diff +0.0 net -0.47 (good to block), half 2 diff +39.3 net +0.76 (blocked winners). Overall the blocked buys beat FULL (net +0.25 vs -0.08) = hurts. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). The 582 buys it blocks did better (net -0.04 / -0.13) than the rest of FULL (-0.17 / -0.26) = hurts."
  },
  {
   "id": "RN-23",
   "date": "2026-11-15",
   "status": "NO EDGE",
   "name": "Green-bar check on every buy trigger",
   "from": "User 11/15: 'for every buy trigger, it will check if next bar will be green, before buying it'. Today only RN-14 (basing at the cross) checks candle colour.",
   "rule": "Applied 11/15 (user chose A): on every entry the bar that triggers the buy must close green (and be awake), buy the next open. If it is red, buy after the first green bar while the setup is still valid: EMA9 above EMA20; reclaim waits and RN-22 also need price above VWAP; opening must still be lined up before 10:00. RN-14 keeps its stricter 2-green-bar wait.",
   "open": "None for now; judge it on the 30 days.",
   "result": "Charts 11/15 (RN-16 off), 6 buys changed, all others already had a green trigger bar. Opening: AMCI 9:36 (-2%) and REPL 9:35 (-2%) gone, VIVO 9:35 -2% -> 9:37 +2%, JOBY 9:50 -> 9:51 still -2%. Deep V: APPS 11:45 -> 11:46 still +2%, CRML 13:31 -> 13:34 still neither. Opening now 4 / 8 / 2 (was 3 / 11 / 2). Same 4 opening changes with RN-16 on. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Adds 147, removes 182. Added: diff -4.3 / +21.8, net -0.03 / -0.04; removed: -5.6 / +10.8, net -0.12 / -0.21. Better in both halves - the most steady rule. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). Buys it keeps net -0.06 / -0.40 vs the ones it drops -0.08 / -0.35. No help (30-day gain did not hold)."
  },
  {
   "id": "RN-22",
   "date": "2026-11-14",
   "status": "NO EDGE",
   "name": "After a cross + sideways run, buy the breakout with state RECLAIM",
   "from": "User 11/14, SOUN 2025-04-09: 'after a cross and side run, enter after ema9 breakout like what happened on this stock around 13:20 with state = reclaim'. SOUN 13:19: a big green bar (7.005 to 7.26) breaks the 12:39-13:18 range (high 7.239), state RECLAIM, EMA9 back over EMA20, buy 13:20 at 7.27, +2% first. (Already a buy under RN-20 + RN-21.)",
   "rule": "Applied 11/14 (user: breakout = B, EMA9 turns up sharply; sideways = more than 10 bars): an EMA9-over-EMA20 cross in the last 60 bars, then the 11 bars before are sideways (closes inside 4 own candles), then EMA9 rises 0.8+ own candle in one bar with state RECLAIM, EMA9 above EMA20, not asleep -> buy next open. One per sideways run. Separate entry, works without a deep V.",
   "open": "My first settings: 4-candle sideways range, 0.8-candle EMA9 jump, cross within 60 bars. SOUN 13:02 is kept out only by the jump size (0.66c vs 0.8 needed); 13:19 jump was 1.03c.",
   "result": "Charts 11/14: fires only twice on the 20 days, both on a bar another rule already buys: SOUN 13:20 +2% first (also RN-20) and FJET 12:59 -2% first (also RN-17). Adds no new buys here. Not tested on 30 days. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Adds only 12 buys: diff -8.3, net -0.59. Too few and negative. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). 148 buys, diff +9.7 / +0.0, net -0.25 / -0.40. Not steady."
  },
  {
   "id": "RN-21",
   "name": "Second leg of a deep V counts as the same deep V",
   "from": "User 11/14, CDE 2025-03-04: 'why there is no buy signal at around 11:30'. The 10:35 deep-V cross (65 bars under, 19c dip) never bought: basing, flat cross candle, and no 2 green bars in a row before EMA9 went back under at 10:46. The 11:22 cross had 36 bars under but its dip was measured only from the 10:11 high 5.02 to the 11:08 low 4.89 = 2.6% = 6.5 own candles (needs 8) -> plain shallow. 11:31 cross = 6 bars under after 11:22, but 11:22 was not deep, so RN-20 re-cross did not apply.",
   "rule": "Applied (user chose A, 11/14): a deep-V cross that never bought, price stayed under VWAP since, and the new low holds within 1 own candle of the deep-V low -> the next cross counts as the same deep V (same waits RN-14/15/19); dip measured from the deep-V high. A buy ends it. It also lets RN-20 re-cross chain after it.",
   "open": "1 own candle tolerance is my first setting.",
   "result": "Charts 11/14 (RN-16 off): 7 new buys, 5 +2% first, 0 -2% first, 2 neither. RN-21 itself: CDE 11:23 +2%, SOUN 12:36 +2%. Re-crosses that now chain after it: CDE 11:32 +2%, SOUN 13:20 +2%, JOBY 13:12 +2%, JOBY 14:38 neither, UUUU 14:04 neither. EMA50 on: adds SOUN 13:20 +2%, JOBY 14:38 neither. Not tested on 30 days. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Adds 45: diff +6.7 / -6.7, net -0.08 / -0.61. Not steady. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). 603 buys, diff +2.7 / -2.9, net -0.28 / -0.29 = about random.",
   "date": "2026-11-14",
   "status": "NO EDGE"
  },
  {
   "id": "RN-20",
   "name": "Re-cross after a deep V counts as the same deep V",
   "from": "User 11/14, ASST 2025-05-21: 'around 11:03-05 we should have a buy signal at that cross'. The 10:46 deep-V cross was asleep, its reclaim wait was cancelled when EMA9 dipped under at 11:00; the 11:05 cross was only 5 bars under = shallow, so nothing fired.",
   "rule": "If EMA9 dips back under EMA20 for 10 bars or fewer right after a deep-V cross, the next cross counts as part of the same deep V (same waits RN-14 / RN-15 / RN-19).",
   "open": "10 bars is my first setting.",
   "result": "Charts 11/14 (RN-16 off): 5 re-cross buys - ASST 11:06 +2% (the user's mark), REPL 13:05 +2%, ACHR 14:01 -2%, SOUN 11:21 -2%, APLD 2/7 12:46 neither. Not tested on the 30 days yet. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Adds 211 re-cross buys: diff +0.0 / +12.7, net +0.00 / +0.03 vs random -0.25 / -0.23. Better than random on net in both halves; still about break-even after cost. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). 3,512 re-cross buys: diff +1.8 / +2.5 vs random -0.9 / -1.0; net -0.19 / -0.19 vs -0.25. Small steady tilt both years, below cost.",
   "date": "2026-11-14",
   "status": "TESTING"
  },
  {
   "id": "RN-19",
   "name": "Never buy while the stock is ASLEEP",
   "from": "User 11/14, APLD 2025-03-11 buy #3 (12:37, shallow + asleep): 'state was asleep, so we should add the rule - dont buy as state is asleep'.",
   "rule": "The bar that triggers a buy must not have the ASLEEP flag. Waits go on while EMA9 stays above EMA20.",
   "open": "Clashes with RN-17 (which waits for a reclaim after a long sleep): with RN-19 on, the RECLAIM bar must also be awake.",
   "result": "Charts 11/14: removed APLD 3/11 12:37 (-2%), UUUU 11:57 (neither) and CRML 11:54 (+2%, asleep the whole reclaim). APPS ~12:20 mark kept: the 12:16 cross bar was already RECLAIM and awake, buy 12:17 (+2%). | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Adds 30, removes 84 (asleep buys). Removed: diff -5.5 / +13.8, net -0.56 / -0.38; added net -0.41 / +0.16. Better than without it in both halves on net. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). The asleep buys it blocks did BETTER (net -0.25 / -0.18) than what replaces them (-0.35 / -0.35). Hurts (30-day gain did not hold).",
   "date": "2026-11-14",
   "status": "NO EDGE"
  },
  {
   "id": "RN-18",
   "name": "Opening style: after the first 5 bars, RUNNING and EMA9 > EMA20 > EMA50 = buy",
   "from": "User 11/14, UPXI 2025-07-21: no deep V at the open, but right after the first 5 bars state is running and EMA9 > EMA20 > EMA50. A separate entry style.",
   "rule": "The first bar from 9:34 to 9:59 with state RUNNING and EMA9 above both EMA20 and EMA50: buy the next bar open. One per day.",
   "open": "11/14 change (user, APLD 2025-03-11: 'first buy should happen at 9:38, next open after the cross'): was EMA9 > EMA20 > EMA50; EMA20 was still a hair under EMA50 at 9:37, so now only EMA9 has to be above both. UPXI still buys 9:38. Cut-off 10:00 is my choice.",
   "result": "Charts 11/14 on the 20 deep-V days: 16 opening buys - 3 hit +2% first (UPXI 9:38, QUBT 9:35, FJET 9:45), 11 hit -2% first, 2 neither. Not tested on the 30 days yet. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Adds 463 opening buys: diff -13.0 / +23.2 vs random 9:35-10:00 -9.2 / +3.7; net -0.34 / +0.41. Big swing with the market; worse than random in half 1. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). 8,676 opening buys: diff +3.8 / -1.7 vs random at the same time -2.3 / -6.8; net -0.09 / -0.33 vs -0.53 / -0.71. Beats same-time random by about +6 diff and +0.4% net in BOTH years = the best tilt in the set, but still below cost.",
   "date": "2026-11-14",
   "status": "TESTING"
  },
  {
   "id": "RN-17",
   "name": "Shallow cross after 11+ asleep bars: wait for RECLAIM, then buy",
   "from": "User 11/14.",
   "rule": "At an EMA9/EMA20 cross that is not a deep V, if the stock was asleep 11+ bars in a row during the dip, wait for state RECLAIM (no time limit while EMA9 stays above EMA20), buy the next bar open.",
   "open": "'Asleep for >10 bars' read as 11+ asleep bars in a row inside the dip (from EMA9 going under EMA20 to the cross). 11/14 fix: the cross bar itself counts for the reclaim wait.",
   "result": "Charts 11/14 (with RN-19): 2 buys - APPS 12:17 +2% (user's ~12:20 mark), FJET 12:59 -2%. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Adds 61 buys: diff +6.5 / +10.0 (above random both halves) but low rise (+0.85%) and net -0.30 / -0.23 = same as random. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). 1,017 buys, diff -4.9 / +2.0, net -0.41 / -0.34 = worse than random.",
   "date": "2026-11-14",
   "status": "NO EDGE"
  },
  {
   "id": "RN-16",
   "name": "At the cross EMA50 must not be falling",
   "from": "User 11/14.",
   "rule": "At the cross, block the buy when EMA50 is lower than 5 bars ago.",
   "open": "'Not falling' read as EMA50 now >= EMA50 5 bars ago.",
   "result": "Charts 11/14 on the 20 deep-V stock-days: deepv_new_rules_entries.pdf (all rules) and deepv_new_rules_entries_no_ema50.pdf (RN-16 off). Not tested on the 30 days yet. Blocks almost every cross: 59 of 72 deep-V / shallow-asleep crosses blocked, winners and losers alike (a deep V almost always has EMA50 still falling at the cross). With it on, almost only the opening entries are left. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Kept 589: diff -10.4 / +19.9, net -0.30 / +0.29. Blocked 750: -2.5 / +12.0, net -0.30 / +0.05. Worse in half 1, better in half 2 = not steady. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). Kept net -0.12 / -0.30 vs blocked -0.21 / -0.22. Better year 1, worse year 2.",
   "date": "2026-11-14",
   "status": "NO EDGE"
  },
  {
   "id": "RN-15",
   "name": "Asleep at the cross: wait for RECLAIM",
   "from": "User 11/14.",
   "rule": "If the stock is ASLEEP at the deep-V cross, wait until the state changes to RECLAIM, buy the next bar open. Cancel if EMA9 drops back under EMA20.",
   "open": "If the cross is both BASING and ASLEEP, this rule wins over RN-14.",
   "result": "Charts 11/14 on the 20 deep-V stock-days: deepv_new_rules_entries.pdf (all rules) and deepv_new_rules_entries_no_ema50.pdf (RN-16 off). Not tested on the 30 days yet. Removed the APPS 14:11 fire (EMA9 went back under before any reclaim) - one of the user's 'should never happen' marks. Also removed SOUN 4/9/25 12:07 (a winner in the old charts). | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Adds 19, removes 67. Added net -0.15 / -0.35, removed +0.44 / -0.23. Mixed, no clear help. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). Adds net -0.24 / -0.21, removes -0.28 / -0.17. Mixed.",
   "date": "2026-11-14",
   "status": "NO EDGE"
  },
  {
   "id": "RN-14",
   "name": "BASING at the buy signal: green candle confirm, else wait for 2 green bars",
   "from": "User 11/14.",
   "rule": "If the state is BASING at the deep-V cross: if the cross candle is green, buy the next bar open; if not, wait for 2 green bars in a row, then buy the next bar open. Cancel if EMA9 drops back under EMA20.",
   "open": "'2 green bars' read as 2 in a row.",
   "result": "Charts 11/14 on the 20 deep-V stock-days: deepv_new_rules_entries.pdf (all rules) and deepv_new_rules_entries_no_ema50.pdf (RN-16 off). Not tested on the 30 days yet. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). Moves basing buys to a green bar. Buys it adds: diff -9.5 / +10.9, net -0.73 / +0.24; buys it removes: -9.2 / +1.7, net -1.03 / +0.01. Better than without it in both halves (small). | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). Its buys net -0.36 / -0.14 vs the ones it replaces -0.32 / -0.15. No help (30-day gain did not hold).",
   "date": "2026-11-14",
   "status": "NO EDGE"
  },
  {
   "id": "RN-13",
   "date": "2026-11-14",
   "name": "Deep-V restart: main entry = EMA9 crosses EMA20 after a deep V",
   "status": "NO EDGE",
   "from": "User 11/14: 'lets start the deep-V rules over, the main entry is: enter when the ema9 cross ema20 after a deep v'. Replaces RN-1 as the base; further deep-V rules get added on top one at a time.",
   "rule": "Buy at the next bar open after EMA9 crosses above EMA20 after a deep V. Deep V for now = v1 values: EMA9 under EMA20 for 20+ bars and a dip (60-bar high to the low) of 8+ own candles. Buy window 9:35-15:00. Guards on. No other filters.",
   "open": "Deep-V definition kept at v1 (20 bars, 8 candles) until you change it.",
   "result": "Charts rebuilt 11/14 (deepv_restart_all_signals.pdf, 20 stock-days, every signal marked). Moving the window to 9:35 added no fires on these 20 days: a 20-bar deep V cannot finish much before 10:00. 2-year result for the same rule is RN-1: about random. | 30-day test 11/15 (Oct 5 - Nov 13, 881 stock-days, guards on; halves split at Oct 26; random: diff -1.4 / +3.7, net -0.25 / -0.23). RN-13 alone: 715 buys, diff -4.6 / +7.7 (random 10:00-15:00 +0.6 / +3.7), net -0.44 / +0.04. Worse than random in half 1, better in half 2. | 2-year test 11/15 (Oct 2024 - Oct 2026, 503 days, 14,754 stock-days; year 1 / year 2; random 10:00-15:00 diff -0.9 / -1.0, net -0.25 / -0.25; random 9:35-10:00 -2.3 / -6.8, net -0.53 / -0.71). RN-13 alone: 11,541 buys, diff +2.2 / +0.5, net -0.17 / -0.22. Small tilt over random, below cost."
  },
  {
   "id": "RN-12",
   "date": "2026-11-13",
   "name": "After a shallow cross, buy when the state changes to RUNNING",
   "status": "TESTING",
   "from": "QUBT 2025-01-24: crosses at 9:59 and 10:12 were too shallow for the deep-V rule (12 and 1 bars under, 4.4 and 4.3 own candles) and nothing bought; price then ran 11.60 to 12.18 by 10:26.",
   "rule": "When EMA9 crosses above EMA20 but the cross is shallow (not a deep V: under 20 bars below, or a dip under 8 own candles), do not buy on the cross itself unless the state is RUNNING. Buy at the next bar open on the first bar where the state is RUNNING (close above VWAP) - the cross bar itself counts. No time limit after the cross, as long as EMA9 stays above EMA20; if EMA9 drops back under EMA20, wait for a new cross. Buy window 9:35-15:00 (at least 5 bars to see how the stock behaves).",
   "open": "Read 'drop below EMA20' as EMA9 going back under EMA20 (the thing that needs a new cross).",
   "result": "30 days (10/5-11/13), first shallow-cross buy per stock-day, guards on: 686 buys, +2% first 32.5% / -2% first 28.4% (diff +4.1), hold60 net +0.00 vs random -0.30. 9:35-10:00: 512 buys diff +1.2 vs random same slot -5.4. 10:00-10:30: 51 buys diff +29.4, net +0.51 (small sample). 10:30-15:00: 123 buys +5.7, net -0.20. Waited 6+ bars after the cross: +13.3; RUNNING on the cross bar: -1.6. QUBT 1/24/25: would buy 9:35 (+2%), 10:06 (-2%), 10:13 (+2%), 11:29 (-2%). 2-year run waits for the user."
  },
  {
   "id": "RN-11",
   "date": "2026-11-13",
   "name": "Looser deep V for the morning",
   "status": "IDEA",
   "from": "QUBT 2025-01-24 10:12 and APPS 9:53: fast morning Vs the deep-V rule is too strict to catch.",
   "rule": "Before about 10:30, accept a cross after 10+ bars under and a 4+ own-candle dip (instead of 20 bars and 8 candles).",
   "open": "Exact morning cut-off and numbers.",
   "result": "Not tested."
  },
  {
   "id": "RN-10",
   "date": "2026-11-13",
   "name": "Price vs EMA50 at the buy",
   "status": "IDEA",
   "from": "Losers PDF with EMA50: all 40 winners and losers bought with EMA50 falling and EMA9 under EMA50, so those cannot block. Cross-during-reclaim losers were a little further above EMA50 (+0.87% vs +0.52%).",
   "rule": "Block cross-during-reclaim buys when the close is more than X% above EMA50.",
   "open": "X to sweep.",
   "result": "20 charts only - hint, not tested."
  },
  {
   "id": "RN-9",
   "date": "2026-11-13",
   "name": "Skip cross-during-reclaim buys before 10:30",
   "status": "IDEA",
   "from": "Cross-during-reclaim charts: 7 of 10 losers bought 10:00-10:22, only 3 of 10 winners before 10:30.",
   "rule": "Cross-during-reclaim entry, buy window 10:30-15:00 instead of 10:00-15:00.",
   "open": "",
   "result": "20 charts only - not tested."
  },
  {
   "id": "RN-8",
   "date": "2026-11-13",
   "name": "Block when resistance is far above (2%+)",
   "status": "IDEA",
   "from": "2-year resistance test: buys with the nearest resistance 2%+ above were the worst group in both years (hold60 net -0.54 / -0.33).",
   "rule": "Reclaim rule, block the buy when the nearest resistance above is 2% or more away.",
   "open": "",
   "result": "Seen inside RN-7 test, not tested on its own."
  },
  {
   "id": "RN-7",
   "date": "2026-11-13",
   "name": "Block the buy if the gap to resistance is under 0.8%",
   "status": "NO EDGE",
   "from": "User rule on top of the reclaim rule.",
   "rule": "Reclaim rule, block when the nearest resistance above (swing levels, open, first-15-min high/low) is under 0.8% away.",
   "open": "",
   "result": "30 days looked good (kept + cross last +13.5 diff). 2 years: kept buys diff +0.8 / +1.5, hold60 net -0.32 / -0.25 = worse than no block (-0.22 / -0.21); the blocked ones held better. Near resistance = smaller moves both ways."
  },
  {
   "id": "RN-6",
   "date": "2026-11-13",
   "name": "Cross during reclaim",
   "status": "NO EDGE (best tilt so far)",
   "from": "Inside the reclaim rule (RN-5): the EMA9/EMA20 cross happens during the reclaim run, not before it.",
   "rule": "RN-5, and the EMA cross bar is at or after the first bar of the run above VWAP.",
   "open": "Exit not built (stop under base low, +1/+2% target, time stop).",
   "result": "2 years: diff +6.0 / +3.2 (+2% first minus -2% first), hold60 net -0.20 / -0.18. Best entry tilt we have, still under the 0.2% cost on a 60-min hold. Charts: cross_during_reclaim_winners_losers.pdf."
  },
  {
   "id": "RN-5",
   "date": "2026-11-13",
   "name": "Reclaim after 6+ basing/asleep bars",
   "status": "NO EDGE",
   "from": "User: 'the state should be reclaim, after it been in an asleep or basing for more the 5 bars', v1 values (SOUN pages).",
   "rule": "State RECLAIM (close above VWAP, first 5 bars of the run, 15 of the 20 bars before under VWAP), at least 6 BASING-or-asleep bars right before, EMA9 > EMA20. Buy next bar open 10:00-15:00. Guards on.",
   "open": "",
   "result": "2 years: diff +1.9 / +1.5, hold60 net -0.22 / -0.21 (random -0.30 / -0.26)."
  },
  {
   "id": "RN-4",
   "date": "2026-11-13",
   "name": "EMA cross with BASING as the gate",
   "status": "NO EDGE",
   "from": "User: use the EMA cross to fire and the basing state to allow the buy.",
   "rule": "EMA9 crosses above EMA20 while the state is BASING; settings swept (EMA gap, range, asleep).",
   "open": "",
   "result": "2 years: quiet bases best (EMAs together <= 0.3 candles: diff +3.5 / +2.7, net -0.10 / -0.17), all below cost. 30 days alone showed nothing."
  },
  {
   "id": "RN-3",
   "date": "2026-11-13",
   "name": "Steep V rises, flat V fades",
   "status": "NO EDGE",
   "from": "User: 'the vs with more vertical angle usually rise, the vs with less angle if rises it will take longer otherwise it fades'.",
   "rule": "Judge deep-V fires by the V angle (own candles per minute).",
   "open": "",
   "result": "2 years: half true - steep Vs move faster both ways (+2 first and -2 first both ~27-30%), flat Vs slower; no edge."
  },
  {
   "id": "RN-2",
   "date": "2026-11-12",
   "name": "APPS marks: first cross 9:53, second ~12:20, never buy with EMAs + VWAP sloping down",
   "status": "IDEA",
   "from": "User marks on APPS 2025-06-25: 9:53 and the 12:16 cross are the right buys, 11:45 is not, the 14:11 fire should never happen.",
   "rule": "Block a cross buy when EMA9, EMA20 and VWAP are all sloping down; allow early (before 10:00) Vs.",
   "open": "3 tests offered, not run.",
   "result": "Not tested."
  },
  {
   "id": "RN-1",
   "date": "2026-11-11",
   "name": "Deep-V EMA cross (core)",
   "status": "NO EDGE (base replaced by RN-13)",
   "from": "Per-stock logic study.",
   "rule": "Buy next bar open after EMA9 crosses above EMA20, EMA9 under EMA20 for 20+ bars, V dip 8+ own candles, 10:00-15:00, guards on.",
   "open": "",
   "result": "2 years: about random; only cross-above-VWAP tilt, below cost."
  }
 ]
}