Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
81 changes: 81 additions & 0 deletions research/fstar-family-gap-v711-seed3e3478d8/CERTIFICATE.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,81 @@
{
"box_attack": {
"box_violations": 0,
"demo_box": 1,
"demo_cert": 2,
"sweep_replayed": 100,
"sweep_total": 126,
"tau0_pattern": 115,
"tau0_total": 115,
"tau_ge1": 11
},
"calibration": "PASS_FG_CALIBRATION tied_min=11/12 cex_min_1=18/19 mp=9/16 chain=22 reach=0/12,8/19",
"cheap": {
"below_threshold": 0,
"falsifiers": 0,
"gap1_witnessed": 452,
"gap2_potential": 70,
"gap2_witnessed": 38,
"min_named_lo_ratio": 0.7143,
"mp_below_threshold": 0,
"records": 1638,
"trivial_gap0": 946,
"witnesses_replayed": 1384
},
"deep": {
"gap2_open_labels": [
"tied_min|0,1,2,3,4,5,6,7,8,9,10",
"tied_min|0,1,2,3,4,5,6,7,8,9,11",
"tied_min|0,1,2,3,4,5,6,7,8,10,11",
"tied_min|0,1,2,3,4,5,6,7,9,10,11",
"tied_min|0,1,2,3,4,5,6,8,9,10,11",
"tied_min|0,1,2,3,4,5,7,8,9,10,11",
"tied_min|0,1,2,3,4,6,7,8,9,10,11",
"tied_min|0,1,2,3,5,6,7,8,9,10,11",
"tied_min|0,1,2,4,5,6,7,8,9,10,11",
"tied_min|0,1,3,4,5,6,7,8,9,10,11",
"tied_min|0,2,3,4,5,6,7,8,9,10,11",
"tied_min|1,2,3,4,5,6,7,8,9,10,11"
],
"gap2_open_scan_only": 12,
"gap2_stored": 5,
"gap_named_proven": 17,
"gap_named_proven_max": 1,
"records": 113,
"reproduced": 24
},
"digest": "a4525ee97862ba34",
"package": "research/fstar-family-gap-v711-seed3e3478d8",
"predecessor_pin_digest": "9b78dfe85f2cd5a08aa2ebb31d814a3416ca55266e5f109121a5a00324136364",
"predecessor_pins": "predecessor/PREDECESSOR-PINS.json",
"receipts": {
"deep-priorities.json": "48ff78484369de0b657f4196581b3cf2c74aa24aab51d38dd3315db7e7d74c7b",
"receipt-cex_min_1-s10-cheap.json": "f9c9fea9edbdd5aa2041e28efe8f23d309f4b0e1108a3dfb977d197a1aeef7b7",
"receipt-cex_min_1-s10-deep.json": "e8ab3a48245e6359981cec546fc58d77c6d475233c1c2e884a79917063bf5ce3",
"receipt-cex_min_1-s11-cheap.json": "8bad12896a00bb4ac6bc9c720d0af41c24e4e5d64d14e9a997aed426a1447557",
"receipt-cex_min_1-s11-deep.json": "90300ac849aad2fc63a279ac4ce5785346fdb869e39f532f1a58b5cff0efc7ce",
"receipt-cex_min_1-s7-cheap.json": "bc0aaa57b285245790e7671bea6dd84d1c3cbb78e98995de79737539d63cd542",
"receipt-cex_min_1-s7-deep.json": "f51b58c4accbcada384d87b1beaef24bfcd7269d55b6ee0497c68c89cddd0d8d",
"receipt-cex_min_1-s8-cheap.json": "b9aa1d86d48597f48ec88dd87fea59080b47bbd85132d48609d1ad1e3937adf5",
"receipt-cex_min_1-s8-deep.json": "a44de741e60f646590ac9d61f895e4f886d94f9656715f6b5713c6cb25aed037",
"receipt-cex_min_1-s9-cheap.json": "e389b1b7d2061b8a72ca7a9c1fcd647207ff1204f67008a1820020c82ea12505",
"receipt-cex_min_1-s9-deep.json": "acab3e324c33cab21af8968cb90f17431b4a1eb391659e6e6784813c6748422d",
"receipt-supplement-settle-named.json": "4168af7a78828d69e628e4b61f6715225f237749ffc3c801c7b58a9714043c1d",
"receipt-tied_min-s10-cheap.json": "b53069652719dbe71c296444c21e9c3cdfc052ed86bc364483b1a4365c118a00",
"receipt-tied_min-s10-deep.json": "acad91c6a7eeac76fb000a4b3b79a112c817f450fbda47caa777fb6f840790c4",
"receipt-tied_min-s11-cheap.json": "e85c76cf6a41c9a6a05cf6f43c965b83f9ea233f61581d950c420cb65550ef59",
"receipt-tied_min-s11-deep.json": "78376e6c86d9571bd834173561e5e8f7e8163572d8fe578e852bed12cec51ddf",
"receipt-tied_min-s7-cheap.json": "7ec3314209628b38e5c09d31da0b7c367b007e4bea561020e8bfff4fcbfa82b9",
"receipt-tied_min-s7-deep.json": "4490c68864ccace776b15a5dcd376488f1596ef8751fb871a4c5adeeac79690f",
"receipt-tied_min-s8-cheap.json": "83590f5cd6c57d92c4ba7e7b71608b0376ba9b772135dddd48fa455101d6bedd",
"receipt-tied_min-s8-deep.json": "077aa377b42ed5ce5b440bbf482b9efed6d608703f1b266535b6802671895d55",
"receipt-tied_min-s9-cheap.json": "042269e7716b9a9f6d5b6fbd29aac608042fa4c5e52484ca7b99eb521cc35149",
"receipt-tied_min-s9-deep.json": "6781995b3c23c9167f72d7a370b39cbc74e2df220294ccfadac45710075c8bd8"
},
"task": "KB5h: the remaining search space of F-star's family gap - v = 7..11 census and the box-completeness attack",
"verdict": {
"box_completeness": "NOT PROVEN at general v; NOT REFUTED. box = cert on all 113 deep records (exact or ceiling/in-box), both fixtures (PR 2914: 11/11, 18/18), all 21 PR 2914 exact records, and all 11 tau >= 1 synthetic instances; every recorded attaining witness is box-valued. tau >= 1 hypothesis PROVEN necessary: explicit v = 2 exact 3-total decoder P = [[1,0,1],[2,1,0]], Q = [[1,0,0],[1,0,1]] (M = [[1,2],[2,2]], tau = (1,0)) has cert = 2 > box = 1; on the 115 tau = 0-line synthetic instances box = #{t : tau(t) >= 1} exactly (CHECKED pattern). Lemma BPP (PROVEN) pins the projection parity obstruction.",
"enumeration": "CHECKED (receipts + independent witness replay): 1638 sub-decoder records at v = 7..11 (tied_min complete at v = 9..11, strided at v = 7..8; cex_min_1 strided), 113 deep records, 126 synthetic instances. Falsifier criterion armed everywhere and PROVEN inoperative on the domain: named_lo = max(MP, reach) >= floor(2v/3) on all 1638 records (min 5/7), and each named_lo is a replayed certificate value, so the chain cost >= cert >= named_lo >= threshold rules out any admissible B below threshold. FIRST gap-2-or-more instance below v = 12 FOUND at v = 7: cex_min_1|0,1,2,5,6,8,15 (cert = 7 = v exact, MP = 5 exact, gap vs named_lo = 2 PROVEN); 22 such records. Family gap: first nonzero below v = 12 is gap_named = 1 PROVEN exact at v = 7 (tied_min|0,1,2,5,6,8,10 and tied_min|2,3,4,7,9,10,11: named = 6 exact, cert = 7 exact). gap_named = 2 below v = 12 EXCLUDED on every enumerated record except the 12 tied_min v = 11 sub-decoders (scan-only named, Lemma MX product 1977326743 - the exact obstruction; gap there is in {0,1,2}). The minimal PROVEN gap_named = 2 instance remains tied_min at v = 12 (PR 2914 record). Scan pitfall quantified: on 3 of 10 settled records the seeded 20k-iteration MX scan under-reported named by 1..2 (8 -> 10 exact on the v = 10 candidate).",
"matched_pivot": "DEMOTED (retained, no new evidence): MP strictly weaker than cert on the fixtures (9 < 11, 16 < 18); MP >= floor(2v/3) witnessed but not proved; MP alone does not meet the threshold on every record (mp_below_threshold counts them - the reach rung carries the threshold there)."
}
}
Loading
Loading