| { | |
| "model": "CryptoReasoner-20B", | |
| "checkpoint": "proof-v5-learned-epoch-4", | |
| "dataset": "itsalissonsilva/crypto-protocol-traces-synthetic", | |
| "dataset_revision": "f32dedb95a889ae8ff550eb61ca2e8a1bd9db5f9", | |
| "source_file": "encryption_graphs_v1/rows.json", | |
| "rows_sha256": "3051cd3b9dfdb597a5be54873968908491d056f39ec6dd875f0bae847a20675c", | |
| "cases": [ | |
| { | |
| "id": "proof-v5-test_iid-0011-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "f7abf9da9c9a7eaab4a7cfd02a0ed4cc91c3eded033777e43570b42a8a6cf87b" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0011-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "91368a944e4e0ccb5d1682a1807480e99293fffa7437480aba5438f28bbe2133" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0026-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "eeeefc92fa2f25553d5e2f59c13ee0205133a26fe87682d56217e48d4976f5e5" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0026-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "dc951b2870dd336697dc33f6a4e07a8c4a1b01e3595944e5e09f2952f36a38fb" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0034-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "36ebdd9ecd156e5e740d50ff7784f636381f7449c3fa24eb179607dc7a6303c9" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0034-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "03ec1b1e3a7bea1b167ed7c56ff2d2af0dd3caee8ca1fd91892f53d898ab12ec" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0036-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "846b93cdf8e67e5eae124d9e0ece529bf1c7df7f42bfef89486966cb77856c39" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0036-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "b3384052eede0fe2e8b4d4e66e809fadc86b0a4ddf590abffa011af9eeedd9e6" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0040-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "d67ca779833371ed2e0d3b1a0e4fb3acd8216f4c9a001246858aa408146499a8" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0040-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "652e2b6a102aa2b76ee07d4a2f0f77bf032471036a3b09f579bfe9734cd26ef1" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0051-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "8d22b941913d1be326c5946269d6df7f0f65265e989f509e8b37e1950a1e6e7c" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0051-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "33b62b321f3e34d18d815202d3446522c389baabc6fd65d356bb8afb5d19e3e3" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0054-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "085b87be80b0dd04c75c450c0b4fd1acde82af5ef8b79580141c8e4fdfbdaccf" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0054-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "29d72f7d0b339d9f0fc2358c328b21e037479e10c8bfa3a89beccf965a5c1739" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0057-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "1473db8c9b9955ea18cc36a2938c0655eaa82d76d0836466321c19b0b8f998b7" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0057-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "44037c7b505ad19cd4b6fcfa50387be854cf5432d8c570d8c3bfa79fae61ffa0" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0061-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "76148c8d1fa51d0275568012c474aab1852d3d475b1ef4e1b3009e736e01075e" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0061-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "9f95d6f599e6a071d8c75acf792cad61905c0b7c5dce1a110f82fa4301bb3c03" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0062-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "05354182cd7396d4e1d08d6fadcd08ed97f7ef6c35b21cc1cd6fe8d1a2dbffd0" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0062-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "d2994a0f7f0e759d5ffd69702c4e0fc7e3afb3aa01267820d45ad0c1d0bda949" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0063-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "b49b6547f90689d4b45589d76f4cd3086ac85b27c92b052779aff1a8a7c55c4a" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0063-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "6f52bf36705e41682f92ce26cf9ba36d6516f67ad4c5deac36f0a41c98efcf42" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0065-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "c486857c7bb94f76e8b5269af5c2349095359a4aa320d8c7ebc5e5ed514d2780" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0065-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "5a1ee56b326d440a2c221c6f044e117bb3b4ee09e265f9c3ef8a21b6b0e5d008" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0091-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "d38b4f6ebdb0e1ac7a30107a1e9890a176f8dac4b2dfa65a667fa757bd8dd347" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0091-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "826d420c79c6cdadb953d70fcfcd82b576340f88460482c75a718b9d25d54de2" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0099-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "c60f76f82dfe0dcbf60abfd56b3170b794845046b08dc5a79f10310b66463493" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0099-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "4adf23b6663b736bf504ad2ed3ee7fe210ff536220d5ad22e7796a16ecb61e76" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0113-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "3c8598c808077e3dfb50076dd65099d7c5155cd28b286726321fd8c1418fccd9" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0113-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "b8f4cfc63e616001d17920f47ce98c41c8a0b780f182a80114ff9760e6ca5719" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0117-reachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "7b59a1c446dee435e8765cd40a035cf4bdf854a7f1df0401ce1b176918db70d8" | |
| }, | |
| { | |
| "id": "proof-v5-test_iid-0117-unreachable", | |
| "split": "test_iid", | |
| "prompt_sha256": "2a31b8966832ed2bed735ec64dd59a07b14c5459f228eebf995054d13f97d479" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0002-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "6b0f712fc9c1b4d33d4ad6342c3a794a2be07276520e171e73b9057e9c48f2b3" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0002-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "95e5f64865073a592196e739e519ff51afd7149e4a9fe5580070b5449aef261e" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0005-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "a05309a6d7ae8a1c9d43dc69b49ba31942e9d47ab713415a2a0513af0e10b46d" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0005-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "2a1201542116ebfa30c187857f523c1cd66b5c5cd2adb743cab35fbe81fe0e40" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0024-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "fa79618dac670254af4bb77835c4aee1effdc60cc72820f226a02f2819c6751e" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0024-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "599448641bfd4cd3c288cb3150bb8858a174ea3dbc401f859691c172a2b5bf38" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0030-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "7f9d7c6997bb611ab338a3acb9407516e075aa2787105b944982c7bf684d12d4" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0030-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "8bb8b99e0052fb527278c1cdab8defbd3e4f4761d236b5613e6807d730c655c2" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0036-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "4ef442ec61e22f804d20832f3df6a833cc549dfc06424a3f9cff0fae78e56d0f" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0036-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "b5130f750ae5cfe2614a6acdfbf557d2331b8af78987251daaa2b7ab7d19797e" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0046-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "56b54a47abaf1bbd100efda1bc488e9927b1008317113bfb729b8030f5fa6585" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0046-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "5797b6e1c8d5224a6b4d5fea3d959e98af90ad5230bc18b8cb267563a9879bbe" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0054-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "0d5bb1aa3989078d3c86a76a72fcd1e6487dfab91b60c1395a29a2710952f5c5" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0054-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "84f3eecefc21f0b2a8c214e6c98ab879e265233e4ac7dbd95103cc13216a781c" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0065-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "c5da08573a10ef1ce0c664dfcb701954ad03a70a8bbee853a336430c6b57ca62" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0065-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "bacf16987da64deec1eaa4c1b9fb7ddac493a4668d503ada273bad6a334c1c47" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0079-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "75d7171ddc165311dfd25713dfe60e07c1c0aa452c64ee410a6cae40b939cbfa" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0079-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "216ea60d2d53dd840757411555d478188ada5b6cbc772ca4f6bedab199c3677a" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0081-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "f472ea43a4025087dad662936c8b4cef18da9668f11cc08b8775c4729209e294" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0081-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "3de760c58176b221f3c16dcccdc15e020eebdbde3ac76d064cac4257b5bb795a" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0088-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "dc23eb381a47f9fd25bcab9c3f67f76b35fb7ff8a956511a6844bf9aacac1cc0" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0088-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "ade5e128a932aec11cef9e57b9d2062269bc0f010900a7cd516dcf40cad3bfde" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0095-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "2d053ade599783a446510d560037c3cfbf66e8f6a556532486b39692cee652ec" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0095-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "789babd23c4087cdaba0a3f7d1fbd217f40c7e37495621ca417491f341dec198" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0096-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "dcbd0cd8a5b907772726bd1cd8024514563e4e7e84e521271b8a11f359fc054e" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0096-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "4c33657a071ceb7034b9e4761836cbd5f8fbf3e9fdc2bd6aeef7115378ca10c5" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0102-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "d73c022579fbed72887b31e7383640cff32e8e2cadf372270d65a1283e36890b" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0102-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "769c926c1cfd7d771789a2a62d31574d311bd7d8ff7d736165f2b079453595f9" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0107-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "0eafb57f22b063c1bb87b41d7d4a33b7fde8bac67d3a7e0448f02f9aeba8dbd8" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0107-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "972f024a4cea2b4de06810993f427e486e7eb6160b20f1eef28fedbc3da4cf08" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0115-reachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "74bab3927d82f1458df8d44eccb3d9f84245545321ae678bdc356718859ec025" | |
| }, | |
| { | |
| "id": "proof-v5-test_depth-0115-unreachable", | |
| "split": "test_depth", | |
| "prompt_sha256": "c3f712ec13d1dc4bc5f7ef2e362ba7ee4ed0fbd7dcf4faf40de57c5ddc61ff3b" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0004-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "8d5314749b485c35c5bf24ffa962ff9c487230fd2128a21f83b6171d60e70c9c" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0004-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "2abed4c441b5e71bb3a6054fa5d047d5b873f17edd455546d113e2b46612f600" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0005-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "a088e0953934545a20e9f2017e007c03be650dc922593b92fd699f023448b79f" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0005-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "6fc6256c28f97812121e1fd8437404dad11eda2f9cbc26d5f0273f2bfce5a1fb" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0019-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "44fa7390dc14369334b21edd9cdc4a2e11a35001b29e2ea0664b8a9e4da160c5" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0019-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "f88318101948e3875cbaf4a0c8343653cf8cafbe90c93de438b9b6846d3a1fbd" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0031-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "9fe0596042deb0a50a5028970eda590096546aae959d802c52e60804af20fce1" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0031-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "80c1109ddf958787e1824fd7dd5e313a545d685ff3b517022b18a35affdfbba1" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0032-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "bc879ca5d1ca895c52a87c4cae3d77b0b34ce9564322159de785e4009e729a1b" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0032-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "5d7c6750a22dca8bc4a1f9581debabc455d17c761c4222f5655dc975f7fdc300" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0036-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "c33ef4e8d86edf7f0137927c8a692f83ca99bfbf3d5c571dadeb46e4707b6835" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0036-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "59adef2df18d65977fe4f11af43b0db2b784c3fd1a9c2afd029c880e646eb25d" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0042-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "39d49a0fb8c62df7c8a3cbfed466278eea9e7b840c3372c58c2ea3a408b1256c" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0042-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "f30b49c825f4296d852afd119de8f2a5d18376943ca797536a252d7fbdf49263" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0046-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "77235260901953990854a302d5750d27486b4444745a93952d8561c7c7690bf5" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0046-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "2612532bf45f234fc514302541b58abf516a61e30f2a2777078bc7bb633227b4" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0048-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "d5f786586a373a1ff537d8f331f53a8ca815e046586420763c4aafad6a9b04bb" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0048-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "deecad6dd10c5f7f24bd26c44fdf13cdf0fe54d07f55e28dc7e80f951f375aea" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0060-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "1254a4890ad469208cb35f0b0c470255361d4f94f868b3fc406059108d478842" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0060-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "fa5aa0239d9b0d54f35fb0ba7ab4ebd9503bebc74c96aacc4aa77d48badfe878" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0063-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "d5d86020a7766886cbb6c5539ded6f02b19125c716c486f032fbb76f307a7722" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0063-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "eb4524534e1eabe3f2d43d01c334b3ca047f8368346e8a0a27e002943ca247dc" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0082-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "f0f9ff1bf3ba30eef0140482fd890584ba120ca55751904a92c79a7e136c5407" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0082-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "d55c546655840838621c17cfc9de465d914438aec25355fecc4cc1e15c7b8db1" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0094-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "69d9236446b06772dbe3ae43fd9578aee01192829cf5b938ada96a04e1874412" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0094-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "16201bdd90bfc8a27af16b2879d295ca119aceb65bb290372d1e5d284c5baa44" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0095-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "85a29232726650890da3bb368831f0126daca69348e9eecc893015d76d7e7776" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0095-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "da187f25325bacb2c2ec97ffb829db842646b7a0146ae9d80d8e24412bb2ab94" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0107-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "edcaf4f07fb7432475e52ad54201cd313a960760b7bbf12483e278fd33ef6e47" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0107-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "af7ad4134e47701ebc6a36c3ee28814b6c78ec83342f46865ade1eb53c4044a0" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0108-reachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "208a1461a8d7ae632f136895cfd4446191f395207e9bd401a5683f9a58063f77" | |
| }, | |
| { | |
| "id": "proof-v5-test_topology-0108-unreachable", | |
| "split": "test_topology", | |
| "prompt_sha256": "613ffa630ad287a7959e2d16496cae2246ef3cb8b2783ea39620cd6cfa0f02ee" | |
| } | |
| ], | |
| "selection": "16 complete paired groups per proof split, sorted by fixed salted group hash", | |
| "native": { | |
| "base": { | |
| "overall": { | |
| "n": 96, | |
| "certificate_pass_rate": 0.03125, | |
| "claim_accuracy": 0.4583333333333333, | |
| "mean_generated_tokens": 1373.40625, | |
| "token_caps": 12, | |
| "failure_types": { | |
| "not_closed": 36, | |
| "redundant_step": 2, | |
| "schema": 17, | |
| "unavailable_key": 26, | |
| "unclean_termination": 12, | |
| "valid": 3 | |
| } | |
| }, | |
| "test_depth": { | |
| "n": 32, | |
| "certificate_pass_rate": 0.03125, | |
| "claim_accuracy": 0.5625, | |
| "mean_generated_tokens": 1161.9375, | |
| "token_caps": 2, | |
| "failure_types": { | |
| "not_closed": 16, | |
| "schema": 3, | |
| "unavailable_key": 10, | |
| "unclean_termination": 2, | |
| "valid": 1 | |
| } | |
| }, | |
| "test_iid": { | |
| "n": 32, | |
| "certificate_pass_rate": 0.0625, | |
| "claim_accuracy": 0.40625, | |
| "mean_generated_tokens": 1366.96875, | |
| "token_caps": 5, | |
| "failure_types": { | |
| "not_closed": 12, | |
| "schema": 7, | |
| "unavailable_key": 6, | |
| "unclean_termination": 5, | |
| "valid": 2 | |
| } | |
| }, | |
| "test_topology": { | |
| "n": 32, | |
| "certificate_pass_rate": 0.0, | |
| "claim_accuracy": 0.40625, | |
| "mean_generated_tokens": 1591.3125, | |
| "token_caps": 5, | |
| "failure_types": { | |
| "not_closed": 8, | |
| "redundant_step": 2, | |
| "schema": 7, | |
| "unavailable_key": 10, | |
| "unclean_termination": 5 | |
| } | |
| } | |
| }, | |
| "learned": { | |
| "overall": { | |
| "n": 96, | |
| "certificate_pass_rate": 0.53125, | |
| "claim_accuracy": 0.9791666666666666, | |
| "mean_generated_tokens": 484.5520833333333, | |
| "token_caps": 0, | |
| "failure_types": { | |
| "not_closed": 6, | |
| "redundant_step": 6, | |
| "unavailable_key": 33, | |
| "valid": 51 | |
| } | |
| }, | |
| "test_depth": { | |
| "n": 32, | |
| "certificate_pass_rate": 0.5, | |
| "claim_accuracy": 0.96875, | |
| "mean_generated_tokens": 587.03125, | |
| "token_caps": 0, | |
| "failure_types": { | |
| "not_closed": 1, | |
| "unavailable_key": 15, | |
| "valid": 16 | |
| } | |
| }, | |
| "test_iid": { | |
| "n": 32, | |
| "certificate_pass_rate": 0.84375, | |
| "claim_accuracy": 1.0, | |
| "mean_generated_tokens": 406.625, | |
| "token_caps": 0, | |
| "failure_types": { | |
| "unavailable_key": 5, | |
| "valid": 27 | |
| } | |
| }, | |
| "test_topology": { | |
| "n": 32, | |
| "certificate_pass_rate": 0.25, | |
| "claim_accuracy": 0.96875, | |
| "mean_generated_tokens": 460.0, | |
| "token_caps": 0, | |
| "failure_types": { | |
| "not_closed": 5, | |
| "redundant_step": 6, | |
| "unavailable_key": 13, | |
| "valid": 8 | |
| } | |
| } | |
| } | |
| }, | |
| "primary_metric": "certificate_pass_rate", | |
| "pass_rule": "Overall paired HF primary metric must be greater with the adapter than with the base." | |
| } | |