{ "checked_at_UTC": "2026-11-06T15:28:41.309151+00:00", "new_family_models_delivered": 4, "total_new_family_models": 4, "reference_deliveries": { "ts1_relative_original56": { "DELIVERY_SHA256": "2f98e06eac1216d5d06f489a0df56fd7a4148166d4840d0bd6686034df0d38a0", "FINAL_VERIFICATION_SHA256": "e0d39c78102aacd1c447f6cbdbc30846cb91ce2a77556c559aa9bc989a8d31ef" }, "ts2_relative_original56": { "DELIVERY_SHA256": "9d9f56ed894c91b391f5dc74c26988e07c7ff45afa55478a14bbf50542425c18", "FINAL_VERIFICATION_SHA256": "44cca7f2bc808d33e584bb481d34039e5230f166d9d16fe3d6d39062cd387dc8" }, "ts3_relative_original56": { "DELIVERY_SHA256": "c2cddcaad020490b37b245fdd1939012c744062cfb088e290756aa544a4e8735", "FINAL_VERIFICATION_SHA256": "0c6e32dfb962608dc4d858f5278bd03f76a5970cf8dbf578dd26f81d9ea6a8c5" }, "gnot_relative_original56": { "DELIVERY_SHA256": "fb37a9f90b2628c04f2ef1ae5211d0537c003f5019ba92407eb88e3813a85b7a", "FINAL_VERIFICATION_SHA256": "d9da2dbca8e67083ff736de8efb7fd4087a1e3c83debc5262492e57d4b6ffb92" }, "oformer_relative_original56": { "DELIVERY_SHA256": "5fd6bea97ef7b7d3824b874fb1b4aa58bc81d04a520a3c0d6ce875bb2c2ef03b", "FINAL_VERIFICATION_SHA256": "a99e1614edc838350b35efec17649876861debdf69e1653981d63b61690daea8" }, "fno_relative_original56": { "DELIVERY_SHA256": "2416fa5364e6041e1529e40c3bac64eebb7c50b0325566cffc56060dbc69bdab", "FINAL_VERIFICATION_SHA256": "59a08d0747e1326173fd92951a34c2d82ca56c0c62afae013e539d36bc3f2291" } }, "rows": [ { "model": "TS1 / Transolver", "variant": "ts1_relative_original56", "status": "delivered", "actual_updates": 6000, "parameters": 982884, "negative_VM_cases": 0, "minimum_VM_MPa": 5.939957903879607, "mean_U_relative_L2_percent": 1.5196610655618397, "worst_U_relative_L2_percent": 3.030126744093248, "mean_VM_relative_L2_percent": 3.052189697599478, "worst_VM_relative_L2_percent": 5.091025717891956, "mean_peak5_VM_relative_L2_percent": 2.70944125374595, "worst_peak5_VM_relative_L2_percent": 7.971015642271305, "mean_VM_max_relative_error_percent": 2.5853859109723976, "worst_VM_max_relative_error_percent": 16.210837270339898, "mean_VM_at_true_peak_relative_error_percent": 2.3480333530263837, "worst_VM_at_true_peak_relative_error_percent": 16.75808088188377 }, { "model": "TS2 / Transolver++", "variant": "ts2_relative_original56", "status": "delivered", "actual_updates": 6000, "parameters": 981172, "negative_VM_cases": 0, "minimum_VM_MPa": 6.251853902424434, "mean_U_relative_L2_percent": 1.579956159500325, "worst_U_relative_L2_percent": 3.3346992035709664, "mean_VM_relative_L2_percent": 3.281953890818957, "worst_VM_relative_L2_percent": 5.24547279076856, "mean_peak5_VM_relative_L2_percent": 2.829486579479652, "worst_peak5_VM_relative_L2_percent": 8.023191338685612, "mean_VM_max_relative_error_percent": 2.8258068796709335, "worst_VM_max_relative_error_percent": 16.455367612224926, "mean_VM_at_true_peak_relative_error_percent": 2.6598194321005337, "worst_VM_at_true_peak_relative_error_percent": 17.12990770576134 }, { "model": "TS3 reference", "variant": "ts3_relative_original56", "status": "delivered", "actual_updates": 6000, "parameters": 982884, "negative_VM_cases": 0, "minimum_VM_MPa": 3.362955985727976, "mean_U_relative_L2_percent": 1.6630223245299152, "worst_U_relative_L2_percent": 3.0118111211664313, "mean_VM_relative_L2_percent": 3.0426989647004974, "worst_VM_relative_L2_percent": 5.119223703720744, "mean_peak5_VM_relative_L2_percent": 2.7921442031648054, "worst_peak5_VM_relative_L2_percent": 8.18864613110814, "mean_VM_max_relative_error_percent": 2.8703645145661243, "worst_VM_max_relative_error_percent": 16.947314998720067, "mean_VM_at_true_peak_relative_error_percent": 2.577308980341227, "worst_VM_at_true_peak_relative_error_percent": 17.351450383019614 }, { "model": "GNOT", "variant": "gnot_relative_original56", "status": "delivered", "actual_updates": 6000, "parameters": 982170, "negative_VM_cases": 2, "minimum_VM_MPa": -4.703555983826, "mean_U_relative_L2_percent": 2.181395649640431, "worst_U_relative_L2_percent": 3.0845613679953963, "mean_VM_relative_L2_percent": 7.219631068187829, "worst_VM_relative_L2_percent": 8.830573007487262, "mean_peak5_VM_relative_L2_percent": 8.086298564659648, "worst_peak5_VM_relative_L2_percent": 9.936608752054603, "mean_VM_max_relative_error_percent": 7.632341902728338, "worst_VM_max_relative_error_percent": 11.083102656526918, "mean_VM_at_true_peak_relative_error_percent": 10.22201371092302, "worst_VM_at_true_peak_relative_error_percent": 16.88234768209511 }, { "model": "OFormer", "variant": "oformer_relative_original56", "status": "delivered", "actual_updates": 6000, "parameters": 990268, "negative_VM_cases": 0, "minimum_VM_MPa": 6.439363325864005, "mean_U_relative_L2_percent": 1.6467976690901922, "worst_U_relative_L2_percent": 1.9883337943297539, "mean_VM_relative_L2_percent": 3.4071957010285128, "worst_VM_relative_L2_percent": 4.534619275001042, "mean_peak5_VM_relative_L2_percent": 2.5496160460531536, "worst_peak5_VM_relative_L2_percent": 3.2298125652435914, "mean_VM_max_relative_error_percent": 1.1810570607870936, "worst_VM_max_relative_error_percent": 3.7231911814005287, "mean_VM_at_true_peak_relative_error_percent": 1.0056797601323026, "worst_VM_at_true_peak_relative_error_percent": 3.6327115327954274 }, { "model": "FNO reference", "variant": "fno_relative_original56", "status": "delivered", "actual_updates": 6000, "parameters": 984668, "negative_VM_cases": 2, "minimum_VM_MPa": -13.581791757407567, "mean_U_relative_L2_percent": 2.0246773217695657, "worst_U_relative_L2_percent": 2.9482398679489186, "mean_VM_relative_L2_percent": 1.8390191447379196, "worst_VM_relative_L2_percent": 2.36372661095492, "mean_peak5_VM_relative_L2_percent": 1.0443500616790806, "worst_peak5_VM_relative_L2_percent": 1.9496937277575301, "mean_VM_max_relative_error_percent": 1.0580704305803375, "worst_VM_max_relative_error_percent": 2.7400886853065956, "mean_VM_at_true_peak_relative_error_percent": 0.5406403603277149, "worst_VM_at_true_peak_relative_error_percent": 1.2944238439767664 } ], "scope": "Identical TRAIN20 maximin cases, original56 inputs/4 outputs, seed20261029, FP64, relative-L2-squared U/VM loss, 6000 actual20-case updates. Active trainable counts matched within1%. TRAIN20 fitting, not heldout generalization; one seed and fixed budget do not establish universal causality.", "final_human_conclusions": [ "At the fixed6000 budget, TS1 / Transolver has the lowest mean U error (1.5197%), while OFormer has the lowest worst-case U error (1.9883%). These are different criteria; there is no single winner on all metrics.", "FNO reference has the lowest mean VM error (1.8390%) and FNO reference the lowest worst-case VM error (2.3637%). FNO nevertheless has 2 cases with raw negative VM, so its lower relative error does not guarantee physically nonnegative predictions.", "Compared with the TS3 reference, TS1, TS2 and OFormer have lower mean U errors but higher mean VM errors. GNOT has higher mean U and VM errors than TS3 under this exact setup. The official architectures with matched parameter counts still behave differently at the same fixed budget; this observation does not establish a universal architectural cause.", "GNOT final6000: mean/worst U 2.1814%/3.0846%, mean/worst VM 7.2196%/8.8306%, 2 negative-VM cases, minimum -4.703556 MPa. The stress field remains the main error component. The completed budget was not extended to reach an accuracy threshold.", "No configuration meets both U and VM <=1% on every TRAIN20 case. These 20 cases are training cases, not an independent test set. One seed, one parameter scale and one fixed optimization budget support this comparison only; the separate 800/100/100 GNOT experiment remains pending and will have its own heldout-test report." ], "all_four_new_family_deliveries_complete": true }