team-riswan / submission_manifest.json
riswanmsm's picture
Submit final system code, manifest, and predictions for team-riswan
682bee1
Raw History Blame Contribute Delete
2.9 kB
{
"team": "riswan",
"codabench_submission_id": 138,
"codabench_filename": "submission_think_ens_v9_final.zip",
"score": {
"macro": 64.2482,
"easy": 65.2648,
"medium": 56.3456,
"hard": 71.134
},
"score_evidence": "User-provided leaderboard screenshot, 2026-10-28; provisional, not recomputed with gold labels.",
"predictions_sha256": "0998ea38f240c05103a7572a9a367a553f4e2b7664a31fe70f5c9668214dd554",
"zip_sha256": "8e11a43b16f6d1ad4a8979f9e2fa1954c3cae48549ec7b9591d3bd31a9cc8735",
"passes": {
"p1": {
"file": "training/passes/pass1_think_2048_orig.jsonl",
"rows": 2238,
"sha256": "602f9f03dd0e655fe8246826a02896bd1f03e815588a0df7c24838268c890568",
"original_project_path": "data/predictions_gemma4_think_kaggle_2238.jsonl",
"matches_original_source": true
},
"p2": {
"file": "training/passes/pass2_think_4096_rot1.jsonl",
"rows": 1100,
"sha256": "fecbb30512b11532b28204c5bb9262f87da1d9d7e9e7ae59d7a636d6f7133d50",
"original_project_path": "predictions_gemma4_think_pass2_ckpt.jsonl",
"matches_original_source": true
},
"p3": {
"file": "training/passes/pass3_think_4096_hint.jsonl",
"rows": 720,
"sha256": "cc724b6eba5b2a42fea1dcd8d143aeedb68406f412fd04fdb0d88028acb2be6c",
"original_project_path": "predictions_gemma4_think_pass3_ckpt.jsonl",
"matches_original_source": true
},
"p4": {
"file": "training/passes/pass4_think_4096_rot2.jsonl",
"rows": 712,
"sha256": "2b2535b1fd58606d2dd2fe43c268a9901df737f2812cabba4afcbde3572f2292",
"original_project_path": "predictions_gemma4_think_pass4_ckpt.jsonl",
"matches_original_source": true
},
"p5": {
"file": "training/passes/pass5_think_4096_rot3.jsonl",
"rows": 712,
"sha256": "2b1fdbc3e2abd4ab1c0dc7990fdc0efe2840fe897892508d6d683e967bfec3d7",
"original_project_path": "predictions_gemma4_think_pass5_ckpt.jsonl",
"matches_original_source": true
},
"mac": {
"file": "training/passes/mac_think_2048_orig.jsonl",
"rows": 1160,
"sha256": "a24d6da87db1b20f82a908f55cc7af9c6320886fd25edf99b5b9673855d468dd",
"original_project_path": "data/predictions_gemma4_think_ckpt.jsonl",
"matches_original_source": true
},
"cot": {
"file": "training/passes/baseline_cot_4shot.jsonl",
"rows": 2238,
"sha256": "9ee658f029f62d37d0c0bcdef8b15151a6f79d31a9ed780b898e836d26641375",
"original_project_path": "data/predictions_gemma4_cot.jsonl",
"matches_original_source": true
},
"dr": {
"file": "training/passes/baseline_direct_4shot.jsonl",
"rows": 2238,
"sha256": "24d9a51a2ad13ab4506398bf54b7989e7511fa82c9d36a954fda210d127254b5",
"original_project_path": "data/predictions_gemma4_direct.jsonl",
"matches_original_source": true
}
}
}