auto-sync 2026-07-04T06:38:25Z workspace (part 3)
Browse files
workspace/runs/paper_ctt_audit/audit.json
CHANGED
|
@@ -1,9 +1,29 @@
|
|
| 1 |
{
|
| 2 |
"audit_policy": {
|
| 3 |
-
"
|
|
|
|
|
|
|
|
|
|
| 4 |
"markdown_policy": "consolidated_readme_only"
|
| 5 |
},
|
| 6 |
"forbidden_patterns": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"paper": "latex/main.tex",
|
| 8 |
"paper_inputs": {
|
| 9 |
"num_inputs": 39,
|
|
@@ -489,307 +509,239 @@
|
|
| 489 |
],
|
| 490 |
"run_artifacts": [
|
| 491 |
{
|
| 492 |
-
"markdown_report_policy": "
|
| 493 |
-
"missing_advisor_contract": [
|
| 494 |
-
"report.md"
|
| 495 |
-
],
|
| 496 |
"missing_required": [],
|
| 497 |
"run_dir": "runs/action_bound_audit_rgb_refs",
|
| 498 |
"status": "pass"
|
| 499 |
},
|
| 500 |
{
|
| 501 |
-
"markdown_report_policy": "
|
| 502 |
-
"missing_advisor_contract": [
|
| 503 |
-
"report.md"
|
| 504 |
-
],
|
| 505 |
"missing_required": [],
|
| 506 |
"run_dir": "runs/ctt_base_context_obj_val_rollout_comparison",
|
| 507 |
"status": "pass"
|
| 508 |
},
|
| 509 |
{
|
| 510 |
-
"markdown_report_policy": "
|
| 511 |
-
"missing_advisor_contract": [
|
| 512 |
-
"report.md"
|
| 513 |
-
],
|
| 514 |
"missing_required": [],
|
| 515 |
"run_dir": "runs/ctt_base_context_obs_dominance_envclip_k16_train_to_test",
|
| 516 |
"status": "pass"
|
| 517 |
},
|
| 518 |
{
|
| 519 |
-
"markdown_report_policy": "
|
| 520 |
-
"missing_advisor_contract": [
|
| 521 |
-
"report.md"
|
| 522 |
-
],
|
| 523 |
"missing_required": [],
|
| 524 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_basic_envclip_train_to_test",
|
| 525 |
"status": "pass"
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"markdown_report_policy": "
|
| 529 |
-
"missing_advisor_contract": [
|
| 530 |
-
"report.md"
|
| 531 |
-
],
|
| 532 |
"missing_required": [],
|
| 533 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_chartcompat_obs_utility_task_envclip_k16_train_to_test",
|
| 534 |
"status": "pass"
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"markdown_report_policy": "
|
| 538 |
-
"missing_advisor_contract": [
|
| 539 |
-
"report.md"
|
| 540 |
-
],
|
| 541 |
"missing_required": [],
|
| 542 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_success_tanh_train_to_test",
|
| 543 |
"status": "pass"
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"markdown_report_policy": "
|
| 547 |
-
"missing_advisor_contract": [
|
| 548 |
-
"report.md"
|
| 549 |
-
],
|
| 550 |
"missing_required": [],
|
| 551 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_tangent_success_tanh_val_to_test",
|
| 552 |
"status": "pass"
|
| 553 |
},
|
| 554 |
{
|
| 555 |
-
"markdown_report_policy": "
|
| 556 |
-
"missing_advisor_contract": [
|
| 557 |
-
"report.md"
|
| 558 |
-
],
|
| 559 |
"missing_required": [],
|
| 560 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_val_to_test",
|
| 561 |
"status": "pass"
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"markdown_report_policy": "
|
| 565 |
-
"missing_advisor_contract": [
|
| 566 |
-
"report.md"
|
| 567 |
-
],
|
| 568 |
"missing_required": [],
|
| 569 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_source_envclip_train_to_test",
|
| 570 |
"status": "pass"
|
| 571 |
},
|
| 572 |
{
|
| 573 |
-
"markdown_report_policy": "
|
| 574 |
-
"missing_advisor_contract": [
|
| 575 |
-
"report.md"
|
| 576 |
-
],
|
| 577 |
"missing_required": [],
|
| 578 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_train_to_test",
|
| 579 |
"status": "pass"
|
| 580 |
},
|
| 581 |
{
|
| 582 |
-
"markdown_report_policy": "
|
| 583 |
-
"missing_advisor_contract": [
|
| 584 |
-
"report.md"
|
| 585 |
-
],
|
| 586 |
"missing_required": [],
|
| 587 |
"run_dir": "runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_train_to_test",
|
| 588 |
"status": "pass"
|
| 589 |
},
|
| 590 |
{
|
| 591 |
-
"markdown_report_policy": "
|
| 592 |
-
"missing_advisor_contract": [
|
| 593 |
-
"report.md"
|
| 594 |
-
],
|
| 595 |
"missing_required": [],
|
| 596 |
"run_dir": "runs/ctt_base_context_obs_test_envclip_k16_rollout_comparison",
|
| 597 |
"status": "pass"
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"markdown_report_policy": "
|
| 601 |
-
"missing_advisor_contract": [
|
| 602 |
-
"report.md"
|
| 603 |
-
],
|
| 604 |
"missing_required": [],
|
| 605 |
"run_dir": "runs/ctt_base_context_obs_test_envclip_rollout_comparison",
|
| 606 |
"status": "pass"
|
| 607 |
},
|
| 608 |
{
|
| 609 |
-
"markdown_report_policy": "
|
| 610 |
-
"missing_advisor_contract": [
|
| 611 |
-
"report.md"
|
| 612 |
-
],
|
| 613 |
"missing_required": [],
|
| 614 |
"run_dir": "runs/ctt_base_context_obs_test_noclip_rollout_comparison",
|
| 615 |
"status": "pass"
|
| 616 |
},
|
| 617 |
{
|
| 618 |
-
"markdown_report_policy": "
|
| 619 |
-
"missing_advisor_contract": [
|
| 620 |
-
"report.md"
|
| 621 |
-
],
|
| 622 |
"missing_required": [],
|
| 623 |
"run_dir": "runs/ctt_base_context_obs_test_perdim_trainmax_rollout_comparison",
|
| 624 |
"status": "pass"
|
| 625 |
},
|
| 626 |
{
|
| 627 |
-
"markdown_report_policy": "
|
| 628 |
-
"missing_advisor_contract": [
|
| 629 |
-
"report.md"
|
| 630 |
-
],
|
| 631 |
"missing_required": [],
|
| 632 |
"run_dir": "runs/ctt_base_context_obs_test_rollout_comparison",
|
| 633 |
"status": "pass"
|
| 634 |
},
|
| 635 |
{
|
| 636 |
-
"markdown_report_policy": "
|
| 637 |
-
"missing_advisor_contract": [
|
| 638 |
-
"report.md"
|
| 639 |
-
],
|
| 640 |
"missing_required": [],
|
| 641 |
"run_dir": "runs/ctt_base_context_obs_test_scaled0215_rollout_comparison",
|
| 642 |
"status": "pass"
|
| 643 |
},
|
| 644 |
{
|
| 645 |
-
"markdown_report_policy": "
|
| 646 |
-
"missing_advisor_contract": [
|
| 647 |
-
"report.md"
|
| 648 |
-
],
|
| 649 |
"missing_required": [],
|
| 650 |
"run_dir": "runs/ctt_base_context_obs_test_tanh_rollout_comparison",
|
| 651 |
"status": "pass"
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"markdown_report_policy": "
|
| 655 |
-
"missing_advisor_contract": [
|
| 656 |
-
"report.md"
|
| 657 |
-
],
|
| 658 |
"missing_required": [],
|
| 659 |
"run_dir": "runs/ctt_base_context_obs_val_envclip_rollout_comparison",
|
| 660 |
"status": "pass"
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"markdown_report_policy": "
|
| 664 |
-
"missing_advisor_contract": [
|
| 665 |
-
"report.md"
|
| 666 |
-
],
|
| 667 |
"missing_required": [],
|
| 668 |
"run_dir": "runs/ctt_base_context_obs_val_noclip_rollout_comparison",
|
| 669 |
"status": "pass"
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"markdown_report_policy": "
|
| 673 |
-
"missing_advisor_contract": [
|
| 674 |
-
"report.md"
|
| 675 |
-
],
|
| 676 |
"missing_required": [],
|
| 677 |
"run_dir": "runs/ctt_base_context_obs_val_perdim_trainmax_rollout_comparison",
|
| 678 |
"status": "pass"
|
| 679 |
},
|
| 680 |
{
|
| 681 |
-
"markdown_report_policy": "
|
| 682 |
-
"missing_advisor_contract": [
|
| 683 |
-
"report.md"
|
| 684 |
-
],
|
| 685 |
"missing_required": [],
|
| 686 |
"run_dir": "runs/ctt_base_context_obs_val_rollout_comparison",
|
| 687 |
"status": "pass"
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"markdown_report_policy": "
|
| 691 |
-
"missing_advisor_contract": [
|
| 692 |
-
"report.md"
|
| 693 |
-
],
|
| 694 |
"missing_required": [],
|
| 695 |
"run_dir": "runs/ctt_base_context_obs_val_scaled0215_rollout_comparison",
|
| 696 |
"status": "pass"
|
| 697 |
},
|
| 698 |
{
|
| 699 |
-
"markdown_report_policy": "
|
| 700 |
-
"missing_advisor_contract": [
|
| 701 |
-
"report.md"
|
| 702 |
-
],
|
| 703 |
"missing_required": [],
|
| 704 |
"run_dir": "runs/ctt_base_context_obs_val_tanh_rollout_comparison",
|
| 705 |
"status": "pass"
|
| 706 |
},
|
| 707 |
{
|
| 708 |
-
"markdown_report_policy": "
|
| 709 |
-
"missing_advisor_contract": [
|
| 710 |
-
"report.md"
|
| 711 |
-
],
|
| 712 |
"missing_required": [],
|
| 713 |
"run_dir": "runs/ctt_dominance_val_to_test",
|
| 714 |
"status": "pass"
|
| 715 |
},
|
| 716 |
{
|
| 717 |
-
"markdown_report_policy": "
|
| 718 |
-
"missing_advisor_contract": [
|
| 719 |
-
"report.md"
|
| 720 |
-
],
|
| 721 |
"missing_required": [],
|
| 722 |
"run_dir": "runs/ctt_learned_dominance_val_to_test",
|
| 723 |
"status": "pass"
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"markdown_report_policy": "
|
| 727 |
-
"missing_advisor_contract": [
|
| 728 |
-
"report.md"
|
| 729 |
-
],
|
| 730 |
"missing_required": [],
|
| 731 |
"run_dir": "runs/ctt_outcome_acceptance_gate",
|
| 732 |
"status": "pass"
|
| 733 |
},
|
| 734 |
{
|
| 735 |
-
"markdown_report_policy": "
|
| 736 |
-
"missing_advisor_contract": [
|
| 737 |
-
"report.md"
|
| 738 |
-
],
|
| 739 |
"missing_required": [],
|
| 740 |
"run_dir": "runs/ctt_residual_smoke_proxy",
|
| 741 |
"status": "pass"
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"markdown_report_policy": "
|
| 745 |
-
"missing_advisor_contract": [
|
| 746 |
-
"report.md"
|
| 747 |
-
],
|
| 748 |
"missing_required": [],
|
| 749 |
"run_dir": "runs/ctt_selector_diagnostic_sweep",
|
| 750 |
"status": "pass"
|
| 751 |
},
|
| 752 |
{
|
| 753 |
-
"markdown_report_policy": "
|
| 754 |
-
"missing_advisor_contract": [
|
| 755 |
-
"report.md"
|
| 756 |
-
],
|
| 757 |
"missing_required": [],
|
| 758 |
"run_dir": "runs/ctt_test_rollout_comparison",
|
| 759 |
"status": "pass"
|
| 760 |
},
|
| 761 |
{
|
| 762 |
-
"markdown_report_policy": "
|
| 763 |
-
"missing_advisor_contract": [
|
| 764 |
-
"report.md"
|
| 765 |
-
],
|
| 766 |
"missing_required": [],
|
| 767 |
"run_dir": "runs/ctt_val_proxy_comparison",
|
| 768 |
"status": "pass"
|
| 769 |
},
|
| 770 |
{
|
| 771 |
-
"markdown_report_policy": "
|
| 772 |
-
"missing_advisor_contract": [
|
| 773 |
-
"report.md"
|
| 774 |
-
],
|
| 775 |
"missing_required": [],
|
| 776 |
"run_dir": "runs/ctt_val_rollout_comparison",
|
| 777 |
"status": "pass"
|
| 778 |
},
|
| 779 |
{
|
| 780 |
-
"markdown_report_policy": "
|
| 781 |
-
"missing_advisor_contract": [
|
| 782 |
-
"report.md"
|
| 783 |
-
],
|
| 784 |
"missing_required": [],
|
| 785 |
"run_dir": "runs/data_accounting",
|
| 786 |
"status": "pass"
|
| 787 |
},
|
| 788 |
{
|
| 789 |
-
"markdown_report_policy": "
|
| 790 |
-
"missing_advisor_contract": [
|
| 791 |
-
"report.md"
|
| 792 |
-
],
|
| 793 |
"missing_required": [],
|
| 794 |
"run_dir": "runs/paper_ctt_audit",
|
| 795 |
"status": "pass"
|
|
@@ -801,7 +753,8 @@
|
|
| 801 |
"num_forbidden_matches": 0,
|
| 802 |
"num_paper_inputs": 39,
|
| 803 |
"num_run_dirs_in_paper": 34,
|
| 804 |
-
"
|
|
|
|
| 805 |
"status": "pass"
|
| 806 |
}
|
| 807 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"audit_policy": {
|
| 3 |
+
"allowed_markdown_files": [
|
| 4 |
+
"README.md"
|
| 5 |
+
],
|
| 6 |
+
"markdown_note": "Advisor checklist asks for report.md files, but the current workspace policy keeps README.md as the only Markdown document. This audit now fails on additional Markdown files instead of regenerating report.md.",
|
| 7 |
"markdown_policy": "consolidated_readme_only"
|
| 8 |
},
|
| 9 |
"forbidden_patterns": [],
|
| 10 |
+
"markdown_policy": {
|
| 11 |
+
"allowed": [
|
| 12 |
+
"README.md"
|
| 13 |
+
],
|
| 14 |
+
"missing_allowed": [],
|
| 15 |
+
"num_markdown_files": 1,
|
| 16 |
+
"num_unexpected_markdown": 0,
|
| 17 |
+
"policy": "consolidated_readme_only",
|
| 18 |
+
"rows": [
|
| 19 |
+
{
|
| 20 |
+
"path": "README.md",
|
| 21 |
+
"status": "pass"
|
| 22 |
+
}
|
| 23 |
+
],
|
| 24 |
+
"status": "pass",
|
| 25 |
+
"unexpected_markdown": []
|
| 26 |
+
},
|
| 27 |
"paper": "latex/main.tex",
|
| 28 |
"paper_inputs": {
|
| 29 |
"num_inputs": 39,
|
|
|
|
| 509 |
],
|
| 510 |
"run_artifacts": [
|
| 511 |
{
|
| 512 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 513 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 514 |
"missing_required": [],
|
| 515 |
"run_dir": "runs/action_bound_audit_rgb_refs",
|
| 516 |
"status": "pass"
|
| 517 |
},
|
| 518 |
{
|
| 519 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 520 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 521 |
"missing_required": [],
|
| 522 |
"run_dir": "runs/ctt_base_context_obj_val_rollout_comparison",
|
| 523 |
"status": "pass"
|
| 524 |
},
|
| 525 |
{
|
| 526 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 527 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 528 |
"missing_required": [],
|
| 529 |
"run_dir": "runs/ctt_base_context_obs_dominance_envclip_k16_train_to_test",
|
| 530 |
"status": "pass"
|
| 531 |
},
|
| 532 |
{
|
| 533 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 534 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 535 |
"missing_required": [],
|
| 536 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_basic_envclip_train_to_test",
|
| 537 |
"status": "pass"
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 541 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 542 |
"missing_required": [],
|
| 543 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_chartcompat_obs_utility_task_envclip_k16_train_to_test",
|
| 544 |
"status": "pass"
|
| 545 |
},
|
| 546 |
{
|
| 547 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 548 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 549 |
"missing_required": [],
|
| 550 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_success_tanh_train_to_test",
|
| 551 |
"status": "pass"
|
| 552 |
},
|
| 553 |
{
|
| 554 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 555 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 556 |
"missing_required": [],
|
| 557 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_tangent_success_tanh_val_to_test",
|
| 558 |
"status": "pass"
|
| 559 |
},
|
| 560 |
{
|
| 561 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 562 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 563 |
"missing_required": [],
|
| 564 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_val_to_test",
|
| 565 |
"status": "pass"
|
| 566 |
},
|
| 567 |
{
|
| 568 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 569 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 570 |
"missing_required": [],
|
| 571 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_source_envclip_train_to_test",
|
| 572 |
"status": "pass"
|
| 573 |
},
|
| 574 |
{
|
| 575 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 576 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 577 |
"missing_required": [],
|
| 578 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_train_to_test",
|
| 579 |
"status": "pass"
|
| 580 |
},
|
| 581 |
{
|
| 582 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 583 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 584 |
"missing_required": [],
|
| 585 |
"run_dir": "runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_train_to_test",
|
| 586 |
"status": "pass"
|
| 587 |
},
|
| 588 |
{
|
| 589 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 590 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 591 |
"missing_required": [],
|
| 592 |
"run_dir": "runs/ctt_base_context_obs_test_envclip_k16_rollout_comparison",
|
| 593 |
"status": "pass"
|
| 594 |
},
|
| 595 |
{
|
| 596 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 597 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 598 |
"missing_required": [],
|
| 599 |
"run_dir": "runs/ctt_base_context_obs_test_envclip_rollout_comparison",
|
| 600 |
"status": "pass"
|
| 601 |
},
|
| 602 |
{
|
| 603 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 604 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 605 |
"missing_required": [],
|
| 606 |
"run_dir": "runs/ctt_base_context_obs_test_noclip_rollout_comparison",
|
| 607 |
"status": "pass"
|
| 608 |
},
|
| 609 |
{
|
| 610 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 611 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 612 |
"missing_required": [],
|
| 613 |
"run_dir": "runs/ctt_base_context_obs_test_perdim_trainmax_rollout_comparison",
|
| 614 |
"status": "pass"
|
| 615 |
},
|
| 616 |
{
|
| 617 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 618 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 619 |
"missing_required": [],
|
| 620 |
"run_dir": "runs/ctt_base_context_obs_test_rollout_comparison",
|
| 621 |
"status": "pass"
|
| 622 |
},
|
| 623 |
{
|
| 624 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 625 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 626 |
"missing_required": [],
|
| 627 |
"run_dir": "runs/ctt_base_context_obs_test_scaled0215_rollout_comparison",
|
| 628 |
"status": "pass"
|
| 629 |
},
|
| 630 |
{
|
| 631 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 632 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 633 |
"missing_required": [],
|
| 634 |
"run_dir": "runs/ctt_base_context_obs_test_tanh_rollout_comparison",
|
| 635 |
"status": "pass"
|
| 636 |
},
|
| 637 |
{
|
| 638 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 639 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 640 |
"missing_required": [],
|
| 641 |
"run_dir": "runs/ctt_base_context_obs_val_envclip_rollout_comparison",
|
| 642 |
"status": "pass"
|
| 643 |
},
|
| 644 |
{
|
| 645 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 646 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 647 |
"missing_required": [],
|
| 648 |
"run_dir": "runs/ctt_base_context_obs_val_noclip_rollout_comparison",
|
| 649 |
"status": "pass"
|
| 650 |
},
|
| 651 |
{
|
| 652 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 653 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 654 |
"missing_required": [],
|
| 655 |
"run_dir": "runs/ctt_base_context_obs_val_perdim_trainmax_rollout_comparison",
|
| 656 |
"status": "pass"
|
| 657 |
},
|
| 658 |
{
|
| 659 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 660 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 661 |
"missing_required": [],
|
| 662 |
"run_dir": "runs/ctt_base_context_obs_val_rollout_comparison",
|
| 663 |
"status": "pass"
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 667 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 668 |
"missing_required": [],
|
| 669 |
"run_dir": "runs/ctt_base_context_obs_val_scaled0215_rollout_comparison",
|
| 670 |
"status": "pass"
|
| 671 |
},
|
| 672 |
{
|
| 673 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 674 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 675 |
"missing_required": [],
|
| 676 |
"run_dir": "runs/ctt_base_context_obs_val_tanh_rollout_comparison",
|
| 677 |
"status": "pass"
|
| 678 |
},
|
| 679 |
{
|
| 680 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 681 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 682 |
"missing_required": [],
|
| 683 |
"run_dir": "runs/ctt_dominance_val_to_test",
|
| 684 |
"status": "pass"
|
| 685 |
},
|
| 686 |
{
|
| 687 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 688 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 689 |
"missing_required": [],
|
| 690 |
"run_dir": "runs/ctt_learned_dominance_val_to_test",
|
| 691 |
"status": "pass"
|
| 692 |
},
|
| 693 |
{
|
| 694 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 695 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 696 |
"missing_required": [],
|
| 697 |
"run_dir": "runs/ctt_outcome_acceptance_gate",
|
| 698 |
"status": "pass"
|
| 699 |
},
|
| 700 |
{
|
| 701 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 702 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 703 |
"missing_required": [],
|
| 704 |
"run_dir": "runs/ctt_residual_smoke_proxy",
|
| 705 |
"status": "pass"
|
| 706 |
},
|
| 707 |
{
|
| 708 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 709 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 710 |
"missing_required": [],
|
| 711 |
"run_dir": "runs/ctt_selector_diagnostic_sweep",
|
| 712 |
"status": "pass"
|
| 713 |
},
|
| 714 |
{
|
| 715 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 716 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 717 |
"missing_required": [],
|
| 718 |
"run_dir": "runs/ctt_test_rollout_comparison",
|
| 719 |
"status": "pass"
|
| 720 |
},
|
| 721 |
{
|
| 722 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 723 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 724 |
"missing_required": [],
|
| 725 |
"run_dir": "runs/ctt_val_proxy_comparison",
|
| 726 |
"status": "pass"
|
| 727 |
},
|
| 728 |
{
|
| 729 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 730 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 731 |
"missing_required": [],
|
| 732 |
"run_dir": "runs/ctt_val_rollout_comparison",
|
| 733 |
"status": "pass"
|
| 734 |
},
|
| 735 |
{
|
| 736 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 737 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 738 |
"missing_required": [],
|
| 739 |
"run_dir": "runs/data_accounting",
|
| 740 |
"status": "pass"
|
| 741 |
},
|
| 742 |
{
|
| 743 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 744 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 745 |
"missing_required": [],
|
| 746 |
"run_dir": "runs/paper_ctt_audit",
|
| 747 |
"status": "pass"
|
|
|
|
| 753 |
"num_forbidden_matches": 0,
|
| 754 |
"num_paper_inputs": 39,
|
| 755 |
"num_run_dirs_in_paper": 34,
|
| 756 |
+
"num_unexpected_markdown": 0,
|
| 757 |
+
"num_warnings": 0,
|
| 758 |
"status": "pass"
|
| 759 |
}
|
| 760 |
}
|
workspace/runs/paper_ctt_audit/config.yaml
CHANGED
|
@@ -1,3 +1,5 @@
|
|
| 1 |
paper: latex/main.tex
|
| 2 |
markdown_policy: consolidated_readme_only
|
| 3 |
strict_report_md: false
|
|
|
|
|
|
|
|
|
| 1 |
paper: latex/main.tex
|
| 2 |
markdown_policy: consolidated_readme_only
|
| 3 |
strict_report_md: false
|
| 4 |
+
allowed_markdown_files:
|
| 5 |
+
- README.md
|
workspace/runs/paper_ctt_audit/metrics.json
CHANGED
|
@@ -1,9 +1,29 @@
|
|
| 1 |
{
|
| 2 |
"audit_policy": {
|
| 3 |
-
"
|
|
|
|
|
|
|
|
|
|
| 4 |
"markdown_policy": "consolidated_readme_only"
|
| 5 |
},
|
| 6 |
"forbidden_patterns": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"paper": "latex/main.tex",
|
| 8 |
"paper_inputs": {
|
| 9 |
"num_inputs": 39,
|
|
@@ -489,307 +509,239 @@
|
|
| 489 |
],
|
| 490 |
"run_artifacts": [
|
| 491 |
{
|
| 492 |
-
"markdown_report_policy": "
|
| 493 |
-
"missing_advisor_contract": [
|
| 494 |
-
"report.md"
|
| 495 |
-
],
|
| 496 |
"missing_required": [],
|
| 497 |
"run_dir": "runs/action_bound_audit_rgb_refs",
|
| 498 |
"status": "pass"
|
| 499 |
},
|
| 500 |
{
|
| 501 |
-
"markdown_report_policy": "
|
| 502 |
-
"missing_advisor_contract": [
|
| 503 |
-
"report.md"
|
| 504 |
-
],
|
| 505 |
"missing_required": [],
|
| 506 |
"run_dir": "runs/ctt_base_context_obj_val_rollout_comparison",
|
| 507 |
"status": "pass"
|
| 508 |
},
|
| 509 |
{
|
| 510 |
-
"markdown_report_policy": "
|
| 511 |
-
"missing_advisor_contract": [
|
| 512 |
-
"report.md"
|
| 513 |
-
],
|
| 514 |
"missing_required": [],
|
| 515 |
"run_dir": "runs/ctt_base_context_obs_dominance_envclip_k16_train_to_test",
|
| 516 |
"status": "pass"
|
| 517 |
},
|
| 518 |
{
|
| 519 |
-
"markdown_report_policy": "
|
| 520 |
-
"missing_advisor_contract": [
|
| 521 |
-
"report.md"
|
| 522 |
-
],
|
| 523 |
"missing_required": [],
|
| 524 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_basic_envclip_train_to_test",
|
| 525 |
"status": "pass"
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"markdown_report_policy": "
|
| 529 |
-
"missing_advisor_contract": [
|
| 530 |
-
"report.md"
|
| 531 |
-
],
|
| 532 |
"missing_required": [],
|
| 533 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_chartcompat_obs_utility_task_envclip_k16_train_to_test",
|
| 534 |
"status": "pass"
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"markdown_report_policy": "
|
| 538 |
-
"missing_advisor_contract": [
|
| 539 |
-
"report.md"
|
| 540 |
-
],
|
| 541 |
"missing_required": [],
|
| 542 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_success_tanh_train_to_test",
|
| 543 |
"status": "pass"
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"markdown_report_policy": "
|
| 547 |
-
"missing_advisor_contract": [
|
| 548 |
-
"report.md"
|
| 549 |
-
],
|
| 550 |
"missing_required": [],
|
| 551 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_tangent_success_tanh_val_to_test",
|
| 552 |
"status": "pass"
|
| 553 |
},
|
| 554 |
{
|
| 555 |
-
"markdown_report_policy": "
|
| 556 |
-
"missing_advisor_contract": [
|
| 557 |
-
"report.md"
|
| 558 |
-
],
|
| 559 |
"missing_required": [],
|
| 560 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_val_to_test",
|
| 561 |
"status": "pass"
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"markdown_report_policy": "
|
| 565 |
-
"missing_advisor_contract": [
|
| 566 |
-
"report.md"
|
| 567 |
-
],
|
| 568 |
"missing_required": [],
|
| 569 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_source_envclip_train_to_test",
|
| 570 |
"status": "pass"
|
| 571 |
},
|
| 572 |
{
|
| 573 |
-
"markdown_report_policy": "
|
| 574 |
-
"missing_advisor_contract": [
|
| 575 |
-
"report.md"
|
| 576 |
-
],
|
| 577 |
"missing_required": [],
|
| 578 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_train_to_test",
|
| 579 |
"status": "pass"
|
| 580 |
},
|
| 581 |
{
|
| 582 |
-
"markdown_report_policy": "
|
| 583 |
-
"missing_advisor_contract": [
|
| 584 |
-
"report.md"
|
| 585 |
-
],
|
| 586 |
"missing_required": [],
|
| 587 |
"run_dir": "runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_train_to_test",
|
| 588 |
"status": "pass"
|
| 589 |
},
|
| 590 |
{
|
| 591 |
-
"markdown_report_policy": "
|
| 592 |
-
"missing_advisor_contract": [
|
| 593 |
-
"report.md"
|
| 594 |
-
],
|
| 595 |
"missing_required": [],
|
| 596 |
"run_dir": "runs/ctt_base_context_obs_test_envclip_k16_rollout_comparison",
|
| 597 |
"status": "pass"
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"markdown_report_policy": "
|
| 601 |
-
"missing_advisor_contract": [
|
| 602 |
-
"report.md"
|
| 603 |
-
],
|
| 604 |
"missing_required": [],
|
| 605 |
"run_dir": "runs/ctt_base_context_obs_test_envclip_rollout_comparison",
|
| 606 |
"status": "pass"
|
| 607 |
},
|
| 608 |
{
|
| 609 |
-
"markdown_report_policy": "
|
| 610 |
-
"missing_advisor_contract": [
|
| 611 |
-
"report.md"
|
| 612 |
-
],
|
| 613 |
"missing_required": [],
|
| 614 |
"run_dir": "runs/ctt_base_context_obs_test_noclip_rollout_comparison",
|
| 615 |
"status": "pass"
|
| 616 |
},
|
| 617 |
{
|
| 618 |
-
"markdown_report_policy": "
|
| 619 |
-
"missing_advisor_contract": [
|
| 620 |
-
"report.md"
|
| 621 |
-
],
|
| 622 |
"missing_required": [],
|
| 623 |
"run_dir": "runs/ctt_base_context_obs_test_perdim_trainmax_rollout_comparison",
|
| 624 |
"status": "pass"
|
| 625 |
},
|
| 626 |
{
|
| 627 |
-
"markdown_report_policy": "
|
| 628 |
-
"missing_advisor_contract": [
|
| 629 |
-
"report.md"
|
| 630 |
-
],
|
| 631 |
"missing_required": [],
|
| 632 |
"run_dir": "runs/ctt_base_context_obs_test_rollout_comparison",
|
| 633 |
"status": "pass"
|
| 634 |
},
|
| 635 |
{
|
| 636 |
-
"markdown_report_policy": "
|
| 637 |
-
"missing_advisor_contract": [
|
| 638 |
-
"report.md"
|
| 639 |
-
],
|
| 640 |
"missing_required": [],
|
| 641 |
"run_dir": "runs/ctt_base_context_obs_test_scaled0215_rollout_comparison",
|
| 642 |
"status": "pass"
|
| 643 |
},
|
| 644 |
{
|
| 645 |
-
"markdown_report_policy": "
|
| 646 |
-
"missing_advisor_contract": [
|
| 647 |
-
"report.md"
|
| 648 |
-
],
|
| 649 |
"missing_required": [],
|
| 650 |
"run_dir": "runs/ctt_base_context_obs_test_tanh_rollout_comparison",
|
| 651 |
"status": "pass"
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"markdown_report_policy": "
|
| 655 |
-
"missing_advisor_contract": [
|
| 656 |
-
"report.md"
|
| 657 |
-
],
|
| 658 |
"missing_required": [],
|
| 659 |
"run_dir": "runs/ctt_base_context_obs_val_envclip_rollout_comparison",
|
| 660 |
"status": "pass"
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"markdown_report_policy": "
|
| 664 |
-
"missing_advisor_contract": [
|
| 665 |
-
"report.md"
|
| 666 |
-
],
|
| 667 |
"missing_required": [],
|
| 668 |
"run_dir": "runs/ctt_base_context_obs_val_noclip_rollout_comparison",
|
| 669 |
"status": "pass"
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"markdown_report_policy": "
|
| 673 |
-
"missing_advisor_contract": [
|
| 674 |
-
"report.md"
|
| 675 |
-
],
|
| 676 |
"missing_required": [],
|
| 677 |
"run_dir": "runs/ctt_base_context_obs_val_perdim_trainmax_rollout_comparison",
|
| 678 |
"status": "pass"
|
| 679 |
},
|
| 680 |
{
|
| 681 |
-
"markdown_report_policy": "
|
| 682 |
-
"missing_advisor_contract": [
|
| 683 |
-
"report.md"
|
| 684 |
-
],
|
| 685 |
"missing_required": [],
|
| 686 |
"run_dir": "runs/ctt_base_context_obs_val_rollout_comparison",
|
| 687 |
"status": "pass"
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"markdown_report_policy": "
|
| 691 |
-
"missing_advisor_contract": [
|
| 692 |
-
"report.md"
|
| 693 |
-
],
|
| 694 |
"missing_required": [],
|
| 695 |
"run_dir": "runs/ctt_base_context_obs_val_scaled0215_rollout_comparison",
|
| 696 |
"status": "pass"
|
| 697 |
},
|
| 698 |
{
|
| 699 |
-
"markdown_report_policy": "
|
| 700 |
-
"missing_advisor_contract": [
|
| 701 |
-
"report.md"
|
| 702 |
-
],
|
| 703 |
"missing_required": [],
|
| 704 |
"run_dir": "runs/ctt_base_context_obs_val_tanh_rollout_comparison",
|
| 705 |
"status": "pass"
|
| 706 |
},
|
| 707 |
{
|
| 708 |
-
"markdown_report_policy": "
|
| 709 |
-
"missing_advisor_contract": [
|
| 710 |
-
"report.md"
|
| 711 |
-
],
|
| 712 |
"missing_required": [],
|
| 713 |
"run_dir": "runs/ctt_dominance_val_to_test",
|
| 714 |
"status": "pass"
|
| 715 |
},
|
| 716 |
{
|
| 717 |
-
"markdown_report_policy": "
|
| 718 |
-
"missing_advisor_contract": [
|
| 719 |
-
"report.md"
|
| 720 |
-
],
|
| 721 |
"missing_required": [],
|
| 722 |
"run_dir": "runs/ctt_learned_dominance_val_to_test",
|
| 723 |
"status": "pass"
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"markdown_report_policy": "
|
| 727 |
-
"missing_advisor_contract": [
|
| 728 |
-
"report.md"
|
| 729 |
-
],
|
| 730 |
"missing_required": [],
|
| 731 |
"run_dir": "runs/ctt_outcome_acceptance_gate",
|
| 732 |
"status": "pass"
|
| 733 |
},
|
| 734 |
{
|
| 735 |
-
"markdown_report_policy": "
|
| 736 |
-
"missing_advisor_contract": [
|
| 737 |
-
"report.md"
|
| 738 |
-
],
|
| 739 |
"missing_required": [],
|
| 740 |
"run_dir": "runs/ctt_residual_smoke_proxy",
|
| 741 |
"status": "pass"
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"markdown_report_policy": "
|
| 745 |
-
"missing_advisor_contract": [
|
| 746 |
-
"report.md"
|
| 747 |
-
],
|
| 748 |
"missing_required": [],
|
| 749 |
"run_dir": "runs/ctt_selector_diagnostic_sweep",
|
| 750 |
"status": "pass"
|
| 751 |
},
|
| 752 |
{
|
| 753 |
-
"markdown_report_policy": "
|
| 754 |
-
"missing_advisor_contract": [
|
| 755 |
-
"report.md"
|
| 756 |
-
],
|
| 757 |
"missing_required": [],
|
| 758 |
"run_dir": "runs/ctt_test_rollout_comparison",
|
| 759 |
"status": "pass"
|
| 760 |
},
|
| 761 |
{
|
| 762 |
-
"markdown_report_policy": "
|
| 763 |
-
"missing_advisor_contract": [
|
| 764 |
-
"report.md"
|
| 765 |
-
],
|
| 766 |
"missing_required": [],
|
| 767 |
"run_dir": "runs/ctt_val_proxy_comparison",
|
| 768 |
"status": "pass"
|
| 769 |
},
|
| 770 |
{
|
| 771 |
-
"markdown_report_policy": "
|
| 772 |
-
"missing_advisor_contract": [
|
| 773 |
-
"report.md"
|
| 774 |
-
],
|
| 775 |
"missing_required": [],
|
| 776 |
"run_dir": "runs/ctt_val_rollout_comparison",
|
| 777 |
"status": "pass"
|
| 778 |
},
|
| 779 |
{
|
| 780 |
-
"markdown_report_policy": "
|
| 781 |
-
"missing_advisor_contract": [
|
| 782 |
-
"report.md"
|
| 783 |
-
],
|
| 784 |
"missing_required": [],
|
| 785 |
"run_dir": "runs/data_accounting",
|
| 786 |
"status": "pass"
|
| 787 |
},
|
| 788 |
{
|
| 789 |
-
"markdown_report_policy": "
|
| 790 |
-
"missing_advisor_contract": [
|
| 791 |
-
"report.md"
|
| 792 |
-
],
|
| 793 |
"missing_required": [],
|
| 794 |
"run_dir": "runs/paper_ctt_audit",
|
| 795 |
"status": "pass"
|
|
@@ -801,7 +753,8 @@
|
|
| 801 |
"num_forbidden_matches": 0,
|
| 802 |
"num_paper_inputs": 39,
|
| 803 |
"num_run_dirs_in_paper": 34,
|
| 804 |
-
"
|
|
|
|
| 805 |
"status": "pass"
|
| 806 |
}
|
| 807 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"audit_policy": {
|
| 3 |
+
"allowed_markdown_files": [
|
| 4 |
+
"README.md"
|
| 5 |
+
],
|
| 6 |
+
"markdown_note": "Advisor checklist asks for report.md files, but the current workspace policy keeps README.md as the only Markdown document. This audit now fails on additional Markdown files instead of regenerating report.md.",
|
| 7 |
"markdown_policy": "consolidated_readme_only"
|
| 8 |
},
|
| 9 |
"forbidden_patterns": [],
|
| 10 |
+
"markdown_policy": {
|
| 11 |
+
"allowed": [
|
| 12 |
+
"README.md"
|
| 13 |
+
],
|
| 14 |
+
"missing_allowed": [],
|
| 15 |
+
"num_markdown_files": 1,
|
| 16 |
+
"num_unexpected_markdown": 0,
|
| 17 |
+
"policy": "consolidated_readme_only",
|
| 18 |
+
"rows": [
|
| 19 |
+
{
|
| 20 |
+
"path": "README.md",
|
| 21 |
+
"status": "pass"
|
| 22 |
+
}
|
| 23 |
+
],
|
| 24 |
+
"status": "pass",
|
| 25 |
+
"unexpected_markdown": []
|
| 26 |
+
},
|
| 27 |
"paper": "latex/main.tex",
|
| 28 |
"paper_inputs": {
|
| 29 |
"num_inputs": 39,
|
|
|
|
| 509 |
],
|
| 510 |
"run_artifacts": [
|
| 511 |
{
|
| 512 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 513 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 514 |
"missing_required": [],
|
| 515 |
"run_dir": "runs/action_bound_audit_rgb_refs",
|
| 516 |
"status": "pass"
|
| 517 |
},
|
| 518 |
{
|
| 519 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 520 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 521 |
"missing_required": [],
|
| 522 |
"run_dir": "runs/ctt_base_context_obj_val_rollout_comparison",
|
| 523 |
"status": "pass"
|
| 524 |
},
|
| 525 |
{
|
| 526 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 527 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 528 |
"missing_required": [],
|
| 529 |
"run_dir": "runs/ctt_base_context_obs_dominance_envclip_k16_train_to_test",
|
| 530 |
"status": "pass"
|
| 531 |
},
|
| 532 |
{
|
| 533 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 534 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 535 |
"missing_required": [],
|
| 536 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_basic_envclip_train_to_test",
|
| 537 |
"status": "pass"
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 541 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 542 |
"missing_required": [],
|
| 543 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_chartcompat_obs_utility_task_envclip_k16_train_to_test",
|
| 544 |
"status": "pass"
|
| 545 |
},
|
| 546 |
{
|
| 547 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 548 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 549 |
"missing_required": [],
|
| 550 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_success_tanh_train_to_test",
|
| 551 |
"status": "pass"
|
| 552 |
},
|
| 553 |
{
|
| 554 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 555 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 556 |
"missing_required": [],
|
| 557 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_tangent_success_tanh_val_to_test",
|
| 558 |
"status": "pass"
|
| 559 |
},
|
| 560 |
{
|
| 561 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 562 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 563 |
"missing_required": [],
|
| 564 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_context_val_to_test",
|
| 565 |
"status": "pass"
|
| 566 |
},
|
| 567 |
{
|
| 568 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 569 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 570 |
"missing_required": [],
|
| 571 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_source_envclip_train_to_test",
|
| 572 |
"status": "pass"
|
| 573 |
},
|
| 574 |
{
|
| 575 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 576 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 577 |
"missing_required": [],
|
| 578 |
"run_dir": "runs/ctt_base_context_obs_learned_dominance_train_to_test",
|
| 579 |
"status": "pass"
|
| 580 |
},
|
| 581 |
{
|
| 582 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 583 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 584 |
"missing_required": [],
|
| 585 |
"run_dir": "runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_train_to_test",
|
| 586 |
"status": "pass"
|
| 587 |
},
|
| 588 |
{
|
| 589 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 590 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 591 |
"missing_required": [],
|
| 592 |
"run_dir": "runs/ctt_base_context_obs_test_envclip_k16_rollout_comparison",
|
| 593 |
"status": "pass"
|
| 594 |
},
|
| 595 |
{
|
| 596 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 597 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 598 |
"missing_required": [],
|
| 599 |
"run_dir": "runs/ctt_base_context_obs_test_envclip_rollout_comparison",
|
| 600 |
"status": "pass"
|
| 601 |
},
|
| 602 |
{
|
| 603 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 604 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 605 |
"missing_required": [],
|
| 606 |
"run_dir": "runs/ctt_base_context_obs_test_noclip_rollout_comparison",
|
| 607 |
"status": "pass"
|
| 608 |
},
|
| 609 |
{
|
| 610 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 611 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 612 |
"missing_required": [],
|
| 613 |
"run_dir": "runs/ctt_base_context_obs_test_perdim_trainmax_rollout_comparison",
|
| 614 |
"status": "pass"
|
| 615 |
},
|
| 616 |
{
|
| 617 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 618 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 619 |
"missing_required": [],
|
| 620 |
"run_dir": "runs/ctt_base_context_obs_test_rollout_comparison",
|
| 621 |
"status": "pass"
|
| 622 |
},
|
| 623 |
{
|
| 624 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 625 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 626 |
"missing_required": [],
|
| 627 |
"run_dir": "runs/ctt_base_context_obs_test_scaled0215_rollout_comparison",
|
| 628 |
"status": "pass"
|
| 629 |
},
|
| 630 |
{
|
| 631 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 632 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 633 |
"missing_required": [],
|
| 634 |
"run_dir": "runs/ctt_base_context_obs_test_tanh_rollout_comparison",
|
| 635 |
"status": "pass"
|
| 636 |
},
|
| 637 |
{
|
| 638 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 639 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 640 |
"missing_required": [],
|
| 641 |
"run_dir": "runs/ctt_base_context_obs_val_envclip_rollout_comparison",
|
| 642 |
"status": "pass"
|
| 643 |
},
|
| 644 |
{
|
| 645 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 646 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 647 |
"missing_required": [],
|
| 648 |
"run_dir": "runs/ctt_base_context_obs_val_noclip_rollout_comparison",
|
| 649 |
"status": "pass"
|
| 650 |
},
|
| 651 |
{
|
| 652 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 653 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 654 |
"missing_required": [],
|
| 655 |
"run_dir": "runs/ctt_base_context_obs_val_perdim_trainmax_rollout_comparison",
|
| 656 |
"status": "pass"
|
| 657 |
},
|
| 658 |
{
|
| 659 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 660 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 661 |
"missing_required": [],
|
| 662 |
"run_dir": "runs/ctt_base_context_obs_val_rollout_comparison",
|
| 663 |
"status": "pass"
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 667 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 668 |
"missing_required": [],
|
| 669 |
"run_dir": "runs/ctt_base_context_obs_val_scaled0215_rollout_comparison",
|
| 670 |
"status": "pass"
|
| 671 |
},
|
| 672 |
{
|
| 673 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 674 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 675 |
"missing_required": [],
|
| 676 |
"run_dir": "runs/ctt_base_context_obs_val_tanh_rollout_comparison",
|
| 677 |
"status": "pass"
|
| 678 |
},
|
| 679 |
{
|
| 680 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 681 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 682 |
"missing_required": [],
|
| 683 |
"run_dir": "runs/ctt_dominance_val_to_test",
|
| 684 |
"status": "pass"
|
| 685 |
},
|
| 686 |
{
|
| 687 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 688 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 689 |
"missing_required": [],
|
| 690 |
"run_dir": "runs/ctt_learned_dominance_val_to_test",
|
| 691 |
"status": "pass"
|
| 692 |
},
|
| 693 |
{
|
| 694 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 695 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 696 |
"missing_required": [],
|
| 697 |
"run_dir": "runs/ctt_outcome_acceptance_gate",
|
| 698 |
"status": "pass"
|
| 699 |
},
|
| 700 |
{
|
| 701 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 702 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 703 |
"missing_required": [],
|
| 704 |
"run_dir": "runs/ctt_residual_smoke_proxy",
|
| 705 |
"status": "pass"
|
| 706 |
},
|
| 707 |
{
|
| 708 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 709 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 710 |
"missing_required": [],
|
| 711 |
"run_dir": "runs/ctt_selector_diagnostic_sweep",
|
| 712 |
"status": "pass"
|
| 713 |
},
|
| 714 |
{
|
| 715 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 716 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 717 |
"missing_required": [],
|
| 718 |
"run_dir": "runs/ctt_test_rollout_comparison",
|
| 719 |
"status": "pass"
|
| 720 |
},
|
| 721 |
{
|
| 722 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 723 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 724 |
"missing_required": [],
|
| 725 |
"run_dir": "runs/ctt_val_proxy_comparison",
|
| 726 |
"status": "pass"
|
| 727 |
},
|
| 728 |
{
|
| 729 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 730 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 731 |
"missing_required": [],
|
| 732 |
"run_dir": "runs/ctt_val_rollout_comparison",
|
| 733 |
"status": "pass"
|
| 734 |
},
|
| 735 |
{
|
| 736 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 737 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 738 |
"missing_required": [],
|
| 739 |
"run_dir": "runs/data_accounting",
|
| 740 |
"status": "pass"
|
| 741 |
},
|
| 742 |
{
|
| 743 |
+
"markdown_report_policy": "consolidated_readme_only",
|
| 744 |
+
"missing_advisor_contract": [],
|
|
|
|
|
|
|
| 745 |
"missing_required": [],
|
| 746 |
"run_dir": "runs/paper_ctt_audit",
|
| 747 |
"status": "pass"
|
|
|
|
| 753 |
"num_forbidden_matches": 0,
|
| 754 |
"num_paper_inputs": 39,
|
| 755 |
"num_run_dirs_in_paper": 34,
|
| 756 |
+
"num_unexpected_markdown": 0,
|
| 757 |
+
"num_warnings": 0,
|
| 758 |
"status": "pass"
|
| 759 |
}
|
| 760 |
}
|
workspace/runs/paper_ctt_audit/table.tex
CHANGED
|
@@ -7,6 +7,7 @@ Forbidden language matches & 0 & pass \\
|
|
| 7 |
Paper inputs & 39 & pass \\
|
| 8 |
Run dirs in paper & 34 & pass \\
|
| 9 |
Implementation paths & 21 & pass \\
|
| 10 |
-
|
|
|
|
| 11 |
\bottomrule
|
| 12 |
\end{tabular}
|
|
|
|
| 7 |
Paper inputs & 39 & pass \\
|
| 8 |
Run dirs in paper & 34 & pass \\
|
| 9 |
Implementation paths & 21 & pass \\
|
| 10 |
+
Unexpected Markdown files & 0 & pass \\
|
| 11 |
+
Advisor-contract warnings & 0 & pass \\
|
| 12 |
\bottomrule
|
| 13 |
\end{tabular}
|