You are working on a research idea from the Modal Research Exchange: LoRA-SFT PubMedQA grader vs untuned Qwen3.5-4B judge Qwen3.5-4B is LoRA-tuned to label PubMedQA candidate answers CORRECT or INCORRECT; we compare its grading accuracy on 2000 expert-labeled items with the untuned base. Goal: reproduce this on Spindle, Modal's Tinker-compatible training service, using the stock tinker SDK or tinker-cookbook pointed at TINKER_BASE_URL. Report real metrics only. If it cannot run on Spindle, say why. Selected experiment version: exp_8088f9d3ee The saved experiment spec below defines the hypothesis, methods and success criterion. Launch mode: ordinary Purpose: Execute the selected saved experiment version. Source: https://modal.enterprise.slack.com/archives/C0BMATL1S4F/p1793036785839779 Triage: LoRA SFT of a served Qwen3.5-4B on public PubMedQA verdict data, run as a short tinker SDK loop with stock cross-entropy, then logprob-based grading eval of the trained and base models. Experiment spec: { "title": "LoRA-SFT PubMedQA grader vs untuned Qwen3.5-4B judge", "hypothesis": "LoRA SFT on 4,800 PubMedQA-artificial grading items raises Qwen3.5-4B grading accuracy on balanced expert-labeled PubMedQA grading items by more than 3 points over the untuned base model under the same prompt and scoring, with the lower confidence bound above that margin.", "method": "Grading items are built deterministically from PubMedQA, with no model-generated data. Each item is (question, abstract contexts, candidate decision in {yes, no, maybe}) with target CORRECT if the candidate equals final_decision, else INCORRECT. Each question gets one correct candidate and one wrong candidate, drawn with seed 0 from the remaining options, so the classes are 50/50 by construction. Training data is 2,400 questions from pqa_artificial (whose labels are auto-derived yes/no), giving 4,800 items. The eval set is all 1,000 expert-labeled pqa_labeled questions, giving 2,000 items. pqa_artificial and pqa_labeled are disjoint by PMID, and this is checked. The treatment is LoRA rank 32 on Qwen/Qwen3.5-4B, trained with a tinker SDK forward_backward + optim_step loop using the stock cross_entropy loss. Loss weight sits only on the verdict tokens. AdamW at lr 1e-4, batch 32, 150 steps (about 1 epoch). The baseline is the untuned Qwen3.5-4B with the identical renderer and prompt. Both are scored by logprob: the predicted verdict is whichever of the 'CORRECT' and 'INCORRECT' completions has the higher summed logprob, computed via forward/compute_logprobs, so there is no sampling noise and no parse failures. The majority-class rate (50%) is reported, along with accuracy on the subsets where the gold label is 'maybe'. Nothing is custom server-side and there is no Spindle fork. correctness_preflight: {\"required\": false, \"reason\": \"stock tinker cross_entropy loss and AdamW; no custom loss or optimizer implementation\"}. Heidi's DPO, batch-size and filtering claims are out of scope for this first node.", "base_model": "Qwen/Qwen3.5-4B", "lora_rank": 32, "training_type": "sft", "dataset": { "name": "PubMedQA (pqa_artificial train, pqa_labeled eval)", "hf_path": "qiaojin/PubMedQA", "split": "pqa_artificial:train (2400 questions -> 4800 grading items); eval pqa_labeled:train (1000 questions -> 2000 items)", "n_examples": 4800 }, "optimizer": { "name": "adam", "lr": 0.0001 }, "steps": 150, "batch_size": 32, "max_seq_len": 1024, "eval": { "benchmark": "PubMedQA pqa_labeled balanced grading set (1 correct + 1 incorrect candidate per question)", "metric": "grading accuracy (argmax logprob of CORRECT vs INCORRECT vs gold verdict)", "n_examples": 2000, "aggregation": null }, "baseline": "Untuned Qwen/Qwen3.5-4B with the same prompt, renderer, eval items and logprob scoring.", "primary_endpoint": "pubmedqa_labeled_grading_accuracy", "arms": [ { "name": "base_untuned", "trained": false, "seed": 0 }, { "name": "lora_sft_grader", "trained": true, "seed": 0, "lr": 0.0001, "steps": 150 } ], "feasibility_required": true, "experiment_features": { "custom_loss": false, "custom_optimizer": false, "paired_comparison": true, "paired_training_arms": false, "checkpoint_restore": false, "warmup_adaptation": false, "generated_training_data": false, "learned_generator": false, "heldout_loss": false, "adaptive_selection": false }, "activation_gate": { "applicable": true, "reason": "Several things must hold before the comparison means anything. The executed model and arms must match the spec. The eval must be balanced and disjoint from training. SFT must actually move the verdict-token loss. The base judge must not be degenerate: if it always answers one class, its 50% is trivial and has to be flagged.", "checks": [ { "metric": "executed_base_model", "measures": "model name reported by the created training/sampling client for both arms", "one_of": [ "Qwen/Qwen3.5-4B" ] }, { "metric": "eval_correct_label_fraction", "measures": "fraction of the 2000 eval items whose gold verdict is CORRECT", "min": 0.49, "max": 0.51 }, { "metric": "train_eval_pmid_overlap", "measures": "count of eval PMIDs present in the training items", "min": 0, "max": 0 }, { "metric": "verdict_token_loss_drop_pilot", "measures": "relative drop in mean verdict-token train NLL from step 0 to step 20 of the treatment pilot", "min": 0.1 }, { "metric": "base_predicted_correct_fraction", "measures": "fraction of the first 200 eval items the base model labels CORRECT", "min": 0.05, "max": 0.95 } ] }, "success_criterion": "Treatment minus baseline grading accuracy on the 2000 paired eval items exceeds 0.03, with the paired Hoeffding 95% lower bound above 0.03 (half-width about 0.06 at n=2000, so an observed gain of roughly 0.09 or more is needed). Otherwise the result is not validated, or failed if the point estimate is <= 0.", "decision_rule": { "version": 1, "estimand": "Per-item grading accuracy on balanced PubMedQA pqa_labeled grading items: LoRA-SFT Qwen3.5-4B minus untuned Qwen3.5-4B, higher is better; inference conditional on the seed-0 checkpoint", "unit": "fixed_checkpoint_items", "seeds": [ 0 ], "alpha": 0.05, "method": "paired_hoeffding", "criteria": [ { "id": "primary", "metric": "accuracy", "weights": { "treatment": 1, "baseline": -1 }, "margin": 0.03, "bounds": [ 0, 1 ] } ] }, "budget": { "gpu_hours": 1.5, "max_wall_minutes": 120 }, "generation_audit": { "required": false, "answer_comparison": "categorical_exact", "min_sample_size": 100, "max_label_errors": 0, "max_eval_overlaps": 0 }, "command": "python grader_sft.py # tinker SDK; nothing custom except dataset construction and logprob eval\nimport os, random, tinker; from datasets import load_dataset\nfrom tinker_cookbook import renderers; from tinker_cookbook.tokenizer_utils import get_tokenizer\nM='Qwen/Qwen3.5-4B'; svc=tinker.ServiceClient(base_url=os.environ['TINKER_BASE_URL'])\ntok=get_tokenizer(M); r=renderers.get_renderer('qwen3', tok)\ndef items(ds, n, rng):\n out=[]\n for ex in list(ds)[:n]:\n g=ex['final_decision']; w=rng.choice([o for o in ['yes','no','maybe'] if o!=g])\n for c,lab in [(g,'CORRECT'),(w,'INCORRECT')]:\n p=f\"Context: {' '.join(ex['context']['contexts'])}\\nQuestion: {ex['question']}\\nCandidate answer: {c}\\nIs the candidate answer correct? Reply CORRECT or INCORRECT.\"\n out.append((ex['pubid'],p,lab))\n return out\nrng=random.Random(0)\ntrain=items(load_dataset('qiaojin/PubMedQA','pqa_artificial',split='train').shuffle(seed=0),2400,rng)\nev=items(load_dataset('qiaojin/PubMedQA','pqa_labeled',split='train'),1000,rng)\nassert not {a for a,_,_ in train}&{a for a,_,_ in ev}\nrandom.Random(0).shuffle(train)\ndef datum(p,lab): # weights only on verdict tokens\n return renderers.build_supervised_example_datum(r,[{'role':'user','content':p},{'role':'assistant','content':lab}],max_length=1024) # last-assistant-only weights\ntc=svc.create_lora_training_client(base_model=M, rank=32)\nfor s in range(150):\n b=[datum(p,l) for _,p,l in train[s*32:(s+1)*32]]\n tc.forward_backward(b,'cross_entropy').result(); tc.optim_step(tinker.AdamParams(learning_rate=1e-4)).result()\nsc_t=tc.save_weights_and_get_sampling_client('pubmedqa-grader'); sc_b=svc.create_sampling_client(base_model=M)\ndef verdict_lp(sc,p,lab): # summed logprob of the verdict tokens\n pre=r.build_generation_prompt([{'role':'user','content':p}]); comp=tok.encode(lab,add_special_tokens=False)\n mi=tinker.ModelInput.from_ints(pre.to_ints()+comp); lp=sc.compute_logprobs(mi).result(); return sum(lp[-len(comp):])\nfor name,sc in [('baseline',sc_b),('treatment',sc_t)]:\n acc=[int((verdict_lp(sc,p,'CORRECT')>verdict_lp(sc,p,'INCORRECT'))==(l=='CORRECT')) for _,p,l in ev]\n print(name, sum(acc)/len(acc)) # save per-item 0/1 for the paired Hoeffding rule", "feasibility": { "config": { "base_model": "Qwen/Qwen3.5-4B", "arms": [ "base_untuned", "lora_sft_grader" ], "steps": 20, "batch_size": 32, "max_seq_len": 1024, "n_eval": 200 }, "effective_config": { "base_model": "Qwen/Qwen3.5-4B", "arms": [ "base_untuned", "lora_sft_grader" ], "steps": 150, "batch_size": 32, "max_seq_len": 1024, "n_eval": 2000 }, "primary_endpoint": "pubmedqa_labeled_grading_accuracy", "source": null, "measurements": null, "generation": null, "recovery": null }, "feasibility_check": { "status": "unknown", "problems": [ "Re-projection required: lora_rank changed or was not recorded", "Re-projection required: dataset changed or was not recorded", "Re-projection required: steps changed or was not recorded", "Re-projection required: n_examples changed or was not recorded", "Re-projection required: n_eval changed or was not recorded", "Pilot evidence source not recorded", "Representative setup timing not recorded", "Representative training timing not recorded", "Representative evaluation timing not recorded", "Positive recovery reserve not recorded" ], "wall_seconds": null, "gpu_hours": null, "known_gpu_hours": 0, "phases": {}, "generation_counts": null, "generation_applicability": { "check": "generation_audit", "status": "not_applicable", "enforce": false, "reasons": [ "spec.generation_audit opts out and no feature it covers is true" ], "features": { "generated_training_data": false } } } } How to work: - Run the experiment on Spindle with the stock tinker SDK (or tinker-cookbook) pointed at $TINKER_BASE_URL. Every request needs the headers Modal-Key: $MODAL_PROXY_TOKEN_ID and Modal-Secret: $MODAL_PROXY_TOKEN_SECRET, plus TINKER_API_KEY. These are already set as env vars in this session: call Spindle directly from here. Don't search the repo for them or wrap your client in a Modal app to get them. Never print their values. - Any Modal app you do need (a Spindle fork, a GPU eval) goes in the environment research-exchange-runs, named with run_03530094ad. Never deploy or run anything in the research-exchange environment (it is production), never mount the volume research-exchange-data, and never create Modal environments. - Keep the run small and inside the spec's budget. Real numbers only; never estimate or invent a metric. - Before a paired comparison, run the restoration preflight in the saved spec. Save initialization_provenance (version 1) with one entry per named arm: initialization (pinned base_checkpoint, measured adapter_sha256, source=server_response or local_hash, evidence_ref, before_first_update=true), restore_count, optimizer_checks, and initial_output. All arms/replays in an initialization group must load the same initial checkpoint/adapter. A matching seed, step-0 loss, or base accuracy does not establish matched initialization (LoRA B may be zero). optimizer_checks must cover creation (after_restore=0) and EVERY restore (1..restore_count), before_next_update=true, actual optimizer family and actual_config from a server_response plus evidence_ref. Compare against each arm's requested optimizer/config. Creating from saved state can silently fall back to AdamW: creating TriMuon first then loading weights is a workaround to verify, not proof. Stop on mismatch. Do not invent SDK inspection methods; if no server response exposes the active optimizer, use source=declared and actual=null: this stays unverified. On a fork, add a minimal observation of the concrete server optimizer after restoration; retain its code revision and response. Check a create-save-restore fixed-gradient update against the uninterrupted client before a sweep. initial_output records available=true, batch_sha256 (token IDs/targets/masks), output_sha256 (all full-precision logits/logprobs, not an averaged loss), evidence_ref and before_first_update=true; compare across the paired group. If capture is unavailable, record available=false with a reason. For exact replay, require it in the spec. Retain the evidence before cleanup. Publish the provenance while running; full training waits for verified checks. - Initialization proof may use measured adapter_sha256, or an immutable FULL initialization checkpoint with source=server_response, checkpoint_uri, checkpoint_immutable=true, checkpoint_scope=full_initialization, loaded_checkpoint_uri (from the actual successful load response), load_succeeded=true, evidence_ref and before_first_update=true. Keep base_checkpoint in both proof types. A declared URI or base-model-only load does not prove matching adapters. Compare all available hashes and URI identities; mixed proofs need a shared identity. A lone resumed training arm may form one group only when checkpoint_restore=true, paired_training_arms=false, and it records at least one actual restore. Exclude frozen, untrained baselines from optimizer restoration groups. - If the spec's base_model is not served on Spindle, use the closest served model of the same family (e.g. Qwen/Qwen3.5-2B for a smaller Qwen3.5) and say so in the summary; a missing model is not a reason to stop. - If the shared Spindle lacks something the experiment needs (an optimizer, loss, or feature), you may fork Spindle (https://github.com/modal-projects/spindle), add it, and deploy your fork following its README as a throwaway Modal app named spindle-fork-run_03530094ad in the research-exchange-runs environment. Call your fork with Modal-Key: $RUNS_PROXY_TOKEN_ID and Modal-Secret: $RUNS_PROXY_TOKEN_SECRET (the shared Spindle token gets 401 on research-exchange-runs); they're also set as env vars here. Run every arm on the fork so the comparison is fair. Never push to, redeploy, reconfigure, or stop the shared Spindle deployment, and never open PRs or issues on the Spindle repo; if the change looks worth upstreaming, propose it in your report. Include the fork's diff and app name in your report, and when you are done stop spindle-fork-run_03530094ad and every app your fork deployed (Spindle deploys separate trainer, lora and inference apps; give them names containing run_03530094ad), with `modal app stop -e research-exchange-runs `, then check `modal app list -e research-exchange-runs` shows none of yours still deployed. Stop nothing else. - Spindle errors like "trainer capacity exhausted" or 429/503 are usually temporary because other runs share it: retry with backoff (e.g. 1, 2, 4 minutes) and update your structured output while you wait. If no comparison training step has run yet and it is still refused after about 10 minutes, don't keep waiting: release the Spindle clients this session created where the SDK lets you (yours only), then finish with "status": "failed", "verdict": "inconclusive", "outcome_reason": "incomplete_execution" and "capacity_block". The exchange may re-queue the run and start a fresh session later, within the spec's wall-time budget. If comparison steps already ran, keep retrying for up to 30 minutes so finished work isn't lost, then stop and report "capacity_block" with the real step count. - Release probe and setup clients you no longer need before starting the paired arms. - Clean up after yourself before you finish: stop every Modal app, sandbox, or other resource you started for this run (by exact name), and nothing else. Use the structured output tool to keep your output updated with exactly this JSON shape, and set "status" to "succeeded" or "failed" when you are done: {"status": "running" | "succeeded" | "failed", "summary": "<= 2 plain sentences: what ran and what it showed", "metrics": {"": , ..., "arms": {"": {"": }}}, "completed_arms": [""], "verdict": "supported" | "refuted" | "inconclusive", "outcome_reason": "supported" | "refuted" | "tie" | "mixed_criteria" | "insufficient_evidence" | "incomplete_execution", "capacity_block": {"error": "", "comparison_steps_completed": , "released_clients": true | false}} Include "capacity_block" only when Spindle capacity stopped the run. A finished result must include a valid "verdict". Finishing execution alone does not support the hypothesis. Update it while you work, not only at the end: post the base eval as soon as you have it, and each arm's metrics under "arms" with the arm added to "completed_arms" as soon as that arm finishes. Keep every number you posted earlier in later updates. The research exchange saves each update, so if the session ends early the finished arms still count as partial results. Leave "verdict" out until you are done. Set "verdict" when you are done: "supported" or "refuted" only if every arm ran and the comparison judged the success criterion; "inconclusive" for a tie, mixed criteria, insufficient evidence, or incomplete comparison. Use "succeeded" when execution completed, including ties and mixed scientific outcomes; "failed" when execution stopped unsuccessfully. Optional "outcome_reason" describes the science separately from execution status: "supported"/"refuted" agree with the corresponding verdict; the other reasons require "inconclusive". "tie" means the completed comparison falls in the spec's tie band; "mixed_criteria" means some success criteria pass and others fail; "insufficient_evidence" means the evidence cannot settle the hypothesis (for example, uncertainty is too large); "incomplete_execution" means required execution or evaluation did not finish. Report the reason only with a final result. Never infer a tie or support just because execution succeeded. Changes from the spec: the output also has "deviations": [{"field": "model" | "objective" | "effective_batch" | "steps" | "dataset" | "evaluator" | "endpoint", "original": "", "effective": "", "reason": ""}], "original_hypothesis_tested": true | false, "tested_instead": "" Use [] when you run the spec as written. effective_batch is sequences per optimizer step after accumulation. Before you train with any change (a substituted model, a different loss or RL objective, a smaller batch, another dataset or split, a different grader or eval set, a different decision metric or step), add it to "deviations" with status "running" first, then continue. A change you only report at the end is flagged as unrecorded. If the change means the run no longer tests the spec's hypothesis, set "original_hypothesis_tested": false and fill "tested_instead". Changing the objective (e.g. GRPO to REINFORCE) or the endpoint always counts as not testing it: the exchange then records the hypothesis as inconclusive and keeps your verdict for the changed experiment. Correctness preflight is required before ANY full sweep using a new/custom/forked loss or optimizer, even if discovered after launch. First reproduce the stock baseline THROUGH the new path, with treatment disabled; then compare the enabled implementation to the pinned treatment reference. Use the same fixed inputs, weights, optimizer state, masks, normalization, precision and seeds. Loss paths need both loss AND full gradient errors; optimizer paths need update errors. Similar gradient norms alone do not prove parity. Check packed versus unpacked layouts on meaningful fixed inputs, including stale inputs when relevant. Reset state independently for each LR probe, measure update norms (per factor when applicable), and verify the prespecified LR scaling. STOP before full training/sweeps if any check is missing or fails. If the spec has no accepted preflight plan for a discovered custom path, report it as required/unverified and request a spec revision; do not pick a loose tolerance after observing errors. Activation and checkpoint provenance are separate gates. Add correctness_preflight alongside status/summary/metrics/verdict in structured output (or RESULT): {"required": true, "paths": [{"id": "", "fixed_input": {"sha256": "<64 hex>", "description": ""}, "baseline_revision": "", "reference_revision": "", "implementation_revision": "", "precision": "", "normalization": "", "errors": {"": {"max_abs_error": , "reference_max_abs": , "relative_l2_error": , "cosine_similarity": }}, "lr_scaling": [{"learning_rate": , "update_norm": }, ...]}]}. For stock-only execution use {"required": false, "paths": []}. Keep probe scripts and inputs as report artifacts. max_abs_error is max(abs(actual-reference)); relative_l2_error is norm(actual-reference)/norm(reference). Acceptance requires max_abs_error <= atol + rtol*reference_max_abs and any prespecified min_cosine. LR scaling checks the relative change of update_norm/LR against the first probe. These are measured errors, not self-declared pass flags. Small standard-library helpers parity_errors and lr_scaling_error live in research_exchange.correctness; `python -m research_exchange.correctness spec.json preflight.json` validates evidence and exits nonzero unless passed/not_applicable. Gate full-sweep launch on that exit code when available. The Exchange validates/persists reported checks and withholds definitive judgments when required checks fail or are missing. It cannot prevent autonomous training calls or attest reported remote measurements. Treatment activation gate: when the spec's "activation_gate" is applicable, first run a short pilot of the treatment arm in the exact regime of the full run (same model, loss path, batch, updates per batch, lag, dtype). Measure every check's metric and record it in "activation_calibration": {"values": {"": }, "note": ""}, before any full training. Keep the spec's accepted ranges fixed. If a check is missing or outside its range, do not start full training; report the evidence and an inconclusive verdict. The exchange validates reported calibration; it cannot prevent autonomous training calls. Freeze the evaluator before scoring any arm. Report an evaluation object alongside metrics: { "version": 1, "evaluators": { "": { "code_sha256": "", "prompt_template": "", "decoding": {"temperature": 0, "max_tokens": 512, "stop": []}, "parser": "", "items": {"ids": [""]} }}, "scores": [{"arm": "baseline", "metric": "accuracy", "value": 0.8, "evaluator_id": "", "seed": 0, "predictions_ref": "predictions.jsonl"}], "comparisons": [{"metric": "accuracy", "arms": ["baseline", "treatment"]}] } evaluator_id is hashlib.sha256(json.dumps(provenance, sort_keys=True, separators=(",", ":"), ensure_ascii=True, allow_nan=False).encode()).hexdigest(). Include seed per score when applicable. For large item lists use items {"manifest_ref": "items.jsonl", "manifest_sha256": ""} instead of ids; references are evidence file names. Include evaluator_id, metric, arm and item_id in each prediction record. Keep the scored model/checkpoint separate from evaluator identity. Any grader, parser, prompt, decoding or item change requires re-evaluating EVERY compared arm/seed and the base model with the new evaluator, including already completed arms. Until then report inconclusive. Keep old scores identified with their original evaluator; never relabel them. When spec.decision_rule is present, report decision {version:1, observations:[ {item_id:"",arm:"treatment",seed:0,metric:"accuracy",value:1, evaluator_id:""}, ...]} for every arm, item and scheduled seed. For large evaluations, avoid putting all rows in structured output. Attach a UTF-8 JSONL file with those same scored rows (or a JSON array / object with observations), retain it via evidence.files as kind metrics, then report only decision {version:1, observations_file:{name:"scored-observations.jsonl",sha256:""}}. Use exactly one of observations or observations_file. The reference is a retained file name and hash, never a path or URL. The server reads only this run's verified immutable evidence copy, capped at 10 MiB and 100000 observations; missing/corrupt files stay unverified. Upload a new immutable file name/hash for each update. Keep selection metadata in the decision object. No scores, item IDs, seeds or evaluator IDs are inferred. Values are finite measured outcomes in the endpoint's original units; never clip or normalize them. For bounded accuracy, include failures as zero, not just successful items. Report unrounded per-arm/seed score means so they reproduce the paired observations. Record evaluation provenance and per-arm/seed scores with explicit items.ids (hashed manifest-only item lists are not yet resolved by the decision validator). Persist the raw predictions through evidence too. The server recomputes paired effects and uncertainty; it does not trust an agent-supplied interval or parse prose. Never add a seed after seeing the gap or treat test items/repeated evals as independent training seeds. For adaptive selection, observations must use only confirmation items, and decision.selection must contain frozen_before_confirmation:true. For kind weight_edit also report budgets:{:{values_touched:N,proposals:N}} for selected and random-control arms. Report supported/refuted only when every criterion's confidence interval settles the prespecified margin; otherwise inconclusive. Retain review evidence in structured output under "evidence": {"version":1,"files":[{"name":"run.py","kind":"script","content":""}, {"name":"effective-config.json","kind":"effective_config","content":""}], "checkpoints":[{"arm":"baseline","step":100,"uri":"tinker://training-id/weights/checkpoint-name"}], "per_arm_metrics":{"baseline":{"accuracy":0.5}}} Include files for the executed script, effective config, code revision (kind code_revision) and any patch (kind code_patch), per-item predictions (kind predictions), and per-arm metrics. Include generated_tasks when training on generated data. Use JSONL predictions with item_id, arm, prediction and reference in each row; retain seed, checkpoint, metric and evaluator_id metadata when available. Invalid outputs must remain rows. For larger files attach them in Devin and set source_url to the HTTPS /attachments/... URL instead of content; never use a session page URL, VM path or arbitrary external URL. Optional sha256 must match the original bytes. The web server copies accepted files into this run's storage and exposes reviewer downloads. Post evidence as stages finish, before cleanup. File names are immutable: use a new name for each stage/checkpoint/update. Each file is capped at 10 MiB, with 64 files / 40 MiB total per run. Never include .env, credentials, auth headers, secret values or credential-bearing URLs. Read credentials from environment variables in scripts. Checkpoint URIs are references, not copied weights; omit credentials and signed URL query strings. Missing evidence is shown as unknown or partial, never as verified. Do not invent an artifact or checkpoint that does not exist. Feasibility is a measured projection, separate from scientific metrics and actual GPU usage. After resolving the served model, run a representative timing pilot before the full comparison. Publish feasibility in structured output before continuing; repeat it after changing model, arms, context, batch, steps, dataset size or evaluation count. Include fork/setup time, training AND held-out evaluation, generation AND filtering samples, measured yield, and a recovery reserve. Never scale timing by parameter count or assume concurrency is free. Measure the actual schedule. Preserve the primary endpoint when downsizing: drop optional secondary evals, extra seeds or LR points first, then shorten training with an explicit deviation; never replace held-out eval by train loss. If the primary comparison cannot fit, stop and report inconclusive. Use this additional structured field (null means no measurements yet): "feasibility": {"config": , "effective_config": , "primary_endpoint": , "source": , "measurements": { "setup": {"seconds": , "units": 1, "planned_units": 1, "samples": 0, "gpu_count": null, "allocation_source": null}, "training": {"seconds": , "units": , "planned_units": , "samples": , "gpu_count": null, "allocation_source": null}, "evaluation": {"seconds": , "units": , "planned_units": , "samples": , "gpu_count": null, "allocation_source": null}}, "generation": null, "recovery": {"seconds": , "gpu_count": null, "allocation_source": null}}. For generated tasks replace generation:null by {"attempted": , "accepted": , "target_accepted": , "filter_samples_per_candidate": } and add generation and filter measurements (units=candidates and filter rollouts respectively). Include an audit measurement for independent task re-solves when the shared generation_audit applicability is enforced. generated_training_data=true overrides a legacy required=false flag; unresolved new feature declarations need resolution and cannot skip generation/filter/audit sizing. Record GPU counts only from explicit allocation evidence, including all trainer/inference GPUs allocated for the timed phase; null for shared Spindle when allocation is unknown. CPU-only phases may explicitly use 0. Keep projected wall seconds, projected GPU-hours and observed usage separate. Do not invent timings or GPU-hours to fill this contract. Resolve applicability with experiment_features.check_applicability(spec,"generation_audit"). An explicit generated_training_data=true requires the audit. False can establish non-applicability when no explicit contract requires the check; missing feature evidence stays unknown. For training on generated tasks, complete generation_audit BEFORE training. Running generated Python only checks execution; it does not verify labels. Save all candidates as JSONL in evidence.files kind generated_tasks: item_id (unique string), prompt, answer, disposition (accepted/rejected/execution_error). Retain generated code and execution errors when available. Save the FULL frozen evaluation set as JSONL (item_id,prompt), kind generated_tasks; this is for overlap checking, never training. Freeze both files before sampling. Report generation_audit with version=1, stage="before_training", dataset_file, evaluation_file, audit_file (a new immutable .json name), sample_seed (integer), counts={generated,accepted,rejected,execution_errors}, samples=[{item_id,independent_answer,resolver_id,method:"independent_resolve",reasoning,blind_to_label:true}], label_error_count, overlap_count. Select min(accepted_count, spec.generation_audit.min_sample_size or 100) accepted tasks deterministically with research_exchange.generation_audit.select_sample(tasks,size,seed), which sorts by SHA256 of the JSON [seed,item_id]. Re-solve those problems from their TEXT without seeing the stored answer or generated code (human or a separate solver invocation); record solver identity and worked solution. Never reuse the generator's Python as independent evidence. Report observed disagreements and the sample denominator; answer agreement with a declared solution does not establish semantic truth. New specs must explicitly set generation_audit.answer_comparison to numeric_exact for strict scalar numbers/fractions (zero tolerance), or categorical_exact for nonempty string labels. Categorical comparison is exact and case-sensitive, with no whitespace normalization or synonym mapping. Choose from the label contract, never the experiment/dataset name; missing or unsupported strategies remain unverified. Use answer_agreement(label, independent_answer, strategy) with that declared strategy, and evaluation_overlap for NFKC/casefold/whitespace-normalized exact prompt overlap against the full held-out set. This does not detect paraphrases or semantic leakage. Report duplicate and overlap counts, and persist the dataset and audit manifest through evidence before cleanup. Failed/missing audits block a definitive scientific verdict. Call generation_audit.validate(report, spec.generation_audit, tasks=tasks, evaluation=evaluation, require_comparison=True) and require status="passed" before the first optimizer update. Do not invent passing re-solve evidence to get past this check. If any sampled label is wrong or overlaps evaluation, repair/reject affected tasks and freeze NEW dataset and audit file versions, then repeat the audit before training. Do not train on known bad labels as-is.