{
  "schemaVersion": 2,
  "date": "2026.08.27",
  "publishedAt": "2026-08-27T18:30:39-07:00",
  "timeZone": "America/Los_Angeles",
  "title": "Phase 3C finds fourteen actionable local experiments",
  "publicationStatus": "Actionable discovery works; Phase 3A now has sufficient planned inputs but remains stopped",
  "executiveSummary": [
    "Qualified experimental feasibility and actionable discovery only. Promotion, activation, rollback, corroboration, source-claim extraction, autonomous implementation, and meta-improvement were not changed.",
    "Reclassified all twenty-five previously validated Phase 3B claims using explicit relevance, asset, compute, and feasibility fields. Twenty-four remain not Hiro-relevant and one cross-domain pre-commitment gating mechanism has a defensible light local experiment path.",
    "Defined a conservative research-asset policy with bounded download, storage, CPU, and GPU tiers; approved public source classes; provenance and license requirements; isolation; supply-chain precautions; and explicit denial of production-write, candidate, and promotion authority.",
    "Added an experiment-feasibility planner after claim validation. It produces exact asset inventories, local hypotheses, observables, falsification criteria, resource budgets, isolation requirements, relevance classifications, feasibility tiers, an independent semantic audit, and deterministic policy results.",
    "Added bounded actionable discovery ranking for empirical, Hiro-relevant, and reproducible research. Every considered source receives a recorded retention or exclusion decision, and the retained corpus is frozen before claim extraction.",
    "The new campaign considered seventy-one sources, retained twenty, extracted and validated thirty-four claims, classified sixteen as directly relevant or explicitly transferable, and produced fourteen valid LOCAL_READY experiment plans.",
    "The first demonstrated feasibility divergence was deterministic rather than semantic: LOCAL_READY correctly prohibited downloads but also prohibited generated scratch output. The minimal correction preserved zero downloads while allowing at most one GiB of disposable scratch storage.",
    "The final disposition is ACTIONABLE DISCOVERY WORKS. Phase 3A now has more than the requested five legitimate experiment plans, but no asset was acquired and no reproduction experiment was executed or resumed."
  ],
  "workstreams": [
    {
      "title": "Existing Phase 3B claim feasibility",
      "status": "Completed",
      "details": [
        "All twenty-five frozen validated claims received exact required-asset records, available and missing inventories, resource estimates, relevance decisions, feasibility tiers, local hypotheses where defensible, observables, falsification criteria, and independent semantic audits.",
        "Twenty-four claims terminate as NOT_HIRO_RELEVANT. Their missing assets remain explicit even though relevance overrides an apparent cost tier.",
        "One driving-system claim transfers defensibly to Hiro: a gate that acts before commitment can be tested as an uncertainty-abstention control in routing. Its bounded plan requires only a small locally constructed adapter and no external download.",
        "No other old claim could responsibly move to a light or moderate acquisition tier from the retained evidence. Common blockers were unavailable paper-specific implementations, benchmarks, models, simulators, annotations, and proprietary agent scaffolds."
      ]
    },
    {
      "title": "Bounded research-asset policy",
      "status": "Implemented",
      "details": [
        "Automatic acquisition stops at ACQUIRABLE_LIGHT: at most 250 MiB download, one GiB storage, sixty CPU minutes, and fifteen GPU minutes.",
        "LOCAL_READY permits no missing-asset download and at most one GiB of disposable generated fixtures and results, thirty CPU minutes, and fifteen GPU minutes.",
        "Moderate and heavy tiers are classified but cannot be acquired automatically. Credentials and paid APIs require explicit authorization and are unavailable to autonomous mode.",
        "Approved source classes are HTTPS GitHub, Hugging Face, Zenodo, PyPI, and arXiv locations. Licenses, immutable provenance, and SHA-256 receipts are mandatory.",
        "Downloaded content remains untrusted input and may execute only in a disposable, network-disabled environment with read-only source, writable scratch, resource limits, dependency locking, archive and malware checks, and setup hooks disabled until review.",
        "Research assets have no authority to modify production, construct or approve a candidate, request promotion, or change the governor."
      ]
    },
    {
      "title": "Experiment-feasibility assessment",
      "status": "Implemented",
      "details": [
        "Added relevance states HIRO_RELEVANT, TRANSFERABLE_WITH_EXPLICIT_HYPOTHESIS, and NOT_HIRO_RELEVANT.",
        "Added feasibility tiers LOCAL_READY, ACQUIRABLE_LIGHT, ACQUIRABLE_MODERATE, ACQUIRABLE_HEAVY, UNAVAILABLE, and NOT_HIRO_RELEVANT.",
        "The planner preserves the exact validated claim and may transfer only a concrete shared mechanism with an explicit Hiro-local hypothesis; generic topical similarity is insufficient.",
        "Each plan records every required asset and its availability, URL, license, byte estimates, requirement status, notes, total resource estimates, isolation controls, effort, observable, falsification criterion, and tier reason.",
        "A separate model operation audits source preservation, transfer defensibility, missing-asset completeness, source support, resource conservatism, policy coherence, and meaningful falsification. Deterministic validation independently enforces schemas, approved hosts, resource limits, and inventory consistency.",
        "Immutable reports and companion hashes preserve both model judgments and deterministic results. A revalidation operation can apply a corrected deterministic policy without rerunning or rewriting either frozen model judgment."
      ]
    },
    {
      "title": "Actionable discovery",
      "status": "Implemented",
      "details": [
        "The new bounded strategy searches empirical work in tool use and selection, retrieval and memory, self-correction and verification, and agent planning and evaluation.",
        "Ranking records distinct Hiro-relevance, empirical-claim, numeric-result, and asset-or-reproduction signals. It prefers actionability but does not select for a predetermined conclusion or claimed improvement.",
        "Seventy-one sources were considered: fifty-three arXiv records, fifteen sanitized Moltbook records, and three GitHub records. Twenty were retained and frozen before claim extraction: fifteen arXiv and five Moltbook.",
        "Fifty-one sources were explicitly excluded: one overall capacity limit, nineteen without asset or reproduction signal, eleven without an empirical-claim signal, one without a Hiro-relevance signal, seventeen per-source capacity limits, and two prompt-injection risks.",
        "The unchanged Phase 3B claim extractor then produced thirty-four claims from the frozen twenty-source corpus. All thirty-four passed claim validation; there were no extraction failures or unavailable-source outcomes."
      ]
    },
    {
      "title": "Observed first divergence and minimal repair",
      "status": "Completed",
      "details": [
        "The first new feasibility run classified sixteen plans LOCAL_READY, and the independent semantic auditor approved their resource bounds, but deterministic validation rejected fourteen because any nonzero generated storage exceeded a zero-byte LOCAL_READY limit.",
        "That limit confused asset acquisition with scratch output. A local experiment can require no download while still generating kilobytes of fixtures and measurements.",
        "The only policy correction was to allow up to one GiB of bounded disposable scratch storage for LOCAL_READY while retaining the zero-download rule and all isolation controls.",
        "Revalidation reused the same frozen planner and auditor outputs. It produced fourteen valid LOCAL_READY experiment plans; no semantic threshold, source claim, discovery result, or model output was changed.",
        "Two assessments remain invalid: one optional PeakBench asset was omitted from its exact missing-assets inventory, and one scientifically irrelevant materials claim had internally inconsistent semantic fields. Neither represents a silently lost valid experiment."
      ]
    },
    {
      "title": "Final qualification funnel",
      "status": "Actionable discovery works",
      "details": [
        "SOURCES_CONSIDERED 71; SOURCES_RETAINED 20; CLAIMS_EXTRACTED 34; CLAIMS_VALIDATED 34.",
        "HIRO_RELEVANT or explicitly transferable 16; NOT_HIRO_RELEVANT 18.",
        "LOCAL_READY 16; ACQUIRABLE_LIGHT 0; ACQUIRABLE_MODERATE 0; ACQUIRABLE_HEAVY 0; UNAVAILABLE 0.",
        "EXPERIMENT_PLANS_VALID 14. The plans cover planner/executor handoffs, graph-based failure attribution, resource-aware scheduling, multi-step planning degradation, failure attribution, verification rules, misleading-premise handling, answer selection, judge reliability, and repository-context test generation.",
        "No asset acquisition, experiment execution, reproduction, candidate construction, governor decision, promotion request, activation, or rollback occurred."
      ]
    }
  ],
  "decisions": [
    "Keep promotion, corroboration, claim extraction, and the Phase 2 actuator unchanged because no observed Phase 3C boundary implicated them.",
    "Separate Hiro relevance from exact-paper reproduction so a cross-domain mechanism is eligible only when it yields an explicit local hypothesis and falsifier.",
    "Allow bounded autonomous acquisition only through ACQUIRABLE_LIGHT and deny downloaded material any production authority.",
    "Freeze ranked source selection before extraction so later claim outcomes cannot influence which campaign sources count.",
    "Record every discovery exclusion and every invalid feasibility assessment rather than silently dropping material.",
    "Correct the demonstrated scratch-storage policy defect without weakening the zero-download meaning of LOCAL_READY.",
    "Stop after planning. Do not automatically acquire assets, reproduce claims, build candidates, or resume Phase 3A."
  ],
  "validation": [
    {
      "check": "Frozen actionable discovery corpus",
      "status": "passed",
      "result": "71 sources considered, 20 retained, and 51 explicitly excluded. The frozen corpus SHA-256 is 23006b78f3a86024bf93cbb43b7e22f1dfa968439ef27540788584484f64b19f."
    },
    {
      "check": "Unchanged source-claim qualification",
      "status": "passed",
      "result": "20 frozen source records produced 34 extracted and 34 validated claims with zero extraction failures. The immutable report SHA-256 is 7d45b4a5bed2b4bc4964df5054e88913b434726f4fc1fdccf0aedadeb2747915."
    },
    {
      "check": "New experiment-feasibility qualification",
      "status": "passed",
      "result": "34 claims were assessed; 16 were LOCAL_READY, 18 NOT_HIRO_RELEVANT, and 14 produced complete valid light-or-local plans. The corrected deterministic revalidation SHA-256 is cf574283c1f6b1144ff3bc43315815b6eda3abd6d8fc4fd2181ca6ad159db093."
    },
    {
      "check": "Existing twenty-five-claim reclassification",
      "status": "passed",
      "result": "All 25 prior claims received explicit asset and feasibility assessments: 24 NOT_HIRO_RELEVANT and one ACQUIRABLE_LIGHT valid plan. The report SHA-256 is fd9bb6a29d7552414555b25d51a531f2e147ce57545ea9cd871d63aa9085e1ee."
    },
    {
      "check": "Focused discovery, feasibility, and source-claim tests",
      "status": "passed",
      "result": "12 tests passed in 0.54 seconds. One non-failing warning concerned the inaccessible pytest cache directory."
    },
    {
      "check": "Full Hiro repository regression suite",
      "status": "passed",
      "result": "815 tests passed in 443.66 seconds. Six non-failing warnings concerned five existing unregistered test marks and the inaccessible pytest cache directory."
    },
    {
      "check": "Public journal tests and build",
      "status": "passed",
      "result": "npm run test:hiro passed. npm run build generated and validated 172 journal pages, compiled TypeScript, and completed the Vite production bundle. The clean checkout first required npm ci; the install reported one existing high-severity dependency advisory, which was not automatically modified because dependency maintenance was outside this session."
    }
  ],
  "currentState": [
    "Phase 3C implementation is committed at revision 46ef20aaa6f4d955b5ad6e54401a0816469d4ddb.",
    "Actionable discovery has empirically produced fourteen legitimate bounded experiment plans, exceeding the target of five.",
    "Phase 3A now has sufficient planned inputs to resume in a separate authorized task.",
    "No Phase 3A reproduction has started, and no research asset has been downloaded.",
    "Promotion, activation, rollback, corroboration, claim extraction, and meta-improvement remain unchanged."
  ],
  "limitations": [
    "Fourteen plans passed planning qualification but have not yet been executed; their hypotheses may be falsified during Phase 3A.",
    "All valid new plans are LOCAL_READY. This campaign did not empirically exercise the asset downloader or an ACQUIRABLE_LIGHT acquisition transaction.",
    "Two of thirty-four feasibility assessments remain invalid with explicit diagnostic reasons; neither is counted as an experiment plan.",
    "Model-based transfer and feasibility judgments can vary, although exact claims, frozen sources, independent auditing, deterministic policy checks, hashes, and explicit falsification criteria constrain that risk.",
    "Moltbook provides bounded excerpts and yielded no qualifying plan in this campaign; most successful inputs came from concrete arXiv abstracts."
  ],
  "nextSteps": [
    "Do not automatically resume Phase 3A. Obtain separate authorization to execute a bounded set of the fourteen frozen plans.",
    "When Phase 3A resumes, execute plans in isolated disposable environments and preserve first-divergence, exact-result, and falsification evidence.",
    "Exercise one genuinely ACQUIRABLE_LIGHT plan in a later qualification before relying on autonomous asset downloading in routine operation.",
    "Keep the twenty-source corpus and thirty-four-claim report immutable as regression evidence for actionable discovery and feasibility planning."
  ],
  "disclosureNote": "This public entry contains no credentials, private source text, private interaction content, local filesystem locations, private network addresses, or actionable unresolved security details."
}