Step 2: tool results

get_claim

{
  "include": [
    "arguments",
    "subclaims",
    "related"
  ],
  "claim_id": "a4bfe1a1-0d33-4876-b6ab-40989cb38bac"
}

{"claim":{"id":"a4bfe1a1-0d33-4876-b6ab-40989cb38bac","kind":"claim","canonical_form":"For realistic tasks, learning decompositions likely requires much less supervision than learning complex behaviors directly.","claim_type":"empirical_derived","state":"active","decomposition_status":"complete","importance":0.5,"contestation":0.45,"domains":[],"tags":[{"slug":"machine-learning","name":"Machine Learning"},{"slug":"scalable-oversight","name":"Scalable Oversight"}],"steward_state":"running","stewarded_at":"2026-11-14T02:27:04.845Z","canonical_direction_note":"The source advances the affirmative thesis that learning task decompositions is likely to be substantially cheaper in supervision than learning complex behaviors directly, including for realistic tasks.","created_at":"2026-11-11T18:55:10.202Z","updated_at":"2026-11-14T02:26:55.889Z","page_url":"https://minerval.ai/claims/a4bfe1a1-0d33-4876-b6ab-40989cb38bac"},"assessment":null,"coverage":{"examined":false,"on":[],"note":"No judgment of this node is in force. That is not a finding either way."},"quantity":null,"threshold_of":null,"question":null,"formalization":null,"formalization_pending":null,"formalization_history":[],"verification":null,"lean_checks":[],"lean_checks_total":0,"waiting_messages":[{"trigger":"structure_and_assess","from":"the system","sender_node_id":null,"sent_at":"2026-11-11T18:55:10.963Z","paid":false,"summary":"New claim onboarded. Give it the structure and assessment its importance warrants; a minor or settled claim may need no decomposition."},{"trigger":"mandate_plan","from":"a mandate's plan","sender_node_id":null,"sent_at":"2026-11-14T02:26:55.892Z","paid":true,"summary":"A funded mandate scheduled a assess pass on this claim."}],"requests":[],"requests_total":0,"subclaim_count":0,"instance_count":1,"source_map":null,"arguments":[],"subclaims":[],"subclaims_assessed":0,"related":[],"unplaced_argument_passages":[{"instance_id":"e797a766-3c17-4d8f-8abf-be8ac776cf2b","source":{"id":"8dd5f960-0544-4bf0-bda1-f37f0d70f734","url":"https://arxiv.org/pdf/1810.08575","title":"Supervising strong learners by amplifying weak experts"},"verbatim_text":"Supervised learning required tens of millions of examples in order to learn these algorithms. This would be a prohibitive cost if the examples were provided by an external expert. In contrast, Iterated Amplification required tens of thousands of examples in order to learn the much simpler decompositions","context":null,"stance":"advances","direction":"for"},{"instance_id":"bd792ba7-3b51-4560-b2a6-6add146a939b","source":{"id":"8dd5f960-0544-4bf0-bda1-f37f0d70f734","url":"https://arxiv.org/pdf/1810.08575","title":"Supervising strong learners by amplifying weak experts"},"verbatim_text":"But the general phenomenon, that learning decompositions can be much cheaper than learning complex behaviors directly, is likely to hold for realistic tasks, since performing decomposition is strictly easier than solving the task without the aid of X.","context":null,"stance":"advances","direction":"for"}],"unplaced_argument_passages_total":2}