{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N2BPTAP4HT5VT2CH5QMHIK76E4","short_pith_number":"pith:N2BPTAP4","schema_version":"1.0","canonical_sha256":"6e82f981fc3cfb59e847ec18742bfe2710a2c4f48249a15e72eb695c2da36189","source":{"kind":"arxiv","id":"2606.30987","version":1},"attestation_state":"computed","paper":{"title":"Measuring Judgment Quality in Natural-Language Explanations: Evidence from Forecasting Tournaments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CL","authors_text":"Christopher W. Karvetski, Ezra Karger, Jingyu Hu, Nadja Flechner, Philip Tetlock, Sheldon S. Huang, Simas Ku\\v{c}inskas","submitted_at":"2026-06-29T23:51:09Z","abstract_excerpt":"Decision-makers routinely rely on expert judgments accompanied by written explanations, yet explanation quality is difficult to measure at scale. Forecasting tournaments offer a natural testing ground: probabilistic judgments are paired with natural-language rationales and scored against realized outcomes. We introduce Explanation Quality Markers (EQMs), a set of sixty theory-guided reasoning patterns scored by large language models (LLMs). In a pre-registered analysis of over 55,000 forecast-rationale pairs from a multiyear forecasting tournament, EQMs predict accuracy at both the forecast an"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.30987","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T23:51:09Z","cross_cats_sorted":["econ.GN","q-fin.EC"],"title_canon_sha256":"3d551cce3d36e6e72635715945417438b796ae430a5f37e0f88ff8af28978159","abstract_canon_sha256":"60443305c6f989f3fe6ff0740cbcf01b922902c150aad5968deea9f7c419f6fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:23.520599Z","signature_b64":"ua00EYtAlvAQhZskol+tWeZ73t/Kaa82rfKyTaEUfWwLca4toQTSX93wqKpXAgA/cSOWGcAFUy7Bqkd9IG1FCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e82f981fc3cfb59e847ec18742bfe2710a2c4f48249a15e72eb695c2da36189","last_reissued_at":"2026-07-01T00:17:23.520169Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:23.520169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Judgment Quality in Natural-Language Explanations: Evidence from Forecasting Tournaments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CL","authors_text":"Christopher W. Karvetski, Ezra Karger, Jingyu Hu, Nadja Flechner, Philip Tetlock, Sheldon S. Huang, Simas Ku\\v{c}inskas","submitted_at":"2026-06-29T23:51:09Z","abstract_excerpt":"Decision-makers routinely rely on expert judgments accompanied by written explanations, yet explanation quality is difficult to measure at scale. Forecasting tournaments offer a natural testing ground: probabilistic judgments are paired with natural-language rationales and scored against realized outcomes. We introduce Explanation Quality Markers (EQMs), a set of sixty theory-guided reasoning patterns scored by large language models (LLMs). In a pre-registered analysis of over 55,000 forecast-rationale pairs from a multiyear forecasting tournament, EQMs predict accuracy at both the forecast an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30987","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.30987/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.30987","created_at":"2026-07-01T00:17:23.520232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30987v1","created_at":"2026-07-01T00:17:23.520232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30987","created_at":"2026-07-01T00:17:23.520232+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2BPTAP4HT5V","created_at":"2026-07-01T00:17:23.520232+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2BPTAP4HT5VT2CH","created_at":"2026-07-01T00:17:23.520232+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2BPTAP4","created_at":"2026-07-01T00:17:23.520232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4","json":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4.json","graph_json":"https://pith.science/api/pith-number/N2BPTAP4HT5VT2CH5QMHIK76E4/graph.json","events_json":"https://pith.science/api/pith-number/N2BPTAP4HT5VT2CH5QMHIK76E4/events.json","paper":"https://pith.science/paper/N2BPTAP4"},"agent_actions":{"view_html":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4","download_json":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4.json","view_paper":"https://pith.science/paper/N2BPTAP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30987&json=true","fetch_graph":"https://pith.science/api/pith-number/N2BPTAP4HT5VT2CH5QMHIK76E4/graph.json","fetch_events":"https://pith.science/api/pith-number/N2BPTAP4HT5VT2CH5QMHIK76E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4/action/storage_attestation","attest_author":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4/action/author_attestation","sign_citation":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4/action/citation_signature","submit_replication":"https://pith.science/pith/N2BPTAP4HT5VT2CH5QMHIK76E4/action/replication_record"}},"created_at":"2026-07-01T00:17:23.520232+00:00","updated_at":"2026-07-01T00:17:23.520232+00:00"}