{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JIBRUOX5P7SHAZ6NSOJTJGP4RS","short_pith_number":"pith:JIBRUOX5","schema_version":"1.0","canonical_sha256":"4a031a3afd7fe47067cd93933499fc8c81f16251561d5f81b5a6b8d54edcb2d7","source":{"kind":"arxiv","id":"2407.01212","version":1},"attestation_state":"computed","paper":{"title":"EconNLI: Evaluating Large Language Models on Economics Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yi Yang, Yue Guo","submitted_at":"2024-07-01T11:58:24Z","abstract_excerpt":"Large Language Models (LLMs) are widely used for writing economic analysis reports or providing financial advice, but their ability to understand economic knowledge and reason about potential results of specific economic events lacks systematic evaluation. To address this gap, we propose a new dataset, natural language inference on economic events (EconNLI), to evaluate LLMs' knowledge and reasoning abilities in the economic domain. We evaluate LLMs on (1) their ability to correctly classify whether a premise event will cause a hypothesis event and (2) their ability to generate reasonable even"},"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":"2407.01212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T11:58:24Z","cross_cats_sorted":[],"title_canon_sha256":"5368ed019cd7ee40f73c90965c08fe9fefb31d51ad94a83ebbb69a618c6eab56","abstract_canon_sha256":"4acb379b41e1d3e525c7ea87ba755d751bba529d1cd9de910dc8821e28e413b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:44.587033Z","signature_b64":"ipM87Tu2TDtpEQtnZlerL7M49CoZemSurbqE/I9e3+Z2lTOKevIcAIxLRy5i6Y4lSvYGQJ2nzVDQM8ZS/3z2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a031a3afd7fe47067cd93933499fc8c81f16251561d5f81b5a6b8d54edcb2d7","last_reissued_at":"2026-07-05T08:38:44.586605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:44.586605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EconNLI: Evaluating Large Language Models on Economics Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yi Yang, Yue Guo","submitted_at":"2024-07-01T11:58:24Z","abstract_excerpt":"Large Language Models (LLMs) are widely used for writing economic analysis reports or providing financial advice, but their ability to understand economic knowledge and reason about potential results of specific economic events lacks systematic evaluation. To address this gap, we propose a new dataset, natural language inference on economic events (EconNLI), to evaluate LLMs' knowledge and reasoning abilities in the economic domain. We evaluate LLMs on (1) their ability to correctly classify whether a premise event will cause a hypothesis event and (2) their ability to generate reasonable even"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01212","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/2407.01212/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":"2407.01212","created_at":"2026-07-05T08:38:44.586670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01212v1","created_at":"2026-07-05T08:38:44.586670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01212","created_at":"2026-07-05T08:38:44.586670+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIBRUOX5P7SH","created_at":"2026-07-05T08:38:44.586670+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIBRUOX5P7SHAZ6N","created_at":"2026-07-05T08:38:44.586670+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIBRUOX5","created_at":"2026-07-05T08:38:44.586670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS","json":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS.json","graph_json":"https://pith.science/api/pith-number/JIBRUOX5P7SHAZ6NSOJTJGP4RS/graph.json","events_json":"https://pith.science/api/pith-number/JIBRUOX5P7SHAZ6NSOJTJGP4RS/events.json","paper":"https://pith.science/paper/JIBRUOX5"},"agent_actions":{"view_html":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS","download_json":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS.json","view_paper":"https://pith.science/paper/JIBRUOX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01212&json=true","fetch_graph":"https://pith.science/api/pith-number/JIBRUOX5P7SHAZ6NSOJTJGP4RS/graph.json","fetch_events":"https://pith.science/api/pith-number/JIBRUOX5P7SHAZ6NSOJTJGP4RS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS/action/storage_attestation","attest_author":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS/action/author_attestation","sign_citation":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS/action/citation_signature","submit_replication":"https://pith.science/pith/JIBRUOX5P7SHAZ6NSOJTJGP4RS/action/replication_record"}},"created_at":"2026-07-05T08:38:44.586670+00:00","updated_at":"2026-07-05T08:38:44.586670+00:00"}