{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2VNTDLOIMM22SQSKMV75G7DHDO","short_pith_number":"pith:2VNTDLOI","schema_version":"1.0","canonical_sha256":"d55b31adc86335a9424a657fd37c671b82288521df3bd34d60bf5835d1432809","source":{"kind":"arxiv","id":"2408.10921","version":1},"attestation_state":"computed","paper":{"title":"MTFinEval:A Multi-domain Chinese Financial Benchmark with Eurypalynous questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ke Jin, Xinyu Liu","submitted_at":"2024-08-20T15:04:38Z","abstract_excerpt":"With the emergence of more and more economy-specific LLMS, how to measure whether they can be safely invested in production becomes a problem. Previous research has primarily focused on evaluating the performance of LLMs within specific application scenarios. However, these benchmarks cannot reflect the theoretical level and generalization ability, and the backward datasets are increasingly unsuitable for problems in real scenarios. In this paper, we have compiled a new benchmark, MTFinEval, focusing on the LLMs' basic knowledge of economics, which can always be used as a basis for judgment. T"},"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":"2408.10921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-20T15:04:38Z","cross_cats_sorted":[],"title_canon_sha256":"b94bcc171fbeb36cca7143b018f5d0047cc3f5de393e01ed3a38c2a085d25eb7","abstract_canon_sha256":"3c92c3b5f0dbd5d734f675cca5d235b5931045c2b8b5532d1a6e0be80dcd788a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:19.707692Z","signature_b64":"xBv9Sf29yrgEPdqp7I2pxrsrju5h7UU5DxCIoL/B69xZdn3vk+ypp5lfB70fOivkEJLylbaGtJAd6M3DfJ9NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d55b31adc86335a9424a657fd37c671b82288521df3bd34d60bf5835d1432809","last_reissued_at":"2026-07-05T08:57:19.707230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:19.707230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTFinEval:A Multi-domain Chinese Financial Benchmark with Eurypalynous questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ke Jin, Xinyu Liu","submitted_at":"2024-08-20T15:04:38Z","abstract_excerpt":"With the emergence of more and more economy-specific LLMS, how to measure whether they can be safely invested in production becomes a problem. Previous research has primarily focused on evaluating the performance of LLMs within specific application scenarios. However, these benchmarks cannot reflect the theoretical level and generalization ability, and the backward datasets are increasingly unsuitable for problems in real scenarios. In this paper, we have compiled a new benchmark, MTFinEval, focusing on the LLMs' basic knowledge of economics, which can always be used as a basis for judgment. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10921","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/2408.10921/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":"2408.10921","created_at":"2026-07-05T08:57:19.707283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10921v1","created_at":"2026-07-05T08:57:19.707283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10921","created_at":"2026-07-05T08:57:19.707283+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VNTDLOIMM22","created_at":"2026-07-05T08:57:19.707283+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VNTDLOIMM22SQSK","created_at":"2026-07-05T08:57:19.707283+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VNTDLOI","created_at":"2026-07-05T08:57:19.707283+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/2VNTDLOIMM22SQSKMV75G7DHDO","json":"https://pith.science/pith/2VNTDLOIMM22SQSKMV75G7DHDO.json","graph_json":"https://pith.science/api/pith-number/2VNTDLOIMM22SQSKMV75G7DHDO/graph.json","events_json":"https://pith.science/api/pith-number/2VNTDLOIMM22SQSKMV75G7DHDO/events.json","paper":"https://pith.science/paper/2VNTDLOI"},"agent_actions":{"view_html":"https://pith.science/pith/2VNTDLOIMM22SQSKMV75G7DHDO","download_json":"https://pith.science/pith/2VNTDLOIMM22SQSKMV75G7DHDO.json","view_paper":"https://pith.science/paper/2VNTDLOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10921&json=true","fetch_graph":"https://pith.science/api/pith-number/2VNTDLOIMM22SQSKMV75G7DHDO/graph.json","fetch_events":"https://pith.science/api/pith-number/2VNTDLOIMM22SQSKMV75G7DHDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VNTDLOIMM22SQSKMV75G7DHDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VNTDLOIMM22SQSKMV75G7DHDO/action/storage_attestation","attest_author":"https://pith.science/pith/2VNTDLOIMM22SQSKMV75G7DHDO/action/author_attestation","sign_citation":"https://pith.science/pith/2VNTDLOIMM22SQSKMV75G7DHDO/action/citation_signature","submit_replication":"https://pith.science/pith/2VNTDLOIMM22SQSKMV75G7DHDO/action/replication_record"}},"created_at":"2026-07-05T08:57:19.707283+00:00","updated_at":"2026-07-05T08:57:19.707283+00:00"}