{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3JIVIHMO6UT7O5W2XB72Z7W6OD","short_pith_number":"pith:3JIVIHMO","schema_version":"1.0","canonical_sha256":"da51541d8ef527f776dab87facfede70f6742ef1ee8a5d02c3ffecf905348784","source":{"kind":"arxiv","id":"2607.24273","version":1},"attestation_state":"computed","paper":{"title":"INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyu Chen, Chenwei Lin, Xian Xu","submitted_at":"2026-07-27T11:12:50Z","abstract_excerpt":"Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reasoning, long-context understanding, and tool use in separate settings. This limits their ability to assess realistic professional workflows that require auditable, context-grounded, and tool-executable decisions. We introduce \\textbf{INS-ActBench}, a comprehensive benchmark for evaluating professional actuarial capability in LLMs. INS-ActBench contains 12,050 Q\\&A pairs from public exams and sample questions released by 16 actuarial associations"},"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":"2607.24273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-27T11:12:50Z","cross_cats_sorted":[],"title_canon_sha256":"4af0cb487299c601c8e58af2781fa5ae06c439516bfe4a78152082898904f94d","abstract_canon_sha256":"83b8387c34b470fd21acd7a869b8109f1fc3785422bc05d67860ea6fc3b7f3c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:54.704368Z","signature_b64":"gf6L62AG84HxzcTpSlrrGZKrajTAy+UIGac/h7XpTEK+RZjWN3g3ZnNg0gW33XSTLGu8Dju6bjZk8N/Z1vw7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da51541d8ef527f776dab87facfede70f6742ef1ee8a5d02c3ffecf905348784","last_reissued_at":"2026-07-28T02:23:54.703355Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:54.703355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INS-ActBench: A Comprehensive Benchmark for Assessing Professional Actuarial Capability of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyu Chen, Chenwei Lin, Xian Xu","submitted_at":"2026-07-27T11:12:50Z","abstract_excerpt":"Large Language Models (LLMs) have shown strong potential in financial reasoning, but existing benchmarks often evaluate domain knowledge, numerical reasoning, long-context understanding, and tool use in separate settings. This limits their ability to assess realistic professional workflows that require auditable, context-grounded, and tool-executable decisions. We introduce \\textbf{INS-ActBench}, a comprehensive benchmark for evaluating professional actuarial capability in LLMs. INS-ActBench contains 12,050 Q\\&A pairs from public exams and sample questions released by 16 actuarial associations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24273","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/2607.24273/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":"2607.24273","created_at":"2026-07-28T02:23:54.703934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24273v1","created_at":"2026-07-28T02:23:54.703934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24273","created_at":"2026-07-28T02:23:54.703934+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JIVIHMO6UT7","created_at":"2026-07-28T02:23:54.703934+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JIVIHMO6UT7O5W2","created_at":"2026-07-28T02:23:54.703934+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JIVIHMO","created_at":"2026-07-28T02:23:54.703934+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/3JIVIHMO6UT7O5W2XB72Z7W6OD","json":"https://pith.science/pith/3JIVIHMO6UT7O5W2XB72Z7W6OD.json","graph_json":"https://pith.science/api/pith-number/3JIVIHMO6UT7O5W2XB72Z7W6OD/graph.json","events_json":"https://pith.science/api/pith-number/3JIVIHMO6UT7O5W2XB72Z7W6OD/events.json","paper":"https://pith.science/paper/3JIVIHMO"},"agent_actions":{"view_html":"https://pith.science/pith/3JIVIHMO6UT7O5W2XB72Z7W6OD","download_json":"https://pith.science/pith/3JIVIHMO6UT7O5W2XB72Z7W6OD.json","view_paper":"https://pith.science/paper/3JIVIHMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24273&json=true","fetch_graph":"https://pith.science/api/pith-number/3JIVIHMO6UT7O5W2XB72Z7W6OD/graph.json","fetch_events":"https://pith.science/api/pith-number/3JIVIHMO6UT7O5W2XB72Z7W6OD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JIVIHMO6UT7O5W2XB72Z7W6OD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JIVIHMO6UT7O5W2XB72Z7W6OD/action/storage_attestation","attest_author":"https://pith.science/pith/3JIVIHMO6UT7O5W2XB72Z7W6OD/action/author_attestation","sign_citation":"https://pith.science/pith/3JIVIHMO6UT7O5W2XB72Z7W6OD/action/citation_signature","submit_replication":"https://pith.science/pith/3JIVIHMO6UT7O5W2XB72Z7W6OD/action/replication_record"}},"created_at":"2026-07-28T02:23:54.703934+00:00","updated_at":"2026-07-28T02:23:54.703934+00:00"}