{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MELTFVWTLHNQN3Y3DYMXNXTV42","short_pith_number":"pith:MELTFVWT","canonical_record":{"source":{"id":"2506.18942","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-06-22T19:36:03Z","cross_cats_sorted":["q-fin.RM"],"title_canon_sha256":"017d27c5e2706a5ce1df8b160ba9b1571e6596d5fcf0acb347a3e674c06f649e","abstract_canon_sha256":"19db42fbec2129ce6ab960014b8f44f8798c5003ad995369c62eec378f9fd490"},"schema_version":"1.0"},"canonical_sha256":"611732d6d359db06ef1b1e1976de75e685a937d59aa551d09846ffe9a86feda2","source":{"kind":"arxiv","id":"2506.18942","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18942","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18942v3","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18942","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"MELTFVWTLHNQ","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"MELTFVWTLHNQN3Y3","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"MELTFVWT","created_at":"2026-06-26T00:15:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MELTFVWTLHNQN3Y3DYMXNXTV42","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18942","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-06-22T19:36:03Z","cross_cats_sorted":["q-fin.RM"],"title_canon_sha256":"017d27c5e2706a5ce1df8b160ba9b1571e6596d5fcf0acb347a3e674c06f649e","abstract_canon_sha256":"19db42fbec2129ce6ab960014b8f44f8798c5003ad995369c62eec378f9fd490"},"schema_version":"1.0"},"canonical_sha256":"611732d6d359db06ef1b1e1976de75e685a937d59aa551d09846ffe9a86feda2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:22.216498Z","signature_b64":"Oo8fXXKYBNEWfVqxl4v1ELF/TBqTVMKY9ZdmU7kdy/XmtXZ9TdjSbh+iFILkiz52RKjObpVsJaM/TY+yqX0SCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"611732d6d359db06ef1b1e1976de75e685a937d59aa551d09846ffe9a86feda2","last_reissued_at":"2026-06-26T00:15:22.215889Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:22.215889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18942","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T00:15:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9wXJ2Xiym0rwYVtHztQDoQodYqcR7TNSnlytT8XkgSQXaBcDiQItOAYRMqFYl4UeK0giwbJGE+2hh22x6DmWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:23:59.014431Z"},"content_sha256":"b0dd9f051ada39ea73ff8021956d2bacc80e2b0dfe41d8494ece87babb692ed1","schema_version":"1.0","event_id":"sha256:b0dd9f051ada39ea73ff8021956d2bacc80e2b0dfe41d8494ece87babb692ed1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MELTFVWTLHNQN3Y3DYMXNXTV42","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advanced Applications of Generative AI in Actuarial Science: Case Studies Beyond ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Generative AI supports actuarial practice through four concrete case studies in insurance.","cross_cats":["q-fin.RM"],"primary_cat":"cs.CY","authors_text":"Iris Nonneman, Simon Hatzesberger","submitted_at":"2025-06-22T19:36:03Z","abstract_excerpt":"This article explores the potential of generative AI (GenAI) to support actuarial practice through four implemented case studies. It situates these case studies within the broader evolution of artificial intelligence in actuarial science, from early neural networks and machine learning to modern transformer-based GenAI systems. The first case study illustrates how large language models (LLMs) can improve claim cost prediction by extracting informative features from unstructured text for use in the underlying supervised learning task. The second case study demonstrates the automation of market "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Generative AI can support actuarial practice through four implemented case studies: LLMs for extracting features from text in claim cost prediction, RAG for structuring information from annual reports, vision-enabled LLMs for car damage classification, and a multi-agent system for migrating legacy R code to Python.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The described implementations function reliably enough for practical use in regulated insurance environments despite the challenges of reproducibility, privacy, and governance that the paper itself lists in its final section.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Four implemented case studies demonstrate generative AI supporting actuarial tasks in claim cost prediction, market report analysis, image-based damage assessment, and legacy code migration.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Generative AI supports actuarial practice through four concrete case studies in insurance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"57f312819217bdfa8e9e929a83708ff2da1defdd34ac530fdc77df78035f5c50"},"source":{"id":"2506.18942","kind":"arxiv","version":3},"verdict":{"id":"2b1918bb-6e8d-4329-b8db-6b62b013ef14","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T07:55:20.320726Z","strongest_claim":"Generative AI can support actuarial practice through four implemented case studies: LLMs for extracting features from text in claim cost prediction, RAG for structuring information from annual reports, vision-enabled LLMs for car damage classification, and a multi-agent system for migrating legacy R code to Python.","one_line_summary":"Four implemented case studies demonstrate generative AI supporting actuarial tasks in claim cost prediction, market report analysis, image-based damage assessment, and legacy code migration.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The described implementations function reliably enough for practical use in regulated insurance environments despite the challenges of reproducibility, privacy, and governance that the paper itself lists in its final section.","pith_extraction_headline":"Generative AI supports actuarial practice through four concrete case studies in insurance."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.18942/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":2,"snapshot_sha256":"8141f9b6586fac44ae1a9a9393456a4e2fe3ad2f2a77834695df5452c144ecd0"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2b1918bb-6e8d-4329-b8db-6b62b013ef14"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T00:15:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/0fdaKUHPUTiHuXQVTLmP6a8j9qEA41kEA8FOWPQcVj3YBARdzruBw8plzQGKM38vaevbTK06lZKrNXs3PDmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:23:59.015594Z"},"content_sha256":"1392e7ccec61b949bcaf5a2024e9ffc6287e19ca9bb2a3bc5e19f858fb03780f","schema_version":"1.0","event_id":"sha256:1392e7ccec61b949bcaf5a2024e9ffc6287e19ca9bb2a3bc5e19f858fb03780f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MELTFVWTLHNQN3Y3DYMXNXTV42/bundle.json","state_url":"https://pith.science/pith/MELTFVWTLHNQN3Y3DYMXNXTV42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MELTFVWTLHNQN3Y3DYMXNXTV42/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T00:23:59Z","links":{"resolver":"https://pith.science/pith/MELTFVWTLHNQN3Y3DYMXNXTV42","bundle":"https://pith.science/pith/MELTFVWTLHNQN3Y3DYMXNXTV42/bundle.json","state":"https://pith.science/pith/MELTFVWTLHNQN3Y3DYMXNXTV42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MELTFVWTLHNQN3Y3DYMXNXTV42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MELTFVWTLHNQN3Y3DYMXNXTV42","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"19db42fbec2129ce6ab960014b8f44f8798c5003ad995369c62eec378f9fd490","cross_cats_sorted":["q-fin.RM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-06-22T19:36:03Z","title_canon_sha256":"017d27c5e2706a5ce1df8b160ba9b1571e6596d5fcf0acb347a3e674c06f649e"},"schema_version":"1.0","source":{"id":"2506.18942","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18942","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18942v3","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18942","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"MELTFVWTLHNQ","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"MELTFVWTLHNQN3Y3","created_at":"2026-06-26T00:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"MELTFVWT","created_at":"2026-06-26T00:15:22Z"}],"graph_snapshots":[{"event_id":"sha256:1392e7ccec61b949bcaf5a2024e9ffc6287e19ca9bb2a3bc5e19f858fb03780f","target":"graph","created_at":"2026-06-26T00:15:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Generative AI can support actuarial practice through four implemented case studies: LLMs for extracting features from text in claim cost prediction, RAG for structuring information from annual reports, vision-enabled LLMs for car damage classification, and a multi-agent system for migrating legacy R code to Python."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The described implementations function reliably enough for practical use in regulated insurance environments despite the challenges of reproducibility, privacy, and governance that the paper itself lists in its final section."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Four implemented case studies demonstrate generative AI supporting actuarial tasks in claim cost prediction, market report analysis, image-based damage assessment, and legacy code migration."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Generative AI supports actuarial practice through four concrete case studies in insurance."}],"snapshot_sha256":"57f312819217bdfa8e9e929a83708ff2da1defdd34ac530fdc77df78035f5c50"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8141f9b6586fac44ae1a9a9393456a4e2fe3ad2f2a77834695df5452c144ecd0"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.18942/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This article explores the potential of generative AI (GenAI) to support actuarial practice through four implemented case studies. It situates these case studies within the broader evolution of artificial intelligence in actuarial science, from early neural networks and machine learning to modern transformer-based GenAI systems. The first case study illustrates how large language models (LLMs) can improve claim cost prediction by extracting informative features from unstructured text for use in the underlying supervised learning task. The second case study demonstrates the automation of market ","authors_text":"Iris Nonneman, Simon Hatzesberger","cross_cats":["q-fin.RM"],"headline":"Generative AI supports actuarial practice through four concrete case studies in insurance.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-06-22T19:36:03Z","title":"Advanced Applications of Generative AI in Actuarial Science: Case Studies Beyond ChatGPT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18942","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-19T07:55:20.320726Z","id":"2b1918bb-6e8d-4329-b8db-6b62b013ef14","model_set":{"reader":"grok-4.3"},"one_line_summary":"Four implemented case studies demonstrate generative AI supporting actuarial tasks in claim cost prediction, market report analysis, image-based damage assessment, and legacy code migration.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Generative AI supports actuarial practice through four concrete case studies in insurance.","strongest_claim":"Generative AI can support actuarial practice through four implemented case studies: LLMs for extracting features from text in claim cost prediction, RAG for structuring information from annual reports, vision-enabled LLMs for car damage classification, and a multi-agent system for migrating legacy R code to Python.","weakest_assumption":"The described implementations function reliably enough for practical use in regulated insurance environments despite the challenges of reproducibility, privacy, and governance that the paper itself lists in its final section."}},"verdict_id":"2b1918bb-6e8d-4329-b8db-6b62b013ef14"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b0dd9f051ada39ea73ff8021956d2bacc80e2b0dfe41d8494ece87babb692ed1","target":"record","created_at":"2026-06-26T00:15:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"19db42fbec2129ce6ab960014b8f44f8798c5003ad995369c62eec378f9fd490","cross_cats_sorted":["q-fin.RM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-06-22T19:36:03Z","title_canon_sha256":"017d27c5e2706a5ce1df8b160ba9b1571e6596d5fcf0acb347a3e674c06f649e"},"schema_version":"1.0","source":{"id":"2506.18942","kind":"arxiv","version":3}},"canonical_sha256":"611732d6d359db06ef1b1e1976de75e685a937d59aa551d09846ffe9a86feda2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"611732d6d359db06ef1b1e1976de75e685a937d59aa551d09846ffe9a86feda2","first_computed_at":"2026-06-26T00:15:22.215889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T00:15:22.215889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Oo8fXXKYBNEWfVqxl4v1ELF/TBqTVMKY9ZdmU7kdy/XmtXZ9TdjSbh+iFILkiz52RKjObpVsJaM/TY+yqX0SCw==","signature_status":"signed_v1","signed_at":"2026-06-26T00:15:22.216498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18942","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0dd9f051ada39ea73ff8021956d2bacc80e2b0dfe41d8494ece87babb692ed1","sha256:1392e7ccec61b949bcaf5a2024e9ffc6287e19ca9bb2a3bc5e19f858fb03780f"],"state_sha256":"ff01ea06802489e2329baeb8b09e3c57a5c85998e0008777a4575ec1f6f0e187"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGRtXbxPtagsWwis7ZtQsBhBy/NBf4FCNVDB6/BZiAoBmuO8UUXmzJrodG1JOCgil9i/mwdAl5UFJgU0zrxQDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:23:59.027615Z","bundle_sha256":"6b51ef96795fbf1d9ffc5e0f297215bd79ff436515b10e5da21928ddcb4d4b61"}}