{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QTAIK3FIER5LTK5IDM2J4RJAWE","short_pith_number":"pith:QTAIK3FI","schema_version":"1.0","canonical_sha256":"84c0856ca8247ab9aba81b349e4520b106a8e6868ccbcb6b3126f0debfb5e138","source":{"kind":"arxiv","id":"2404.09690","version":1},"attestation_state":"computed","paper":{"title":"Harnessing GPT-4V(ision) for Insurance: A Preliminary Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenwei Lin, Hanjia Lyu, Jiebo Luo, Xian Xu","submitted_at":"2024-04-15T11:45:30Z","abstract_excerpt":"The emergence of Large Multimodal Models (LMMs) marks a significant milestone in the development of artificial intelligence. Insurance, as a vast and complex discipline, involves a wide variety of data forms in its operational processes, including text, images, and videos, thereby giving rise to diverse multimodal tasks. Despite this, there has been limited systematic exploration of multimodal tasks specific to insurance, nor a thorough investigation into how LMMs can address these challenges. In this paper, we explore GPT-4V's capabilities in the insurance domain. We categorize multimodal tas"},"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":"2404.09690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-15T11:45:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"56712af26555574fc8252189e8f124e045670eb1c7c02cd78c8cf4f1ffbcf20e","abstract_canon_sha256":"6a301786eeee95c445f5aafbf1dbc78952139efaa5befab66e8d64d2cf997123"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:10.367024Z","signature_b64":"ucyrc1LCEQbnQVoPdFEa9o+AT5RFxaZVHmgP54U8mefxmQiVUnIaiiZCLKNY7VYj2DOSuDz6zeAoONgOanJNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84c0856ca8247ab9aba81b349e4520b106a8e6868ccbcb6b3126f0debfb5e138","last_reissued_at":"2026-07-05T08:08:10.366601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:10.366601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing GPT-4V(ision) for Insurance: A Preliminary Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenwei Lin, Hanjia Lyu, Jiebo Luo, Xian Xu","submitted_at":"2024-04-15T11:45:30Z","abstract_excerpt":"The emergence of Large Multimodal Models (LMMs) marks a significant milestone in the development of artificial intelligence. Insurance, as a vast and complex discipline, involves a wide variety of data forms in its operational processes, including text, images, and videos, thereby giving rise to diverse multimodal tasks. Despite this, there has been limited systematic exploration of multimodal tasks specific to insurance, nor a thorough investigation into how LMMs can address these challenges. In this paper, we explore GPT-4V's capabilities in the insurance domain. We categorize multimodal tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09690","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/2404.09690/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":"2404.09690","created_at":"2026-07-05T08:08:10.366656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09690v1","created_at":"2026-07-05T08:08:10.366656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09690","created_at":"2026-07-05T08:08:10.366656+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTAIK3FIER5L","created_at":"2026-07-05T08:08:10.366656+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTAIK3FIER5LTK5I","created_at":"2026-07-05T08:08:10.366656+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTAIK3FI","created_at":"2026-07-05T08:08:10.366656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04978","citing_title":"Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE","json":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE.json","graph_json":"https://pith.science/api/pith-number/QTAIK3FIER5LTK5IDM2J4RJAWE/graph.json","events_json":"https://pith.science/api/pith-number/QTAIK3FIER5LTK5IDM2J4RJAWE/events.json","paper":"https://pith.science/paper/QTAIK3FI"},"agent_actions":{"view_html":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE","download_json":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE.json","view_paper":"https://pith.science/paper/QTAIK3FI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09690&json=true","fetch_graph":"https://pith.science/api/pith-number/QTAIK3FIER5LTK5IDM2J4RJAWE/graph.json","fetch_events":"https://pith.science/api/pith-number/QTAIK3FIER5LTK5IDM2J4RJAWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE/action/storage_attestation","attest_author":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE/action/author_attestation","sign_citation":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE/action/citation_signature","submit_replication":"https://pith.science/pith/QTAIK3FIER5LTK5IDM2J4RJAWE/action/replication_record"}},"created_at":"2026-07-05T08:08:10.366656+00:00","updated_at":"2026-07-05T08:08:10.366656+00:00"}