{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCPN6OO3QW55ZWFNIKA6JBVGS6","short_pith_number":"pith:YCPN6OO3","schema_version":"1.0","canonical_sha256":"c09edf39db85bbdcd8ad4281e486a6978203de25946f3ed88198f6fb3ea47d2f","source":{"kind":"arxiv","id":"2507.18311","version":3},"attestation_state":"computed","paper":{"title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyu Zheng, Jinghuan Wei, Junhong Zou, Xiangyu Zhu, Xiaomei Zhang, Zhaoxiang Zhang, Zhen Lei","submitted_at":"2025-07-24T11:28:53Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, such as image captioning and visual question answering. These models are trained on large-scale image and video datasets paired with text, enabling them to bridge visual perception and natural language processing. However, their application to scientific domains, especially in interpreting complex field data commonly used in the natural sciences, remains underexplored. In this work, we introduce FieldLVLM, a novel framework designed to improve large v"},"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":"2507.18311","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-24T11:28:53Z","cross_cats_sorted":[],"title_canon_sha256":"e68fc11f3d1a816103a392f80da34cf459720cbbcf0cb0d0fd0b807bc1676ee5","abstract_canon_sha256":"ac221ac89fbd807720353e19adb44ea15844522fe430aada5ee9fe41499eaa05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:19:47.982241Z","signature_b64":"xr97hGMTb4tejtCtZhWSl8tTOj3N43eCzOGFxULWUKa1hbj9LVoPqBg6bYQFyp50uMJWG6bjCJ3gDwjGoQGVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c09edf39db85bbdcd8ad4281e486a6978203de25946f3ed88198f6fb3ea47d2f","last_reissued_at":"2026-07-27T01:19:47.980887Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:19:47.980887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Large Vision-Language Models' Understanding for Flow Field Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyu Zheng, Jinghuan Wei, Junhong Zou, Xiangyu Zhu, Xiaomei Zhang, Zhaoxiang Zhang, Zhen Lei","submitted_at":"2025-07-24T11:28:53Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have shown impressive capabilities across a range of tasks that integrate visual and textual understanding, such as image captioning and visual question answering. These models are trained on large-scale image and video datasets paired with text, enabling them to bridge visual perception and natural language processing. However, their application to scientific domains, especially in interpreting complex field data commonly used in the natural sciences, remains underexplored. In this work, we introduce FieldLVLM, a novel framework designed to improve large v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18311","kind":"arxiv","version":3},"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/2507.18311/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":"2507.18311","created_at":"2026-07-27T01:19:47.981513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18311v3","created_at":"2026-07-27T01:19:47.981513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18311","created_at":"2026-07-27T01:19:47.981513+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCPN6OO3QW55","created_at":"2026-07-27T01:19:47.981513+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCPN6OO3QW55ZWFN","created_at":"2026-07-27T01:19:47.981513+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCPN6OO3","created_at":"2026-07-27T01:19:47.981513+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/YCPN6OO3QW55ZWFNIKA6JBVGS6","json":"https://pith.science/pith/YCPN6OO3QW55ZWFNIKA6JBVGS6.json","graph_json":"https://pith.science/api/pith-number/YCPN6OO3QW55ZWFNIKA6JBVGS6/graph.json","events_json":"https://pith.science/api/pith-number/YCPN6OO3QW55ZWFNIKA6JBVGS6/events.json","paper":"https://pith.science/paper/YCPN6OO3"},"agent_actions":{"view_html":"https://pith.science/pith/YCPN6OO3QW55ZWFNIKA6JBVGS6","download_json":"https://pith.science/pith/YCPN6OO3QW55ZWFNIKA6JBVGS6.json","view_paper":"https://pith.science/paper/YCPN6OO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18311&json=true","fetch_graph":"https://pith.science/api/pith-number/YCPN6OO3QW55ZWFNIKA6JBVGS6/graph.json","fetch_events":"https://pith.science/api/pith-number/YCPN6OO3QW55ZWFNIKA6JBVGS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCPN6OO3QW55ZWFNIKA6JBVGS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCPN6OO3QW55ZWFNIKA6JBVGS6/action/storage_attestation","attest_author":"https://pith.science/pith/YCPN6OO3QW55ZWFNIKA6JBVGS6/action/author_attestation","sign_citation":"https://pith.science/pith/YCPN6OO3QW55ZWFNIKA6JBVGS6/action/citation_signature","submit_replication":"https://pith.science/pith/YCPN6OO3QW55ZWFNIKA6JBVGS6/action/replication_record"}},"created_at":"2026-07-27T01:19:47.981513+00:00","updated_at":"2026-07-27T01:19:47.981513+00:00"}