{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LSCOLHTRHQO4JAP2DYO2GA3YJX","short_pith_number":"pith:LSCOLHTR","schema_version":"1.0","canonical_sha256":"5c84e59e713c1dc481fa1e1da303784df733026fddde00dfd432cdbae3c7bbd1","source":{"kind":"arxiv","id":"2405.10948","version":3},"attestation_state":"computed","paper":{"title":"Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","eess.IV"],"primary_cat":"cs.CV","authors_text":"Guankun Wang, Hongbin Liu, Hongliang Ren, Jie Wang, Jinlin Wu, Long Bai, Mobarakol Islam, Wan Jun Nah, Zhaoxi Zhang, Zhen Chen","submitted_at":"2024-03-22T08:38:27Z","abstract_excerpt":"Recent advancements in Surgical Visual Question Answering (Surgical-VQA) and related region grounding have shown great promise for robotic and medical applications, addressing the critical need for automated methods in personalized surgical mentorship. However, existing models primarily provide simple structured answers and struggle with complex scenarios due to their limited capability in recognizing long-range dependencies and aligning multimodal information. In this paper, we introduce Surgical-LVLM, a novel personalized large vision-language model tailored for complex surgical scenarios. L"},"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":"2405.10948","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-22T08:38:27Z","cross_cats_sorted":["cs.AI","cs.RO","eess.IV"],"title_canon_sha256":"de01be3ce8c1bf8a6daf99a6d646b0c579b6057773edef4367dc6dc03784fc10","abstract_canon_sha256":"bdb3c1e323deda92f35dcc38a1a806ce9f45f77a43e9535fb884982a201dbaa2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:43.396790Z","signature_b64":"juxaYc7KdB9K5mAtO0JHO6ThR1WHC/gIJkDGt5tm28Ds0r2pDbvENrjgLCGHVhyktuSOPXrPO5Cziiq89z/RCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c84e59e713c1dc481fa1e1da303784df733026fddde00dfd432cdbae3c7bbd1","last_reissued_at":"2026-07-05T10:31:43.396276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:43.396276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","eess.IV"],"primary_cat":"cs.CV","authors_text":"Guankun Wang, Hongbin Liu, Hongliang Ren, Jie Wang, Jinlin Wu, Long Bai, Mobarakol Islam, Wan Jun Nah, Zhaoxi Zhang, Zhen Chen","submitted_at":"2024-03-22T08:38:27Z","abstract_excerpt":"Recent advancements in Surgical Visual Question Answering (Surgical-VQA) and related region grounding have shown great promise for robotic and medical applications, addressing the critical need for automated methods in personalized surgical mentorship. However, existing models primarily provide simple structured answers and struggle with complex scenarios due to their limited capability in recognizing long-range dependencies and aligning multimodal information. In this paper, we introduce Surgical-LVLM, a novel personalized large vision-language model tailored for complex surgical scenarios. L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10948","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/2405.10948/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":"2405.10948","created_at":"2026-07-05T10:31:43.396340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10948v3","created_at":"2026-07-05T10:31:43.396340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10948","created_at":"2026-07-05T10:31:43.396340+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSCOLHTRHQO4","created_at":"2026-07-05T10:31:43.396340+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSCOLHTRHQO4JAP2","created_at":"2026-07-05T10:31:43.396340+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSCOLHTR","created_at":"2026-07-05T10:31:43.396340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23593","citing_title":"Real-Time Multimodal Activity-Aware Error Detection in Robot-Assisted Surgery","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17279","citing_title":"Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00573","citing_title":"LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00535","citing_title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23775","citing_title":"Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20319","citing_title":"SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10233","citing_title":"Adapting 2D Multi-Modal Large Language Model for 3D CT Image Analysis","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX","json":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX.json","graph_json":"https://pith.science/api/pith-number/LSCOLHTRHQO4JAP2DYO2GA3YJX/graph.json","events_json":"https://pith.science/api/pith-number/LSCOLHTRHQO4JAP2DYO2GA3YJX/events.json","paper":"https://pith.science/paper/LSCOLHTR"},"agent_actions":{"view_html":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX","download_json":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX.json","view_paper":"https://pith.science/paper/LSCOLHTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10948&json=true","fetch_graph":"https://pith.science/api/pith-number/LSCOLHTRHQO4JAP2DYO2GA3YJX/graph.json","fetch_events":"https://pith.science/api/pith-number/LSCOLHTRHQO4JAP2DYO2GA3YJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX/action/storage_attestation","attest_author":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX/action/author_attestation","sign_citation":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX/action/citation_signature","submit_replication":"https://pith.science/pith/LSCOLHTRHQO4JAP2DYO2GA3YJX/action/replication_record"}},"created_at":"2026-07-05T10:31:43.396340+00:00","updated_at":"2026-07-05T10:31:43.396340+00:00"}