{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LX57AL2CO7LNEN7VD3WTWPBKI5","short_pith_number":"pith:LX57AL2C","schema_version":"1.0","canonical_sha256":"5dfbf02f4277d6d237f51eed3b3c2a475dbc7184291b454709948256ddeb59b5","source":{"kind":"arxiv","id":"2601.18929","version":2},"attestation_state":"computed","paper":{"title":"On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Schmidt, Anita Rau, Chinedu Nwoye, Jie Ying Wu, John J. Han, Muhammad Abdullah Jamal, Omid Mohareri","submitted_at":"2026-01-26T20:04:57Z","abstract_excerpt":"Vision foundation models (VFMs) have emerged as powerful tools for surgical scene understanding. However, current approaches predominantly rely on unimodal RGB pre-training, overlooking the complex 3D geometry inherent to surgical environments. Although several architectures support multimodal or geometry-aware inputs in general computer vision, the benefits of incorporating depth information in surgical settings remain underexplored. We conduct a large-scale empirical study comparing eight ViT-based VFMs that differ in pre-training domain, learning objective, and input modality (RGB vs. RGB-D"},"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":"2601.18929","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-26T20:04:57Z","cross_cats_sorted":[],"title_canon_sha256":"9f816c6be43854061ba22eeff386f2b36b790dc715152b893f8bd99ea3041105","abstract_canon_sha256":"884a5ad01c4d25256aec1c67848c76d07cfc543cd54f55cd2aae55ad7d60d80c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T00:18:18.163521Z","signature_b64":"sd677DycS/onw5UnGeJcmAarIMOG33KTwy38s+JGwY4dxJhK76Qqeyxtf1u5IbDHwQvGSezgl6apuqwpa5AfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dfbf02f4277d6d237f51eed3b3c2a475dbc7184291b454709948256ddeb59b5","last_reissued_at":"2026-07-20T00:18:18.162547Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T00:18:18.162547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Schmidt, Anita Rau, Chinedu Nwoye, Jie Ying Wu, John J. Han, Muhammad Abdullah Jamal, Omid Mohareri","submitted_at":"2026-01-26T20:04:57Z","abstract_excerpt":"Vision foundation models (VFMs) have emerged as powerful tools for surgical scene understanding. However, current approaches predominantly rely on unimodal RGB pre-training, overlooking the complex 3D geometry inherent to surgical environments. Although several architectures support multimodal or geometry-aware inputs in general computer vision, the benefits of incorporating depth information in surgical settings remain underexplored. We conduct a large-scale empirical study comparing eight ViT-based VFMs that differ in pre-training domain, learning objective, and input modality (RGB vs. RGB-D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18929","kind":"arxiv","version":2},"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/2601.18929/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":"2601.18929","created_at":"2026-07-20T00:18:18.162997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18929v2","created_at":"2026-07-20T00:18:18.162997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18929","created_at":"2026-07-20T00:18:18.162997+00:00"},{"alias_kind":"pith_short_12","alias_value":"LX57AL2CO7LN","created_at":"2026-07-20T00:18:18.162997+00:00"},{"alias_kind":"pith_short_16","alias_value":"LX57AL2CO7LNEN7V","created_at":"2026-07-20T00:18:18.162997+00:00"},{"alias_kind":"pith_short_8","alias_value":"LX57AL2C","created_at":"2026-07-20T00:18:18.162997+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/LX57AL2CO7LNEN7VD3WTWPBKI5","json":"https://pith.science/pith/LX57AL2CO7LNEN7VD3WTWPBKI5.json","graph_json":"https://pith.science/api/pith-number/LX57AL2CO7LNEN7VD3WTWPBKI5/graph.json","events_json":"https://pith.science/api/pith-number/LX57AL2CO7LNEN7VD3WTWPBKI5/events.json","paper":"https://pith.science/paper/LX57AL2C"},"agent_actions":{"view_html":"https://pith.science/pith/LX57AL2CO7LNEN7VD3WTWPBKI5","download_json":"https://pith.science/pith/LX57AL2CO7LNEN7VD3WTWPBKI5.json","view_paper":"https://pith.science/paper/LX57AL2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18929&json=true","fetch_graph":"https://pith.science/api/pith-number/LX57AL2CO7LNEN7VD3WTWPBKI5/graph.json","fetch_events":"https://pith.science/api/pith-number/LX57AL2CO7LNEN7VD3WTWPBKI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LX57AL2CO7LNEN7VD3WTWPBKI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LX57AL2CO7LNEN7VD3WTWPBKI5/action/storage_attestation","attest_author":"https://pith.science/pith/LX57AL2CO7LNEN7VD3WTWPBKI5/action/author_attestation","sign_citation":"https://pith.science/pith/LX57AL2CO7LNEN7VD3WTWPBKI5/action/citation_signature","submit_replication":"https://pith.science/pith/LX57AL2CO7LNEN7VD3WTWPBKI5/action/replication_record"}},"created_at":"2026-07-20T00:18:18.162997+00:00","updated_at":"2026-07-20T00:18:18.162997+00:00"}