{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LX57AL2CO7LNEN7VD3WTWPBKI5","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":"884a5ad01c4d25256aec1c67848c76d07cfc543cd54f55cd2aae55ad7d60d80c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-26T20:04:57Z","title_canon_sha256":"9f816c6be43854061ba22eeff386f2b36b790dc715152b893f8bd99ea3041105"},"schema_version":"1.0","source":{"id":"2601.18929","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.18929","created_at":"2026-07-20T00:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"2601.18929v2","created_at":"2026-07-20T00:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18929","created_at":"2026-07-20T00:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"LX57AL2CO7LN","created_at":"2026-07-20T00:18:18Z"},{"alias_kind":"pith_short_16","alias_value":"LX57AL2CO7LNEN7V","created_at":"2026-07-20T00:18:18Z"},{"alias_kind":"pith_short_8","alias_value":"LX57AL2C","created_at":"2026-07-20T00:18:18Z"}],"graph_snapshots":[{"event_id":"sha256:744fbd2446cd60cf115f826fed9df6d29966385928dd8692ce46794f2f14efac","target":"graph","created_at":"2026-07-20T00:18:18Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.18929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adam Schmidt, Anita Rau, Chinedu Nwoye, Jie Ying Wu, John J. Han, Muhammad Abdullah Jamal, Omid Mohareri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-26T20:04:57Z","title":"On the Role of Depth in Surgical Vision Foundation Models: An Empirical Study of RGB-D Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18929","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:784a726ed027f09353eb7a291661918c340512a8e303094d912ca3b3c0330649","target":"record","created_at":"2026-07-20T00:18:18Z","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":"884a5ad01c4d25256aec1c67848c76d07cfc543cd54f55cd2aae55ad7d60d80c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-26T20:04:57Z","title_canon_sha256":"9f816c6be43854061ba22eeff386f2b36b790dc715152b893f8bd99ea3041105"},"schema_version":"1.0","source":{"id":"2601.18929","kind":"arxiv","version":2}},"canonical_sha256":"5dfbf02f4277d6d237f51eed3b3c2a475dbc7184291b454709948256ddeb59b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dfbf02f4277d6d237f51eed3b3c2a475dbc7184291b454709948256ddeb59b5","first_computed_at":"2026-07-20T00:18:18.162547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T00:18:18.162547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sd677DycS/onw5UnGeJcmAarIMOG33KTwy38s+JGwY4dxJhK76Qqeyxtf1u5IbDHwQvGSezgl6apuqwpa5AfCw==","signature_status":"signed_v1","signed_at":"2026-07-20T00:18:18.163521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.18929","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:784a726ed027f09353eb7a291661918c340512a8e303094d912ca3b3c0330649","sha256:744fbd2446cd60cf115f826fed9df6d29966385928dd8692ce46794f2f14efac"],"state_sha256":"3d3fe07b90dfee013bb1e5d661fad7ff4cc968da35221401dcc27c72c9d06e8c"}