{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3ZU3E2NASQSPMKN4HK32R6XMTQ","short_pith_number":"pith:3ZU3E2NA","schema_version":"1.0","canonical_sha256":"de69b269a09424f629bc3ab7a8faec9c06716ad1905d4fc6d0e38858ebd35535","source":{"kind":"arxiv","id":"2501.15326","version":2},"attestation_state":"computed","paper":{"title":"Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian R Quaranto, Chenhui Xu, Dancheng Liu, Ishan Mishra, Jiajie Li, Jinjun Xiong, Peter C W Kim, Ruiyang Qin","submitted_at":"2025-01-25T21:01:52Z","abstract_excerpt":"We present RASO, a foundation model designed to Recognize Any Surgical Object, offering robust open-set recognition capabilities across a broad range of surgical procedures and object classes, in both surgical images and videos. RASO leverages a novel weakly-supervised learning framework that generates tag-image-text pairs automatically from large-scale unannotated surgical lecture videos, significantly reducing the need for manual annotations. Our scalable data generation pipeline gathers 2,200 surgical procedures and produces 3.6 million tag annotations across 2,066 unique surgical tags. Our"},"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":"2501.15326","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-25T21:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"2fdad3a4b40475bfe0940b76370256fcec7d724a4bb602ce8a8a4fc9b9eb33be","abstract_canon_sha256":"455a2ab5b36938cecbe1c3bde1b2b72667e37cb4b55fac61b926ec72f5241a3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:05.129393Z","signature_b64":"gtpg6l/AmVB4ErEPJ3KxKrFuAWCMtBLUvRYpOF6t2VsKV14CPNOmR7LBmyK8sOsYIkbKXPlJcGCjSuuAV7q4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de69b269a09424f629bc3ab7a8faec9c06716ad1905d4fc6d0e38858ebd35535","last_reissued_at":"2026-07-05T10:59:05.128875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:05.128875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian R Quaranto, Chenhui Xu, Dancheng Liu, Ishan Mishra, Jiajie Li, Jinjun Xiong, Peter C W Kim, Ruiyang Qin","submitted_at":"2025-01-25T21:01:52Z","abstract_excerpt":"We present RASO, a foundation model designed to Recognize Any Surgical Object, offering robust open-set recognition capabilities across a broad range of surgical procedures and object classes, in both surgical images and videos. RASO leverages a novel weakly-supervised learning framework that generates tag-image-text pairs automatically from large-scale unannotated surgical lecture videos, significantly reducing the need for manual annotations. Our scalable data generation pipeline gathers 2,200 surgical procedures and produces 3.6 million tag annotations across 2,066 unique surgical tags. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15326","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/2501.15326/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":"2501.15326","created_at":"2026-07-05T10:59:05.128931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15326v2","created_at":"2026-07-05T10:59:05.128931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15326","created_at":"2026-07-05T10:59:05.128931+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZU3E2NASQSP","created_at":"2026-07-05T10:59:05.128931+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZU3E2NASQSPMKN4","created_at":"2026-07-05T10:59:05.128931+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZU3E2NA","created_at":"2026-07-05T10:59:05.128931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17279","citing_title":"Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ","json":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ.json","graph_json":"https://pith.science/api/pith-number/3ZU3E2NASQSPMKN4HK32R6XMTQ/graph.json","events_json":"https://pith.science/api/pith-number/3ZU3E2NASQSPMKN4HK32R6XMTQ/events.json","paper":"https://pith.science/paper/3ZU3E2NA"},"agent_actions":{"view_html":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ","download_json":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ.json","view_paper":"https://pith.science/paper/3ZU3E2NA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15326&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZU3E2NASQSPMKN4HK32R6XMTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZU3E2NASQSPMKN4HK32R6XMTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ/action/storage_attestation","attest_author":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ/action/author_attestation","sign_citation":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ/action/citation_signature","submit_replication":"https://pith.science/pith/3ZU3E2NASQSPMKN4HK32R6XMTQ/action/replication_record"}},"created_at":"2026-07-05T10:59:05.128931+00:00","updated_at":"2026-07-05T10:59:05.128931+00:00"}