{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SJPQ23ZM7J3HHPHAIH4DQ6SVDC","short_pith_number":"pith:SJPQ23ZM","schema_version":"1.0","canonical_sha256":"925f0d6f2cfa7673bce041f8387a5518b59b0edc88b5a949864f3b9fa11e7b29","source":{"kind":"arxiv","id":"2606.31007","version":1},"attestation_state":"computed","paper":{"title":"Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyan Jing, Hao Ding, Jacob M. Delgado L\\'opez, Lalithkumar Seenivasan, Mathias Unberath","submitted_at":"2026-06-30T00:50:46Z","abstract_excerpt":"Vision foundation models such as SAM 3 can provide transferable object-level structure across diverse surgical video conditions, but segmentation outputs do not explicitly encode the action-conditioned semantics that define functional surgical landmarks. Estimating instrument extent and geometry differs from localizing the tip or anchor relevant to clipping, grasping, or dissecting. We investigate vision foundation model-enabled sparse action-aware landmark localization, using zero-shot, point-prompted structural masks to provide dense instrument-level context without manual pixel-level mask a"},"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":"2606.31007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T00:50:46Z","cross_cats_sorted":[],"title_canon_sha256":"9a16e6617b2ddb38d4969f139f7df6df8b06a32a2bc57ae13d7bc578042c4459","abstract_canon_sha256":"c0cf402f9368a9c75f8d2b2716b26d38b0ff88aa3bdd42f99e31073604c4ab2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:24.061392Z","signature_b64":"KXY87kGfHkkzr0j8x4OC916LhBs6O9zxVEd365GB9NtkDk8JhtIjIv2MkZe9MLjPj5fZVgsF8lCGzx8P8NKqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"925f0d6f2cfa7673bce041f8387a5518b59b0edc88b5a949864f3b9fa11e7b29","last_reissued_at":"2026-07-01T00:17:24.060968Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:24.060968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense Structural Priors for Sparse Functional Landmark Localization in Surgical Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyan Jing, Hao Ding, Jacob M. Delgado L\\'opez, Lalithkumar Seenivasan, Mathias Unberath","submitted_at":"2026-06-30T00:50:46Z","abstract_excerpt":"Vision foundation models such as SAM 3 can provide transferable object-level structure across diverse surgical video conditions, but segmentation outputs do not explicitly encode the action-conditioned semantics that define functional surgical landmarks. Estimating instrument extent and geometry differs from localizing the tip or anchor relevant to clipping, grasping, or dissecting. We investigate vision foundation model-enabled sparse action-aware landmark localization, using zero-shot, point-prompted structural masks to provide dense instrument-level context without manual pixel-level mask a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31007","kind":"arxiv","version":1},"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/2606.31007/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":"2606.31007","created_at":"2026-07-01T00:17:24.061028+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31007v1","created_at":"2026-07-01T00:17:24.061028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31007","created_at":"2026-07-01T00:17:24.061028+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJPQ23ZM7J3H","created_at":"2026-07-01T00:17:24.061028+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJPQ23ZM7J3HHPHA","created_at":"2026-07-01T00:17:24.061028+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJPQ23ZM","created_at":"2026-07-01T00:17:24.061028+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/SJPQ23ZM7J3HHPHAIH4DQ6SVDC","json":"https://pith.science/pith/SJPQ23ZM7J3HHPHAIH4DQ6SVDC.json","graph_json":"https://pith.science/api/pith-number/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/graph.json","events_json":"https://pith.science/api/pith-number/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/events.json","paper":"https://pith.science/paper/SJPQ23ZM"},"agent_actions":{"view_html":"https://pith.science/pith/SJPQ23ZM7J3HHPHAIH4DQ6SVDC","download_json":"https://pith.science/pith/SJPQ23ZM7J3HHPHAIH4DQ6SVDC.json","view_paper":"https://pith.science/paper/SJPQ23ZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31007&json=true","fetch_graph":"https://pith.science/api/pith-number/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/graph.json","fetch_events":"https://pith.science/api/pith-number/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/action/storage_attestation","attest_author":"https://pith.science/pith/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/action/author_attestation","sign_citation":"https://pith.science/pith/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/action/citation_signature","submit_replication":"https://pith.science/pith/SJPQ23ZM7J3HHPHAIH4DQ6SVDC/action/replication_record"}},"created_at":"2026-07-01T00:17:24.061028+00:00","updated_at":"2026-07-01T00:17:24.061028+00:00"}