{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JTEWTUAENT53GWG4JK7FIR7U6V","short_pith_number":"pith:JTEWTUAE","schema_version":"1.0","canonical_sha256":"4cc969d0046cfbb358dc4abe5447f4f579b02a086e836fe6033d751bad36b088","source":{"kind":"arxiv","id":"2607.02571","version":1},"attestation_state":"computed","paper":{"title":"Dual-Adaptive SAM3: Hierarchical Routing over Low-Rank Expert Layers for Parameter-Efficient Medical Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinyue Li, Kun Wang, Qiankun Li, Yang Liu, Ying Chen","submitted_at":"2026-06-30T08:14:18Z","abstract_excerpt":"The Segment Anything Model with Concepts (SAM3) heralds a new paradigm for open-vocabulary segmentation through natural language interaction, offering significant potential for medical image analysis. However, effectively adapting such a powerful vision-language model to the diverse and nuanced domain of medical imaging remains a key challenge. Naive fine-tuning is parameter-inefficient, while standard Mixture-of-Experts (MoE) methods introduce prohibitive computational overhead, limiting their clinical applicability. To address this, we propose Dual-Adaptive SAM3 (DA-SAM3), a novel framework "},"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":"2607.02571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T08:14:18Z","cross_cats_sorted":[],"title_canon_sha256":"574c6eede41fb34b5c6c3aa6cdd86560b923d4401a79dfb51089eaf825114a50","abstract_canon_sha256":"47ebd8611a1624f4e1ee0809a50c025770a62ef9ea54dcde1824f19ee7ca3205"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T00:16:01.043182Z","signature_b64":"9hfonmlgGzfiq7PI3cL8NNXjJhVvBx1AXJG9EOHpr4GWjBSX8a+dmeZe+lGVxL/8zWR9wid4F2vLwcDQmvP6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cc969d0046cfbb358dc4abe5447f4f579b02a086e836fe6033d751bad36b088","last_reissued_at":"2026-07-07T00:16:01.042530Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T00:16:01.042530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-Adaptive SAM3: Hierarchical Routing over Low-Rank Expert Layers for Parameter-Efficient Medical Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinyue Li, Kun Wang, Qiankun Li, Yang Liu, Ying Chen","submitted_at":"2026-06-30T08:14:18Z","abstract_excerpt":"The Segment Anything Model with Concepts (SAM3) heralds a new paradigm for open-vocabulary segmentation through natural language interaction, offering significant potential for medical image analysis. However, effectively adapting such a powerful vision-language model to the diverse and nuanced domain of medical imaging remains a key challenge. Naive fine-tuning is parameter-inefficient, while standard Mixture-of-Experts (MoE) methods introduce prohibitive computational overhead, limiting their clinical applicability. To address this, we propose Dual-Adaptive SAM3 (DA-SAM3), a novel framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02571","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/2607.02571/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":"2607.02571","created_at":"2026-07-07T00:16:01.042628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02571v1","created_at":"2026-07-07T00:16:01.042628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02571","created_at":"2026-07-07T00:16:01.042628+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTEWTUAENT53","created_at":"2026-07-07T00:16:01.042628+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTEWTUAENT53GWG4","created_at":"2026-07-07T00:16:01.042628+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTEWTUAE","created_at":"2026-07-07T00:16:01.042628+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/JTEWTUAENT53GWG4JK7FIR7U6V","json":"https://pith.science/pith/JTEWTUAENT53GWG4JK7FIR7U6V.json","graph_json":"https://pith.science/api/pith-number/JTEWTUAENT53GWG4JK7FIR7U6V/graph.json","events_json":"https://pith.science/api/pith-number/JTEWTUAENT53GWG4JK7FIR7U6V/events.json","paper":"https://pith.science/paper/JTEWTUAE"},"agent_actions":{"view_html":"https://pith.science/pith/JTEWTUAENT53GWG4JK7FIR7U6V","download_json":"https://pith.science/pith/JTEWTUAENT53GWG4JK7FIR7U6V.json","view_paper":"https://pith.science/paper/JTEWTUAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02571&json=true","fetch_graph":"https://pith.science/api/pith-number/JTEWTUAENT53GWG4JK7FIR7U6V/graph.json","fetch_events":"https://pith.science/api/pith-number/JTEWTUAENT53GWG4JK7FIR7U6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTEWTUAENT53GWG4JK7FIR7U6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTEWTUAENT53GWG4JK7FIR7U6V/action/storage_attestation","attest_author":"https://pith.science/pith/JTEWTUAENT53GWG4JK7FIR7U6V/action/author_attestation","sign_citation":"https://pith.science/pith/JTEWTUAENT53GWG4JK7FIR7U6V/action/citation_signature","submit_replication":"https://pith.science/pith/JTEWTUAENT53GWG4JK7FIR7U6V/action/replication_record"}},"created_at":"2026-07-07T00:16:01.042628+00:00","updated_at":"2026-07-07T00:16:01.042628+00:00"}