{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7QCVV6OYHBG4HGNPKXMQLTNGOF","short_pith_number":"pith:7QCVV6OY","schema_version":"1.0","canonical_sha256":"fc055af9d8384dc399af55d905cda67162a71b357d5eca23ca214bbc2ff5d77e","source":{"kind":"arxiv","id":"2407.21284","version":1},"attestation_state":"computed","paper":{"title":"Robust Box Prompt based SAM for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong Ni, Fajin Dong, Han Zhou, Haoran Dou, Xin Yang, Yan Cao, Yuhao Huang","submitted_at":"2024-07-31T02:16:28Z","abstract_excerpt":"The Segment Anything Model (SAM) can achieve satisfactory segmentation performance under high-quality box prompts. However, SAM's robustness is compromised by the decline in box quality, limiting its practicality in clinical reality. In this study, we propose a novel Robust Box prompt based SAM (\\textbf{RoBox-SAM}) to ensure SAM's segmentation performance under prompts with different qualities. Our contribution is three-fold. First, we propose a prompt refinement module to implicitly perceive the potential targets, and output the offsets to directly transform the low-quality box prompt into 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":"2407.21284","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T02:16:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"822084dcefe367474e8e8b6bc3c27b07166aa1c391ff183a4246e6524b8361cd","abstract_canon_sha256":"08f73112711d6fe544b0b24f6a379e796cde4b34730b225c9dc3e1f907786330"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:37.030257Z","signature_b64":"FUO/elY/syj2TwHdTiBtvF83WJTrbxF3pplJw+0hBkcKPKP1kbjLehsaMh/X00ZrmlpLDm7UswOZom8tfZaFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc055af9d8384dc399af55d905cda67162a71b357d5eca23ca214bbc2ff5d77e","last_reissued_at":"2026-07-05T08:50:37.029857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:37.029857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Box Prompt based SAM for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dong Ni, Fajin Dong, Han Zhou, Haoran Dou, Xin Yang, Yan Cao, Yuhao Huang","submitted_at":"2024-07-31T02:16:28Z","abstract_excerpt":"The Segment Anything Model (SAM) can achieve satisfactory segmentation performance under high-quality box prompts. However, SAM's robustness is compromised by the decline in box quality, limiting its practicality in clinical reality. In this study, we propose a novel Robust Box prompt based SAM (\\textbf{RoBox-SAM}) to ensure SAM's segmentation performance under prompts with different qualities. Our contribution is three-fold. First, we propose a prompt refinement module to implicitly perceive the potential targets, and output the offsets to directly transform the low-quality box prompt into a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21284","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/2407.21284/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":"2407.21284","created_at":"2026-07-05T08:50:37.029918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21284v1","created_at":"2026-07-05T08:50:37.029918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21284","created_at":"2026-07-05T08:50:37.029918+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QCVV6OYHBG4","created_at":"2026-07-05T08:50:37.029918+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QCVV6OYHBG4HGNP","created_at":"2026-07-05T08:50:37.029918+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QCVV6OY","created_at":"2026-07-05T08:50:37.029918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09562","citing_title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF","json":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF.json","graph_json":"https://pith.science/api/pith-number/7QCVV6OYHBG4HGNPKXMQLTNGOF/graph.json","events_json":"https://pith.science/api/pith-number/7QCVV6OYHBG4HGNPKXMQLTNGOF/events.json","paper":"https://pith.science/paper/7QCVV6OY"},"agent_actions":{"view_html":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF","download_json":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF.json","view_paper":"https://pith.science/paper/7QCVV6OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21284&json=true","fetch_graph":"https://pith.science/api/pith-number/7QCVV6OYHBG4HGNPKXMQLTNGOF/graph.json","fetch_events":"https://pith.science/api/pith-number/7QCVV6OYHBG4HGNPKXMQLTNGOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF/action/storage_attestation","attest_author":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF/action/author_attestation","sign_citation":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF/action/citation_signature","submit_replication":"https://pith.science/pith/7QCVV6OYHBG4HGNPKXMQLTNGOF/action/replication_record"}},"created_at":"2026-07-05T08:50:37.029918+00:00","updated_at":"2026-07-05T08:50:37.029918+00:00"}