{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:35KXB3UJSC3SCST6US55VNWM3N","short_pith_number":"pith:35KXB3UJ","schema_version":"1.0","canonical_sha256":"df5570ee8990b7214a7ea4bbdab6ccdb7eeb68a46910c7742b53a6fa622fde1b","source":{"kind":"arxiv","id":"2306.13731","version":1},"attestation_state":"computed","paper":{"title":"How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaowei Xu, Xinrong Hu, Yiyu Shi","submitted_at":"2023-06-23T18:34:30Z","abstract_excerpt":"The emerging scale segmentation model, Segment Anything (SAM), exhibits impressive capabilities in zero-shot segmentation for natural images. However, when applied to medical images, SAM suffers from noticeable performance drop. To make SAM a real ``foundation model\" for the computer vision community, it is critical to find an efficient way to customize SAM for medical image dataset. In this work, we propose to freeze SAM encoder and finetune a lightweight task-specific prediction head, as most of weights in SAM are contributed by the encoder. In addition, SAM is a promptable model, while prom"},"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":"2306.13731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T18:34:30Z","cross_cats_sorted":[],"title_canon_sha256":"05688d4f0012d8908fa45da33c5d636c71113333b4140ca71c9dad230cdfcd41","abstract_canon_sha256":"c64193650db4edde1ad1d6f0b4cc4ce5a5064a9c7f7efdcb44785a5a67b141fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:14.624687Z","signature_b64":"cQh0O/hLN/zh43DWTivvLR3L+/uImZsIROmWuU64mqi8zXjmzAWp6kCCItspt2t0+lQUkM+ZSzrfdCtm48XwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df5570ee8990b7214a7ea4bbdab6ccdb7eeb68a46910c7742b53a6fa622fde1b","last_reissued_at":"2026-07-05T06:24:14.624268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:14.624268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaowei Xu, Xinrong Hu, Yiyu Shi","submitted_at":"2023-06-23T18:34:30Z","abstract_excerpt":"The emerging scale segmentation model, Segment Anything (SAM), exhibits impressive capabilities in zero-shot segmentation for natural images. However, when applied to medical images, SAM suffers from noticeable performance drop. To make SAM a real ``foundation model\" for the computer vision community, it is critical to find an efficient way to customize SAM for medical image dataset. In this work, we propose to freeze SAM encoder and finetune a lightweight task-specific prediction head, as most of weights in SAM are contributed by the encoder. In addition, SAM is a promptable model, while prom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13731","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/2306.13731/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":"2306.13731","created_at":"2026-07-05T06:24:14.624333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13731v1","created_at":"2026-07-05T06:24:14.624333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13731","created_at":"2026-07-05T06:24:14.624333+00:00"},{"alias_kind":"pith_short_12","alias_value":"35KXB3UJSC3S","created_at":"2026-07-05T06:24:14.624333+00:00"},{"alias_kind":"pith_short_16","alias_value":"35KXB3UJSC3SCST6","created_at":"2026-07-05T06:24:14.624333+00:00"},{"alias_kind":"pith_short_8","alias_value":"35KXB3UJ","created_at":"2026-07-05T06:24:14.624333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06972","citing_title":"HPR-SAM: Hierarchical Probabilistic Representation Learning for Prompt-free SAM-based Medical Image Segmentation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12286","citing_title":"CellNet -- Localizing Cells using Sparse and Noisy Point Annotations","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07965","citing_title":"Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07953","citing_title":"Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26630","citing_title":"Attenuation-Resilient Alternating Optimization for Laparoscopic Liver Landmark Detection","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02458","citing_title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","ref_index":118,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N","json":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N.json","graph_json":"https://pith.science/api/pith-number/35KXB3UJSC3SCST6US55VNWM3N/graph.json","events_json":"https://pith.science/api/pith-number/35KXB3UJSC3SCST6US55VNWM3N/events.json","paper":"https://pith.science/paper/35KXB3UJ"},"agent_actions":{"view_html":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N","download_json":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N.json","view_paper":"https://pith.science/paper/35KXB3UJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13731&json=true","fetch_graph":"https://pith.science/api/pith-number/35KXB3UJSC3SCST6US55VNWM3N/graph.json","fetch_events":"https://pith.science/api/pith-number/35KXB3UJSC3SCST6US55VNWM3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N/action/storage_attestation","attest_author":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N/action/author_attestation","sign_citation":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N/action/citation_signature","submit_replication":"https://pith.science/pith/35KXB3UJSC3SCST6US55VNWM3N/action/replication_record"}},"created_at":"2026-07-05T06:24:14.624333+00:00","updated_at":"2026-07-05T06:24:14.624333+00:00"}