{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WNON2GELZDGLWLN7DSO4GK2GSZ","short_pith_number":"pith:WNON2GEL","schema_version":"1.0","canonical_sha256":"b35cdd188bc8ccbb2dbf1c9dc32b4696561e0bcae37ba9e9cd1c9836b00a459c","source":{"kind":"arxiv","id":"2503.04826","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Haiyue Zu, Heting Xiao, Huilin Yang, Jiayi Ni, Jile Xie, Jun Ge, Junjie Niu, Li Ni, Linlin Zhang, Yifan Meng, Zhangzhe Zhou","submitted_at":"2025-03-05T06:12:13Z","abstract_excerpt":"The reliance on large labeled datasets presents a significant challenge in medical image segmentation. Few-shot learning offers a potential solution, but existing methods often still require substantial training data. This paper proposes a novel approach that leverages the Segment Anything Model 2 (SAM2), a vision foundation model with strong video segmentation capabilities. We conceptualize 3D medical image volumes as video sequences, departing from the traditional slice-by-slice paradigm. Our core innovation is a support-query matching strategy: we perform extensive data augmentation on a si"},"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":"2503.04826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-03-05T06:12:13Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0431cc21552e7f47c4af7c3bb8b1ad2130c800bc331ebc112f92914775b9b98c","abstract_canon_sha256":"bc18a60ba2a7e0d747d7b99a2c8a8627613fba7523a72826ca8981a494a8922f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:49.950700Z","signature_b64":"25B1nk9GITsCMg4Aq/XwEnL2TOgjNmu6/GOTMhDKxi0uuz//ko0JiPlAcQ+F2WOIJ04m187Z20eQJmY5ZgViAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b35cdd188bc8ccbb2dbf1c9dc32b4696561e0bcae37ba9e9cd1c9836b00a459c","last_reissued_at":"2026-07-05T10:25:49.949872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:49.949872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Few-Shot Medical Image Segmentation by SAM2: A Training-Free Framework with Augmentative Prompting and Dynamic Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Haiyue Zu, Heting Xiao, Huilin Yang, Jiayi Ni, Jile Xie, Jun Ge, Junjie Niu, Li Ni, Linlin Zhang, Yifan Meng, Zhangzhe Zhou","submitted_at":"2025-03-05T06:12:13Z","abstract_excerpt":"The reliance on large labeled datasets presents a significant challenge in medical image segmentation. Few-shot learning offers a potential solution, but existing methods often still require substantial training data. This paper proposes a novel approach that leverages the Segment Anything Model 2 (SAM2), a vision foundation model with strong video segmentation capabilities. We conceptualize 3D medical image volumes as video sequences, departing from the traditional slice-by-slice paradigm. Our core innovation is a support-query matching strategy: we perform extensive data augmentation on a si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04826","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/2503.04826/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":"2503.04826","created_at":"2026-07-05T10:25:49.949976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04826v1","created_at":"2026-07-05T10:25:49.949976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04826","created_at":"2026-07-05T10:25:49.949976+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNON2GELZDGL","created_at":"2026-07-05T10:25:49.949976+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNON2GELZDGLWLN7","created_at":"2026-07-05T10:25:49.949976+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNON2GEL","created_at":"2026-07-05T10:25:49.949976+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17451","citing_title":"SegTTA: Training-Free Test-Time Augmentation for Zero-Shot Medical Imaging Segmentation","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ","json":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ.json","graph_json":"https://pith.science/api/pith-number/WNON2GELZDGLWLN7DSO4GK2GSZ/graph.json","events_json":"https://pith.science/api/pith-number/WNON2GELZDGLWLN7DSO4GK2GSZ/events.json","paper":"https://pith.science/paper/WNON2GEL"},"agent_actions":{"view_html":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ","download_json":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ.json","view_paper":"https://pith.science/paper/WNON2GEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04826&json=true","fetch_graph":"https://pith.science/api/pith-number/WNON2GELZDGLWLN7DSO4GK2GSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WNON2GELZDGLWLN7DSO4GK2GSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ/action/storage_attestation","attest_author":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ/action/author_attestation","sign_citation":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ/action/citation_signature","submit_replication":"https://pith.science/pith/WNON2GELZDGLWLN7DSO4GK2GSZ/action/replication_record"}},"created_at":"2026-07-05T10:25:49.949976+00:00","updated_at":"2026-07-05T10:25:49.949976+00:00"}