{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZJIOL3NPYIB5XYBWQHMXD7W2VH","short_pith_number":"pith:ZJIOL3NP","schema_version":"1.0","canonical_sha256":"ca50e5edafc203dbe03681d971fedaa9f74d0a6649aaa414026ae5b372c23f61","source":{"kind":"arxiv","id":"2304.09148","version":3},"attestation_state":"computed","paper":{"title":"SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaotao Ding, Lanyun Zhu, Lingyun Sun, Papa Mao, Runlong Cao, Tianrun Chen, Yan Wang, Ying Zang, Zejian Li","submitted_at":"2023-04-18T17:38:54Z","abstract_excerpt":"The emergence of large models, also known as foundation models, has brought significant advancements to AI research. One such model is Segment Anything (SAM), which is designed for image segmentation tasks. However, as with other foundation models, our experimental findings suggest that SAM may fail or perform poorly in certain segmentation tasks, such as shadow detection and camouflaged object detection (concealed object detection). This study first paves the way for applying the large pre-trained image segmentation model SAM to these downstream tasks, even in situations where SAM performs po"},"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":"2304.09148","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-18T17:38:54Z","cross_cats_sorted":[],"title_canon_sha256":"5aaef4d8c77da7c4e03d7162dc49c97977332c2f229c5904f66e2e2b5b3102b8","abstract_canon_sha256":"d09a765921066ef667028af039ee9810b97a529c239adb6af67b157d5cdbea63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:18.246081Z","signature_b64":"5bJgZRP1+huAO+ImWe4ClXmYntgNFAWghA70524meY4MY387WJhtlMwx/9pJyR0qb9nb/FkFsgyoT0bLs9KBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca50e5edafc203dbe03681d971fedaa9f74d0a6649aaa414026ae5b372c23f61","last_reissued_at":"2026-07-05T06:06:18.245717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:18.245717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM Fails to Segment Anything? -- SAM-Adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaotao Ding, Lanyun Zhu, Lingyun Sun, Papa Mao, Runlong Cao, Tianrun Chen, Yan Wang, Ying Zang, Zejian Li","submitted_at":"2023-04-18T17:38:54Z","abstract_excerpt":"The emergence of large models, also known as foundation models, has brought significant advancements to AI research. One such model is Segment Anything (SAM), which is designed for image segmentation tasks. However, as with other foundation models, our experimental findings suggest that SAM may fail or perform poorly in certain segmentation tasks, such as shadow detection and camouflaged object detection (concealed object detection). This study first paves the way for applying the large pre-trained image segmentation model SAM to these downstream tasks, even in situations where SAM performs po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.09148","kind":"arxiv","version":3},"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/2304.09148/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":"2304.09148","created_at":"2026-07-05T06:06:18.245774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.09148v3","created_at":"2026-07-05T06:06:18.245774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.09148","created_at":"2026-07-05T06:06:18.245774+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJIOL3NPYIB5","created_at":"2026-07-05T06:06:18.245774+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJIOL3NPYIB5XYBW","created_at":"2026-07-05T06:06:18.245774+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJIOL3NP","created_at":"2026-07-05T06:06:18.245774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24807","citing_title":"CLIP-Guided SAM: Parameter-Efficient Semantic Conditioning for Promptable Segmentation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04960","citing_title":"On Efficient Variants of Segment Anything Model: A Survey","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02018","citing_title":"Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22825","citing_title":"SGP-SAM: Self-Gated Prompting for Transferring 3D Segment Anything Models to Lesion Segmentation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20748","citing_title":"Amodal SAM: A Unified Amodal Segmentation Framework with Generalization","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH","json":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH.json","graph_json":"https://pith.science/api/pith-number/ZJIOL3NPYIB5XYBWQHMXD7W2VH/graph.json","events_json":"https://pith.science/api/pith-number/ZJIOL3NPYIB5XYBWQHMXD7W2VH/events.json","paper":"https://pith.science/paper/ZJIOL3NP"},"agent_actions":{"view_html":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH","download_json":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH.json","view_paper":"https://pith.science/paper/ZJIOL3NP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.09148&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJIOL3NPYIB5XYBWQHMXD7W2VH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJIOL3NPYIB5XYBWQHMXD7W2VH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH/action/storage_attestation","attest_author":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH/action/author_attestation","sign_citation":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH/action/citation_signature","submit_replication":"https://pith.science/pith/ZJIOL3NPYIB5XYBWQHMXD7W2VH/action/replication_record"}},"created_at":"2026-07-05T06:06:18.245774+00:00","updated_at":"2026-07-05T06:06:18.245774+00:00"}