{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6WXNNOTZEMQDLDDADAKGEL3TYJ","short_pith_number":"pith:6WXNNOTZ","schema_version":"1.0","canonical_sha256":"f5aed6ba792320358c601814622f73c26001aadd98cdc53f1e765e48bacd8fb3","source":{"kind":"arxiv","id":"2408.04579","version":2},"attestation_state":"computed","paper":{"title":"SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: 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":"Ankang Lu, Chaotao Ding, Chunan Yu, Deyi Ji, Lanyun Zhu, Lingyun Sun, Papa Mao, Tianrun Chen, Ying Zang, Zejian Li","submitted_at":"2024-08-08T16:40:15Z","abstract_excerpt":"The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2), a successor with enhanced architecture and a larger t"},"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":"2408.04579","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-08T16:40:15Z","cross_cats_sorted":[],"title_canon_sha256":"57919e62959d2bb4dfff0e0697af1a3e115e2488c28a601d7e7268b1dbadb3cf","abstract_canon_sha256":"0a923da3ae1429eadd307458178fe10fb36551652b85e9a39be25f9bbf992b9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:17.282552Z","signature_b64":"Dhx5LlWcQMN6eGQ5/Tss78UqcawnYAmxYtLV7o+YTeKJDGC+vk8d9hD0FI6kvpUMEENYCbDvruscDZL7I6exAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5aed6ba792320358c601814622f73c26001aadd98cdc53f1e765e48bacd8fb3","last_reissued_at":"2026-07-05T08:54:17.282101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:17.282101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: 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":"Ankang Lu, Chaotao Ding, Chunan Yu, Deyi Ji, Lanyun Zhu, Lingyun Sun, Papa Mao, Tianrun Chen, Ying Zang, Zejian Li","submitted_at":"2024-08-08T16:40:15Z","abstract_excerpt":"The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2), a successor with enhanced architecture and a larger t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04579","kind":"arxiv","version":2},"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/2408.04579/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":"2408.04579","created_at":"2026-07-05T08:54:17.282157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04579v2","created_at":"2026-07-05T08:54:17.282157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04579","created_at":"2026-07-05T08:54:17.282157+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WXNNOTZEMQD","created_at":"2026-07-05T08:54:17.282157+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WXNNOTZEMQDLDDA","created_at":"2026-07-05T08:54:17.282157+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WXNNOTZ","created_at":"2026-07-05T08:54:17.282157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23486","citing_title":"From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08906","citing_title":"DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24893","citing_title":"BED-SAM2: Boundary-Enhanced-Depth SAM2 via Monocular Geometric Priors","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11760","citing_title":"M$^4$-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detection","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12380","citing_title":"Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07674","citing_title":"Weight Group-wise Post-Training Quantization for Medical Foundation Model","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ","json":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ.json","graph_json":"https://pith.science/api/pith-number/6WXNNOTZEMQDLDDADAKGEL3TYJ/graph.json","events_json":"https://pith.science/api/pith-number/6WXNNOTZEMQDLDDADAKGEL3TYJ/events.json","paper":"https://pith.science/paper/6WXNNOTZ"},"agent_actions":{"view_html":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ","download_json":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ.json","view_paper":"https://pith.science/paper/6WXNNOTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04579&json=true","fetch_graph":"https://pith.science/api/pith-number/6WXNNOTZEMQDLDDADAKGEL3TYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6WXNNOTZEMQDLDDADAKGEL3TYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ/action/storage_attestation","attest_author":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ/action/author_attestation","sign_citation":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ/action/citation_signature","submit_replication":"https://pith.science/pith/6WXNNOTZEMQDLDDADAKGEL3TYJ/action/replication_record"}},"created_at":"2026-07-05T08:54:17.282157+00:00","updated_at":"2026-07-05T08:54:17.282157+00:00"}