{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OCRQMAD7MUPZSK64KOQK4T6DW4","short_pith_number":"pith:OCRQMAD7","schema_version":"1.0","canonical_sha256":"70a306007f651f992bdc53a0ae4fc3b735153b8144ea00a2174bcfb200903d1f","source":{"kind":"arxiv","id":"2401.13051","version":1},"attestation_state":"computed","paper":{"title":"PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Bochen Guan, Hongtao Lu, Lei Zhang, Muyang Yi, Weihao Jiang, Yue Ding, Zhaozhi Xie","submitted_at":"2024-01-23T19:20:22Z","abstract_excerpt":"The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially in real-world contexts. In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM. By exclusively training the prompt adapter, PA-SAM extracts detailed information from images and optimizes the mask decoder feature at both spars"},"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":"2401.13051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T19:20:22Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"ff21eaffddb96d43f145a569ac6a6cff8454ba89e4c32591470c9606aaf24af1","abstract_canon_sha256":"407366a5a05930716834d5f98d4ad218fbc7868984717247ffc7d032ba4237d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:59.895269Z","signature_b64":"XCGjBhV0OBtXgO5kIhhQ2S/nDkIoEDTRtq/WmJsFeGIuboElS1OHOtcybKzNa7MZiBBONeAhbtf0wqEpdtbqAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70a306007f651f992bdc53a0ae4fc3b735153b8144ea00a2174bcfb200903d1f","last_reissued_at":"2026-07-05T07:36:59.894729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:59.894729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Bochen Guan, Hongtao Lu, Lei Zhang, Muyang Yi, Weihao Jiang, Yue Ding, Zhaozhi Xie","submitted_at":"2024-01-23T19:20:22Z","abstract_excerpt":"The Segment Anything Model (SAM) has exhibited outstanding performance in various image segmentation tasks. Despite being trained with over a billion masks, SAM faces challenges in mask prediction quality in numerous scenarios, especially in real-world contexts. In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM. By exclusively training the prompt adapter, PA-SAM extracts detailed information from images and optimizes the mask decoder feature at both spars"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13051","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/2401.13051/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":"2401.13051","created_at":"2026-07-05T07:36:59.894795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13051v1","created_at":"2026-07-05T07:36:59.894795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13051","created_at":"2026-07-05T07:36:59.894795+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCRQMAD7MUPZ","created_at":"2026-07-05T07:36:59.894795+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCRQMAD7MUPZSK64","created_at":"2026-07-05T07:36:59.894795+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCRQMAD7","created_at":"2026-07-05T07:36:59.894795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02993","citing_title":"EchoONE: Segmenting Multiple echocardiography Planes in One Model","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4","json":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4.json","graph_json":"https://pith.science/api/pith-number/OCRQMAD7MUPZSK64KOQK4T6DW4/graph.json","events_json":"https://pith.science/api/pith-number/OCRQMAD7MUPZSK64KOQK4T6DW4/events.json","paper":"https://pith.science/paper/OCRQMAD7"},"agent_actions":{"view_html":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4","download_json":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4.json","view_paper":"https://pith.science/paper/OCRQMAD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13051&json=true","fetch_graph":"https://pith.science/api/pith-number/OCRQMAD7MUPZSK64KOQK4T6DW4/graph.json","fetch_events":"https://pith.science/api/pith-number/OCRQMAD7MUPZSK64KOQK4T6DW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4/action/storage_attestation","attest_author":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4/action/author_attestation","sign_citation":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4/action/citation_signature","submit_replication":"https://pith.science/pith/OCRQMAD7MUPZSK64KOQK4T6DW4/action/replication_record"}},"created_at":"2026-07-05T07:36:59.894795+00:00","updated_at":"2026-07-05T07:36:59.894795+00:00"}