{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TH67IREWBVJ2TTX2T6VZ6WLYTW","short_pith_number":"pith:TH67IREW","schema_version":"1.0","canonical_sha256":"99fdf444960d53a9cefa9fab9f59789da948824987234e17645af40c3424818d","source":{"kind":"arxiv","id":"2411.18858","version":1},"attestation_state":"computed","paper":{"title":"COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deng-Ping Fan, Guobao Xiao, Li Zhao, Xiaoqin Zhang, Zhenni Yu","submitted_at":"2024-11-28T01:58:28Z","abstract_excerpt":"We rethink the segment anything model (SAM) and propose a novel multiprompt network called COMPrompter for camouflaged object detection (COD). SAM has zero-shot generalization ability beyond other models and can provide an ideal framework for COD. Our network aims to enhance the single prompt strategy in SAM to a multiprompt strategy. To achieve this, we propose an edge gradient extraction module, which generates a mask containing gradient information regarding the boundaries of camouflaged objects. This gradient mask is then used as a novel boundary prompt, enhancing the segmentation process."},"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":"2411.18858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T01:58:28Z","cross_cats_sorted":[],"title_canon_sha256":"6a592527a41f09ed780130fbd655b6e14c98b9f6a4d3aa95fa563ecd59c1d37e","abstract_canon_sha256":"f1e4c0d7258720a836c2437f9ae5bbfbaef94c15f9a4a68f233c50fbbd02ee12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:52.660458Z","signature_b64":"CDhMD5H5J51XI/w2taJmIM7b2q/y23DzhJcSKC3gkdps11b16av4NBHN8NZtw+wW1/aAKEtnfDQJXkg4+5opAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99fdf444960d53a9cefa9fab9f59789da948824987234e17645af40c3424818d","last_reissued_at":"2026-07-05T09:41:52.660092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:52.660092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COMPrompter: reconceptualized segment anything model with multiprompt network for camouflaged object detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deng-Ping Fan, Guobao Xiao, Li Zhao, Xiaoqin Zhang, Zhenni Yu","submitted_at":"2024-11-28T01:58:28Z","abstract_excerpt":"We rethink the segment anything model (SAM) and propose a novel multiprompt network called COMPrompter for camouflaged object detection (COD). SAM has zero-shot generalization ability beyond other models and can provide an ideal framework for COD. Our network aims to enhance the single prompt strategy in SAM to a multiprompt strategy. To achieve this, we propose an edge gradient extraction module, which generates a mask containing gradient information regarding the boundaries of camouflaged objects. This gradient mask is then used as a novel boundary prompt, enhancing the segmentation process."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18858","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/2411.18858/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":"2411.18858","created_at":"2026-07-05T09:41:52.660146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18858v1","created_at":"2026-07-05T09:41:52.660146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18858","created_at":"2026-07-05T09:41:52.660146+00:00"},{"alias_kind":"pith_short_12","alias_value":"TH67IREWBVJ2","created_at":"2026-07-05T09:41:52.660146+00:00"},{"alias_kind":"pith_short_16","alias_value":"TH67IREWBVJ2TTX2","created_at":"2026-07-05T09:41:52.660146+00:00"},{"alias_kind":"pith_short_8","alias_value":"TH67IREW","created_at":"2026-07-05T09:41:52.660146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09562","citing_title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","ref_index":77,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW","json":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW.json","graph_json":"https://pith.science/api/pith-number/TH67IREWBVJ2TTX2T6VZ6WLYTW/graph.json","events_json":"https://pith.science/api/pith-number/TH67IREWBVJ2TTX2T6VZ6WLYTW/events.json","paper":"https://pith.science/paper/TH67IREW"},"agent_actions":{"view_html":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW","download_json":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW.json","view_paper":"https://pith.science/paper/TH67IREW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18858&json=true","fetch_graph":"https://pith.science/api/pith-number/TH67IREWBVJ2TTX2T6VZ6WLYTW/graph.json","fetch_events":"https://pith.science/api/pith-number/TH67IREWBVJ2TTX2T6VZ6WLYTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW/action/storage_attestation","attest_author":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW/action/author_attestation","sign_citation":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW/action/citation_signature","submit_replication":"https://pith.science/pith/TH67IREWBVJ2TTX2T6VZ6WLYTW/action/replication_record"}},"created_at":"2026-07-05T09:41:52.660146+00:00","updated_at":"2026-07-05T09:41:52.660146+00:00"}