{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4CHY7GZUSIWFYRSEX5XO6APKHT","short_pith_number":"pith:4CHY7GZU","schema_version":"1.0","canonical_sha256":"e08f8f9b34922c5c4644bf6eef01ea3cc7394349ea51868e8aea2b047ab4fce5","source":{"kind":"arxiv","id":"2506.10712","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyu Fang, Chunming He, Fengyang Xiao, Sujie Hu, Xiu Li, Yifan Pu, Youwei Pang, Yuqi Shen","submitted_at":"2025-06-12T14:02:18Z","abstract_excerpt":"Camouflaged Object Detection (COD) presents inherent challenges due to the subtle visual differences between targets and their backgrounds. While existing methods have made notable progress, there remains significant potential for post-processing refinement that has yet to be fully explored. To address this limitation, we propose the Uncertainty-Masked Bernoulli Diffusion (UMBD) model, the first generative refinement framework specifically designed for COD. UMBD introduces an uncertainty-guided masking mechanism that selectively applies Bernoulli diffusion to residual regions with poor segment"},"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":"2506.10712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-12T14:02:18Z","cross_cats_sorted":[],"title_canon_sha256":"2dd38bad2d8920c94a379bf7a065198a88d479078079c3c3d52be34b34ff67ec","abstract_canon_sha256":"a606a7042673bd9c137a2b71bf67f05a82dd4d06b9af255d938740301ef2e67f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:28.971552Z","signature_b64":"albWFqXrLA3AYSW+nCeVcjO9kQltUr6Pk54KbDGKtqjh0zjKo090VhPs0ZqoaLLMrT8+/gbswfsS/n3LNDazBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e08f8f9b34922c5c4644bf6eef01ea3cc7394349ea51868e8aea2b047ab4fce5","last_reissued_at":"2026-07-05T11:20:28.971049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:28.971049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Masked Bernoulli Diffusion for Camouflaged Object Detection Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengyu Fang, Chunming He, Fengyang Xiao, Sujie Hu, Xiu Li, Yifan Pu, Youwei Pang, Yuqi Shen","submitted_at":"2025-06-12T14:02:18Z","abstract_excerpt":"Camouflaged Object Detection (COD) presents inherent challenges due to the subtle visual differences between targets and their backgrounds. While existing methods have made notable progress, there remains significant potential for post-processing refinement that has yet to be fully explored. To address this limitation, we propose the Uncertainty-Masked Bernoulli Diffusion (UMBD) model, the first generative refinement framework specifically designed for COD. UMBD introduces an uncertainty-guided masking mechanism that selectively applies Bernoulli diffusion to residual regions with poor segment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10712","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/2506.10712/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":"2506.10712","created_at":"2026-07-05T11:20:28.971106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10712v1","created_at":"2026-07-05T11:20:28.971106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10712","created_at":"2026-07-05T11:20:28.971106+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CHY7GZUSIWF","created_at":"2026-07-05T11:20:28.971106+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CHY7GZUSIWFYRSE","created_at":"2026-07-05T11:20:28.971106+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CHY7GZU","created_at":"2026-07-05T11:20:28.971106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15803","citing_title":"Embedding-perturbed Exploration Preference Optimization for Flow Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15450","citing_title":"RIDE: Retinex-Informed Decoupling for Exposing Concealed Objects","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT","json":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT.json","graph_json":"https://pith.science/api/pith-number/4CHY7GZUSIWFYRSEX5XO6APKHT/graph.json","events_json":"https://pith.science/api/pith-number/4CHY7GZUSIWFYRSEX5XO6APKHT/events.json","paper":"https://pith.science/paper/4CHY7GZU"},"agent_actions":{"view_html":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT","download_json":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT.json","view_paper":"https://pith.science/paper/4CHY7GZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10712&json=true","fetch_graph":"https://pith.science/api/pith-number/4CHY7GZUSIWFYRSEX5XO6APKHT/graph.json","fetch_events":"https://pith.science/api/pith-number/4CHY7GZUSIWFYRSEX5XO6APKHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT/action/storage_attestation","attest_author":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT/action/author_attestation","sign_citation":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT/action/citation_signature","submit_replication":"https://pith.science/pith/4CHY7GZUSIWFYRSEX5XO6APKHT/action/replication_record"}},"created_at":"2026-07-05T11:20:28.971106+00:00","updated_at":"2026-07-05T11:20:28.971106+00:00"}