{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JZSBF7S7BUREU5R6MLXLNA3PUJ","short_pith_number":"pith:JZSBF7S7","schema_version":"1.0","canonical_sha256":"4e6412fe5f0d224a763e62eeb6836fa275926735a18f35b1549fad7c1de5655d","source":{"kind":"arxiv","id":"2504.00375","version":2},"attestation_state":"computed","paper":{"title":"CamoSAM2: SAM2-oriented Prompt Auto-Refinement for Video Camouflaged Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Keren Fu, Qijun Zhao, Xin Zhang","submitted_at":"2025-04-01T02:45:17Z","abstract_excerpt":"The Segment Anything Model 2 (SAM2), a prompt-guided video foundation model, has remarkably performed in video object segmentation, drawing significant attention in the community. Due to the high similarity between camouflaged objects and their surroundings, which makes them difficult to distinguish even by the human eye, the application of SAM2 for automated segmentation in real-world scenarios faces challenges in camouflage perception and reliable prompts generation. To address these issues, we propose CamoSAM2, a motion-appearance prompt inducer (MAPI) and refinement framework to automatica"},"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":"2504.00375","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-01T02:45:17Z","cross_cats_sorted":[],"title_canon_sha256":"2a63c927f133823759e9da66abfcbe53f1c08158d64b0621e4d5e90def9f4ecd","abstract_canon_sha256":"7484b16060d07f076ddc207f0111b16c6f6ca00f73c2ad52e2a05343ad6723a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:06.143496Z","signature_b64":"dqZs6p9G/TZKBh7QyAUIAuuw8CmWxJJES/1mswbjX42FMvj5ucY0GXp5LYuCEqOM8ixJI5In/izv2cYMKsL2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e6412fe5f0d224a763e62eeb6836fa275926735a18f35b1549fad7c1de5655d","last_reissued_at":"2026-06-09T01:05:06.142954Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:06.142954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CamoSAM2: SAM2-oriented Prompt Auto-Refinement for Video Camouflaged Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Keren Fu, Qijun Zhao, Xin Zhang","submitted_at":"2025-04-01T02:45:17Z","abstract_excerpt":"The Segment Anything Model 2 (SAM2), a prompt-guided video foundation model, has remarkably performed in video object segmentation, drawing significant attention in the community. Due to the high similarity between camouflaged objects and their surroundings, which makes them difficult to distinguish even by the human eye, the application of SAM2 for automated segmentation in real-world scenarios faces challenges in camouflage perception and reliable prompts generation. To address these issues, we propose CamoSAM2, a motion-appearance prompt inducer (MAPI) and refinement framework to automatica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00375","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/2504.00375/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":"2504.00375","created_at":"2026-06-09T01:05:06.143020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00375v2","created_at":"2026-06-09T01:05:06.143020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00375","created_at":"2026-06-09T01:05:06.143020+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZSBF7S7BURE","created_at":"2026-06-09T01:05:06.143020+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZSBF7S7BUREU5R6","created_at":"2026-06-09T01:05:06.143020+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZSBF7S7","created_at":"2026-06-09T01:05:06.143020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.27499","citing_title":"Towards All-Day Perception for Off-Road Driving: A Large-Scale Multispectral Dataset and Comprehensive Benchmark","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ","json":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ.json","graph_json":"https://pith.science/api/pith-number/JZSBF7S7BUREU5R6MLXLNA3PUJ/graph.json","events_json":"https://pith.science/api/pith-number/JZSBF7S7BUREU5R6MLXLNA3PUJ/events.json","paper":"https://pith.science/paper/JZSBF7S7"},"agent_actions":{"view_html":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ","download_json":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ.json","view_paper":"https://pith.science/paper/JZSBF7S7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00375&json=true","fetch_graph":"https://pith.science/api/pith-number/JZSBF7S7BUREU5R6MLXLNA3PUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JZSBF7S7BUREU5R6MLXLNA3PUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ/action/storage_attestation","attest_author":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ/action/author_attestation","sign_citation":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ/action/citation_signature","submit_replication":"https://pith.science/pith/JZSBF7S7BUREU5R6MLXLNA3PUJ/action/replication_record"}},"created_at":"2026-06-09T01:05:06.143020+00:00","updated_at":"2026-06-09T01:05:06.143020+00:00"}