{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RBXBAA3LPMUTOPOXQ3N6YE7RIC","short_pith_number":"pith:RBXBAA3L","schema_version":"1.0","canonical_sha256":"886e10036b7b29373dd786dbec13f1409ea8cf0bab06837bf72701a62b481ed9","source":{"kind":"arxiv","id":"2407.21596","version":1},"attestation_state":"computed","paper":{"title":"Evaluating SAM2's Role in Camouflaged Object Detection: From SAM to SAM2","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Lv Tang","submitted_at":"2024-07-31T13:32:10Z","abstract_excerpt":"The Segment Anything Model (SAM), introduced by Meta AI Research as a generic object segmentation model, quickly garnered widespread attention and significantly influenced the academic community. To extend its application to video, Meta further develops Segment Anything Model 2 (SAM2), a unified model capable of both video and image segmentation. SAM2 shows notable improvements over its predecessor in terms of applicable domains, promptable segmentation accuracy, and running speed. However, this report reveals a decline in SAM2's ability to perceive different objects in images without prompts "},"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":"2407.21596","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T13:32:10Z","cross_cats_sorted":[],"title_canon_sha256":"7c17f989b064e053c3249612afd0d790057ffce836648f7416f15ffa2cf95ee0","abstract_canon_sha256":"f8c5c738fbf2d70d83f47deb4540a0ec5f72d355770496a66090f61d3ce7d2ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:41.318910Z","signature_b64":"TPgE37SSWMegpFDZrHxE7AIwzhmIFNN4nsg/YXQT3dMjtBk+6ust/ltDiaHKWKbCvd7aHxkBXfo6sRNP6G5CDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"886e10036b7b29373dd786dbec13f1409ea8cf0bab06837bf72701a62b481ed9","last_reissued_at":"2026-07-05T08:50:41.318550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:41.318550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating SAM2's Role in Camouflaged Object Detection: From SAM to SAM2","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Li, Lv Tang","submitted_at":"2024-07-31T13:32:10Z","abstract_excerpt":"The Segment Anything Model (SAM), introduced by Meta AI Research as a generic object segmentation model, quickly garnered widespread attention and significantly influenced the academic community. To extend its application to video, Meta further develops Segment Anything Model 2 (SAM2), a unified model capable of both video and image segmentation. SAM2 shows notable improvements over its predecessor in terms of applicable domains, promptable segmentation accuracy, and running speed. However, this report reveals a decline in SAM2's ability to perceive different objects in images without prompts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21596","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/2407.21596/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":"2407.21596","created_at":"2026-07-05T08:50:41.318609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21596v1","created_at":"2026-07-05T08:50:41.318609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21596","created_at":"2026-07-05T08:50:41.318609+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBXBAA3LPMUT","created_at":"2026-07-05T08:50:41.318609+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBXBAA3LPMUTOPOX","created_at":"2026-07-05T08:50:41.318609+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBXBAA3L","created_at":"2026-07-05T08:50:41.318609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19293","citing_title":"When SAM2 Meets Video Shadow and Mirror Detection","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC","json":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC.json","graph_json":"https://pith.science/api/pith-number/RBXBAA3LPMUTOPOXQ3N6YE7RIC/graph.json","events_json":"https://pith.science/api/pith-number/RBXBAA3LPMUTOPOXQ3N6YE7RIC/events.json","paper":"https://pith.science/paper/RBXBAA3L"},"agent_actions":{"view_html":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC","download_json":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC.json","view_paper":"https://pith.science/paper/RBXBAA3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21596&json=true","fetch_graph":"https://pith.science/api/pith-number/RBXBAA3LPMUTOPOXQ3N6YE7RIC/graph.json","fetch_events":"https://pith.science/api/pith-number/RBXBAA3LPMUTOPOXQ3N6YE7RIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC/action/storage_attestation","attest_author":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC/action/author_attestation","sign_citation":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC/action/citation_signature","submit_replication":"https://pith.science/pith/RBXBAA3LPMUTOPOXQ3N6YE7RIC/action/replication_record"}},"created_at":"2026-07-05T08:50:41.318609+00:00","updated_at":"2026-07-05T08:50:41.318609+00:00"}