{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K3LCTZDN5GZNFBE3MVDC4OBCB2","short_pith_number":"pith:K3LCTZDN","schema_version":"1.0","canonical_sha256":"56d629e46de9b2d2849b65462e38220eb8deef114aa0d897c95bbf896dfc06cc","source":{"kind":"arxiv","id":"2312.00863","version":1},"attestation_state":"computed","paper":{"title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bala Varadarajan, Chenchen Zhu, Dilin Wang, Fanyi Xiao, Fei Sun, Forrest Iandola, Lemeng Wu, Raghuraman Krishnamoorthi, Vikas Chandra, Xiaoliang Dai, Xiaoyu Xiang, Yunyang Xiong","submitted_at":"2023-12-01T18:31:00Z","abstract_excerpt":"Segment Anything Model (SAM) has emerged as a powerful tool for numerous vision applications. A key component that drives the impressive performance for zero-shot transfer and high versatility is a super large Transformer model trained on the extensive high-quality SA-1B dataset. While beneficial, the huge computation cost of SAM model has limited its applications to wider real-world applications. To address this limitation, we propose EfficientSAMs, light-weight SAM models that exhibits decent performance with largely reduced complexity. Our idea is based on leveraging masked image pretrainin"},"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":"2312.00863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:31:00Z","cross_cats_sorted":[],"title_canon_sha256":"cdca47a94e81f528193cb30612c413d1b77d06159d9d3fc197d3de61128cb122","abstract_canon_sha256":"ba3659c9d04d9d62867ae6ba5a64be48df9b24a3a29acc87f2b31d4c2fdf6ee2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:25.599877Z","signature_b64":"M8xxp3yxaJUM45LYU1U9M5/Xz7yiXTutKSav7huBxFn+d/uQ79czbA4Hty1uCCxBmiELJHUrqotIzdHsjPqODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56d629e46de9b2d2849b65462e38220eb8deef114aa0d897c95bbf896dfc06cc","last_reissued_at":"2026-07-05T07:19:25.599373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:25.599373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bala Varadarajan, Chenchen Zhu, Dilin Wang, Fanyi Xiao, Fei Sun, Forrest Iandola, Lemeng Wu, Raghuraman Krishnamoorthi, Vikas Chandra, Xiaoliang Dai, Xiaoyu Xiang, Yunyang Xiong","submitted_at":"2023-12-01T18:31:00Z","abstract_excerpt":"Segment Anything Model (SAM) has emerged as a powerful tool for numerous vision applications. A key component that drives the impressive performance for zero-shot transfer and high versatility is a super large Transformer model trained on the extensive high-quality SA-1B dataset. While beneficial, the huge computation cost of SAM model has limited its applications to wider real-world applications. To address this limitation, we propose EfficientSAMs, light-weight SAM models that exhibits decent performance with largely reduced complexity. Our idea is based on leveraging masked image pretrainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00863","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/2312.00863/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":"2312.00863","created_at":"2026-07-05T07:19:25.599438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00863v1","created_at":"2026-07-05T07:19:25.599438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00863","created_at":"2026-07-05T07:19:25.599438+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3LCTZDN5GZN","created_at":"2026-07-05T07:19:25.599438+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3LCTZDN5GZNFBE3","created_at":"2026-07-05T07:19:25.599438+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3LCTZDN","created_at":"2026-07-05T07:19:25.599438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17633","citing_title":"SparseSAM: Structured Sparsification of Activations in Segment Anything Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02018","citing_title":"Towards Any-Quality Image Segmentation via Generative and Adaptive Latent Space Enhancement","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27128","citing_title":"Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2","json":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2.json","graph_json":"https://pith.science/api/pith-number/K3LCTZDN5GZNFBE3MVDC4OBCB2/graph.json","events_json":"https://pith.science/api/pith-number/K3LCTZDN5GZNFBE3MVDC4OBCB2/events.json","paper":"https://pith.science/paper/K3LCTZDN"},"agent_actions":{"view_html":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2","download_json":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2.json","view_paper":"https://pith.science/paper/K3LCTZDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00863&json=true","fetch_graph":"https://pith.science/api/pith-number/K3LCTZDN5GZNFBE3MVDC4OBCB2/graph.json","fetch_events":"https://pith.science/api/pith-number/K3LCTZDN5GZNFBE3MVDC4OBCB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2/action/storage_attestation","attest_author":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2/action/author_attestation","sign_citation":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2/action/citation_signature","submit_replication":"https://pith.science/pith/K3LCTZDN5GZNFBE3MVDC4OBCB2/action/replication_record"}},"created_at":"2026-07-05T07:19:25.599438+00:00","updated_at":"2026-07-05T07:19:25.599438+00:00"}