{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A4A7RCFIHXRTUXEV7BUM2MSRON","short_pith_number":"pith:A4A7RCFI","schema_version":"1.0","canonical_sha256":"0701f888a83de33a5c95f868cd3251735381a25534e844695cfd09000368ac5f","source":{"kind":"arxiv","id":"2312.05760","version":2},"attestation_state":"computed","paper":{"title":"RepViT-SAM: Towards Real-Time Segmenting Anything","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ao Wang, Guiguang Ding, Hui Chen, Jungong Han, Zijia Lin","submitted_at":"2023-12-10T04:42:56Z","abstract_excerpt":"Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting for practical applications. MobileSAM proposes to replace the heavyweight image encoder in SAM with TinyViT by employing distillation, which results in a significant reduction in computational requirements. However, its deployment on resource-constrained mobile devices still encounters challenges due to the substantial memory and computational overhead caused by self-attention mechanisms. Recently, RepViT achieves the "},"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":"2312.05760","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-10T04:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"42ef0128cb5619b651b0226405b9a1aa511837a56fd2d7aaa96edbee9ca285aa","abstract_canon_sha256":"40e4d0d069933250a88271a43e1dfa00d4972bac63c178b87b82de85b4db9203"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:22.462025Z","signature_b64":"0ghncT+Yn/YHwm7vBgfS+CPhTA9U64wx+PH60GSpE8J6onDoq0kWSvPchjTG/RVWywdCS9pkT+nr5yyd3EuyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0701f888a83de33a5c95f868cd3251735381a25534e844695cfd09000368ac5f","last_reissued_at":"2026-07-05T07:50:22.461406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:22.461406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepViT-SAM: Towards Real-Time Segmenting Anything","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ao Wang, Guiguang Ding, Hui Chen, Jungong Han, Zijia Lin","submitted_at":"2023-12-10T04:42:56Z","abstract_excerpt":"Segment Anything Model (SAM) has shown impressive zero-shot transfer performance for various computer vision tasks recently. However, its heavy computation costs remain daunting for practical applications. MobileSAM proposes to replace the heavyweight image encoder in SAM with TinyViT by employing distillation, which results in a significant reduction in computational requirements. However, its deployment on resource-constrained mobile devices still encounters challenges due to the substantial memory and computational overhead caused by self-attention mechanisms. Recently, RepViT achieves the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05760","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/2312.05760/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":"2312.05760","created_at":"2026-07-05T07:50:22.461481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05760v2","created_at":"2026-07-05T07:50:22.461481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05760","created_at":"2026-07-05T07:50:22.461481+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4A7RCFIHXRT","created_at":"2026-07-05T07:50:22.461481+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4A7RCFIHXRTUXEV","created_at":"2026-07-05T07:50:22.461481+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4A7RCFI","created_at":"2026-07-05T07:50:22.461481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08992","citing_title":"SpaceVLN: A Zero-Shot Vision-and-Language Navigation Agent with Online Spatial Cognitive Memory and Reasoning","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04960","citing_title":"On Efficient Variants of Segment Anything Model: A Survey","ref_index":113,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON","json":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON.json","graph_json":"https://pith.science/api/pith-number/A4A7RCFIHXRTUXEV7BUM2MSRON/graph.json","events_json":"https://pith.science/api/pith-number/A4A7RCFIHXRTUXEV7BUM2MSRON/events.json","paper":"https://pith.science/paper/A4A7RCFI"},"agent_actions":{"view_html":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON","download_json":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON.json","view_paper":"https://pith.science/paper/A4A7RCFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05760&json=true","fetch_graph":"https://pith.science/api/pith-number/A4A7RCFIHXRTUXEV7BUM2MSRON/graph.json","fetch_events":"https://pith.science/api/pith-number/A4A7RCFIHXRTUXEV7BUM2MSRON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON/action/storage_attestation","attest_author":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON/action/author_attestation","sign_citation":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON/action/citation_signature","submit_replication":"https://pith.science/pith/A4A7RCFIHXRTUXEV7BUM2MSRON/action/replication_record"}},"created_at":"2026-07-05T07:50:22.461481+00:00","updated_at":"2026-07-05T07:50:22.461481+00:00"}