{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RVRYHD2RFXGU67XQ6UVLH5KVCJ","short_pith_number":"pith:RVRYHD2R","schema_version":"1.0","canonical_sha256":"8d63838f512dcd4f7ef0f52ab3f555127d78dfc1ce8007c42cc64bf0e437941c","source":{"kind":"arxiv","id":"2504.03709","version":1},"attestation_state":"computed","paper":{"title":"Ocularone-Bench: Benchmarking DNN Models on GPUs to Assist the Visually Impaired","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Arnav A Rajesh, Bhavani A Madhabhavi, Kautuk Astu, Pratham M, Suman Raj, Yogesh Simmhan","submitted_at":"2025-03-27T10:08:18Z","abstract_excerpt":"VIP navigation requires multiple DNN models for identification, posture analysis, and depth estimation to ensure safe mobility. Using a hazard vest as a unique identifier enhances visibility while selecting the right DNN model and computing device balances accuracy and real-time performance. We present Ocularone-Bench, which is a benchmark suite designed to address the lack of curated datasets for uniquely identifying individuals in crowded environments and the need for benchmarking DNN inference times on resource-constrained edge devices. The suite evaluates the accuracy-latency trade-offs of"},"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":"2504.03709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2025-03-27T10:08:18Z","cross_cats_sorted":[],"title_canon_sha256":"edecfd46ed242120a7030f387301a4ae0c9ed325efcf61b091c061b2486f1cf5","abstract_canon_sha256":"01d6fd09f196f2c2a4e2ec8c994e2d7e981e0aa8df91c5101ca27dde5b01738c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:46.828332Z","signature_b64":"nzCpnnBuy5a4ubmp8NnY0xhRuCDPt/NmbezRsPp7RqMDk+ZMMM0Vkiiq9Iz5mVGw54rOTKB4JgXP0+poqgyxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d63838f512dcd4f7ef0f52ab3f555127d78dfc1ce8007c42cc64bf0e437941c","last_reissued_at":"2026-07-05T10:44:46.827869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:46.827869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ocularone-Bench: Benchmarking DNN Models on GPUs to Assist the Visually Impaired","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Arnav A Rajesh, Bhavani A Madhabhavi, Kautuk Astu, Pratham M, Suman Raj, Yogesh Simmhan","submitted_at":"2025-03-27T10:08:18Z","abstract_excerpt":"VIP navigation requires multiple DNN models for identification, posture analysis, and depth estimation to ensure safe mobility. Using a hazard vest as a unique identifier enhances visibility while selecting the right DNN model and computing device balances accuracy and real-time performance. We present Ocularone-Bench, which is a benchmark suite designed to address the lack of curated datasets for uniquely identifying individuals in crowded environments and the need for benchmarking DNN inference times on resource-constrained edge devices. The suite evaluates the accuracy-latency trade-offs of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03709","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/2504.03709/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":"2504.03709","created_at":"2026-07-05T10:44:46.827927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03709v1","created_at":"2026-07-05T10:44:46.827927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03709","created_at":"2026-07-05T10:44:46.827927+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVRYHD2RFXGU","created_at":"2026-07-05T10:44:46.827927+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVRYHD2RFXGU67XQ","created_at":"2026-07-05T10:44:46.827927+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVRYHD2R","created_at":"2026-07-05T10:44:46.827927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20860","citing_title":"Adaptive Heuristics for Scheduling DNN Inferencing on Edge and Cloud for Personalized UAV Fleets","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ","json":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ.json","graph_json":"https://pith.science/api/pith-number/RVRYHD2RFXGU67XQ6UVLH5KVCJ/graph.json","events_json":"https://pith.science/api/pith-number/RVRYHD2RFXGU67XQ6UVLH5KVCJ/events.json","paper":"https://pith.science/paper/RVRYHD2R"},"agent_actions":{"view_html":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ","download_json":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ.json","view_paper":"https://pith.science/paper/RVRYHD2R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03709&json=true","fetch_graph":"https://pith.science/api/pith-number/RVRYHD2RFXGU67XQ6UVLH5KVCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RVRYHD2RFXGU67XQ6UVLH5KVCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ/action/storage_attestation","attest_author":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ/action/author_attestation","sign_citation":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ/action/citation_signature","submit_replication":"https://pith.science/pith/RVRYHD2RFXGU67XQ6UVLH5KVCJ/action/replication_record"}},"created_at":"2026-07-05T10:44:46.827927+00:00","updated_at":"2026-07-05T10:44:46.827927+00:00"}