{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ADXZJEXZ26JQQIGOBVBBGFTRGK","short_pith_number":"pith:ADXZJEXZ","schema_version":"1.0","canonical_sha256":"00ef9492f9d7930820ce0d4213167132adb9696beb8a30236f823d25ed252c01","source":{"kind":"arxiv","id":"2402.05981","version":2},"attestation_state":"computed","paper":{"title":"Anatomizing Deep Learning Inference in Web Browsers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Aoyu Li, Qipeng Wang, Shiqi Jiang, Ting Cao, Xuanzhe Liu, Xu Cao, Yuanchun Li, Yun Ma, Zhenpeng Chen","submitted_at":"2024-02-08T08:02:57Z","abstract_excerpt":"Web applications have increasingly adopted Deep Learning (DL) through in-browser inference, wherein DL inference performs directly within Web browsers. The actual performance of in-browser inference and its impacts on the quality of experience (QoE) remain unexplored, and urgently require new QoE measurements beyond traditional ones, e.g., mainly focusing on page load time. To bridge this gap, we make the first comprehensive performance measurement of in-browser inference to date. Our approach proposes new metrics to measure in-browser inference: responsiveness, smoothness, and inference accur"},"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":"2402.05981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T08:02:57Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"bbd413d97b212de6e936a3fd151ac8a3f35269c88e0a071bde17bdebc0c7bb84","abstract_canon_sha256":"f8187d2033d7a30610cbbbf96b00283543ad349fc2583748a0be1f73678b37cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:31.208168Z","signature_b64":"B6lA5Xbth4GT/R6T6JkSRtIIzAwGTN0lcQEzFdnLMfvqMdBIwlDgucp+XHNY1/C1hbbD0diOAUQ4cIa1oYZNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00ef9492f9d7930820ce0d4213167132adb9696beb8a30236f823d25ed252c01","last_reissued_at":"2026-07-05T08:48:31.207781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:31.207781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Anatomizing Deep Learning Inference in Web Browsers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Aoyu Li, Qipeng Wang, Shiqi Jiang, Ting Cao, Xuanzhe Liu, Xu Cao, Yuanchun Li, Yun Ma, Zhenpeng Chen","submitted_at":"2024-02-08T08:02:57Z","abstract_excerpt":"Web applications have increasingly adopted Deep Learning (DL) through in-browser inference, wherein DL inference performs directly within Web browsers. The actual performance of in-browser inference and its impacts on the quality of experience (QoE) remain unexplored, and urgently require new QoE measurements beyond traditional ones, e.g., mainly focusing on page load time. To bridge this gap, we make the first comprehensive performance measurement of in-browser inference to date. Our approach proposes new metrics to measure in-browser inference: responsiveness, smoothness, and inference accur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05981","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/2402.05981/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":"2402.05981","created_at":"2026-07-05T08:48:31.207836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05981v2","created_at":"2026-07-05T08:48:31.207836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05981","created_at":"2026-07-05T08:48:31.207836+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADXZJEXZ26JQ","created_at":"2026-07-05T08:48:31.207836+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADXZJEXZ26JQQIGO","created_at":"2026-07-05T08:48:31.207836+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADXZJEXZ","created_at":"2026-07-05T08:48:31.207836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08821","citing_title":"DejAIvu: Identifying and Explaining AI Art on the Web in Real-Time with Saliency Maps","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK","json":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK.json","graph_json":"https://pith.science/api/pith-number/ADXZJEXZ26JQQIGOBVBBGFTRGK/graph.json","events_json":"https://pith.science/api/pith-number/ADXZJEXZ26JQQIGOBVBBGFTRGK/events.json","paper":"https://pith.science/paper/ADXZJEXZ"},"agent_actions":{"view_html":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK","download_json":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK.json","view_paper":"https://pith.science/paper/ADXZJEXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05981&json=true","fetch_graph":"https://pith.science/api/pith-number/ADXZJEXZ26JQQIGOBVBBGFTRGK/graph.json","fetch_events":"https://pith.science/api/pith-number/ADXZJEXZ26JQQIGOBVBBGFTRGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK/action/storage_attestation","attest_author":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK/action/author_attestation","sign_citation":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK/action/citation_signature","submit_replication":"https://pith.science/pith/ADXZJEXZ26JQQIGOBVBBGFTRGK/action/replication_record"}},"created_at":"2026-07-05T08:48:31.207836+00:00","updated_at":"2026-07-05T08:48:31.207836+00:00"}