{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z6VMXML5EC34RDFGX7GWNYSKJH","short_pith_number":"pith:Z6VMXML5","schema_version":"1.0","canonical_sha256":"cfaacbb17d20b7c88ca6bfcd66e24a49cca0bafa1f5322782254c05758fd0eba","source":{"kind":"arxiv","id":"2605.18853","version":1},"attestation_state":"computed","paper":{"title":"INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Ahmed \\v{S}abanovi\\'c, Ivona Brandi\\'c, Paul Joe Maliakel","submitted_at":"2026-05-13T12:44:10Z","abstract_excerpt":"Edge deployment of Vision-Language Models (VLMs) faces a tradeoff between latency and accuracy: cloud execution provides high-quality predictions but incurs communication delay and energy cost, while edge-only execution is faster but less accurate due to limited model capacity. This trade-off is further complicated by heterogeneity in image quality and reasoning complexity, making static placement suboptimal. We present INAR-VL, a lightweight edge-cloud routing system for multimodal inference in a two-tier deployment. INAR-VL maintains complementary VLMs across edge and cloud and uses lightwei"},"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":"2605.18853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T12:44:10Z","cross_cats_sorted":["cs.CV","cs.DC"],"title_canon_sha256":"bb0cb5fd4d0d462b23f9d3de99b13fd23201898aca0e153905e42983319ff2fa","abstract_canon_sha256":"8556ca505a6ce32cb13ba4322e620f8a368396e8b1c4d73f001bc740dc10beed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:25.771675Z","signature_b64":"VFrUiz41kidDbLDdmwTUfZutQKqUGgzk9sEmFSbdWE+DVpEUbUkZqvbnmZEXrxA+9LE3AnmAQBNvK/FIwIZsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfaacbb17d20b7c88ca6bfcd66e24a49cca0bafa1f5322782254c05758fd0eba","last_reissued_at":"2026-05-20T00:06:25.770923Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:25.770923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.DC"],"primary_cat":"cs.LG","authors_text":"Ahmed \\v{S}abanovi\\'c, Ivona Brandi\\'c, Paul Joe Maliakel","submitted_at":"2026-05-13T12:44:10Z","abstract_excerpt":"Edge deployment of Vision-Language Models (VLMs) faces a tradeoff between latency and accuracy: cloud execution provides high-quality predictions but incurs communication delay and energy cost, while edge-only execution is faster but less accurate due to limited model capacity. This trade-off is further complicated by heterogeneity in image quality and reasoning complexity, making static placement suboptimal. We present INAR-VL, a lightweight edge-cloud routing system for multimodal inference in a two-tier deployment. INAR-VL maintains complementary VLMs across edge and cloud and uses lightwei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18853","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/2605.18853/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":"2605.18853","created_at":"2026-05-20T00:06:25.771048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18853v1","created_at":"2026-05-20T00:06:25.771048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18853","created_at":"2026-05-20T00:06:25.771048+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6VMXML5EC34","created_at":"2026-05-20T00:06:25.771048+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6VMXML5EC34RDFG","created_at":"2026-05-20T00:06:25.771048+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6VMXML5","created_at":"2026-05-20T00:06:25.771048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH","json":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH.json","graph_json":"https://pith.science/api/pith-number/Z6VMXML5EC34RDFGX7GWNYSKJH/graph.json","events_json":"https://pith.science/api/pith-number/Z6VMXML5EC34RDFGX7GWNYSKJH/events.json","paper":"https://pith.science/paper/Z6VMXML5"},"agent_actions":{"view_html":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH","download_json":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH.json","view_paper":"https://pith.science/paper/Z6VMXML5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18853&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6VMXML5EC34RDFGX7GWNYSKJH/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6VMXML5EC34RDFGX7GWNYSKJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH/action/storage_attestation","attest_author":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH/action/author_attestation","sign_citation":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH/action/citation_signature","submit_replication":"https://pith.science/pith/Z6VMXML5EC34RDFGX7GWNYSKJH/action/replication_record"}},"created_at":"2026-05-20T00:06:25.771048+00:00","updated_at":"2026-05-20T00:06:25.771048+00:00"}