{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QZOC67LFTBPBMVYKDEGIK3IXLR","short_pith_number":"pith:QZOC67LF","schema_version":"1.0","canonical_sha256":"865c2f7d65985e16570a190c856d175c46f403165ae548b2a132356f47f074f5","source":{"kind":"arxiv","id":"2607.17415","version":1},"attestation_state":"computed","paper":{"title":"Transition-Aware Backend Dispatch for Edge LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Alaaddin Goktug Ayar, Martin Margala","submitted_at":"2026-07-19T21:22:22Z","abstract_excerpt":"Efficient large language model (LLM) inference on edge platforms is limited not only by model size, but also by shape-dependent performance differences across execution backends. Static backend assignment cannot exploit this variation, while independent per-operator selection can introduce costly device and framework switches. This paper presents a transition-aware backend dispatch approach for edge transformer inference. The approach combines current operator features with the previously selected backend to preserve beneficial shape-specific choices while avoiding unnecessary transitions. Ord"},"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":"2607.17415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-07-19T21:22:22Z","cross_cats_sorted":[],"title_canon_sha256":"fc73bd3ba8be29b1dd473fb3f69d0c28ac5d813821cb5a7e408478ef662810cd","abstract_canon_sha256":"22381d9ebdf434a075f93101f88916f85c5f0e7d3a2c96e23e704baef24056d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:31.838599Z","signature_b64":"MWrpp7tD8HxNtL5GVJ6XQi5QPQU+LT3fTcicGK7Ybhj+Go5MehuDiOUmqwYZjw11LneoARS+mLwiCkhRSTm8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"865c2f7d65985e16570a190c856d175c46f403165ae548b2a132356f47f074f5","last_reissued_at":"2026-07-21T01:21:31.837714Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:31.837714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transition-Aware Backend Dispatch for Edge LLM Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Alaaddin Goktug Ayar, Martin Margala","submitted_at":"2026-07-19T21:22:22Z","abstract_excerpt":"Efficient large language model (LLM) inference on edge platforms is limited not only by model size, but also by shape-dependent performance differences across execution backends. Static backend assignment cannot exploit this variation, while independent per-operator selection can introduce costly device and framework switches. This paper presents a transition-aware backend dispatch approach for edge transformer inference. The approach combines current operator features with the previously selected backend to preserve beneficial shape-specific choices while avoiding unnecessary transitions. Ord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17415","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/2607.17415/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":"2607.17415","created_at":"2026-07-21T01:21:31.838175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17415v1","created_at":"2026-07-21T01:21:31.838175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17415","created_at":"2026-07-21T01:21:31.838175+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZOC67LFTBPB","created_at":"2026-07-21T01:21:31.838175+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZOC67LFTBPBMVYK","created_at":"2026-07-21T01:21:31.838175+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZOC67LF","created_at":"2026-07-21T01:21:31.838175+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/QZOC67LFTBPBMVYKDEGIK3IXLR","json":"https://pith.science/pith/QZOC67LFTBPBMVYKDEGIK3IXLR.json","graph_json":"https://pith.science/api/pith-number/QZOC67LFTBPBMVYKDEGIK3IXLR/graph.json","events_json":"https://pith.science/api/pith-number/QZOC67LFTBPBMVYKDEGIK3IXLR/events.json","paper":"https://pith.science/paper/QZOC67LF"},"agent_actions":{"view_html":"https://pith.science/pith/QZOC67LFTBPBMVYKDEGIK3IXLR","download_json":"https://pith.science/pith/QZOC67LFTBPBMVYKDEGIK3IXLR.json","view_paper":"https://pith.science/paper/QZOC67LF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17415&json=true","fetch_graph":"https://pith.science/api/pith-number/QZOC67LFTBPBMVYKDEGIK3IXLR/graph.json","fetch_events":"https://pith.science/api/pith-number/QZOC67LFTBPBMVYKDEGIK3IXLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZOC67LFTBPBMVYKDEGIK3IXLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZOC67LFTBPBMVYKDEGIK3IXLR/action/storage_attestation","attest_author":"https://pith.science/pith/QZOC67LFTBPBMVYKDEGIK3IXLR/action/author_attestation","sign_citation":"https://pith.science/pith/QZOC67LFTBPBMVYKDEGIK3IXLR/action/citation_signature","submit_replication":"https://pith.science/pith/QZOC67LFTBPBMVYKDEGIK3IXLR/action/replication_record"}},"created_at":"2026-07-21T01:21:31.838175+00:00","updated_at":"2026-07-21T01:21:31.838175+00:00"}