{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XPILMLRJ625XSO3XSO3EDTAEFF","short_pith_number":"pith:XPILMLRJ","schema_version":"1.0","canonical_sha256":"bbd0b62e29f6bb793b7793b641cc042959b3ffe6ca6c3d2d25f5ed80ec57055f","source":{"kind":"arxiv","id":"2605.17653","version":1},"attestation_state":"computed","paper":{"title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ben Laurie, Gregory Kielian, Junyi Luo, Kauna Lei, Mehdi Saligane, Ruichen Qi, Xinting Jiang","submitted_at":"2026-05-17T21:10:54Z","abstract_excerpt":"Sub-billion-parameter Transformer language models are increasingly deployed on edge devices, where the privacy, latency, and operating-cost advantages of on-device inference are constrained by tight memory-bandwidth, energy, and thermal budgets that make architectural choice and accelerator-specific cost central to efficient inference. We present LLMForge, a hardware-aware neural architecture search (NAS) framework whose three composable contributions together make edge-LM architecture search hardware-conditioned, since different substrates impose different hardware cost bottlenecks. Infinite-"},"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":"2605.17653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T21:10:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7fb1d8c58ce13c260d6f4774d7dbb35171eaf89dbfc0a1ba163f98beb8997a4","abstract_canon_sha256":"1c5ee6dc2c7b14b4e6a94db6b4da7dd1baee7e8e0e2fe5e681ada116526c2dc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:50.756153Z","signature_b64":"H7WHbk1ZtwWleWrBQHbCUQXQz+gelwv2haJ68ArKL0IB5aQu9k1dAcV3FWzACMgRoKzEzJj22KjAvsaoWWqNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbd0b62e29f6bb793b7793b641cc042959b3ffe6ca6c3d2d25f5ed80ec57055f","last_reissued_at":"2026-05-20T00:04:50.755252Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:50.755252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ben Laurie, Gregory Kielian, Junyi Luo, Kauna Lei, Mehdi Saligane, Ruichen Qi, Xinting Jiang","submitted_at":"2026-05-17T21:10:54Z","abstract_excerpt":"Sub-billion-parameter Transformer language models are increasingly deployed on edge devices, where the privacy, latency, and operating-cost advantages of on-device inference are constrained by tight memory-bandwidth, energy, and thermal budgets that make architectural choice and accelerator-specific cost central to efficient inference. We present LLMForge, a hardware-aware neural architecture search (NAS) framework whose three composable contributions together make edge-LM architecture search hardware-conditioned, since different substrates impose different hardware cost bottlenecks. Infinite-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17653","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/2605.17653/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T22:22:35.535199Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:44.274983Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.545382Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.463738Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"34640012abace0e3a09b431a65df3facfeec13b9e3f37059ab3aec2d66b67689"},"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":"2605.17653","created_at":"2026-05-20T00:04:50.755417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17653v1","created_at":"2026-05-20T00:04:50.755417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17653","created_at":"2026-05-20T00:04:50.755417+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPILMLRJ625X","created_at":"2026-05-20T00:04:50.755417+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPILMLRJ625XSO3X","created_at":"2026-05-20T00:04:50.755417+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPILMLRJ","created_at":"2026-05-20T00:04:50.755417+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/XPILMLRJ625XSO3XSO3EDTAEFF","json":"https://pith.science/pith/XPILMLRJ625XSO3XSO3EDTAEFF.json","graph_json":"https://pith.science/api/pith-number/XPILMLRJ625XSO3XSO3EDTAEFF/graph.json","events_json":"https://pith.science/api/pith-number/XPILMLRJ625XSO3XSO3EDTAEFF/events.json","paper":"https://pith.science/paper/XPILMLRJ"},"agent_actions":{"view_html":"https://pith.science/pith/XPILMLRJ625XSO3XSO3EDTAEFF","download_json":"https://pith.science/pith/XPILMLRJ625XSO3XSO3EDTAEFF.json","view_paper":"https://pith.science/paper/XPILMLRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17653&json=true","fetch_graph":"https://pith.science/api/pith-number/XPILMLRJ625XSO3XSO3EDTAEFF/graph.json","fetch_events":"https://pith.science/api/pith-number/XPILMLRJ625XSO3XSO3EDTAEFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPILMLRJ625XSO3XSO3EDTAEFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPILMLRJ625XSO3XSO3EDTAEFF/action/storage_attestation","attest_author":"https://pith.science/pith/XPILMLRJ625XSO3XSO3EDTAEFF/action/author_attestation","sign_citation":"https://pith.science/pith/XPILMLRJ625XSO3XSO3EDTAEFF/action/citation_signature","submit_replication":"https://pith.science/pith/XPILMLRJ625XSO3XSO3EDTAEFF/action/replication_record"}},"created_at":"2026-05-20T00:04:50.755417+00:00","updated_at":"2026-05-20T00:04:50.755417+00:00"}