{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U3V6CUZO5NLE7JXYCDZHAM5SXG","short_pith_number":"pith:U3V6CUZO","schema_version":"1.0","canonical_sha256":"a6ebe1532eeb564fa6f810f27033b2b98481c3345d8851ef9a308e184b1abdae","source":{"kind":"arxiv","id":"2607.05114","version":1},"attestation_state":"computed","paper":{"title":"Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Babak Barazandeh, George Michailidis, Subhabrata Majumdar, Vinay Prithyani","submitted_at":"2026-07-06T14:06:18Z","abstract_excerpt":"Large Language Models (LLMs) and high-dimensional perception networks increasingly rely on parameter-efficient fine-tuning (PEFT) to adapt to diverse operational contexts. However, standard methods like LoRA are structurally limited by a monolithic bottleneck, making them highly susceptible to gradient warfare. Interleaved multi-task streams may trigger destructive optimization feedback, collapsing adapter weights into unspecialized averages. While recent spatial partitioning methods have introduced block-wise isolation, they remain trapped in static topologies, unable to adapt to dynamic task"},"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":"2607.05114","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-06T14:06:18Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1d2da3b0147df98828d4115b4ecd96475e412b0522cf7dbde44fda66862d52f7","abstract_canon_sha256":"13f351ef18758586361999c311000f5c80e5013e3c4d91c2bf6d320610ea520a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T03:19:16.521699Z","signature_b64":"2UrjGJU45uLd8oDExJLUXtyAWrbaGa+1QjwBLg57HU2azhx9krIdIL2Tl9REbFzY3UtlfGAR2qS1Fr4WZA31AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6ebe1532eeb564fa6f810f27033b2b98481c3345d8851ef9a308e184b1abdae","last_reissued_at":"2026-07-07T03:19:16.521274Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T03:19:16.521274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Babak Barazandeh, George Michailidis, Subhabrata Majumdar, Vinay Prithyani","submitted_at":"2026-07-06T14:06:18Z","abstract_excerpt":"Large Language Models (LLMs) and high-dimensional perception networks increasingly rely on parameter-efficient fine-tuning (PEFT) to adapt to diverse operational contexts. However, standard methods like LoRA are structurally limited by a monolithic bottleneck, making them highly susceptible to gradient warfare. Interleaved multi-task streams may trigger destructive optimization feedback, collapsing adapter weights into unspecialized averages. While recent spatial partitioning methods have introduced block-wise isolation, they remain trapped in static topologies, unable to adapt to dynamic task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05114","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/2607.05114/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":"2607.05114","created_at":"2026-07-07T03:19:16.521342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05114v1","created_at":"2026-07-07T03:19:16.521342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05114","created_at":"2026-07-07T03:19:16.521342+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3V6CUZO5NLE","created_at":"2026-07-07T03:19:16.521342+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3V6CUZO5NLE7JXY","created_at":"2026-07-07T03:19:16.521342+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3V6CUZO","created_at":"2026-07-07T03:19:16.521342+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/U3V6CUZO5NLE7JXYCDZHAM5SXG","json":"https://pith.science/pith/U3V6CUZO5NLE7JXYCDZHAM5SXG.json","graph_json":"https://pith.science/api/pith-number/U3V6CUZO5NLE7JXYCDZHAM5SXG/graph.json","events_json":"https://pith.science/api/pith-number/U3V6CUZO5NLE7JXYCDZHAM5SXG/events.json","paper":"https://pith.science/paper/U3V6CUZO"},"agent_actions":{"view_html":"https://pith.science/pith/U3V6CUZO5NLE7JXYCDZHAM5SXG","download_json":"https://pith.science/pith/U3V6CUZO5NLE7JXYCDZHAM5SXG.json","view_paper":"https://pith.science/paper/U3V6CUZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05114&json=true","fetch_graph":"https://pith.science/api/pith-number/U3V6CUZO5NLE7JXYCDZHAM5SXG/graph.json","fetch_events":"https://pith.science/api/pith-number/U3V6CUZO5NLE7JXYCDZHAM5SXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3V6CUZO5NLE7JXYCDZHAM5SXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3V6CUZO5NLE7JXYCDZHAM5SXG/action/storage_attestation","attest_author":"https://pith.science/pith/U3V6CUZO5NLE7JXYCDZHAM5SXG/action/author_attestation","sign_citation":"https://pith.science/pith/U3V6CUZO5NLE7JXYCDZHAM5SXG/action/citation_signature","submit_replication":"https://pith.science/pith/U3V6CUZO5NLE7JXYCDZHAM5SXG/action/replication_record"}},"created_at":"2026-07-07T03:19:16.521342+00:00","updated_at":"2026-07-07T03:19:16.521342+00:00"}