{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6NNQ2QMLIADB2M4E2IS2HVNM2N","short_pith_number":"pith:6NNQ2QML","schema_version":"1.0","canonical_sha256":"f35b0d418b40061d3384d225a3d5acd36511505cb893a1a9f3b94dd9b8322e79","source":{"kind":"arxiv","id":"2606.19025","version":1},"attestation_state":"computed","paper":{"title":"FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Alex Iacob, Andrej Jovanovic, Lorenzo Sani, Meghdad Kurmanji, Nicholas D. Lane, Wanru Zhao, Yan Gao, Zeyu Cao","submitted_at":"2026-06-17T12:50:07Z","abstract_excerpt":"Pre-training Large Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators. While increasing model and dataset scale remains the dominant driver of performance, Mixture-of-Experts (MoEs) architectures have recently achieved state-of-the-art results by decoupling parameter count from computational cost. This efficiency enables training massive models on constrained compute budgets, yet it typically requires the high-speed interconnects of a single datacenter. To overcome these physical limits, recent approaches such as DiLoCo and Photon use"},"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":"2606.19025","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T12:50:07Z","cross_cats_sorted":["cs.AI","cs.DC","cs.SY","eess.SY"],"title_canon_sha256":"094af62d91fc40591207fd1268173ecd9df9e56cfb55fc5f0127124df7aa400b","abstract_canon_sha256":"5d80bbf4a2fe7d703bb27341c3522e807fcae632ac1763b983649e1c61bd823f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:54.832246Z","signature_b64":"z0ap9bzttgm4+k99W9c0VQWXLdzimC86q7AoYC6ZMdYcUlWV5zpiYe+xeelbUl2TIuOIMcRT3OCjVw0MJxNTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f35b0d418b40061d3384d225a3d5acd36511505cb893a1a9f3b94dd9b8322e79","last_reissued_at":"2026-06-19T16:11:54.831897Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:54.831897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Alex Iacob, Andrej Jovanovic, Lorenzo Sani, Meghdad Kurmanji, Nicholas D. Lane, Wanru Zhao, Yan Gao, Zeyu Cao","submitted_at":"2026-06-17T12:50:07Z","abstract_excerpt":"Pre-training Large Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators. While increasing model and dataset scale remains the dominant driver of performance, Mixture-of-Experts (MoEs) architectures have recently achieved state-of-the-art results by decoupling parameter count from computational cost. This efficiency enables training massive models on constrained compute budgets, yet it typically requires the high-speed interconnects of a single datacenter. To overcome these physical limits, recent approaches such as DiLoCo and Photon use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19025","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/2606.19025/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":"2606.19025","created_at":"2026-06-19T16:11:54.831960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19025v1","created_at":"2026-06-19T16:11:54.831960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19025","created_at":"2026-06-19T16:11:54.831960+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NNQ2QMLIADB","created_at":"2026-06-19T16:11:54.831960+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NNQ2QMLIADB2M4E","created_at":"2026-06-19T16:11:54.831960+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NNQ2QML","created_at":"2026-06-19T16:11:54.831960+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/6NNQ2QMLIADB2M4E2IS2HVNM2N","json":"https://pith.science/pith/6NNQ2QMLIADB2M4E2IS2HVNM2N.json","graph_json":"https://pith.science/api/pith-number/6NNQ2QMLIADB2M4E2IS2HVNM2N/graph.json","events_json":"https://pith.science/api/pith-number/6NNQ2QMLIADB2M4E2IS2HVNM2N/events.json","paper":"https://pith.science/paper/6NNQ2QML"},"agent_actions":{"view_html":"https://pith.science/pith/6NNQ2QMLIADB2M4E2IS2HVNM2N","download_json":"https://pith.science/pith/6NNQ2QMLIADB2M4E2IS2HVNM2N.json","view_paper":"https://pith.science/paper/6NNQ2QML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19025&json=true","fetch_graph":"https://pith.science/api/pith-number/6NNQ2QMLIADB2M4E2IS2HVNM2N/graph.json","fetch_events":"https://pith.science/api/pith-number/6NNQ2QMLIADB2M4E2IS2HVNM2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NNQ2QMLIADB2M4E2IS2HVNM2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NNQ2QMLIADB2M4E2IS2HVNM2N/action/storage_attestation","attest_author":"https://pith.science/pith/6NNQ2QMLIADB2M4E2IS2HVNM2N/action/author_attestation","sign_citation":"https://pith.science/pith/6NNQ2QMLIADB2M4E2IS2HVNM2N/action/citation_signature","submit_replication":"https://pith.science/pith/6NNQ2QMLIADB2M4E2IS2HVNM2N/action/replication_record"}},"created_at":"2026-06-19T16:11:54.831960+00:00","updated_at":"2026-06-19T16:11:54.831960+00:00"}