{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HM4B64GMZK24XITKFQ6ZTT2FRP","short_pith_number":"pith:HM4B64GM","schema_version":"1.0","canonical_sha256":"3b381f70cccab5cba26a2c3d99cf458bd0527420dbce0617202be13fcdfee4c2","source":{"kind":"arxiv","id":"2608.09907","version":1},"attestation_state":"computed","paper":{"title":"DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Mainak Singha, Niccol\\`o Biondi, Subhankar Roy","submitted_at":"2026-08-10T17:52:14Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domains typically assumes centralized data access and costly joint training. This is restrictive when data is distributed across private, domain-specific, or permission-limited clients. To this end, we propose DistMoE, a mixture-of-experts (MoE) approach for distributed visual instruction tuning. In each layer of the language decoder it augments the public feedforward network (FFN) with a client-specific private FFN expert, with the goal to acquire d"},"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":"2608.09907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-10T17:52:14Z","cross_cats_sorted":[],"title_canon_sha256":"b76d9a6282def23d49938365fc353c47267436a3424ed1db14c1cf4214b6aecc","abstract_canon_sha256":"855934fd5764dae148b4b5fa3fc46e0ec0eb536022e57dbe69d828823562e9aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:25:25.115936Z","signature_b64":"D6PuzCTm9pEW9LDx2ob9a/tI0XUDYRAt+ozTgUIQWO8gSkR4uehpU+bA91j4m7ZCFVkeqrTNVFqfaUD22/hRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b381f70cccab5cba26a2c3d99cf458bd0527420dbce0617202be13fcdfee4c2","last_reissued_at":"2026-08-11T02:25:25.114320Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:25:25.114320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Mainak Singha, Niccol\\`o Biondi, Subhankar Roy","submitted_at":"2026-08-10T17:52:14Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domains typically assumes centralized data access and costly joint training. This is restrictive when data is distributed across private, domain-specific, or permission-limited clients. To this end, we propose DistMoE, a mixture-of-experts (MoE) approach for distributed visual instruction tuning. In each layer of the language decoder it augments the public feedforward network (FFN) with a client-specific private FFN expert, with the goal to acquire d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09907","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/2608.09907/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":"2608.09907","created_at":"2026-08-11T02:25:25.114966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09907v1","created_at":"2026-08-11T02:25:25.114966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09907","created_at":"2026-08-11T02:25:25.114966+00:00"},{"alias_kind":"pith_short_12","alias_value":"HM4B64GMZK24","created_at":"2026-08-11T02:25:25.114966+00:00"},{"alias_kind":"pith_short_16","alias_value":"HM4B64GMZK24XITK","created_at":"2026-08-11T02:25:25.114966+00:00"},{"alias_kind":"pith_short_8","alias_value":"HM4B64GM","created_at":"2026-08-11T02:25:25.114966+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/HM4B64GMZK24XITKFQ6ZTT2FRP","json":"https://pith.science/pith/HM4B64GMZK24XITKFQ6ZTT2FRP.json","graph_json":"https://pith.science/api/pith-number/HM4B64GMZK24XITKFQ6ZTT2FRP/graph.json","events_json":"https://pith.science/api/pith-number/HM4B64GMZK24XITKFQ6ZTT2FRP/events.json","paper":"https://pith.science/paper/HM4B64GM"},"agent_actions":{"view_html":"https://pith.science/pith/HM4B64GMZK24XITKFQ6ZTT2FRP","download_json":"https://pith.science/pith/HM4B64GMZK24XITKFQ6ZTT2FRP.json","view_paper":"https://pith.science/paper/HM4B64GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09907&json=true","fetch_graph":"https://pith.science/api/pith-number/HM4B64GMZK24XITKFQ6ZTT2FRP/graph.json","fetch_events":"https://pith.science/api/pith-number/HM4B64GMZK24XITKFQ6ZTT2FRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HM4B64GMZK24XITKFQ6ZTT2FRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HM4B64GMZK24XITKFQ6ZTT2FRP/action/storage_attestation","attest_author":"https://pith.science/pith/HM4B64GMZK24XITKFQ6ZTT2FRP/action/author_attestation","sign_citation":"https://pith.science/pith/HM4B64GMZK24XITKFQ6ZTT2FRP/action/citation_signature","submit_replication":"https://pith.science/pith/HM4B64GMZK24XITKFQ6ZTT2FRP/action/replication_record"}},"created_at":"2026-08-11T02:25:25.114966+00:00","updated_at":"2026-08-11T02:25:25.114966+00:00"}