{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UDPV3RHUGBQVHLKZITY4TOCAJ6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4fce2e5175349baf1b9cc10eea55af7426f18f355f81211893b5799720aa6af6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T07:49:24Z","title_canon_sha256":"dd3acacc2bc1ba496a7f48b37e0f3b56314599ee50d3c9d13265d969dbc03a33"},"schema_version":"1.0","source":{"id":"2501.13985","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13985","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13985v1","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13985","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"UDPV3RHUGBQV","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"UDPV3RHUGBQVHLKZ","created_at":"2026-07-05T10:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"UDPV3RHU","created_at":"2026-07-05T10:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:5d61442467c1be76e787a4578fce070f6be8f45560e503a4666f7500c7715679","target":"graph","created_at":"2026-07-05T10:04:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.13985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we explore a novel federated multimodal instruction tuning task(FedMIT), which is significant for collaboratively fine-tuning MLLMs on different types of multimodal instruction data on distributed devices. To solve the new task, we propose a federated multimodal instruction tuning framework(Pilot). Our framework integrates two stages of \"adapter on adapter\" into the connector of the vision encoder and the LLM. In stage 1, we extract task-specific features and client-specific features from visual information. In stage 2, we build the cross-task Mixture-of-Adapters(CT-MoA) module ","authors_text":"Baochen Xiong, Changsheng Xu, Xiaoshan Yang, Yaguang Song, Yaowei Wang","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T07:49:24Z","title":"Pilot: Building the Federated Multimodal Instruction Tuning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13985","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:43e02b2a9f5dffb479472e0cbaa4a73bff4f62e0a3796edffbdc65341a22e40d","target":"record","created_at":"2026-07-05T10:04:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4fce2e5175349baf1b9cc10eea55af7426f18f355f81211893b5799720aa6af6","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-23T07:49:24Z","title_canon_sha256":"dd3acacc2bc1ba496a7f48b37e0f3b56314599ee50d3c9d13265d969dbc03a33"},"schema_version":"1.0","source":{"id":"2501.13985","kind":"arxiv","version":1}},"canonical_sha256":"a0df5dc4f4306153ad5944f1c9b8404f9ba298edc88f140d92c4add88cbe11b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0df5dc4f4306153ad5944f1c9b8404f9ba298edc88f140d92c4add88cbe11b7","first_computed_at":"2026-07-05T10:04:43.466676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:43.466676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WrSumabBYJZvnxLV7Tm59QBkRJA3/ybrDwm+gpMWpUQX4BE61IgfalGCoDB3ZogPHum2TjaJZH5uqvpMw8VeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:43.467077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13985","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43e02b2a9f5dffb479472e0cbaa4a73bff4f62e0a3796edffbdc65341a22e40d","sha256:5d61442467c1be76e787a4578fce070f6be8f45560e503a4666f7500c7715679"],"state_sha256":"b529c5c32e05ab377a9658b30659e1f739364dbbb6688515945e857ebb3e2be6"}