{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W4HL5SH7IHQEBK47GWZLGUYQWR","short_pith_number":"pith:W4HL5SH7","canonical_record":{"source":{"id":"2410.15524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T22:24:40Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"21717f615e8db0f9fb51b2476c4f150c4384eca1b6680b89b8e82051778b4382","abstract_canon_sha256":"4b69485109ca65fc4fa4b6e2f496322fcb2075084271624cccef423ff66eb5da"},"schema_version":"1.0"},"canonical_sha256":"b70ebec8ff41e040ab9f35b2b35310b47c91957c5a6adbe09a2f1a7b7c638615","source":{"kind":"arxiv","id":"2410.15524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15524","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15524v1","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15524","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"W4HL5SH7IHQE","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"W4HL5SH7IHQEBK47","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"W4HL5SH7","created_at":"2026-07-05T09:23:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W4HL5SH7IHQEBK47GWZLGUYQWR","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T22:24:40Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"21717f615e8db0f9fb51b2476c4f150c4384eca1b6680b89b8e82051778b4382","abstract_canon_sha256":"4b69485109ca65fc4fa4b6e2f496322fcb2075084271624cccef423ff66eb5da"},"schema_version":"1.0"},"canonical_sha256":"b70ebec8ff41e040ab9f35b2b35310b47c91957c5a6adbe09a2f1a7b7c638615","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:20.917221Z","signature_b64":"74rQW3WtYpiKPBKCC7AR4bYoji/bt2iR5JLfi7P6AOXouD4BVo+TG3pJN0QlVWNCDpko/bNViWcNDeRJUsvgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b70ebec8ff41e040ab9f35b2b35310b47c91957c5a6adbe09a2f1a7b7c638615","last_reissued_at":"2026-07-05T09:23:20.916780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:20.916780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15524","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3wfKcPS2Z/wQUY0uLJAFpjRoyVTG8EuSnkT+sQ9HICO5fJ9x34KexbFsMjCulcDaQ3+eZesd0zURybPbpJS+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:24:41.332630Z"},"content_sha256":"8b18682a088e7fa28880a656106c4a3360eda0eab086c1b919588bfdc7660295","schema_version":"1.0","event_id":"sha256:8b18682a088e7fa28880a656106c4a3360eda0eab086c1b919588bfdc7660295"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W4HL5SH7IHQEBK47GWZLGUYQWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Ahmed Elbakary, Chaouki Ben Issaid, Karim Seddik, Mehdi Bennis, Tamer ElBatt","submitted_at":"2024-10-20T22:24:40Z","abstract_excerpt":"In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that considers other clients' tasks and data distribution. To mitigate the extensive computational and communication overhead often associated with LLMs, we utilize a parameter-efficient fine-tuning method, specifically Low-Rank Adaptation (LoRA), reducing the number of trainable parameters. Experimental results, with different datasets and models, demonstrate the propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15524","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/2410.15524/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:23:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/Wrh19lZVGoVZf7YL7cwnbR6w/ewhzgYhDWMEpuRrlfYgxPN0F0QirDi2gE7KNLAdquz/oNOgdQZayNdBzgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:24:41.333005Z"},"content_sha256":"d9b5907e1dae8a64bdff0dc6400274d388a512794420d88b58de7f999892ef3d","schema_version":"1.0","event_id":"sha256:d9b5907e1dae8a64bdff0dc6400274d388a512794420d88b58de7f999892ef3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4HL5SH7IHQEBK47GWZLGUYQWR/bundle.json","state_url":"https://pith.science/pith/W4HL5SH7IHQEBK47GWZLGUYQWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4HL5SH7IHQEBK47GWZLGUYQWR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T09:24:41Z","links":{"resolver":"https://pith.science/pith/W4HL5SH7IHQEBK47GWZLGUYQWR","bundle":"https://pith.science/pith/W4HL5SH7IHQEBK47GWZLGUYQWR/bundle.json","state":"https://pith.science/pith/W4HL5SH7IHQEBK47GWZLGUYQWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4HL5SH7IHQEBK47GWZLGUYQWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W4HL5SH7IHQEBK47GWZLGUYQWR","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":"4b69485109ca65fc4fa4b6e2f496322fcb2075084271624cccef423ff66eb5da","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T22:24:40Z","title_canon_sha256":"21717f615e8db0f9fb51b2476c4f150c4384eca1b6680b89b8e82051778b4382"},"schema_version":"1.0","source":{"id":"2410.15524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15524","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15524v1","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15524","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"W4HL5SH7IHQE","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"W4HL5SH7IHQEBK47","created_at":"2026-07-05T09:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"W4HL5SH7","created_at":"2026-07-05T09:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:d9b5907e1dae8a64bdff0dc6400274d388a512794420d88b58de7f999892ef3d","target":"graph","created_at":"2026-07-05T09:23:20Z","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/2410.15524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that considers other clients' tasks and data distribution. To mitigate the extensive computational and communication overhead often associated with LLMs, we utilize a parameter-efficient fine-tuning method, specifically Low-Rank Adaptation (LoRA), reducing the number of trainable parameters. Experimental results, with different datasets and models, demonstrate the propo","authors_text":"Ahmed Elbakary, Chaouki Ben Issaid, Karim Seddik, Mehdi Bennis, Tamer ElBatt","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T22:24:40Z","title":"MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15524","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":"sha256:8b18682a088e7fa28880a656106c4a3360eda0eab086c1b919588bfdc7660295","target":"record","created_at":"2026-07-05T09:23:20Z","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":"4b69485109ca65fc4fa4b6e2f496322fcb2075084271624cccef423ff66eb5da","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T22:24:40Z","title_canon_sha256":"21717f615e8db0f9fb51b2476c4f150c4384eca1b6680b89b8e82051778b4382"},"schema_version":"1.0","source":{"id":"2410.15524","kind":"arxiv","version":1}},"canonical_sha256":"b70ebec8ff41e040ab9f35b2b35310b47c91957c5a6adbe09a2f1a7b7c638615","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b70ebec8ff41e040ab9f35b2b35310b47c91957c5a6adbe09a2f1a7b7c638615","first_computed_at":"2026-07-05T09:23:20.916780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:20.916780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"74rQW3WtYpiKPBKCC7AR4bYoji/bt2iR5JLfi7P6AOXouD4BVo+TG3pJN0QlVWNCDpko/bNViWcNDeRJUsvgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:20.917221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b18682a088e7fa28880a656106c4a3360eda0eab086c1b919588bfdc7660295","sha256:d9b5907e1dae8a64bdff0dc6400274d388a512794420d88b58de7f999892ef3d"],"state_sha256":"6dde70344b4ca4475d3ae3aa46e9777fd46035d95b2b721ef5dceb4dfa62a198"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrWw/vi2GA+ZfRB4CiFkAtBlZEnUBaGcuKSZ8Y0geEv5O2vS7+X2NDa18xatJ1e6w5z72ZOnSITrqSmgu4WwDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:24:41.334978Z","bundle_sha256":"253d027a1465c34f2ead2092b4cf8603a28e720044b4739967f5cda6a630e768"}}