{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MKGVHFWCHTLPAKESFGCDXMJD3O","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":"c23ae633864f2c87324da37fe0fe2791fc9bba9f4916c15e660173400b829cba","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T17:32:24Z","title_canon_sha256":"6db0f49fb41175fa61d27f80faeeee3479c88615f43ca5055761c58553acc27b"},"schema_version":"1.0","source":{"id":"2404.15247","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15247","created_at":"2026-07-05T08:28:40Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15247v2","created_at":"2026-07-05T08:28:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15247","created_at":"2026-07-05T08:28:40Z"},{"alias_kind":"pith_short_12","alias_value":"MKGVHFWCHTLP","created_at":"2026-07-05T08:28:40Z"},{"alias_kind":"pith_short_16","alias_value":"MKGVHFWCHTLPAKES","created_at":"2026-07-05T08:28:40Z"},{"alias_kind":"pith_short_8","alias_value":"MKGVHFWC","created_at":"2026-07-05T08:28:40Z"}],"graph_snapshots":[{"event_id":"sha256:10f602719796537276f24780c7647c6168f10e930e6f49d99132c7969175d03c","target":"graph","created_at":"2026-07-05T08:28:40Z","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/2404.15247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce XFT, a simple yet powerful training scheme, by simply merging upcycled Mixture-of-Experts (MoE) to unleash the performance limit of instruction-tuned code Large Language Models (LLMs). While vanilla sparse upcycling fails to improve instruction tuning, XFT introduces a shared expert mechanism with a novel routing weight normalization strategy into sparse upcycling, which significantly boosts instruction tuning. After fine-tuning the upcycled MoE model, XFT introduces a learnable model merging mechanism to compile the upcycled MoE model back to a dense model, achieving upcycled MoE","authors_text":"Jiawei Liu, Lingming Zhang, Terry Yue Zhuo, Yifeng Ding, Yuxiang Wei","cross_cats":["cs.AI","cs.LG","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T17:32:24Z","title":"XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15247","kind":"arxiv","version":2},"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":"sha256:4936ce03b3d9eb4338002d1b7c7d97c47bcfb8a14c52e4b25a0cdd8ff2acd038","target":"record","created_at":"2026-07-05T08:28:40Z","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":"c23ae633864f2c87324da37fe0fe2791fc9bba9f4916c15e660173400b829cba","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-23T17:32:24Z","title_canon_sha256":"6db0f49fb41175fa61d27f80faeeee3479c88615f43ca5055761c58553acc27b"},"schema_version":"1.0","source":{"id":"2404.15247","kind":"arxiv","version":2}},"canonical_sha256":"628d5396c23cd6f0289229843bb123dbab444ae1afbfdc1513c4fa628077671b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"628d5396c23cd6f0289229843bb123dbab444ae1afbfdc1513c4fa628077671b","first_computed_at":"2026-07-05T08:28:40.456014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:40.456014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"reeceRkW9EH3U+fO0kFycj2EnDVaGeWnU82yKamCYgfihxbTQSIrwv2WxzzbdCD4btjRMkZ5DMI10BXUkT2oDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:40.456567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15247","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4936ce03b3d9eb4338002d1b7c7d97c47bcfb8a14c52e4b25a0cdd8ff2acd038","sha256:10f602719796537276f24780c7647c6168f10e930e6f49d99132c7969175d03c"],"state_sha256":"e8d70870dd5f4cd69cebeb47701fe876b104682fd4544d58edf18eeed0e92582"}