{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VUDU6LD7LW5EAX2QV6WTTVEXYK","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":"0c905b060ece686860acac0f5fe4e822924eee33777cf504b1b1603dbd0604ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T05:01:28Z","title_canon_sha256":"7759d9d17c21aa2e0dd14b7d27c8f65c01dd5989603ac2169bdf5d457d4f4d21"},"schema_version":"1.0","source":{"id":"2406.08811","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08811","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08811v2","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08811","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"pith_short_12","alias_value":"VUDU6LD7LW5E","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"pith_short_16","alias_value":"VUDU6LD7LW5EAX2Q","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"pith_short_8","alias_value":"VUDU6LD7","created_at":"2026-07-05T09:16:17Z"}],"graph_snapshots":[{"event_id":"sha256:bf23d252c61aa60ce83cfe294902673da65f74d48673ec6966b40d56536ec511","target":"graph","created_at":"2026-07-05T09:16:17Z","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/2406.08811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are typically fine-tuned on diverse and extensive datasets sourced from various origins to develop a comprehensive range of skills, such as writing, reasoning, chatting, coding, and more. Each skill has unique characteristics, and these datasets are often heterogeneous and imbalanced, making the fine-tuning process highly challenging. Balancing the development of each skill while ensuring the model maintains its overall performance requires sophisticated techniques and careful dataset curation. In this work, we propose a general, model-agnostic, reinforcement learn","authors_text":"Gholamreza Haffari, Lizhen Qu, Minghao Wu, Thuy-Trang Vu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T05:01:28Z","title":"Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08811","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:f09aee870fd247fe0101edb36203f24ae149c2fa5a35b762d294ad2829b5a1c5","target":"record","created_at":"2026-07-05T09:16:17Z","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":"0c905b060ece686860acac0f5fe4e822924eee33777cf504b1b1603dbd0604ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T05:01:28Z","title_canon_sha256":"7759d9d17c21aa2e0dd14b7d27c8f65c01dd5989603ac2169bdf5d457d4f4d21"},"schema_version":"1.0","source":{"id":"2406.08811","kind":"arxiv","version":2}},"canonical_sha256":"ad074f2c7f5dba405f50afad39d497c2bc00f171f9d19ebe7a47d245b6c2ca82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad074f2c7f5dba405f50afad39d497c2bc00f171f9d19ebe7a47d245b6c2ca82","first_computed_at":"2026-07-05T09:16:17.944148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:17.944148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gwrNf4+gWsoHBSk7TWchFgmONvSV0LvfueByO0lg/jqvBvLI/rnTEEKwVJT52XnHqS3MTJHgF813Fl8/bDBJCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:17.944724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08811","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f09aee870fd247fe0101edb36203f24ae149c2fa5a35b762d294ad2829b5a1c5","sha256:bf23d252c61aa60ce83cfe294902673da65f74d48673ec6966b40d56536ec511"],"state_sha256":"f1b81d44ba58e8493afa7651c500e1de0b72acc2fe01c060b82769572762c2e1"}