{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TP7HZRPLXFEYP3HKTYBFPXTDKQ","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":"ecd5fad23dfbe9e56871b41c1d412c85ce4fa15e5e70eaf4f317a6990b594508","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T01:42:35Z","title_canon_sha256":"aaed082db9add9f8665c41a6aa2a687e1d5de43aacc8522d4ccece30513ca8f6"},"schema_version":"1.0","source":{"id":"2410.03077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03077","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03077v1","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03077","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"TP7HZRPLXFEY","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"TP7HZRPLXFEYP3HK","created_at":"2026-07-05T09:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"TP7HZRPL","created_at":"2026-07-05T09:15:43Z"}],"graph_snapshots":[{"event_id":"sha256:b9908b69eb9decfa49dcb674677a2b449f1d8f0a5fd90d4052e9b0fe8076a1c5","target":"graph","created_at":"2026-07-05T09:15:43Z","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/2410.03077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With instruction tuning, Large Language Models (LLMs) can enhance their ability to adhere to commands. Diverging from most works focusing on data mixing, our study concentrates on enhancing the model's capabilities from the perspective of data sampling during training. Drawing inspiration from the human learning process, where it is generally easier to master solutions to similar topics through focused practice on a single type of topic, we introduce a novel instruction tuning strategy termed CommonIT: Commonality-aware Instruction Tuning. Specifically, we cluster instruction datasets into dis","authors_text":"Jun Rao, Lian Lian, Min Zhang, Shengjun Cheng, Xuebo Liu, Yunjie Liao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T01:42:35Z","title":"CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03077","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:c3d171c8d14b6f450dbaf869266b9ee5391967cf4db8c1e9087c2135d89150f6","target":"record","created_at":"2026-07-05T09:15:43Z","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":"ecd5fad23dfbe9e56871b41c1d412c85ce4fa15e5e70eaf4f317a6990b594508","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T01:42:35Z","title_canon_sha256":"aaed082db9add9f8665c41a6aa2a687e1d5de43aacc8522d4ccece30513ca8f6"},"schema_version":"1.0","source":{"id":"2410.03077","kind":"arxiv","version":1}},"canonical_sha256":"9bfe7cc5ebb94987ecea9e0257de63541eb7ee08d68619dd2c26a4a888a9f7e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bfe7cc5ebb94987ecea9e0257de63541eb7ee08d68619dd2c26a4a888a9f7e6","first_computed_at":"2026-07-05T09:15:43.840532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:43.840532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EQkw9MXsfnAIVh6xqjffgLVP6oJm3aR+tY11Qj6mFEa9IvRIN9fKUTu81xKAX9sBA2mAQ993nKCu3AwzS2NLCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:43.840998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3d171c8d14b6f450dbaf869266b9ee5391967cf4db8c1e9087c2135d89150f6","sha256:b9908b69eb9decfa49dcb674677a2b449f1d8f0a5fd90d4052e9b0fe8076a1c5"],"state_sha256":"945b7087cd961c873d58e4eb12487bdc716f5658c52514b0fe7e545e2e349fdc"}