{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H2IJ2QYI5J4EF2H2L2W4PZ5ETH","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":"4e7359ae9a16c3b4ddf1fc09b0cea4065728e579e586c6e053e3b8138ff91330","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T09:33:13Z","title_canon_sha256":"ba7746440afb8e39db77fae31c8f535cc584361789df19c3a47321e514ab3956"},"schema_version":"1.0","source":{"id":"2311.15653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.15653","created_at":"2026-07-05T07:17:07Z"},{"alias_kind":"arxiv_version","alias_value":"2311.15653v1","created_at":"2026-07-05T07:17:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15653","created_at":"2026-07-05T07:17:07Z"},{"alias_kind":"pith_short_12","alias_value":"H2IJ2QYI5J4E","created_at":"2026-07-05T07:17:07Z"},{"alias_kind":"pith_short_16","alias_value":"H2IJ2QYI5J4EF2H2","created_at":"2026-07-05T07:17:07Z"},{"alias_kind":"pith_short_8","alias_value":"H2IJ2QYI","created_at":"2026-07-05T07:17:07Z"}],"graph_snapshots":[{"event_id":"sha256:8c760a98df0d4f73b329041718078d72d07983e0f8c9d183d182fb039b2bd994","target":"graph","created_at":"2026-07-05T07:17:07Z","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/2311.15653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning has become the de facto method to equip large language models (LLMs) with the ability of following user instructions. Usually, hundreds of thousands or millions of instruction-following pairs are employed to fine-tune the foundation LLMs. Recently, some studies show that a small number of high-quality instruction data is enough. However, how to select appropriate instruction data for a given LLM is still an open problem. To address this problem, in this paper we present a model-oriented data selection (MoDS) approach, which selects instruction data based on a new criteria co","authors_text":"Chengqing Zong, Jiajun Zhang, Qianlong Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T09:33:13Z","title":"MoDS: Model-oriented Data Selection for Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15653","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":"sha256:23e8abc22506b4cb300f28d947c549a18f978beeab3b00da08e4819cceca8bd7","target":"record","created_at":"2026-07-05T07:17:07Z","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":"4e7359ae9a16c3b4ddf1fc09b0cea4065728e579e586c6e053e3b8138ff91330","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-27T09:33:13Z","title_canon_sha256":"ba7746440afb8e39db77fae31c8f535cc584361789df19c3a47321e514ab3956"},"schema_version":"1.0","source":{"id":"2311.15653","kind":"arxiv","version":1}},"canonical_sha256":"3e909d4308ea7842e8fa5eadc7e7a499e961d9aab87db032a7a89d12cb356fca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e909d4308ea7842e8fa5eadc7e7a499e961d9aab87db032a7a89d12cb356fca","first_computed_at":"2026-07-05T07:17:07.579517Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:07.579517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6Z/9EF/j+jb83rTEzSsASY1ETidXhTodChVbxnloZ3p5KrN3tS1Pf/JCq/cCbTogKZ0tfdeRFqdXBML8sieCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:07.580257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.15653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23e8abc22506b4cb300f28d947c549a18f978beeab3b00da08e4819cceca8bd7","sha256:8c760a98df0d4f73b329041718078d72d07983e0f8c9d183d182fb039b2bd994"],"state_sha256":"cbaffb153745f98509d0776af4b994ce6eb97bfdbef5ae8da2fae26e818c761d"}