{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GF2WXYTCQF7EDREO2ENNR6D3EU","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":"524bceac18820ba9c8ebef90d55f53639bb32e08166b7a51c40bf6c6ece81cc1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T03:39:37Z","title_canon_sha256":"5b778c6a27738bc0ef18bd25f8fe2084d2a393f893ffe4bb1c949b7f90955fda"},"schema_version":"1.0","source":{"id":"2402.10430","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10430","created_at":"2026-07-05T07:45:56Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10430v1","created_at":"2026-07-05T07:45:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10430","created_at":"2026-07-05T07:45:56Z"},{"alias_kind":"pith_short_12","alias_value":"GF2WXYTCQF7E","created_at":"2026-07-05T07:45:56Z"},{"alias_kind":"pith_short_16","alias_value":"GF2WXYTCQF7EDREO","created_at":"2026-07-05T07:45:56Z"},{"alias_kind":"pith_short_8","alias_value":"GF2WXYTC","created_at":"2026-07-05T07:45:56Z"}],"graph_snapshots":[{"event_id":"sha256:84c50e2f400e42292a4b23719e8a95d6a9ce39f1a2fb1d463bfff006d838be6d","target":"graph","created_at":"2026-07-05T07:45:56Z","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/2402.10430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-tuning language models has become a crucial step in aligning them for general use. Typically, this process involves extensive training on large datasets, incurring high training costs. In this paper, we introduce a novel training data selection based on the learning percentage of the samples. We assert that current language models possess the capability to autonomously select high-quality training data, leading to comparable or improved performance compared to training on the entire dataset. Our experiments span different-sized models, revealing that this characteristic holds for m","authors_text":"Alex Nguyen, Dheeraj Mekala, Jingbo Shang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T03:39:37Z","title":"Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10430","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:b6f48775e318994654a1e198b09298d2d7019abb05964da7373005e415118a64","target":"record","created_at":"2026-07-05T07:45:56Z","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":"524bceac18820ba9c8ebef90d55f53639bb32e08166b7a51c40bf6c6ece81cc1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T03:39:37Z","title_canon_sha256":"5b778c6a27738bc0ef18bd25f8fe2084d2a393f893ffe4bb1c949b7f90955fda"},"schema_version":"1.0","source":{"id":"2402.10430","kind":"arxiv","version":1}},"canonical_sha256":"31756be262817e41c48ed11ad8f87b2524e9afa5eb76aed715376c75a4337723","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31756be262817e41c48ed11ad8f87b2524e9afa5eb76aed715376c75a4337723","first_computed_at":"2026-07-05T07:45:56.298894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:56.298894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q2YQ2kdJxEp6c38uxxxE80ZUL4kKZNTh4I9X2M350JpXQnSy05bkBpqPJ8wb2/8DwwUjnZIcOTaUXQ5YMAB8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:56.299443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10430","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6f48775e318994654a1e198b09298d2d7019abb05964da7373005e415118a64","sha256:84c50e2f400e42292a4b23719e8a95d6a9ce39f1a2fb1d463bfff006d838be6d"],"state_sha256":"752ef5490686717b1f631251e2c5fab0e26984953265a2611b2aaea6a98f0267"}