{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4BHVSGH35KFNUIX3CAJD6RKQ7Z","short_pith_number":"pith:4BHVSGH3","schema_version":"1.0","canonical_sha256":"e04f5918fbea8ada22fb10123f4550fe504fdbcc628a2fe8d8ff0046c6e331f3","source":{"kind":"arxiv","id":"2410.09335","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"An Yang, Bowen Yu, Junyang Lin, Kai Dang, Tingyu Xia, Yi Chang, Yuan Tian, Yuan Wu","submitted_at":"2024-10-12T02:48:34Z","abstract_excerpt":"Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that fine-tuning with this subset achieves results comparable to or even exceeding those obtained using the entire dataset. However, most existing data selection techniques are designed for small-scale data pools, which fail to meet the demands of real-world SFT scenarios. In this paper, we replicated several self-scoring methods those that do not rely on external model a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.09335","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-12T02:48:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49d4843896f6667bab9e792becf24acf9c7d6534e2e47337b137bd01685008ae","abstract_canon_sha256":"18010861e7480a626a00786a3e5caa67edf1f7c331ea927a98c8dcfe020e2e2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:56.128553Z","signature_b64":"FAfXSXUJUBj2fGeLgJIBIlB/3H7KwTv0aJVOmvPW+Q3QKws7pzpRim+0cpLDqICvbgHTvydaj1J4fqzLg5PODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e04f5918fbea8ada22fb10123f4550fe504fdbcc628a2fe8d8ff0046c6e331f3","last_reissued_at":"2026-07-05T09:45:56.128081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:56.128081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"An Yang, Bowen Yu, Junyang Lin, Kai Dang, Tingyu Xia, Yi Chang, Yuan Tian, Yuan Wu","submitted_at":"2024-10-12T02:48:34Z","abstract_excerpt":"Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet representative subset of training data from the larger pool, such that fine-tuning with this subset achieves results comparable to or even exceeding those obtained using the entire dataset. However, most existing data selection techniques are designed for small-scale data pools, which fail to meet the demands of real-world SFT scenarios. In this paper, we replicated several self-scoring methods those that do not rely on external model a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09335","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.09335/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.09335","created_at":"2026-07-05T09:45:56.128142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09335v2","created_at":"2026-07-05T09:45:56.128142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09335","created_at":"2026-07-05T09:45:56.128142+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BHVSGH35KFN","created_at":"2026-07-05T09:45:56.128142+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BHVSGH35KFNUIX3","created_at":"2026-07-05T09:45:56.128142+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BHVSGH3","created_at":"2026-07-05T09:45:56.128142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12906","citing_title":"Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25167","citing_title":"From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10666","citing_title":"Omnimodal Dataset Distillation via High-order Proxy Alignment","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z","json":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z.json","graph_json":"https://pith.science/api/pith-number/4BHVSGH35KFNUIX3CAJD6RKQ7Z/graph.json","events_json":"https://pith.science/api/pith-number/4BHVSGH35KFNUIX3CAJD6RKQ7Z/events.json","paper":"https://pith.science/paper/4BHVSGH3"},"agent_actions":{"view_html":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z","download_json":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z.json","view_paper":"https://pith.science/paper/4BHVSGH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09335&json=true","fetch_graph":"https://pith.science/api/pith-number/4BHVSGH35KFNUIX3CAJD6RKQ7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/4BHVSGH35KFNUIX3CAJD6RKQ7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/action/storage_attestation","attest_author":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/action/author_attestation","sign_citation":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/action/citation_signature","submit_replication":"https://pith.science/pith/4BHVSGH35KFNUIX3CAJD6RKQ7Z/action/replication_record"}},"created_at":"2026-07-05T09:45:56.128142+00:00","updated_at":"2026-07-05T09:45:56.128142+00:00"}