{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AHSQIEEX63E4BXAWNYSUE5OHKO","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":"a0a8a11b379613d3d38b6149c3ad1b9a5a647d1c2e75b3d54eb65e2c5164acbf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T13:32:11Z","title_canon_sha256":"5dfe69b78ab1b849a91abe78607c51711002f781adae3779e324135b200b9e5d"},"schema_version":"1.0","source":{"id":"2402.04833","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04833","created_at":"2026-07-05T08:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04833v2","created_at":"2026-07-05T08:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04833","created_at":"2026-07-05T08:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"AHSQIEEX63E4","created_at":"2026-07-05T08:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"AHSQIEEX63E4BXAW","created_at":"2026-07-05T08:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"AHSQIEEX","created_at":"2026-07-05T08:27:03Z"}],"graph_snapshots":[{"event_id":"sha256:fe8de9785b9ac9412a4df18f952759477c69497270058b91a9b7855c4c5c6053","target":"graph","created_at":"2026-07-05T08:27:03Z","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/2402.04833/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There is a consensus that instruction fine-tuning of LLMs requires high-quality data, but what are they? LIMA (NeurIPS 2023) and AlpaGasus (ICLR 2024) are state-of-the-art methods for selecting such high-quality examples, either via manual curation or using GPT-3.5-Turbo as a quality scorer. We show that the extremely simple baseline of selecting the 1,000 instructions with longest responses -- that intuitively contain more learnable information and are harder to overfit -- from standard datasets can consistently outperform these sophisticated methods according to GPT-4 and PaLM-2 as judges, w","authors_text":"Francesco Croce, Hao Zhao, Maksym Andriushchenko, Nicolas Flammarion","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T13:32:11Z","title":"Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04833","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":"sha256:954bbca8a64aeaf11550abb82a316898d440f0f2b0dbde97b15188b4cf6daf9a","target":"record","created_at":"2026-07-05T08:27:03Z","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":"a0a8a11b379613d3d38b6149c3ad1b9a5a647d1c2e75b3d54eb65e2c5164acbf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T13:32:11Z","title_canon_sha256":"5dfe69b78ab1b849a91abe78607c51711002f781adae3779e324135b200b9e5d"},"schema_version":"1.0","source":{"id":"2402.04833","kind":"arxiv","version":2}},"canonical_sha256":"01e5041097f6c9c0dc166e254275c753bbb00bd24c0dfc0330878e8f4a7c49f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01e5041097f6c9c0dc166e254275c753bbb00bd24c0dfc0330878e8f4a7c49f4","first_computed_at":"2026-07-05T08:27:03.310646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:03.310646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eHK4KO1u4ssFzUOAUXugHxh0Ab2UToDL9S1Rphic0ZCRA13XoR1CmptEgawxBfi3g9lY4uAt7AWI7o09P3QhCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:03.311062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04833","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:954bbca8a64aeaf11550abb82a316898d440f0f2b0dbde97b15188b4cf6daf9a","sha256:fe8de9785b9ac9412a4df18f952759477c69497270058b91a9b7855c4c5c6053"],"state_sha256":"8e43548f0041127fe0993a055217914e7c9b40bafdf994a47c5d0ceb895b1281"}