{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FYM2NAGGVIDTANF6UJBSWR3RNR","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":"3670c56e4b86004dee33659c496ea243699bb071a7bc765c5d52d136be378aa9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T17:01:11Z","title_canon_sha256":"f59d679d92f89f77a36ce7e3bb7f3e80c520ef62f0ec84b76deb729a5b99c884"},"schema_version":"1.0","source":{"id":"2502.09650","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09650","created_at":"2026-07-05T11:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09650v2","created_at":"2026-07-05T11:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09650","created_at":"2026-07-05T11:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"FYM2NAGGVIDT","created_at":"2026-07-05T11:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"FYM2NAGGVIDTANF6","created_at":"2026-07-05T11:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"FYM2NAGG","created_at":"2026-07-05T11:02:41Z"}],"graph_snapshots":[{"event_id":"sha256:1b78c3b2c6009e0b14abcdb9311a714474cb3655643bc2af2f1483327e147fc4","target":"graph","created_at":"2026-07-05T11:02:41Z","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/2502.09650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference data vary in difficulty, and overly difficult examples hinder alignment, by exceeding the model's capacity. Through systematic experimentation, we validate this principle with three key findings: (1) preference examples vary in difficulty, as evidenced by consistent learning orders across alignment runs; (2) overly difficult examples significantly degrade perfo","authors_text":"Chengqian Gao, Haonan Li, Liu Liu, Peilin Zhao, Zeke Xie, Zhiqiang Xu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T17:01:11Z","title":"Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09650","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":"sha256:905f6883a5c51e42aa249fe81bd28d5e366acceb84cac88f670c51a290317ac6","target":"record","created_at":"2026-07-05T11:02:41Z","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":"3670c56e4b86004dee33659c496ea243699bb071a7bc765c5d52d136be378aa9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T17:01:11Z","title_canon_sha256":"f59d679d92f89f77a36ce7e3bb7f3e80c520ef62f0ec84b76deb729a5b99c884"},"schema_version":"1.0","source":{"id":"2502.09650","kind":"arxiv","version":2}},"canonical_sha256":"2e19a680c6aa073034bea2432b47716c7395fe00e51908cc6a7ffebe999f0b0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e19a680c6aa073034bea2432b47716c7395fe00e51908cc6a7ffebe999f0b0b","first_computed_at":"2026-07-05T11:02:41.767228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:41.767228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sdUtRlygtdYx5Cp0t+DnypvBdF9Pkk/4DEPtJQ5CKUoEbrac1It4mutuOyJ+gJ7iGte2NuaqJkBZM+qvcbkaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:41.767744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09650","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:905f6883a5c51e42aa249fe81bd28d5e366acceb84cac88f670c51a290317ac6","sha256:1b78c3b2c6009e0b14abcdb9311a714474cb3655643bc2af2f1483327e147fc4"],"state_sha256":"c3da5dfe242066e9cec8ab515c7cc449cb468d78111f1c6c5ec822d670473e19"}