{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2ESKPHPY35P4ENMCIGL4H6RK7J","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":"43e17b835660abd3fd05a8a4482fab58faf4724dc076928d5da04df1821522ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T00:19:03Z","title_canon_sha256":"62867f59037dc06ead34d66b9b354c84563aa1e48aad058f5c22b330ad89436a"},"schema_version":"1.0","source":{"id":"2607.19408","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19408","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19408v1","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19408","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"pith_short_12","alias_value":"2ESKPHPY35P4","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"pith_short_16","alias_value":"2ESKPHPY35P4ENMC","created_at":"2026-07-23T00:23:48Z"},{"alias_kind":"pith_short_8","alias_value":"2ESKPHPY","created_at":"2026-07-23T00:23:48Z"}],"graph_snapshots":[{"event_id":"sha256:65e6ff5b300ef2b660146acd020ab050c8c28e2ce0696f7b33d645c485b141ff","target":"graph","created_at":"2026-07-23T00:23:48Z","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/2607.19408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using Evolutionary Strategies (ES) for fine-tuning large language models is attractive because it is memory-efficient, parallel, and compatible with black-box or discrete rewards. Yet its population-size conclusions conflict sharply: fine-tuning with cross-entropy (CE) reward succeeds with $N=1$, while binary-reward training often needs $N \\approx 30$. We show this gap is largely about reward design and normalization, not population size. In the capable-model regime we study, z-score advantage normalization can cause $N=2$ to fail. Disabling normalization lets binary-reward ES with $N=2$ impro","authors_text":"Gyubin Han, Sung Cho","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T00:19:03Z","title":"Reward-Aware Population Scaling of Evolutionary Strategies in LLM Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19408","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":"sha256:8c4b69139635f29f09740c2d1d49d9171c4ad1d1c705f7bf7a4defaa882ef798","target":"record","created_at":"2026-07-23T00:23:48Z","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":"43e17b835660abd3fd05a8a4482fab58faf4724dc076928d5da04df1821522ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T00:19:03Z","title_canon_sha256":"62867f59037dc06ead34d66b9b354c84563aa1e48aad058f5c22b330ad89436a"},"schema_version":"1.0","source":{"id":"2607.19408","kind":"arxiv","version":1}},"canonical_sha256":"d124a79df8df5fc235824197c3fa2afa68e47bc206f0a71085d4811fcc444dd5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d124a79df8df5fc235824197c3fa2afa68e47bc206f0a71085d4811fcc444dd5","first_computed_at":"2026-07-23T00:23:48.545112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T00:23:48.545112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"twRQoRPgGBeNCXasAQCid6KVE3Pk+L0sVtv58VclB3eBH2A+AiY2q/I/mXkKGPslOu6izYJNWIJVsmhGrOtkBQ==","signature_status":"signed_v1","signed_at":"2026-07-23T00:23:48.545997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19408","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c4b69139635f29f09740c2d1d49d9171c4ad1d1c705f7bf7a4defaa882ef798","sha256:65e6ff5b300ef2b660146acd020ab050c8c28e2ce0696f7b33d645c485b141ff"],"state_sha256":"3774d8ab05ce15c15eea6ec3cd0e5dabcafe88c005a87533b5f3dd39002b2712"}