{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F5H7G3CYIZ3ONQX4DHWZC4BGT4","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":"8406288a1eb6776e3bed064f1684d6b035a51e072ca7ff4d89786beec7ec2971","cross_cats_sorted":["cs.AI","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2025-05-06T04:03:11Z","title_canon_sha256":"27805f6ebf069ef404d0d78f5e0004a725126a625a49c1067d4359c3080a08ed"},"schema_version":"1.0","source":{"id":"2505.03156","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03156","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03156v1","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03156","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"F5H7G3CYIZ3O","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"F5H7G3CYIZ3ONQX4","created_at":"2026-07-05T10:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"F5H7G3CY","created_at":"2026-07-05T10:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:feefb50a308aa7d1c3afb7f9b43326fde3b33174b36a1aede626bee42b6845ab","target":"graph","created_at":"2026-07-05T10:59:10Z","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/2505.03156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Best-of-$n$ (BoN) sampling is a practical approach for aligning language model outputs with human preferences without expensive fine-tuning. BoN sampling is performed by generating $n$ responses to a prompt and then selecting the sample that maximizes a reward function. BoN yields high reward values in practice at a distortion cost, as measured by the KL-divergence between the sampled and original distribution. This distortion is coarsely controlled by varying the number of samples: larger $n$ yields a higher reward at a higher distortion cost. We introduce Soft Best-of-$n$ sampling, a general","authors_text":"Alex Oesterling, Claudio Mayrink Verdun, Flavio P. Calmon, Himabindu Lakkaraju","cross_cats":["cs.AI","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2025-05-06T04:03:11Z","title":"Soft Best-of-n Sampling for Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03156","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":"sha256:166a15c377d43ff437be00f122b52710eedf5078b982d1eaa20e286a8cb6d140","target":"record","created_at":"2026-07-05T10:59:10Z","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":"8406288a1eb6776e3bed064f1684d6b035a51e072ca7ff4d89786beec7ec2971","cross_cats_sorted":["cs.AI","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IT","submitted_at":"2025-05-06T04:03:11Z","title_canon_sha256":"27805f6ebf069ef404d0d78f5e0004a725126a625a49c1067d4359c3080a08ed"},"schema_version":"1.0","source":{"id":"2505.03156","kind":"arxiv","version":1}},"canonical_sha256":"2f4ff36c584676e6c2fc19ed9170269f3aad63b3f156743cc8c5c3eecc9fde14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f4ff36c584676e6c2fc19ed9170269f3aad63b3f156743cc8c5c3eecc9fde14","first_computed_at":"2026-07-05T10:59:10.985201Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:10.985201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DQvWaPIYB5+TgcW0uDLYBrlppQUI33P47KauyoPwrvASNT0x16TnkYYckWSQRMp6vaH320nQTHJCU+yMG8DZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:10.985686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03156","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:166a15c377d43ff437be00f122b52710eedf5078b982d1eaa20e286a8cb6d140","sha256:feefb50a308aa7d1c3afb7f9b43326fde3b33174b36a1aede626bee42b6845ab"],"state_sha256":"23e13c7e676c01b1ea747a268c8a6000c486a2bf9974bcfede38824f87a0be59"}