{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K5M3J6QPFFOIYWLD67OH45M6CR","short_pith_number":"pith:K5M3J6QP","canonical_record":{"source":{"id":"2507.05913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-08T11:59:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"67a9e1e8087766196e787231f4c5d44b1e0eb507b531389bc7a0b6fe9671c180","abstract_canon_sha256":"5169db44ff1149174e6a20b62ed64a81ff68d968eef3cc385db97c1a599e7d00"},"schema_version":"1.0"},"canonical_sha256":"5759b4fa0f295c8c5963f7dc7e759e147d2ad441171c753433e3d5b6e50c8399","source":{"kind":"arxiv","id":"2507.05913","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05913","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05913v1","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05913","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"pith_short_12","alias_value":"K5M3J6QPFFOI","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"pith_short_16","alias_value":"K5M3J6QPFFOIYWLD","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"pith_short_8","alias_value":"K5M3J6QP","created_at":"2026-07-05T11:33:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K5M3J6QPFFOIYWLD67OH45M6CR","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-08T11:59:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"67a9e1e8087766196e787231f4c5d44b1e0eb507b531389bc7a0b6fe9671c180","abstract_canon_sha256":"5169db44ff1149174e6a20b62ed64a81ff68d968eef3cc385db97c1a599e7d00"},"schema_version":"1.0"},"canonical_sha256":"5759b4fa0f295c8c5963f7dc7e759e147d2ad441171c753433e3d5b6e50c8399","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:38.299732Z","signature_b64":"j4obLRpl8+0ldD7ySnzqmJ6EESibFhCNInb35lyfabcbIoGAMWs1rWwQVkRsyHwUYWOoV2Sph1F9K5gE+oQpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5759b4fa0f295c8c5963f7dc7e759e147d2ad441171c753433e3d5b6e50c8399","last_reissued_at":"2026-07-05T11:33:38.299212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:38.299212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05913","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DQXGSsuaFTBEGTbul0Ty7Wt3wuiEdRFgJb7FdicCxzJN3IQx/GVxAxTdpOwJ+zkIah0zXPveUE3UxzvDWWqGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:46:00.396183Z"},"content_sha256":"3dc2d60e21f50143bf91276f1a2d29c82db9fb6096c2200e1cfdfb49c8b317f9","schema_version":"1.0","event_id":"sha256:3dc2d60e21f50143bf91276f1a2d29c82db9fb6096c2200e1cfdfb49c8b317f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K5M3J6QPFFOIYWLD67OH45M6CR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ahmad Beirami, Amir R. Asadi, Gholamali Aminian, Idan Shenfeld, Youssef Mroueh","submitted_at":"2025-07-08T11:59:48Z","abstract_excerpt":"A simple yet effective method for inference-time alignment of generative models is Best-of-$N$ (BoN), where $N$ outcomes are sampled from a reference policy, evaluated using a proxy reward model, and the highest-scoring one is selected. While prior work argues that BoN is almost optimal in reward vs KL tradeoffs, the effectiveness of BoN depends critically on the quality of the proxy reward model used for selection. For this purpose, we study BoN through a smooth version known as Soft Best-of-N (SBoN) and develop a theoretical framework to address this gap. We analyze the scaling behaviour of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05913","kind":"arxiv","version":1},"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/2507.05913/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4U2SCldr9Y5m/kuy/EZFDxJkP+5AbrQlfEXkFZHy3EBFSKm16bZcYNfEqmoXle1samGFP+tPnD06JrC9Lk1HDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T13:46:00.398606Z"},"content_sha256":"f932fb44cf8c32af4a6127b02d28caa1cb9328665e0e4166129215cd35149eee","schema_version":"1.0","event_id":"sha256:f932fb44cf8c32af4a6127b02d28caa1cb9328665e0e4166129215cd35149eee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5M3J6QPFFOIYWLD67OH45M6CR/bundle.json","state_url":"https://pith.science/pith/K5M3J6QPFFOIYWLD67OH45M6CR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5M3J6QPFFOIYWLD67OH45M6CR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T13:46:00Z","links":{"resolver":"https://pith.science/pith/K5M3J6QPFFOIYWLD67OH45M6CR","bundle":"https://pith.science/pith/K5M3J6QPFFOIYWLD67OH45M6CR/bundle.json","state":"https://pith.science/pith/K5M3J6QPFFOIYWLD67OH45M6CR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5M3J6QPFFOIYWLD67OH45M6CR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K5M3J6QPFFOIYWLD67OH45M6CR","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":"5169db44ff1149174e6a20b62ed64a81ff68d968eef3cc385db97c1a599e7d00","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-08T11:59:48Z","title_canon_sha256":"67a9e1e8087766196e787231f4c5d44b1e0eb507b531389bc7a0b6fe9671c180"},"schema_version":"1.0","source":{"id":"2507.05913","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05913","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05913v1","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05913","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"pith_short_12","alias_value":"K5M3J6QPFFOI","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"pith_short_16","alias_value":"K5M3J6QPFFOIYWLD","created_at":"2026-07-05T11:33:38Z"},{"alias_kind":"pith_short_8","alias_value":"K5M3J6QP","created_at":"2026-07-05T11:33:38Z"}],"graph_snapshots":[{"event_id":"sha256:f932fb44cf8c32af4a6127b02d28caa1cb9328665e0e4166129215cd35149eee","target":"graph","created_at":"2026-07-05T11:33:38Z","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/2507.05913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A simple yet effective method for inference-time alignment of generative models is Best-of-$N$ (BoN), where $N$ outcomes are sampled from a reference policy, evaluated using a proxy reward model, and the highest-scoring one is selected. While prior work argues that BoN is almost optimal in reward vs KL tradeoffs, the effectiveness of BoN depends critically on the quality of the proxy reward model used for selection. For this purpose, we study BoN through a smooth version known as Soft Best-of-N (SBoN) and develop a theoretical framework to address this gap. We analyze the scaling behaviour of ","authors_text":"Ahmad Beirami, Amir R. Asadi, Gholamali Aminian, Idan Shenfeld, Youssef Mroueh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-08T11:59:48Z","title":"Best-of-N through the Smoothing Lens: KL Divergence and Regret Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05913","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":"sha256:3dc2d60e21f50143bf91276f1a2d29c82db9fb6096c2200e1cfdfb49c8b317f9","target":"record","created_at":"2026-07-05T11:33:38Z","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":"5169db44ff1149174e6a20b62ed64a81ff68d968eef3cc385db97c1a599e7d00","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-07-08T11:59:48Z","title_canon_sha256":"67a9e1e8087766196e787231f4c5d44b1e0eb507b531389bc7a0b6fe9671c180"},"schema_version":"1.0","source":{"id":"2507.05913","kind":"arxiv","version":1}},"canonical_sha256":"5759b4fa0f295c8c5963f7dc7e759e147d2ad441171c753433e3d5b6e50c8399","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5759b4fa0f295c8c5963f7dc7e759e147d2ad441171c753433e3d5b6e50c8399","first_computed_at":"2026-07-05T11:33:38.299212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:38.299212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j4obLRpl8+0ldD7ySnzqmJ6EESibFhCNInb35lyfabcbIoGAMWs1rWwQVkRsyHwUYWOoV2Sph1F9K5gE+oQpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:38.299732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05913","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dc2d60e21f50143bf91276f1a2d29c82db9fb6096c2200e1cfdfb49c8b317f9","sha256:f932fb44cf8c32af4a6127b02d28caa1cb9328665e0e4166129215cd35149eee"],"state_sha256":"c6a6f200a85a60395b7912a595f6cd0bcfb11d5560d7c70016a8602e8813069c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9l3909pb1kJduN2aabGKCTSQ3+vJUBlMk5iLUfcusNQxznuemjgK1SPjQ12I4PuAgO0bMEg9txxLO3gSRwXUAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T13:46:00.421652Z","bundle_sha256":"57ec358321bf81942bdb01b902c5af381a4e53c379f41605c70a30c1235cc676"}}