{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DT7KGEF35RI56XRN43RYREYUPX","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":"edaaca028be5657aa59ee544efb892e4db6aa2b8d6a00f56ae404f76272b1a74","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-27T18:00:08Z","title_canon_sha256":"720afa453ef9992e3b1d2c2b6aa24ac6979557b07ca2e2123ab51b5937bfa66c"},"schema_version":"1.0","source":{"id":"2503.21878","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.21878","created_at":"2026-07-05T10:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2503.21878v2","created_at":"2026-07-05T10:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21878","created_at":"2026-07-05T10:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"DT7KGEF35RI5","created_at":"2026-07-05T10:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"DT7KGEF35RI56XRN","created_at":"2026-07-05T10:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"DT7KGEF3","created_at":"2026-07-05T10:45:39Z"}],"graph_snapshots":[{"event_id":"sha256:64b58a4a594a10ff23406bb0fc45bb51eea4d25ff8b26891e4219b7672edf76a","target":"graph","created_at":"2026-07-05T10:45:39Z","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/2503.21878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inference-time computation offers a powerful axis for scaling the performance of language models. However, naively increasing computation in techniques like Best-of-N sampling can lead to performance degradation due to reward hacking. Toward a theoretical understanding of how to best leverage additional computation, we focus on inference-time alignment, which we formalize as the problem of improving the quality of responses drawn from a pre-trained policy, given a prompt of interest and access to an imperfect reward model. We analyze the performance of inference-time alignment algorithms in te","authors_text":"Adam Block, Akshay Krishnamurthy, Audrey Huang, Dylan J. Foster, Nan Jiang, Qinghua Liu","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-27T18:00:08Z","title":"Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21878","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":"sha256:36cd4977c4948a6e49ab0e415ff921480d79d9b9d603b8675dcdd48868774322","target":"record","created_at":"2026-07-05T10:45:39Z","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":"edaaca028be5657aa59ee544efb892e4db6aa2b8d6a00f56ae404f76272b1a74","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-27T18:00:08Z","title_canon_sha256":"720afa453ef9992e3b1d2c2b6aa24ac6979557b07ca2e2123ab51b5937bfa66c"},"schema_version":"1.0","source":{"id":"2503.21878","kind":"arxiv","version":2}},"canonical_sha256":"1cfea310bbec51df5e2de6e38893147dd14d63f15caef77f1ac67acd177a0317","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cfea310bbec51df5e2de6e38893147dd14d63f15caef77f1ac67acd177a0317","first_computed_at":"2026-07-05T10:45:39.218272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:39.218272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g/4s2e3DmmGIibG7cWnfZAJHhxBPGS1BTghfvYI8OyQYkhRCa4g0+Ud4As38rK+ph1UGRyz5tkUSEDSa3xOLAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:39.218770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.21878","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36cd4977c4948a6e49ab0e415ff921480d79d9b9d603b8675dcdd48868774322","sha256:64b58a4a594a10ff23406bb0fc45bb51eea4d25ff8b26891e4219b7672edf76a"],"state_sha256":"cafa71d4b0c0ed73aa5161f790f4bf18a466c2691e5032743e0acd5ed849dcb9"}