{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RCDZCAHEWYKFWQ62Q7GT7WBESQ","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":"6593968d566dfda3f515354543d091729369d54eef476502a3c574e2bb06b306","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:58:24Z","title_canon_sha256":"801f582ffd8dbe1be02009aa5d5de0a93b54b44c492e319f29cd12bc46c3b550"},"schema_version":"1.0","source":{"id":"2410.08193","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08193","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08193v5","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08193","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_12","alias_value":"RCDZCAHEWYKF","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_16","alias_value":"RCDZCAHEWYKFWQ62","created_at":"2026-07-05T11:37:11Z"},{"alias_kind":"pith_short_8","alias_value":"RCDZCAHE","created_at":"2026-07-05T11:37:11Z"}],"graph_snapshots":[{"event_id":"sha256:af84d1255057e47f84c2529cd31e4235931b3a300c227a95eb614cd19dc127b2","target":"graph","created_at":"2026-07-05T11:37:11Z","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/2410.08193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) exhibit impressive capabilities but require careful alignment with human preferences. Traditional training-time methods finetune LLMs using human preference datasets but incur significant training costs and require repeated training to handle diverse user preferences. Test-time alignment methods address this by using reward models (RMs) to guide frozen LLMs without retraining. However, existing test-time approaches rely on trajectory-level RMs which are designed to evaluate complete responses, making them unsuitable for autoregressive text generation that requires ","authors_text":"Alec Koppel, Bang An, Furong Huang, Sicheng Zhu, Sumitra Ganesh, Udari Madhushani Sehwag, Yuancheng Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:58:24Z","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08193","kind":"arxiv","version":5},"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:de56f7320d978931a99f5096a6013e046136545eb56a685fa8f3646b633667dc","target":"record","created_at":"2026-07-05T11:37:11Z","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":"6593968d566dfda3f515354543d091729369d54eef476502a3c574e2bb06b306","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T17:58:24Z","title_canon_sha256":"801f582ffd8dbe1be02009aa5d5de0a93b54b44c492e319f29cd12bc46c3b550"},"schema_version":"1.0","source":{"id":"2410.08193","kind":"arxiv","version":5}},"canonical_sha256":"88879100e4b6145b43da87cd3fd824942b283e6838cbe2e3ad6770c2886eff21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88879100e4b6145b43da87cd3fd824942b283e6838cbe2e3ad6770c2886eff21","first_computed_at":"2026-07-05T11:37:11.461594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:11.461594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qzSseq6yz5naD9V3Y5SMqqOGZMfDLfkiPzUq0jHB8nDXcMOB38BqyzESWF7v9ywYWbeA/jx5epbSN+37KW0tCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:11.462027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08193","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de56f7320d978931a99f5096a6013e046136545eb56a685fa8f3646b633667dc","sha256:af84d1255057e47f84c2529cd31e4235931b3a300c227a95eb614cd19dc127b2"],"state_sha256":"94bf646b2a23ae0deffc09137ac4916634cf464916095deacfb1f2f9c89abfa7"}