{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SV2CP7DQZPIAV4WZPFHBFEC5KZ","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":"a6736a93b8acf07c58ec1fdf93f414deac667fc9390bed72286533d1d8489b7e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T15:43:55Z","title_canon_sha256":"66a6d37c918b2b05c534fd2c38c63bdc1b449f3d4169abde9783f32e14464c3e"},"schema_version":"1.0","source":{"id":"2410.08048","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08048","created_at":"2026-07-05T09:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08048v1","created_at":"2026-07-05T09:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08048","created_at":"2026-07-05T09:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"SV2CP7DQZPIA","created_at":"2026-07-05T09:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"SV2CP7DQZPIAV4WZ","created_at":"2026-07-05T09:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"SV2CP7DQ","created_at":"2026-07-05T09:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:02693c156fc57858510c2e80ab0e9bb63c1a67de604d7867eea1209069b015c9","target":"graph","created_at":"2026-07-05T09:18:47Z","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/2410.08048/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in test time compute, particularly through the use of verifier models, have significantly enhanced the reasoning capabilities of Large Language Models (LLMs). This generator-verifier approach closely resembles the actor-critic framework in reinforcement learning (RL). However, current verifier models in LLMs often rely on supervised fine-tuning without temporal difference learning such as Q-learning. This paper introduces VerifierQ, a novel approach that integrates Offline Q-learning into LLM verifier models. We address three key challenges in applying Q-learning to LLMs: (","authors_text":"Hao Tang, Jianing Qi, Zhigang Zhu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T15:43:55Z","title":"VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08048","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":"sha256:9bb4c8dd752cf051ef76f910404c815a7b410f986d4893543d26bfb0a01a7340","target":"record","created_at":"2026-07-05T09:18:47Z","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":"a6736a93b8acf07c58ec1fdf93f414deac667fc9390bed72286533d1d8489b7e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T15:43:55Z","title_canon_sha256":"66a6d37c918b2b05c534fd2c38c63bdc1b449f3d4169abde9783f32e14464c3e"},"schema_version":"1.0","source":{"id":"2410.08048","kind":"arxiv","version":1}},"canonical_sha256":"957427fc70cbd00af2d9794e12905d564d8e615f65ae50be23fc857c0348523d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"957427fc70cbd00af2d9794e12905d564d8e615f65ae50be23fc857c0348523d","first_computed_at":"2026-07-05T09:18:47.872568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:47.872568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0RYnLkHBmp6Kbk8EAAaWTk64eKxCIjBj0RlQovBJ01VVb+ugtYNfqNCXFTPVOe4gAH4I7HHm5QyIbnqJp0IKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:47.873051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08048","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bb4c8dd752cf051ef76f910404c815a7b410f986d4893543d26bfb0a01a7340","sha256:02693c156fc57858510c2e80ab0e9bb63c1a67de604d7867eea1209069b015c9"],"state_sha256":"f7dcba89269fa50c5e3bcb7548d270e5ffc9680dd0ff986ad41c9a07aab82373"}