{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DLMTC2XYUADOF23FLLFGDNETX3","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":"3ec9ab30a500fe26e8acb05badcd5237f057e30d757038beaa0d908069dd31d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T11:25:41Z","title_canon_sha256":"2bbfc8a98a88e6750614c95872c2a2f6024e6439b5efa1b9b21d63cdbaecbb9f"},"schema_version":"1.0","source":{"id":"2212.10938","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.10938","created_at":"2026-07-05T05:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2212.10938v1","created_at":"2026-07-05T05:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10938","created_at":"2026-07-05T05:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"DLMTC2XYUADO","created_at":"2026-07-05T05:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"DLMTC2XYUADOF23F","created_at":"2026-07-05T05:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"DLMTC2XY","created_at":"2026-07-05T05:27:24Z"}],"graph_snapshots":[{"event_id":"sha256:c62d038665d4af6299ee239a1258e67647c6615ee21ea6144eb39bc4d8a81380","target":"graph","created_at":"2026-07-05T05:27:24Z","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/2212.10938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Steering language generation towards objectives or away from undesired content has been a long-standing goal in utilizing language models (LM). Recent work has demonstrated reinforcement learning and weighted decoding as effective approaches to achieve a higher level of language control and quality with pros and cons. In this work, we propose a novel critic decoding method for controlled language generation (CriticControl) that combines the strengths of reinforcement learning and weighted decoding. Specifically, we adopt the actor-critic framework to train an LM-steering critic from non-differ","authors_text":"Hwanhee Lee, Hwaran Lee, Joonsuk Park, Kang Min Yoo, Kyomin Jung, Minbeom Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T11:25:41Z","title":"Critic-Guided Decoding for Controlled Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10938","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":"sha256:0097ca4f95d6592802f67a4531d0e299ac49e2fdd9aa04657c27d4e0e39b2fb3","target":"record","created_at":"2026-07-05T05:27:24Z","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":"3ec9ab30a500fe26e8acb05badcd5237f057e30d757038beaa0d908069dd31d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T11:25:41Z","title_canon_sha256":"2bbfc8a98a88e6750614c95872c2a2f6024e6439b5efa1b9b21d63cdbaecbb9f"},"schema_version":"1.0","source":{"id":"2212.10938","kind":"arxiv","version":1}},"canonical_sha256":"1ad9316af8a006e2eb655aca61b493bede437d570b3747bd759763986b6601ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ad9316af8a006e2eb655aca61b493bede437d570b3747bd759763986b6601ac","first_computed_at":"2026-07-05T05:27:24.616515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:27:24.616515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b8FzeB7L69Pk/zMkDqVuBNo5HQ2XkZ/pn9EnDTOtHs2mnlOsuU9OSBOCPq3XeupZDr3cjq84d5VVfl2EkW1yBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:27:24.616978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.10938","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0097ca4f95d6592802f67a4531d0e299ac49e2fdd9aa04657c27d4e0e39b2fb3","sha256:c62d038665d4af6299ee239a1258e67647c6615ee21ea6144eb39bc4d8a81380"],"state_sha256":"8aed25d8e745e0e23e98f7abba1db679e594c2ef88fc8b59660918e314fe7c5f"}