{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VYWLUPAD7QU6YDWWYA647D5IWZ","short_pith_number":"pith:VYWLUPAD","canonical_record":{"source":{"id":"2310.17022","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T22:00:05Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6043eb8476b1a8b17d1911a2ee33074b7c0e315b8f0992b00bc0830610c8aefd","abstract_canon_sha256":"d93f01f494854b393b8756e7e8999e09ac311ba6b156df170ffaadf01e82df91"},"schema_version":"1.0"},"canonical_sha256":"ae2cba3c03fc29ec0ed6c03dcf8fa8b656c6f8c36c62d607c63dfd8cd78e944e","source":{"kind":"arxiv","id":"2310.17022","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17022","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17022v3","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17022","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"VYWLUPAD7QU6","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"VYWLUPAD7QU6YDWW","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"VYWLUPAD","created_at":"2026-07-05T08:26:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VYWLUPAD7QU6YDWWYA647D5IWZ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17022","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T22:00:05Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6043eb8476b1a8b17d1911a2ee33074b7c0e315b8f0992b00bc0830610c8aefd","abstract_canon_sha256":"d93f01f494854b393b8756e7e8999e09ac311ba6b156df170ffaadf01e82df91"},"schema_version":"1.0"},"canonical_sha256":"ae2cba3c03fc29ec0ed6c03dcf8fa8b656c6f8c36c62d607c63dfd8cd78e944e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:42.973046Z","signature_b64":"MKsvUiiSCei2iE+oX0zLwzKIWws5xG+lUwsG2EY44eN5lhEsaKGJqEMyyLa71OMOfYsh6n5DI3a8N5XO6QVsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae2cba3c03fc29ec0ed6c03dcf8fa8b656c6f8c36c62d607c63dfd8cd78e944e","last_reissued_at":"2026-07-05T08:26:42.972572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:42.972572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17022","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RL+gWEqZOww91hJaGhdiRf3fjJllBjv+JKXj7IQSvND10jjSKxB2BA8VNPNZeRaqH7EwLIlzhx3KXkRkN8Z2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:55:37.617555Z"},"content_sha256":"6aa30b90f224c536d5b51b0e88c55c71ce25d1c38df47395b86a3119880500c0","schema_version":"1.0","event_id":"sha256:6aa30b90f224c536d5b51b0e88c55c71ce25d1c38df47395b86a3119880500c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VYWLUPAD7QU6YDWWYA647D5IWZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Controlled Decoding from Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ahmad Beirami, Alex Beutel, Harish Ganapathy, Heng-Tze Cheng, Jilin Chen, Jong Lee, Michael Collins, Sidharth Mudgal, Tao Wang, Trevor Strohman, Yaguang Li, Yanping Huang, Zhifeng Chen","submitted_at":"2023-10-25T22:00:05Z","abstract_excerpt":"KL-regularized reinforcement learning (RL) is a popular alignment framework to control the language model responses towards high reward outcomes. We pose a tokenwise RL objective and propose a modular solver for it, called controlled decoding (CD). CD exerts control through a separate prefix scorer module, which is trained to learn a value function for the reward. The prefix scorer is used at inference time to control the generation from a frozen base model, provably sampling from a solution to the RL objective. We empirically demonstrate that CD is effective as a control mechanism on popular "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17022","kind":"arxiv","version":3},"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/2310.17022/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":"2026-07-05T08:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+yXrvRb+uzCAFiA7W73c4cQCho969ADJIgMtAwfMiJthQihiAuCjHDPN8L5M+dU+xIfAvOw0YZ/Y7HXIahcMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:55:37.617943Z"},"content_sha256":"bda11fc6d7a4ac4ac9059c4b87a4f1d106556a2f7894b718fda360e6914a48fc","schema_version":"1.0","event_id":"sha256:bda11fc6d7a4ac4ac9059c4b87a4f1d106556a2f7894b718fda360e6914a48fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VYWLUPAD7QU6YDWWYA647D5IWZ/bundle.json","state_url":"https://pith.science/pith/VYWLUPAD7QU6YDWWYA647D5IWZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VYWLUPAD7QU6YDWWYA647D5IWZ/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":"2026-07-07T06:55:37Z","links":{"resolver":"https://pith.science/pith/VYWLUPAD7QU6YDWWYA647D5IWZ","bundle":"https://pith.science/pith/VYWLUPAD7QU6YDWWYA647D5IWZ/bundle.json","state":"https://pith.science/pith/VYWLUPAD7QU6YDWWYA647D5IWZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VYWLUPAD7QU6YDWWYA647D5IWZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VYWLUPAD7QU6YDWWYA647D5IWZ","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":"d93f01f494854b393b8756e7e8999e09ac311ba6b156df170ffaadf01e82df91","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T22:00:05Z","title_canon_sha256":"6043eb8476b1a8b17d1911a2ee33074b7c0e315b8f0992b00bc0830610c8aefd"},"schema_version":"1.0","source":{"id":"2310.17022","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17022","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17022v3","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17022","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"VYWLUPAD7QU6","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"VYWLUPAD7QU6YDWW","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"VYWLUPAD","created_at":"2026-07-05T08:26:42Z"}],"graph_snapshots":[{"event_id":"sha256:bda11fc6d7a4ac4ac9059c4b87a4f1d106556a2f7894b718fda360e6914a48fc","target":"graph","created_at":"2026-07-05T08:26:42Z","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/2310.17022/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"KL-regularized reinforcement learning (RL) is a popular alignment framework to control the language model responses towards high reward outcomes. We pose a tokenwise RL objective and propose a modular solver for it, called controlled decoding (CD). CD exerts control through a separate prefix scorer module, which is trained to learn a value function for the reward. The prefix scorer is used at inference time to control the generation from a frozen base model, provably sampling from a solution to the RL objective. We empirically demonstrate that CD is effective as a control mechanism on popular ","authors_text":"Ahmad Beirami, Alex Beutel, Harish Ganapathy, Heng-Tze Cheng, Jilin Chen, Jong Lee, Michael Collins, Sidharth Mudgal, Tao Wang, Trevor Strohman, Yaguang Li, Yanping Huang, Zhifeng Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T22:00:05Z","title":"Controlled Decoding from Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17022","kind":"arxiv","version":3},"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":"sha256:6aa30b90f224c536d5b51b0e88c55c71ce25d1c38df47395b86a3119880500c0","target":"record","created_at":"2026-07-05T08:26:42Z","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":"d93f01f494854b393b8756e7e8999e09ac311ba6b156df170ffaadf01e82df91","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T22:00:05Z","title_canon_sha256":"6043eb8476b1a8b17d1911a2ee33074b7c0e315b8f0992b00bc0830610c8aefd"},"schema_version":"1.0","source":{"id":"2310.17022","kind":"arxiv","version":3}},"canonical_sha256":"ae2cba3c03fc29ec0ed6c03dcf8fa8b656c6f8c36c62d607c63dfd8cd78e944e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae2cba3c03fc29ec0ed6c03dcf8fa8b656c6f8c36c62d607c63dfd8cd78e944e","first_computed_at":"2026-07-05T08:26:42.972572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:42.972572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MKsvUiiSCei2iE+oX0zLwzKIWws5xG+lUwsG2EY44eN5lhEsaKGJqEMyyLa71OMOfYsh6n5DI3a8N5XO6QVsAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:42.973046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17022","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6aa30b90f224c536d5b51b0e88c55c71ce25d1c38df47395b86a3119880500c0","sha256:bda11fc6d7a4ac4ac9059c4b87a4f1d106556a2f7894b718fda360e6914a48fc"],"state_sha256":"86da7e571aee9c0b7a85fd9a480dda1f50790a1e5b6da7fb70de98bc3ecfc27e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cIN/VfAn1eUO6d5hzAWw3HMQXMgiJRNJ0vMSCudS9jVx6/1Cbvi9AVo2caodtL0U7xfB4mkEjY1PbX3cfDteAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:55:37.620061Z","bundle_sha256":"db854870b9d5f3092b9c29185db52215755996d2a5b875b48dbe364c986297c4"}}