{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3G5K23ZWPN2YY5EFFLVAWY7EJ4","short_pith_number":"pith:3G5K23ZW","schema_version":"1.0","canonical_sha256":"d9baad6f367b758c74852aea0b63e44f14635bd2f350b900c23e349670a19e65","source":{"kind":"arxiv","id":"1701.06549","version":2},"attestation_state":"computed","paper":{"title":"Learning to Decode for Future Success","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Jiwei Li, Will Monroe","submitted_at":"2017-01-23T18:36:37Z","abstract_excerpt":"We introduce a simple, general strategy to manipulate the behavior of a neural decoder that enables it to generate outputs that have specific properties of interest (e.g., sequences of a pre-specified length). The model can be thought of as a simple version of the actor-critic model that uses an interpolation of the actor (the MLE-based token generation policy) and the critic (a value function that estimates the future values of the desired property) for decision making. We demonstrate that the approach is able to incorporate a variety of properties that cannot be handled by standard neural se"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1701.06549","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-23T18:36:37Z","cross_cats_sorted":[],"title_canon_sha256":"d5c558939858662c6c34bf7d5e0be770d1f65681afc5b94ab9ad8b54420f3875","abstract_canon_sha256":"570f01fbd646b94bebbd1fe266656e2ab3d24d2a745f0d5fffa5d0db6ef70b01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:24.649823Z","signature_b64":"aHS6V6pGk7ifqy/KfncDnMeNJn2mYDXYIaytT1LPlp0Y+8MT7RdA0HISH1t3DERnmDVIgqGHucoEUHgojBXMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9baad6f367b758c74852aea0b63e44f14635bd2f350b900c23e349670a19e65","last_reissued_at":"2026-05-18T00:51:24.649190Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:24.649190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Decode for Future Success","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Jurafsky, Jiwei Li, Will Monroe","submitted_at":"2017-01-23T18:36:37Z","abstract_excerpt":"We introduce a simple, general strategy to manipulate the behavior of a neural decoder that enables it to generate outputs that have specific properties of interest (e.g., sequences of a pre-specified length). The model can be thought of as a simple version of the actor-critic model that uses an interpolation of the actor (the MLE-based token generation policy) and the critic (a value function that estimates the future values of the desired property) for decision making. We demonstrate that the approach is able to incorporate a variety of properties that cannot be handled by standard neural se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.06549","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1701.06549","created_at":"2026-05-18T00:51:24.649297+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.06549v2","created_at":"2026-05-18T00:51:24.649297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.06549","created_at":"2026-05-18T00:51:24.649297+00:00"},{"alias_kind":"pith_short_12","alias_value":"3G5K23ZWPN2Y","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3G5K23ZWPN2YY5EF","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3G5K23ZW","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2408.07199","citing_title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","ref_index":224,"is_internal_anchor":true},{"citing_arxiv_id":"2309.11495","citing_title":"Chain-of-Verification Reduces Hallucination in Large Language Models","ref_index":147,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4","json":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4.json","graph_json":"https://pith.science/api/pith-number/3G5K23ZWPN2YY5EFFLVAWY7EJ4/graph.json","events_json":"https://pith.science/api/pith-number/3G5K23ZWPN2YY5EFFLVAWY7EJ4/events.json","paper":"https://pith.science/paper/3G5K23ZW"},"agent_actions":{"view_html":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4","download_json":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4.json","view_paper":"https://pith.science/paper/3G5K23ZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.06549&json=true","fetch_graph":"https://pith.science/api/pith-number/3G5K23ZWPN2YY5EFFLVAWY7EJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/3G5K23ZWPN2YY5EFFLVAWY7EJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4/action/storage_attestation","attest_author":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4/action/author_attestation","sign_citation":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4/action/citation_signature","submit_replication":"https://pith.science/pith/3G5K23ZWPN2YY5EFFLVAWY7EJ4/action/replication_record"}},"created_at":"2026-05-18T00:51:24.649297+00:00","updated_at":"2026-05-18T00:51:24.649297+00:00"}