{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:L444FFWMPG3WQYV3KISUOG3GFH","short_pith_number":"pith:L444FFWM","schema_version":"1.0","canonical_sha256":"5f39c296cc79b76862bb5225471b6629dcc5aab47fb4f1198dea0a34420e0eb9","source":{"kind":"arxiv","id":"1811.00696","version":1},"attestation_state":"computed","paper":{"title":"Sequence Generation with Guider Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyou Chen, Dinghan Shen, Guoyin Wang, Lawrence Carin, Liqun Chen, Ruiyi Zhang, Wenlin Wang, Zhe Gan","submitted_at":"2018-11-02T01:21:17Z","abstract_excerpt":"Sequence generation with reinforcement learning (RL) has received significant attention recently. However, a challenge with such methods is the sparse-reward problem in the RL training process, in which a scalar guiding signal is often only available after an entire sequence has been generated. This type of sparse reward tends to ignore the global structural information of a sequence, causing generation of sequences that are semantically inconsistent. In this paper, we present a model-based RL approach to overcome this issue. Specifically, we propose a novel guider network to model the sequenc"},"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":"1811.00696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T01:21:17Z","cross_cats_sorted":[],"title_canon_sha256":"419e9a463d0e356147a27d2a89303d52ec9f3db583a999a0e09ed87c3de09fac","abstract_canon_sha256":"95a2be27b13b4807c4838eff29b1f0e2c4ff5e759f3408e655d37b24d6d0d5eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:42.481273Z","signature_b64":"PPp8X2tQjQ+DROC2XRfOiVA9Q+9qUMiQwlKeW5YSvNEKCwmj6kWOETTxN62uJ3APV43APbiXYf8c9kj/Xq9nDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f39c296cc79b76862bb5225471b6629dcc5aab47fb4f1198dea0a34420e0eb9","last_reissued_at":"2026-05-18T00:01:42.480841Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:42.480841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequence Generation with Guider Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changyou Chen, Dinghan Shen, Guoyin Wang, Lawrence Carin, Liqun Chen, Ruiyi Zhang, Wenlin Wang, Zhe Gan","submitted_at":"2018-11-02T01:21:17Z","abstract_excerpt":"Sequence generation with reinforcement learning (RL) has received significant attention recently. However, a challenge with such methods is the sparse-reward problem in the RL training process, in which a scalar guiding signal is often only available after an entire sequence has been generated. This type of sparse reward tends to ignore the global structural information of a sequence, causing generation of sequences that are semantically inconsistent. In this paper, we present a model-based RL approach to overcome this issue. Specifically, we propose a novel guider network to model the sequenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00696","kind":"arxiv","version":1},"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":"1811.00696","created_at":"2026-05-18T00:01:42.480904+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00696v1","created_at":"2026-05-18T00:01:42.480904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00696","created_at":"2026-05-18T00:01:42.480904+00:00"},{"alias_kind":"pith_short_12","alias_value":"L444FFWMPG3W","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"L444FFWMPG3WQYV3","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"L444FFWM","created_at":"2026-05-18T12:32:33.847187+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH","json":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH.json","graph_json":"https://pith.science/api/pith-number/L444FFWMPG3WQYV3KISUOG3GFH/graph.json","events_json":"https://pith.science/api/pith-number/L444FFWMPG3WQYV3KISUOG3GFH/events.json","paper":"https://pith.science/paper/L444FFWM"},"agent_actions":{"view_html":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH","download_json":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH.json","view_paper":"https://pith.science/paper/L444FFWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00696&json=true","fetch_graph":"https://pith.science/api/pith-number/L444FFWMPG3WQYV3KISUOG3GFH/graph.json","fetch_events":"https://pith.science/api/pith-number/L444FFWMPG3WQYV3KISUOG3GFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH/action/storage_attestation","attest_author":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH/action/author_attestation","sign_citation":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH/action/citation_signature","submit_replication":"https://pith.science/pith/L444FFWMPG3WQYV3KISUOG3GFH/action/replication_record"}},"created_at":"2026-05-18T00:01:42.480904+00:00","updated_at":"2026-05-18T00:01:42.480904+00:00"}