{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FKCQCTXZITCI3FWQR55KG3YLUX","short_pith_number":"pith:FKCQCTXZ","schema_version":"1.0","canonical_sha256":"2a85014ef944c48d96d08f7aa36f0ba5e8181dba751ad126667d9a3eec40eea2","source":{"kind":"arxiv","id":"1905.12835","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Sub-sequence for Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Song, Jiajun Chen, Jiuhua Zhang, Peng Jin, Xingyuan Chen, Xinyu Dai, Yanzhe Li","submitted_at":"2019-05-30T02:51:15Z","abstract_excerpt":"Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode collapse. To tackle these problems, we propose a novel mechanism. It first segments the entire sequence into several sub-sequences. Then these sub-sequences, together with the entire sequence, are evaluated individually by the discriminator. At last these feedback signals are all used to guide the learning of GAN. This mechanism learns the generation of both the e"},"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":"1905.12835","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T02:51:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4b52a57413a175addcf705fd4651dbf24ee651bec008d3caf77dbfcca58739c6","abstract_canon_sha256":"8ed5b17218d1165292a2f72fae5b9ceb34ba0bb78790aa3a674718ca5cee0d64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:39.537181Z","signature_b64":"zvzpgJNlRu07Bb01TG5dFK2XdSy9tAmo56VZkpaGA3CGH5HS4EgcgGmYwQRXYibk60WEA7w4WpCg1vpqQtCBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a85014ef944c48d96d08f7aa36f0ba5e8181dba751ad126667d9a3eec40eea2","last_reissued_at":"2026-05-17T23:44:39.536770Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:39.536770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Sub-sequence for Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Song, Jiajun Chen, Jiuhua Zhang, Peng Jin, Xingyuan Chen, Xinyu Dai, Yanzhe Li","submitted_at":"2019-05-30T02:51:15Z","abstract_excerpt":"Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode collapse. To tackle these problems, we propose a novel mechanism. It first segments the entire sequence into several sub-sequences. Then these sub-sequences, together with the entire sequence, are evaluated individually by the discriminator. At last these feedback signals are all used to guide the learning of GAN. This mechanism learns the generation of both the e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12835","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":"1905.12835","created_at":"2026-05-17T23:44:39.536830+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12835v1","created_at":"2026-05-17T23:44:39.536830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12835","created_at":"2026-05-17T23:44:39.536830+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKCQCTXZITCI","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKCQCTXZITCI3FWQ","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKCQCTXZ","created_at":"2026-05-18T12:33:15.570797+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/FKCQCTXZITCI3FWQR55KG3YLUX","json":"https://pith.science/pith/FKCQCTXZITCI3FWQR55KG3YLUX.json","graph_json":"https://pith.science/api/pith-number/FKCQCTXZITCI3FWQR55KG3YLUX/graph.json","events_json":"https://pith.science/api/pith-number/FKCQCTXZITCI3FWQR55KG3YLUX/events.json","paper":"https://pith.science/paper/FKCQCTXZ"},"agent_actions":{"view_html":"https://pith.science/pith/FKCQCTXZITCI3FWQR55KG3YLUX","download_json":"https://pith.science/pith/FKCQCTXZITCI3FWQR55KG3YLUX.json","view_paper":"https://pith.science/paper/FKCQCTXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12835&json=true","fetch_graph":"https://pith.science/api/pith-number/FKCQCTXZITCI3FWQR55KG3YLUX/graph.json","fetch_events":"https://pith.science/api/pith-number/FKCQCTXZITCI3FWQR55KG3YLUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKCQCTXZITCI3FWQR55KG3YLUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKCQCTXZITCI3FWQR55KG3YLUX/action/storage_attestation","attest_author":"https://pith.science/pith/FKCQCTXZITCI3FWQR55KG3YLUX/action/author_attestation","sign_citation":"https://pith.science/pith/FKCQCTXZITCI3FWQR55KG3YLUX/action/citation_signature","submit_replication":"https://pith.science/pith/FKCQCTXZITCI3FWQR55KG3YLUX/action/replication_record"}},"created_at":"2026-05-17T23:44:39.536830+00:00","updated_at":"2026-05-17T23:44:39.536830+00:00"}