{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OTIMNFZCKV7Y4RCWP6NNWMAD2S","short_pith_number":"pith:OTIMNFZC","schema_version":"1.0","canonical_sha256":"74d0c69722557f8e44567f9adb3003d491d25e1c2b5c9d7fb076cf9c17d48ea1","source":{"kind":"arxiv","id":"1706.03850","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Feature Matching for Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dinghan Shen, Kai Fan, Lawrence Carin, Ricardo Henao, Yizhe Zhang, Zhe Gan, Zhi Chen","submitted_at":"2017-06-12T20:55:51Z","abstract_excerpt":"The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We employ a long short-term memory network as generator, and a convolutional network as discriminator. Instead of using the standard objective of GAN, we propose matching the high-dimensional latent feature distributions of real and synthetic sentences, via a kernelized discrepancy met"},"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":"1706.03850","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-06-12T20:55:51Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"57368f2df2b5bb228f78ce8f1e089dcb03485ab25088ccd4db57b7e77e0c4060","abstract_canon_sha256":"39e6672231fc67ed81f79b9cfeca6771a617b1649d1d3cb6f0fd0ae6e9ce5e60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:16.732594Z","signature_b64":"333IX37htZIpsWybRR/ZJn7kNRBG4Tqvbfmh1mLg1Mgv1e14X4vN+mV0ZB2gI2JQ2tdPnPp7zOoQTmQCxU0kCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74d0c69722557f8e44567f9adb3003d491d25e1c2b5c9d7fb076cf9c17d48ea1","last_reissued_at":"2026-05-18T00:30:16.731985Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:16.731985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Feature Matching for Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Dinghan Shen, Kai Fan, Lawrence Carin, Ricardo Henao, Yizhe Zhang, Zhe Gan, Zhi Chen","submitted_at":"2017-06-12T20:55:51Z","abstract_excerpt":"The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We employ a long short-term memory network as generator, and a convolutional network as discriminator. Instead of using the standard objective of GAN, we propose matching the high-dimensional latent feature distributions of real and synthetic sentences, via a kernelized discrepancy met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03850","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":""},"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":"1706.03850","created_at":"2026-05-18T00:30:16.732092+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.03850v3","created_at":"2026-05-18T00:30:16.732092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03850","created_at":"2026-05-18T00:30:16.732092+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTIMNFZCKV7Y","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTIMNFZCKV7Y4RCW","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTIMNFZC","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00139","citing_title":"Deep Learning for CMB Foreground Removal and Beam Deconvolution: A U-Net GAN Approach","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S","json":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S.json","graph_json":"https://pith.science/api/pith-number/OTIMNFZCKV7Y4RCWP6NNWMAD2S/graph.json","events_json":"https://pith.science/api/pith-number/OTIMNFZCKV7Y4RCWP6NNWMAD2S/events.json","paper":"https://pith.science/paper/OTIMNFZC"},"agent_actions":{"view_html":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S","download_json":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S.json","view_paper":"https://pith.science/paper/OTIMNFZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.03850&json=true","fetch_graph":"https://pith.science/api/pith-number/OTIMNFZCKV7Y4RCWP6NNWMAD2S/graph.json","fetch_events":"https://pith.science/api/pith-number/OTIMNFZCKV7Y4RCWP6NNWMAD2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S/action/storage_attestation","attest_author":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S/action/author_attestation","sign_citation":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S/action/citation_signature","submit_replication":"https://pith.science/pith/OTIMNFZCKV7Y4RCWP6NNWMAD2S/action/replication_record"}},"created_at":"2026-05-18T00:30:16.732092+00:00","updated_at":"2026-05-18T00:30:16.732092+00:00"}