{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CBZB7GAJL3GVXG2IYJK6GXHMD2","short_pith_number":"pith:CBZB7GAJ","schema_version":"1.0","canonical_sha256":"10721f98095ecd5b9b48c255e35cec1eaec89e760b36d97e062fd11238ecee92","source":{"kind":"arxiv","id":"1702.08431","version":4},"attestation_state":"computed","paper":{"title":"Boundary-Seeking Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam Trischler, Athul Paul Jacob, Kyunghyun Cho, R Devon Hjelm, Tong Che, Yoshua Bengio","submitted_at":"2017-02-27T18:51:41Z","abstract_excerpt":"Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus do not work for discrete data. We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator. The importa"},"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":"1702.08431","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-27T18:51:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c1f10ef81f0b417274d81dfdf8b028a9ee5883d0cdca0b635173e57fef8c7fbb","abstract_canon_sha256":"a02702553078e27f90ad35d9717d1a7335ed921cecf1aac8ddd55529335aab98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:49.368695Z","signature_b64":"qEankbWHPiu3zocZA8zIcl7TMGWKhOzKlsFVRNRmd/XLFIJjkAe7qNSTyl7mBcEC2e0dMPeq3GYfx05rKp4KBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10721f98095ecd5b9b48c255e35cec1eaec89e760b36d97e062fd11238ecee92","last_reissued_at":"2026-05-18T00:22:49.368145Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:49.368145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boundary-Seeking Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Adam Trischler, Athul Paul Jacob, Kyunghyun Cho, R Devon Hjelm, Tong Che, Yoshua Bengio","submitted_at":"2017-02-27T18:51:41Z","abstract_excerpt":"Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus do not work for discrete data. We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator. The importa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08431","kind":"arxiv","version":4},"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":"1702.08431","created_at":"2026-05-18T00:22:49.368218+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08431v4","created_at":"2026-05-18T00:22:49.368218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08431","created_at":"2026-05-18T00:22:49.368218+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBZB7GAJL3GV","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBZB7GAJL3GVXG2I","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBZB7GAJ","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1710.10196","citing_title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2","json":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2.json","graph_json":"https://pith.science/api/pith-number/CBZB7GAJL3GVXG2IYJK6GXHMD2/graph.json","events_json":"https://pith.science/api/pith-number/CBZB7GAJL3GVXG2IYJK6GXHMD2/events.json","paper":"https://pith.science/paper/CBZB7GAJ"},"agent_actions":{"view_html":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2","download_json":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2.json","view_paper":"https://pith.science/paper/CBZB7GAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08431&json=true","fetch_graph":"https://pith.science/api/pith-number/CBZB7GAJL3GVXG2IYJK6GXHMD2/graph.json","fetch_events":"https://pith.science/api/pith-number/CBZB7GAJL3GVXG2IYJK6GXHMD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2/action/storage_attestation","attest_author":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2/action/author_attestation","sign_citation":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2/action/citation_signature","submit_replication":"https://pith.science/pith/CBZB7GAJL3GVXG2IYJK6GXHMD2/action/replication_record"}},"created_at":"2026-05-18T00:22:49.368218+00:00","updated_at":"2026-05-18T00:22:49.368218+00:00"}