{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3BGTSADX7QSONNT3XMPMVMOI3I","short_pith_number":"pith:3BGTSADX","schema_version":"1.0","canonical_sha256":"d84d390077fc24e6b67bbb1ecab1c8da13287891a5afd68e975337cc58ae1e59","source":{"kind":"arxiv","id":"1710.10779","version":1},"attestation_state":"computed","paper":{"title":"Generative Adversarial Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.SD","authors_text":"Cem Subakan, Paris Smaragdis","submitted_at":"2017-10-30T05:42:25Z","abstract_excerpt":"Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density. We show on a speech source separation experiment that, a multi-layer perceptron trained with a Wasserstein-GAN formulation outperforms NMF, auto-encoders trained with maximum likelihood, and variational auto-encoders in terms of source to distortion ratio."},"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":"1710.10779","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-10-30T05:42:25Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"0c216e4cde153eb457769e521d23f83d785739ed8bd2253a987ea362fb675e17","abstract_canon_sha256":"6aa0674aa57e74e0245b179ac1df315bd733f4b89ae75334a079a85047cf4984"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:46.516735Z","signature_b64":"lj/u7wFS/ZGeQDyBLIC2llDoInurMymCjmwku2h6aBFw4raLQlsa+mg59S4MIs94XozvS0gyoSMrQ20L40RUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d84d390077fc24e6b67bbb1ecab1c8da13287891a5afd68e975337cc58ae1e59","last_reissued_at":"2026-05-18T00:31:46.516188Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:46.516188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Adversarial Source Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.SD","authors_text":"Cem Subakan, Paris Smaragdis","submitted_at":"2017-10-30T05:42:25Z","abstract_excerpt":"Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density. We show on a speech source separation experiment that, a multi-layer perceptron trained with a Wasserstein-GAN formulation outperforms NMF, auto-encoders trained with maximum likelihood, and variational auto-encoders in terms of source to distortion ratio."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10779","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":"1710.10779","created_at":"2026-05-18T00:31:46.516274+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10779v1","created_at":"2026-05-18T00:31:46.516274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10779","created_at":"2026-05-18T00:31:46.516274+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BGTSADX7QSO","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BGTSADX7QSONNT3","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BGTSADX","created_at":"2026-05-18T12:30:58.224056+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/3BGTSADX7QSONNT3XMPMVMOI3I","json":"https://pith.science/pith/3BGTSADX7QSONNT3XMPMVMOI3I.json","graph_json":"https://pith.science/api/pith-number/3BGTSADX7QSONNT3XMPMVMOI3I/graph.json","events_json":"https://pith.science/api/pith-number/3BGTSADX7QSONNT3XMPMVMOI3I/events.json","paper":"https://pith.science/paper/3BGTSADX"},"agent_actions":{"view_html":"https://pith.science/pith/3BGTSADX7QSONNT3XMPMVMOI3I","download_json":"https://pith.science/pith/3BGTSADX7QSONNT3XMPMVMOI3I.json","view_paper":"https://pith.science/paper/3BGTSADX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10779&json=true","fetch_graph":"https://pith.science/api/pith-number/3BGTSADX7QSONNT3XMPMVMOI3I/graph.json","fetch_events":"https://pith.science/api/pith-number/3BGTSADX7QSONNT3XMPMVMOI3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BGTSADX7QSONNT3XMPMVMOI3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BGTSADX7QSONNT3XMPMVMOI3I/action/storage_attestation","attest_author":"https://pith.science/pith/3BGTSADX7QSONNT3XMPMVMOI3I/action/author_attestation","sign_citation":"https://pith.science/pith/3BGTSADX7QSONNT3XMPMVMOI3I/action/citation_signature","submit_replication":"https://pith.science/pith/3BGTSADX7QSONNT3XMPMVMOI3I/action/replication_record"}},"created_at":"2026-05-18T00:31:46.516274+00:00","updated_at":"2026-05-18T00:31:46.516274+00:00"}