{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:V2E5SLFCAT7H7HWRJITWT5DZKO","short_pith_number":"pith:V2E5SLFC","schema_version":"1.0","canonical_sha256":"ae89d92ca204fe7f9ed14a2769f479538d76fa37a252e3a948515e450bf46d00","source":{"kind":"arxiv","id":"1711.00048","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Daniel Stoller, Sebastian Ewert, Simon Dixon","submitted_at":"2017-10-31T18:35:45Z","abstract_excerpt":"The state of the art in music source separation employs neural networks trained in a supervised fashion on multi-track databases to estimate the sources from a given mixture. With only few datasets available, often extensive data augmentation is used to combat overfitting. Mixing random tracks, however, can even reduce separation performance as instruments in real music are strongly correlated. The key concept in our approach is that source estimates of an optimal separator should be indistinguishable from real source signals. Based on this idea, we drive the separator towards outputs deemed a"},"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":"1711.00048","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-31T18:35:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b6e85369a8235b3e314a8dfb39fd39be8ca5db4c3c30ba32a5d709eb5098693d","abstract_canon_sha256":"805491a19d1b7782350188e4381d3a475fdd955f52a4a7b9d6ed495e2c60e965"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:08.605746Z","signature_b64":"p7pgfjRDety9EF0ry8qiSnagYnMSCi7Hfqc01Xz5+dwNUOUIKH8eT0VYR/HcP5PY+XHBheM9K1XrjcsGW3f4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae89d92ca204fe7f9ed14a2769f479538d76fa37a252e3a948515e450bf46d00","last_reissued_at":"2026-05-18T00:19:08.604986Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:08.604986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Daniel Stoller, Sebastian Ewert, Simon Dixon","submitted_at":"2017-10-31T18:35:45Z","abstract_excerpt":"The state of the art in music source separation employs neural networks trained in a supervised fashion on multi-track databases to estimate the sources from a given mixture. With only few datasets available, often extensive data augmentation is used to combat overfitting. Mixing random tracks, however, can even reduce separation performance as instruments in real music are strongly correlated. The key concept in our approach is that source estimates of an optimal separator should be indistinguishable from real source signals. Based on this idea, we drive the separator towards outputs deemed a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00048","kind":"arxiv","version":2},"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":"1711.00048","created_at":"2026-05-18T00:19:08.605105+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00048v2","created_at":"2026-05-18T00:19:08.605105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00048","created_at":"2026-05-18T00:19:08.605105+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2E5SLFCAT7H","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2E5SLFCAT7H7HWR","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2E5SLFC","created_at":"2026-05-18T12:31:49.984773+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/V2E5SLFCAT7H7HWRJITWT5DZKO","json":"https://pith.science/pith/V2E5SLFCAT7H7HWRJITWT5DZKO.json","graph_json":"https://pith.science/api/pith-number/V2E5SLFCAT7H7HWRJITWT5DZKO/graph.json","events_json":"https://pith.science/api/pith-number/V2E5SLFCAT7H7HWRJITWT5DZKO/events.json","paper":"https://pith.science/paper/V2E5SLFC"},"agent_actions":{"view_html":"https://pith.science/pith/V2E5SLFCAT7H7HWRJITWT5DZKO","download_json":"https://pith.science/pith/V2E5SLFCAT7H7HWRJITWT5DZKO.json","view_paper":"https://pith.science/paper/V2E5SLFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00048&json=true","fetch_graph":"https://pith.science/api/pith-number/V2E5SLFCAT7H7HWRJITWT5DZKO/graph.json","fetch_events":"https://pith.science/api/pith-number/V2E5SLFCAT7H7HWRJITWT5DZKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2E5SLFCAT7H7HWRJITWT5DZKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2E5SLFCAT7H7HWRJITWT5DZKO/action/storage_attestation","attest_author":"https://pith.science/pith/V2E5SLFCAT7H7HWRJITWT5DZKO/action/author_attestation","sign_citation":"https://pith.science/pith/V2E5SLFCAT7H7HWRJITWT5DZKO/action/citation_signature","submit_replication":"https://pith.science/pith/V2E5SLFCAT7H7HWRJITWT5DZKO/action/replication_record"}},"created_at":"2026-05-18T00:19:08.605105+00:00","updated_at":"2026-05-18T00:19:08.605105+00:00"}