{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T4EUDOC2MUF353RGELS6IXZKTK","short_pith_number":"pith:T4EUDOC2","schema_version":"1.0","canonical_sha256":"9f0941b85a650bbeee2622e5e45f2a9aa15df9a55911425723bd8b5b5ff13fee","source":{"kind":"arxiv","id":"2006.12701","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Sound Separation Using Mixture Invariant Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Efthymios Tzinis, Hakan Erdogan, John R. Hershey, Kevin Wilson, Ron J. Weiss, Scott Wisdom","submitted_at":"2020-06-23T02:22:14Z","abstract_excerpt":"In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from synthetic mixtures created by adding up isolated ground-truth sources. Reliance on this synthetic training data is problematic because good performance depends upon the degree of match between the training data and real-world audio, especially in terms of the acoustic conditions and distribution of sources. The acoustic properties can be challenging to accurately"},"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":"2006.12701","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-23T02:22:14Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"17c16dd6cf4d2b949f28027a4881e39a88793851608235bce2a600df1f1355d8","abstract_canon_sha256":"49784f41d7511b9eb603d918977053e017e743a2ee6f9a6c48f375443685c7ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:43.756631Z","signature_b64":"RIRomKUJWGMTBTxzb1umzvPTq/RvlI00E62YUq5nPQ0WTW8ClO9E5jlvDPxsYm2exxx47y47XSM3mHO/GFBnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f0941b85a650bbeee2622e5e45f2a9aa15df9a55911425723bd8b5b5ff13fee","last_reissued_at":"2026-07-05T01:45:43.756163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:43.756163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Sound Separation Using Mixture Invariant Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Efthymios Tzinis, Hakan Erdogan, John R. Hershey, Kevin Wilson, Ron J. Weiss, Scott Wisdom","submitted_at":"2020-06-23T02:22:14Z","abstract_excerpt":"In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component sources from synthetic mixtures created by adding up isolated ground-truth sources. Reliance on this synthetic training data is problematic because good performance depends upon the degree of match between the training data and real-world audio, especially in terms of the acoustic conditions and distribution of sources. The acoustic properties can be challenging to accurately"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12701","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.12701/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2006.12701","created_at":"2026-07-05T01:45:43.756221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12701v2","created_at":"2026-07-05T01:45:43.756221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12701","created_at":"2026-07-05T01:45:43.756221+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4EUDOC2MUF3","created_at":"2026-07-05T01:45:43.756221+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4EUDOC2MUF353RG","created_at":"2026-07-05T01:45:43.756221+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4EUDOC2","created_at":"2026-07-05T01:45:43.756221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03264","citing_title":"Hear to See: Discerning Stateful Listening for Audio-Visual Instance Segmentation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK","json":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK.json","graph_json":"https://pith.science/api/pith-number/T4EUDOC2MUF353RGELS6IXZKTK/graph.json","events_json":"https://pith.science/api/pith-number/T4EUDOC2MUF353RGELS6IXZKTK/events.json","paper":"https://pith.science/paper/T4EUDOC2"},"agent_actions":{"view_html":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK","download_json":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK.json","view_paper":"https://pith.science/paper/T4EUDOC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12701&json=true","fetch_graph":"https://pith.science/api/pith-number/T4EUDOC2MUF353RGELS6IXZKTK/graph.json","fetch_events":"https://pith.science/api/pith-number/T4EUDOC2MUF353RGELS6IXZKTK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK/action/storage_attestation","attest_author":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK/action/author_attestation","sign_citation":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK/action/citation_signature","submit_replication":"https://pith.science/pith/T4EUDOC2MUF353RGELS6IXZKTK/action/replication_record"}},"created_at":"2026-07-05T01:45:43.756221+00:00","updated_at":"2026-07-05T01:45:43.756221+00:00"}