{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2MRXV47RMEZD3U66HM7FMTNCAE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"03743e5d46389922487b9e99775ea7ec8009b7230c1746393641cf5da554efd9","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-04T03:51:23Z","title_canon_sha256":"70a8f9a5f0b8c49c3cacf31a8c5732ec4c0307444be9d77fcdc1af3e2c895d7b"},"schema_version":"1.0","source":{"id":"2211.02250","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02250","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02250v3","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02250","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"2MRXV47RMEZD","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"2MRXV47RMEZD3U66","created_at":"2026-07-05T06:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"2MRXV47R","created_at":"2026-07-05T06:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:704d884d65475d1aab5a60fab579a8fb24d8379bead8b59911626a34cebff21e","target":"graph","created_at":"2026-07-05T06:02:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.02250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the first neural network model to achieve real-time and streaming target sound extraction. To accomplish this, we propose Waveformer, an encoder-decoder architecture with a stack of dilated causal convolution layers as the encoder, and a transformer decoder layer as the decoder. This hybrid architecture uses dilated causal convolutions for processing large receptive fields in a computationally efficient manner while also leveraging the generalization performance of transformer-based architectures. Our evaluations show as much as 2.2-3.3 dB improvement in SI-SNRi compared to the prio","authors_text":"Bandhav Veluri, Justin Chan, Malek Itani, Shyamnath Gollakota, Takuya Yoshioka, Tuochao Chen","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-04T03:51:23Z","title":"Real-Time Target Sound Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02250","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:39921a3c65e9320a53fa7249178be997efc9f7fc6654e75f5439fb32ca4d6dc8","target":"record","created_at":"2026-07-05T06:02:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"03743e5d46389922487b9e99775ea7ec8009b7230c1746393641cf5da554efd9","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-04T03:51:23Z","title_canon_sha256":"70a8f9a5f0b8c49c3cacf31a8c5732ec4c0307444be9d77fcdc1af3e2c895d7b"},"schema_version":"1.0","source":{"id":"2211.02250","kind":"arxiv","version":3}},"canonical_sha256":"d3237af3f161323dd3de3b3e564da2013dec74048eba4be61593ef599812e140","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3237af3f161323dd3de3b3e564da2013dec74048eba4be61593ef599812e140","first_computed_at":"2026-07-05T06:02:30.584659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:30.584659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NEDcnijdYKPtId7Nqg2gtEgDwF72zA4u939d/zhy9xaUAsBj56kpGjrZnIHqFHx2suI9PmJFwBRkJsonlPffBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:30.585102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.02250","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39921a3c65e9320a53fa7249178be997efc9f7fc6654e75f5439fb32ca4d6dc8","sha256:704d884d65475d1aab5a60fab579a8fb24d8379bead8b59911626a34cebff21e"],"state_sha256":"69eeaee48b8ef73a7f2569c761be8b50fe3682917c8e6c4288e66c49c3a84109"}