{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZHQ7ZTBA33VQJHSKW3FHG3IK4U","short_pith_number":"pith:ZHQ7ZTBA","canonical_record":{"source":{"id":"2003.12222","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-03-27T03:47:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"a34ecf5103a31966d91ff11f300b1be165a25e141d03ece29c3f4f43ae222ca5","abstract_canon_sha256":"5809fed3dde2d17526c3c76302a0949982d539ea7f8e5a09726105845d9116fa"},"schema_version":"1.0"},"canonical_sha256":"c9e1fccc20deeb049e4ab6ca736d0ae53126fa4e7aac1c6240f634cd16cc54de","source":{"kind":"arxiv","id":"2003.12222","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12222","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12222v6","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12222","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZHQ7ZTBA33VQ","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZHQ7ZTBA33VQJHSK","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZHQ7ZTBA","created_at":"2026-07-05T01:27:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZHQ7ZTBA33VQJHSKW3FHG3IK4U","target":"record","payload":{"canonical_record":{"source":{"id":"2003.12222","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-03-27T03:47:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"a34ecf5103a31966d91ff11f300b1be165a25e141d03ece29c3f4f43ae222ca5","abstract_canon_sha256":"5809fed3dde2d17526c3c76302a0949982d539ea7f8e5a09726105845d9116fa"},"schema_version":"1.0"},"canonical_sha256":"c9e1fccc20deeb049e4ab6ca736d0ae53126fa4e7aac1c6240f634cd16cc54de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:22.285176Z","signature_b64":"KNW11ieK0VEvpccn8aQVx0VjdGecJHobZX9/oGEuoXdyanAXLFmQovmf+PTzS70/PqIomijb/sI9l06fsd9SDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9e1fccc20deeb049e4ab6ca736d0ae53126fa4e7aac1c6240f634cd16cc54de","last_reissued_at":"2026-07-05T01:27:22.284474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:22.284474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.12222","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:27:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6a16TixRh+oDPhX3IjA/a1ZYSE5icAUMz/fQ89nFtOYxctdBO96Ua7VkZRBk1AKF+moi96toGM/zvo2QzgoCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:37:16.334784Z"},"content_sha256":"58487ef54ad823907007533f05e42f46d2e20f82a9de3b69fb6267318c1b0b84","schema_version":"1.0","event_id":"sha256:58487ef54ad823907007533f05e42f46d2e20f82a9de3b69fb6267318c1b0b84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZHQ7ZTBA33VQJHSKW3FHG3IK4U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Voice activity detection in the wild via weakly supervised sound event detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu, Yefei Chen","submitted_at":"2020-03-27T03:47:12Z","abstract_excerpt":"Traditional supervised voice activity detection (VAD) methods work well in clean and controlled scenarios, with performance severely degrading in real-world applications. One possible bottleneck is that speech in the wild contains unpredictable noise types, hence frame-level label prediction is difficult, which is required for traditional supervised VAD training. In contrast, we propose a general-purpose VAD (GPVAD) framework, which can be easily trained from noisy data in a weakly supervised fashion, requiring only clip-level labels. We proposed two GPVAD models, one full (GPV-F), trained on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12222","kind":"arxiv","version":6},"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/2003.12222/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:27:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xCA4YJXXDpu6etUMDAEFkTvYQZTDyv9wRfL7I7gGz6zJAcot5KX+a9MqzKoNX6QE57TjWIzgImKS8VMD3JIeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:37:16.335304Z"},"content_sha256":"10383e8b052d0df4fe019b0dabf46d3454f3378bf79d2429eef179da143691b0","schema_version":"1.0","event_id":"sha256:10383e8b052d0df4fe019b0dabf46d3454f3378bf79d2429eef179da143691b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/bundle.json","state_url":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T18:37:16Z","links":{"resolver":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U","bundle":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/bundle.json","state":"https://pith.science/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHQ7ZTBA33VQJHSKW3FHG3IK4U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZHQ7ZTBA33VQJHSKW3FHG3IK4U","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":"5809fed3dde2d17526c3c76302a0949982d539ea7f8e5a09726105845d9116fa","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-03-27T03:47:12Z","title_canon_sha256":"a34ecf5103a31966d91ff11f300b1be165a25e141d03ece29c3f4f43ae222ca5"},"schema_version":"1.0","source":{"id":"2003.12222","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12222","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12222v6","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12222","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZHQ7ZTBA33VQ","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZHQ7ZTBA33VQJHSK","created_at":"2026-07-05T01:27:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZHQ7ZTBA","created_at":"2026-07-05T01:27:22Z"}],"graph_snapshots":[{"event_id":"sha256:10383e8b052d0df4fe019b0dabf46d3454f3378bf79d2429eef179da143691b0","target":"graph","created_at":"2026-07-05T01:27:22Z","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/2003.12222/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional supervised voice activity detection (VAD) methods work well in clean and controlled scenarios, with performance severely degrading in real-world applications. One possible bottleneck is that speech in the wild contains unpredictable noise types, hence frame-level label prediction is difficult, which is required for traditional supervised VAD training. In contrast, we propose a general-purpose VAD (GPVAD) framework, which can be easily trained from noisy data in a weakly supervised fashion, requiring only clip-level labels. We proposed two GPVAD models, one full (GPV-F), trained on ","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu, Yefei Chen","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-03-27T03:47:12Z","title":"Voice activity detection in the wild via weakly supervised sound event detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12222","kind":"arxiv","version":6},"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":"sha256:58487ef54ad823907007533f05e42f46d2e20f82a9de3b69fb6267318c1b0b84","target":"record","created_at":"2026-07-05T01:27:22Z","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":"5809fed3dde2d17526c3c76302a0949982d539ea7f8e5a09726105845d9116fa","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-03-27T03:47:12Z","title_canon_sha256":"a34ecf5103a31966d91ff11f300b1be165a25e141d03ece29c3f4f43ae222ca5"},"schema_version":"1.0","source":{"id":"2003.12222","kind":"arxiv","version":6}},"canonical_sha256":"c9e1fccc20deeb049e4ab6ca736d0ae53126fa4e7aac1c6240f634cd16cc54de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9e1fccc20deeb049e4ab6ca736d0ae53126fa4e7aac1c6240f634cd16cc54de","first_computed_at":"2026-07-05T01:27:22.284474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:22.284474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KNW11ieK0VEvpccn8aQVx0VjdGecJHobZX9/oGEuoXdyanAXLFmQovmf+PTzS70/PqIomijb/sI9l06fsd9SDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:22.285176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.12222","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58487ef54ad823907007533f05e42f46d2e20f82a9de3b69fb6267318c1b0b84","sha256:10383e8b052d0df4fe019b0dabf46d3454f3378bf79d2429eef179da143691b0"],"state_sha256":"38c195134da5fcd30ab68a6f3dcb7e734b8ede90f242d31aa0c526724303385c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XGtq7e+3+R/e1HYLyOtQQ5Mtzu2SYAYeukM7ck/eza9Pi+ZQb4lZEfNlxTJxuVw8dmB7s/uDNTFlG1drleMUDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:37:16.339062Z","bundle_sha256":"d07bd54e0eb49bc38f7108cfa3fb3bc87867af9ecf7797a37bda8bdff7af8cf7"}}