{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JOMNKNS2RISW3L5IZRK5J244TS","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":"144698340a67ab42daca5bb5a7b7d8d3b9f46cf0b48fcb0967988ced16ec7286","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-06T18:00:14Z","title_canon_sha256":"642856e29bb3c9509cb21ab443236ae90357387d3159e7ea72f6ba39ce529f18"},"schema_version":"1.0","source":{"id":"2501.03184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03184","created_at":"2026-07-05T09:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03184v1","created_at":"2026-07-05T09:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03184","created_at":"2026-07-05T09:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"JOMNKNS2RISW","created_at":"2026-07-05T09:57:32Z"},{"alias_kind":"pith_short_16","alias_value":"JOMNKNS2RISW3L5I","created_at":"2026-07-05T09:57:32Z"},{"alias_kind":"pith_short_8","alias_value":"JOMNKNS2","created_at":"2026-07-05T09:57:32Z"}],"graph_snapshots":[{"event_id":"sha256:b8c0384fedd83e025ffe64aa687dca289eff742b44bd4407516d00ea0c48316a","target":"graph","created_at":"2026-07-05T09:57:32Z","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/2501.03184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Target-Speaker Voice Activity Detection (TS-VAD) is the task of detecting the presence of speech from a known target-speaker in an audio frame. Recently, deep neural network-based models have shown good performance in this task. However, training these models requires extensive labelled data, which is costly and time-consuming to obtain, particularly if generalization to unseen environments is crucial. To mitigate this, we propose a causal, Self-Supervised Learning (SSL) pretraining framework, called Denoising Autoregressive Predictive Coding (DN-APC), to enhance TS-VAD performance in noisy co","authors_text":"2), (2) Oticon A/S), Holger Severin Bovbjerg (1), Jan {\\O}stergaard (1), Jesper Jensen (1, Zheng-Hua Tan (1) ((1) Aalborg University","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-06T18:00:14Z","title":"Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03184","kind":"arxiv","version":1},"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":"sha256:44edc68f0b1ff9d52ae5456195d5e2ea281a6ce5a4c9a7a348712ad9817adbe0","target":"record","created_at":"2026-07-05T09:57:32Z","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":"144698340a67ab42daca5bb5a7b7d8d3b9f46cf0b48fcb0967988ced16ec7286","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-06T18:00:14Z","title_canon_sha256":"642856e29bb3c9509cb21ab443236ae90357387d3159e7ea72f6ba39ce529f18"},"schema_version":"1.0","source":{"id":"2501.03184","kind":"arxiv","version":1}},"canonical_sha256":"4b98d5365a8a256dafa8cc55d4eb9c9c8497c1109cf1d6de3c2cbabec3e17c11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b98d5365a8a256dafa8cc55d4eb9c9c8497c1109cf1d6de3c2cbabec3e17c11","first_computed_at":"2026-07-05T09:57:32.841906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:32.841906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kwVGUHqE61O6SwUMlYpi7xn+p/vmfyV71zJ8RTq987pbGwIAlb4j/4shxCYQUBmNI+ObwMhC2RIouuW7GD4bCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:32.842385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44edc68f0b1ff9d52ae5456195d5e2ea281a6ce5a4c9a7a348712ad9817adbe0","sha256:b8c0384fedd83e025ffe64aa687dca289eff742b44bd4407516d00ea0c48316a"],"state_sha256":"ebbc13d641b9391a2baf5977f7087fd981c1fa89274aaa0cc72895c845b27ccc"}