{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GQLVZV55WRDDQ75PEK4Y4DD3PI","short_pith_number":"pith:GQLVZV55","canonical_record":{"source":{"id":"2506.01365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T06:47:42Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"1a12de5de738697bed2b019dac4e636918f7ddd09fa7c86a4fe0502ced262fd0","abstract_canon_sha256":"ec49325e24696e7758a0afd9d7ce1624539aaf2f42e154940f410b9bc2e6237e"},"schema_version":"1.0"},"canonical_sha256":"34175cd7bdb446387faf22b98e0c7b7a0f7d808839fe43e40f567e4f82d9a6a2","source":{"kind":"arxiv","id":"2506.01365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01365","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01365v1","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01365","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_12","alias_value":"GQLVZV55WRDD","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_16","alias_value":"GQLVZV55WRDDQ75P","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_8","alias_value":"GQLVZV55","created_at":"2026-07-05T11:14:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GQLVZV55WRDDQ75PEK4Y4DD3PI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T06:47:42Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"1a12de5de738697bed2b019dac4e636918f7ddd09fa7c86a4fe0502ced262fd0","abstract_canon_sha256":"ec49325e24696e7758a0afd9d7ce1624539aaf2f42e154940f410b9bc2e6237e"},"schema_version":"1.0"},"canonical_sha256":"34175cd7bdb446387faf22b98e0c7b7a0f7d808839fe43e40f567e4f82d9a6a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:12.258156Z","signature_b64":"xc8rBegkEqNQZwbgGpdKnjos/1P2AN033QmJFuxIUiTAkzroSkaXB80IqaxjREbwrI/7qRBwhpZ2pp0w/NTcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34175cd7bdb446387faf22b98e0c7b7a0f7d808839fe43e40f567e4f82d9a6a2","last_reissued_at":"2026-07-05T11:14:12.257667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:12.257667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01365","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5SJQQDqKhuu2VAZ5WG3Fi1m71H0xDOUyDqkuz6kgORCKRGYLaOzrVolUa9Uy0F7ehvhFhF5W4ai/AfzpOC1IBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:34:48.848240Z"},"content_sha256":"fa8936f41e9494267d612af2d614b4b6500bafd25e0bad14919e15436bdbd41a","schema_version":"1.0","event_id":"sha256:fa8936f41e9494267d612af2d614b4b6500bafd25e0bad14919e15436bdbd41a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GQLVZV55WRDDQ75PEK4Y4DD3PI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chowdam Venkata Kumar, Kumud Tripathi, Pankaj Wasnik","submitted_at":"2025-06-02T06:47:42Z","abstract_excerpt":"Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper. We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention (CA). Experimental results reveal that simple fusion techniques, particularly addition, outperform CA in both accuracy and efficiency. Fusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01365","kind":"arxiv","version":1},"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/2506.01365/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":"2026-07-05T11:14:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+3mrKpmwlZ+Mq410SBcpy0nvddQM/4I2bX/VPCvOuk64quqAie3g88XlIAb+xKpvhT7GGP5wEHBqPlTKV2AxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:34:48.848739Z"},"content_sha256":"60ea41809b23d324ed2b890022a84ed5d53d1adc4defee1303236751375c6bfa","schema_version":"1.0","event_id":"sha256:60ea41809b23d324ed2b890022a84ed5d53d1adc4defee1303236751375c6bfa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/bundle.json","state_url":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/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":"2026-08-08T02:34:48Z","links":{"resolver":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI","bundle":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/bundle.json","state":"https://pith.science/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQLVZV55WRDDQ75PEK4Y4DD3PI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GQLVZV55WRDDQ75PEK4Y4DD3PI","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":"ec49325e24696e7758a0afd9d7ce1624539aaf2f42e154940f410b9bc2e6237e","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T06:47:42Z","title_canon_sha256":"1a12de5de738697bed2b019dac4e636918f7ddd09fa7c86a4fe0502ced262fd0"},"schema_version":"1.0","source":{"id":"2506.01365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01365","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01365v1","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01365","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_12","alias_value":"GQLVZV55WRDD","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_16","alias_value":"GQLVZV55WRDDQ75P","created_at":"2026-07-05T11:14:12Z"},{"alias_kind":"pith_short_8","alias_value":"GQLVZV55","created_at":"2026-07-05T11:14:12Z"}],"graph_snapshots":[{"event_id":"sha256:60ea41809b23d324ed2b890022a84ed5d53d1adc4defee1303236751375c6bfa","target":"graph","created_at":"2026-07-05T11:14:12Z","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/2506.01365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper. We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention (CA). Experimental results reveal that simple fusion techniques, particularly addition, outperform CA in both accuracy and efficiency. Fusio","authors_text":"Chowdam Venkata Kumar, Kumud Tripathi, Pankaj Wasnik","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T06:47:42Z","title":"Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01365","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:fa8936f41e9494267d612af2d614b4b6500bafd25e0bad14919e15436bdbd41a","target":"record","created_at":"2026-07-05T11:14:12Z","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":"ec49325e24696e7758a0afd9d7ce1624539aaf2f42e154940f410b9bc2e6237e","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T06:47:42Z","title_canon_sha256":"1a12de5de738697bed2b019dac4e636918f7ddd09fa7c86a4fe0502ced262fd0"},"schema_version":"1.0","source":{"id":"2506.01365","kind":"arxiv","version":1}},"canonical_sha256":"34175cd7bdb446387faf22b98e0c7b7a0f7d808839fe43e40f567e4f82d9a6a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34175cd7bdb446387faf22b98e0c7b7a0f7d808839fe43e40f567e4f82d9a6a2","first_computed_at":"2026-07-05T11:14:12.257667Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:12.257667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xc8rBegkEqNQZwbgGpdKnjos/1P2AN033QmJFuxIUiTAkzroSkaXB80IqaxjREbwrI/7qRBwhpZ2pp0w/NTcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:12.258156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa8936f41e9494267d612af2d614b4b6500bafd25e0bad14919e15436bdbd41a","sha256:60ea41809b23d324ed2b890022a84ed5d53d1adc4defee1303236751375c6bfa"],"state_sha256":"dd02afd3ee5e7f2c610206777ce74fd735900d3ca708a6f4ce4298e7a0a3cbf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pir0P6YoqgRGTopPLQoDgCGVNkCH5yZfe0KcVqXM6sURKlzWvcRgQ+hiE/X9P1CtTSdrnOF7Zb9eCc1Oa/wvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:34:48.852496Z","bundle_sha256":"32d65ac38d728fc46dabddb42e86a7287fd2bfd39592dfa3a0596c98d62788ae"}}