{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6MJHJOAQV3Q2IAPHLDYLQWWW22","short_pith_number":"pith:6MJHJOAQ","schema_version":"1.0","canonical_sha256":"f31274b810aee1a401e758f0b85ad6d6a13649cb46a25b8f7b2091e3fc56c32b","source":{"kind":"arxiv","id":"2607.25870","version":1},"attestation_state":"computed","paper":{"title":"VAD to the Bone: Ultra-Tiny Speech Activity Detection for Edge Deployment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Gorkem Ulkar, Scott Veidenheimer, Shanza Iftikhar, Sheila Seidel, Stephen Bauer","submitted_at":"2026-07-28T15:37:44Z","abstract_excerpt":"Voice activity detection (VAD) triggers downstream speech processing in always-on systems under strict memory, latency, and compute constraints. Recent compact models report strong accuracy but rely on components that are not widely supported: learnable filterbanks, recurrent layers, or non-causal post-processing. We propose kiloVAD, designed for embedded inference using standard Mel features, CNN-only layers, and tunable context/spectral parameters. We introduce per-layer structured pruning with self-distillation and angle-based quantization-aware training (QAT) that outperforms standard QAT "},"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":"2607.25870","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-28T15:37:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"979500724c8f75db25144527489fcdd9f0dcc2664d18b2f412909496c1917050","abstract_canon_sha256":"4692d2a8118b7205cd64a3037259ca166d01b7cbe0541e35653ddf42ce7080cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:26:07.857640Z","signature_b64":"21YB6yUesbrUnorz0Y3b2MNB7tZgljcBbDxpXqnougLQRsHOovkLxjoqZFp7SiPob2Ijo0NVA2seOhMd7VM5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f31274b810aee1a401e758f0b85ad6d6a13649cb46a25b8f7b2091e3fc56c32b","last_reissued_at":"2026-07-29T01:26:07.856739Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:26:07.856739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAD to the Bone: Ultra-Tiny Speech Activity Detection for Edge Deployment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Gorkem Ulkar, Scott Veidenheimer, Shanza Iftikhar, Sheila Seidel, Stephen Bauer","submitted_at":"2026-07-28T15:37:44Z","abstract_excerpt":"Voice activity detection (VAD) triggers downstream speech processing in always-on systems under strict memory, latency, and compute constraints. Recent compact models report strong accuracy but rely on components that are not widely supported: learnable filterbanks, recurrent layers, or non-causal post-processing. We propose kiloVAD, designed for embedded inference using standard Mel features, CNN-only layers, and tunable context/spectral parameters. We introduce per-layer structured pruning with self-distillation and angle-based quantization-aware training (QAT) that outperforms standard QAT "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25870","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/2607.25870/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":"2607.25870","created_at":"2026-07-29T01:26:07.857191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25870v1","created_at":"2026-07-29T01:26:07.857191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25870","created_at":"2026-07-29T01:26:07.857191+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MJHJOAQV3Q2","created_at":"2026-07-29T01:26:07.857191+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MJHJOAQV3Q2IAPH","created_at":"2026-07-29T01:26:07.857191+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MJHJOAQ","created_at":"2026-07-29T01:26:07.857191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22","json":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22.json","graph_json":"https://pith.science/api/pith-number/6MJHJOAQV3Q2IAPHLDYLQWWW22/graph.json","events_json":"https://pith.science/api/pith-number/6MJHJOAQV3Q2IAPHLDYLQWWW22/events.json","paper":"https://pith.science/paper/6MJHJOAQ"},"agent_actions":{"view_html":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22","download_json":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22.json","view_paper":"https://pith.science/paper/6MJHJOAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25870&json=true","fetch_graph":"https://pith.science/api/pith-number/6MJHJOAQV3Q2IAPHLDYLQWWW22/graph.json","fetch_events":"https://pith.science/api/pith-number/6MJHJOAQV3Q2IAPHLDYLQWWW22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22/action/storage_attestation","attest_author":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22/action/author_attestation","sign_citation":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22/action/citation_signature","submit_replication":"https://pith.science/pith/6MJHJOAQV3Q2IAPHLDYLQWWW22/action/replication_record"}},"created_at":"2026-07-29T01:26:07.857191+00:00","updated_at":"2026-07-29T01:26:07.857191+00:00"}