{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RHRHJBHBNLPCVVVJZVUNWLZ3AZ","short_pith_number":"pith:RHRHJBHB","schema_version":"1.0","canonical_sha256":"89e27484e16ade2ad6a9cd68db2f3b064d3b839ec3d56acb4c7ac8d8d150ec13","source":{"kind":"arxiv","id":"2412.17778","version":2},"attestation_state":"computed","paper":{"title":"From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"eess.AS","authors_text":"Chen Chen, Eng Siong Chng, Haoyang Li, Sabato Marco Siniscalchi, Songting Liu, Yuchen Hu","submitted_at":"2024-12-23T18:38:32Z","abstract_excerpt":"Deep neural network (DNN)-based speech enhancement (SE) usually uses conventional activation functions, which lack the expressiveness to capture complex multiscale structures needed for high-fidelity SE. Group-Rational KAN (GR-KAN), a variant of Kolmogorov-Arnold Networks (KAN), retains KAN's expressiveness while improving scalability on complex tasks. We adapt GR-KAN to existing DNN-based SE by replacing dense layers with GR-KAN layers in the time-frequency (T-F) domain MP-SENet and adapting GR-KAN's activations into the 1D CNN layers in the time-domain Demucs. Results on Voicebank-DEMAND sho"},"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":"2412.17778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-23T18:38:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"00b443b1d71ec40fd2e0219c788c8d5735bffa3f4ef229a7691c481e33580301","abstract_canon_sha256":"54750efda72c7afa3e4ff575ac53016c3b47ae9f7a0ced72634be0a4ba231893"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:26.294367Z","signature_b64":"CDAOpchqRcvI8PgYTIMPW4BP6mMZ3mINW94KUUl+ZbaR5DVrTmHa67O57qznQfBTmF2+a1+SfUu1h7TAFB79CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89e27484e16ade2ad6a9cd68db2f3b064d3b839ec3d56acb4c7ac8d8d150ec13","last_reissued_at":"2026-07-05T11:06:26.293844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:26.293844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"eess.AS","authors_text":"Chen Chen, Eng Siong Chng, Haoyang Li, Sabato Marco Siniscalchi, Songting Liu, Yuchen Hu","submitted_at":"2024-12-23T18:38:32Z","abstract_excerpt":"Deep neural network (DNN)-based speech enhancement (SE) usually uses conventional activation functions, which lack the expressiveness to capture complex multiscale structures needed for high-fidelity SE. Group-Rational KAN (GR-KAN), a variant of Kolmogorov-Arnold Networks (KAN), retains KAN's expressiveness while improving scalability on complex tasks. We adapt GR-KAN to existing DNN-based SE by replacing dense layers with GR-KAN layers in the time-frequency (T-F) domain MP-SENet and adapting GR-KAN's activations into the 1D CNN layers in the time-domain Demucs. Results on Voicebank-DEMAND sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17778","kind":"arxiv","version":2},"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/2412.17778/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":"2412.17778","created_at":"2026-07-05T11:06:26.293902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17778v2","created_at":"2026-07-05T11:06:26.293902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17778","created_at":"2026-07-05T11:06:26.293902+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHRHJBHBNLPC","created_at":"2026-07-05T11:06:26.293902+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHRHJBHBNLPCVVVJ","created_at":"2026-07-05T11:06:26.293902+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHRHJBHB","created_at":"2026-07-05T11:06:26.293902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21210","citing_title":"Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21210","citing_title":"Impact Analysis of Speech Representation Learning Models for Acoustic Side-Channel Attack","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ","json":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ.json","graph_json":"https://pith.science/api/pith-number/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/graph.json","events_json":"https://pith.science/api/pith-number/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/events.json","paper":"https://pith.science/paper/RHRHJBHB"},"agent_actions":{"view_html":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ","download_json":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ.json","view_paper":"https://pith.science/paper/RHRHJBHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17778&json=true","fetch_graph":"https://pith.science/api/pith-number/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/action/storage_attestation","attest_author":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/action/author_attestation","sign_citation":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/action/citation_signature","submit_replication":"https://pith.science/pith/RHRHJBHBNLPCVVVJZVUNWLZ3AZ/action/replication_record"}},"created_at":"2026-07-05T11:06:26.293902+00:00","updated_at":"2026-07-05T11:06:26.293902+00:00"}