{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NDJS75ZIRTDXLWEARXQQ2HPHRL","short_pith_number":"pith:NDJS75ZI","schema_version":"1.0","canonical_sha256":"68d32ff7288cc775d8808de10d1de78ae20b07f6fbd354ae288ac4552c65a539","source":{"kind":"arxiv","id":"2502.02019","version":1},"attestation_state":"computed","paper":{"title":"ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Richard, Dejan Markovi\\'c, Israel D. Gebru, Steven Krenn, Yi-Chiao Wu","submitted_at":"2025-02-04T05:16:15Z","abstract_excerpt":"Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs struggle to model out-of-domain audio, resulting in error propagations to downstream generative tasks. In this paper, we first argue that information loss from codec compression degrades out-of-domain robustness. Then, we propose full-band 48~kHz ComplexDec with complex spectral input and output to ease the information loss while adopting the same 24~kbps bit"},"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":"2502.02019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-04T05:16:15Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b6c7a3f13917538e6961878cc40aaaa4d92f39518ca1e6db9ba7d9e4f0bce716","abstract_canon_sha256":"2752e7c386265ae9cdb1f84f65dcff83b6be1c4d055f50c0cb83252b693d01de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:22.405455Z","signature_b64":"goKKH+RCqHO/7B5o+LEAXw7v8CT2eY7NL/kNq2cBaNhxqD13ybeJwk/gUzpNDVsbCENsTrGMrSviixMHQDhODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68d32ff7288cc775d8808de10d1de78ae20b07f6fbd354ae288ac4552c65a539","last_reissued_at":"2026-07-05T10:09:22.404946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:22.404946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComplexDec: A Domain-robust High-fidelity Neural Audio Codec with Complex Spectrum Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander Richard, Dejan Markovi\\'c, Israel D. Gebru, Steven Krenn, Yi-Chiao Wu","submitted_at":"2025-02-04T05:16:15Z","abstract_excerpt":"Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs struggle to model out-of-domain audio, resulting in error propagations to downstream generative tasks. In this paper, we first argue that information loss from codec compression degrades out-of-domain robustness. Then, we propose full-band 48~kHz ComplexDec with complex spectral input and output to ease the information loss while adopting the same 24~kbps bit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02019","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/2502.02019/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":"2502.02019","created_at":"2026-07-05T10:09:22.405003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02019v1","created_at":"2026-07-05T10:09:22.405003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02019","created_at":"2026-07-05T10:09:22.405003+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDJS75ZIRTDX","created_at":"2026-07-05T10:09:22.405003+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDJS75ZIRTDXLWEA","created_at":"2026-07-05T10:09:22.405003+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDJS75ZI","created_at":"2026-07-05T10:09:22.405003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29480","citing_title":"DTM-Codec: Dynamic Token Masking for VFR Speech Coding with Efficient Boundary Selection","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL","json":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL.json","graph_json":"https://pith.science/api/pith-number/NDJS75ZIRTDXLWEARXQQ2HPHRL/graph.json","events_json":"https://pith.science/api/pith-number/NDJS75ZIRTDXLWEARXQQ2HPHRL/events.json","paper":"https://pith.science/paper/NDJS75ZI"},"agent_actions":{"view_html":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL","download_json":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL.json","view_paper":"https://pith.science/paper/NDJS75ZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02019&json=true","fetch_graph":"https://pith.science/api/pith-number/NDJS75ZIRTDXLWEARXQQ2HPHRL/graph.json","fetch_events":"https://pith.science/api/pith-number/NDJS75ZIRTDXLWEARXQQ2HPHRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL/action/storage_attestation","attest_author":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL/action/author_attestation","sign_citation":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL/action/citation_signature","submit_replication":"https://pith.science/pith/NDJS75ZIRTDXLWEARXQQ2HPHRL/action/replication_record"}},"created_at":"2026-07-05T10:09:22.405003+00:00","updated_at":"2026-07-05T10:09:22.405003+00:00"}