{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KQERU5ILJ27YK7SARZV22EBXQX","short_pith_number":"pith:KQERU5IL","schema_version":"1.0","canonical_sha256":"54091a750b4ebf857e408e6bad103785e94ae782ede677462de17a4716f81060","source":{"kind":"arxiv","id":"2503.01485","version":1},"attestation_state":"computed","paper":{"title":"FlowDec: A flow-based full-band general audio codec with high perceptual quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Alexander Richard, Matthew Le, Ricky T. Q. Chen, Simon Welker, Timo Gerkmann, Wei-Ning Hsu, Yi-Chiao Wu","submitted_at":"2025-03-03T12:49:09Z","abstract_excerpt":"We propose FlowDec, a neural full-band audio codec for general audio sampled at 48 kHz that combines non-adversarial codec training with a stochastic postfilter based on a novel conditional flow matching method. Compared to the prior work ScoreDec which is based on score matching, we generalize from speech to general audio and move from 24 kbit/s to as low as 4 kbit/s, while improving output quality and reducing the required postfilter DNN evaluations from 60 to 6 without any fine-tuning or distillation techniques. We provide theoretical insights and geometric intuitions for our approach in co"},"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":"2503.01485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-03-03T12:49:09Z","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"9504231ebd25571c1a6a671448c8c022f180ce39c5b600b16f50ae266a311d68","abstract_canon_sha256":"c22d9d452921ad4506e23119c99a1966efc31759867feb3c1e09ef3fecf1e5fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:08.142794Z","signature_b64":"T759jkC1N5R+SF7RbW+caw9k/Ly0n2fWqAAwoSotqrH4lZa79gZ4DEigzBFxfPdTaaE2f7wCiryS1KLEZimrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54091a750b4ebf857e408e6bad103785e94ae782ede677462de17a4716f81060","last_reissued_at":"2026-07-05T10:23:08.142111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:08.142111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowDec: A flow-based full-band general audio codec with high perceptual quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Alexander Richard, Matthew Le, Ricky T. Q. Chen, Simon Welker, Timo Gerkmann, Wei-Ning Hsu, Yi-Chiao Wu","submitted_at":"2025-03-03T12:49:09Z","abstract_excerpt":"We propose FlowDec, a neural full-band audio codec for general audio sampled at 48 kHz that combines non-adversarial codec training with a stochastic postfilter based on a novel conditional flow matching method. Compared to the prior work ScoreDec which is based on score matching, we generalize from speech to general audio and move from 24 kbit/s to as low as 4 kbit/s, while improving output quality and reducing the required postfilter DNN evaluations from 60 to 6 without any fine-tuning or distillation techniques. We provide theoretical insights and geometric intuitions for our approach in co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01485","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/2503.01485/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":"2503.01485","created_at":"2026-07-05T10:23:08.142192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01485v1","created_at":"2026-07-05T10:23:08.142192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01485","created_at":"2026-07-05T10:23:08.142192+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQERU5ILJ27Y","created_at":"2026-07-05T10:23:08.142192+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQERU5ILJ27YK7SA","created_at":"2026-07-05T10:23:08.142192+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQERU5IL","created_at":"2026-07-05T10:23:08.142192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":231,"is_internal_anchor":false},{"citing_arxiv_id":"2505.24437","citing_title":"SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX","json":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX.json","graph_json":"https://pith.science/api/pith-number/KQERU5ILJ27YK7SARZV22EBXQX/graph.json","events_json":"https://pith.science/api/pith-number/KQERU5ILJ27YK7SARZV22EBXQX/events.json","paper":"https://pith.science/paper/KQERU5IL"},"agent_actions":{"view_html":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX","download_json":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX.json","view_paper":"https://pith.science/paper/KQERU5IL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01485&json=true","fetch_graph":"https://pith.science/api/pith-number/KQERU5ILJ27YK7SARZV22EBXQX/graph.json","fetch_events":"https://pith.science/api/pith-number/KQERU5ILJ27YK7SARZV22EBXQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX/action/storage_attestation","attest_author":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX/action/author_attestation","sign_citation":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX/action/citation_signature","submit_replication":"https://pith.science/pith/KQERU5ILJ27YK7SARZV22EBXQX/action/replication_record"}},"created_at":"2026-07-05T10:23:08.142192+00:00","updated_at":"2026-07-05T10:23:08.142192+00:00"}