{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WH76AKF4YYAA3LRJMLDBIURUL2","short_pith_number":"pith:WH76AKF4","schema_version":"1.0","canonical_sha256":"b1ffe028bcc6000dae2962c61452345e89847e7303c26da9b60346160b4aa62b","source":{"kind":"arxiv","id":"2605.18749","version":1},"attestation_state":"computed","paper":{"title":"WavFlow: Audio Generation in Waveform Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.SD","authors_text":"Belinda Zeng, Fanny Yang, Feiyan Zhou, Luyuan Wang, Shoufa Chen, Xiaohui Zhang, Yuren Cong, Zhe Wang, Zhiheng Liu","submitted_at":"2026-05-18T17:59:10Z","abstract_excerpt":"Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate representations. To overcome the inherent difficulties of modeling high-dimensional and low-energy signals, we reshape audio into 2D token grids through waveform patchify and introduce amplitude lifting to align signal scales, enabling stable optimization via direct x-prediction in flow matching. To captu"},"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":"2605.18749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-18T17:59:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6ed282045f8a77d4cbc538a9ece6b6fb29cb39ca4b911a040d5d967dd8452a64","abstract_canon_sha256":"8059b8d02ca0313ac709258af280659996736fb9611bc1ad62c89e98675720b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:19.383844Z","signature_b64":"pGZoUn3EyQugvvIuSncxxlxySl7FOU/yLtX8fFumqtQeFycFF9tI3TDHrptaNAP/crRocog6DxNDSfqkgbKjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1ffe028bcc6000dae2962c61452345e89847e7303c26da9b60346160b4aa62b","last_reissued_at":"2026-05-20T00:06:19.382814Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:19.382814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WavFlow: Audio Generation in Waveform Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.SD","authors_text":"Belinda Zeng, Fanny Yang, Feiyan Zhou, Luyuan Wang, Shoufa Chen, Xiaohui Zhang, Yuren Cong, Zhe Wang, Zhiheng Liu","submitted_at":"2026-05-18T17:59:10Z","abstract_excerpt":"Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we challenge this paradigm with WavFlow, a framework that generates high-fidelity audio directly in raw waveform space without intermediate representations. To overcome the inherent difficulties of modeling high-dimensional and low-energy signals, we reshape audio into 2D token grids through waveform patchify and introduce amplitude lifting to align signal scales, enabling stable optimization via direct x-prediction in flow matching. To captu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18749","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/2605.18749/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:58.979613Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fee82102a682e8fa2fd728dbab6dea5bf38e20309386ea1e573900b980a79466"},"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":"2605.18749","created_at":"2026-05-20T00:06:19.382933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18749v1","created_at":"2026-05-20T00:06:19.382933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18749","created_at":"2026-05-20T00:06:19.382933+00:00"},{"alias_kind":"pith_short_12","alias_value":"WH76AKF4YYAA","created_at":"2026-05-20T00:06:19.382933+00:00"},{"alias_kind":"pith_short_16","alias_value":"WH76AKF4YYAA3LRJ","created_at":"2026-05-20T00:06:19.382933+00:00"},{"alias_kind":"pith_short_8","alias_value":"WH76AKF4","created_at":"2026-05-20T00:06:19.382933+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/WH76AKF4YYAA3LRJMLDBIURUL2","json":"https://pith.science/pith/WH76AKF4YYAA3LRJMLDBIURUL2.json","graph_json":"https://pith.science/api/pith-number/WH76AKF4YYAA3LRJMLDBIURUL2/graph.json","events_json":"https://pith.science/api/pith-number/WH76AKF4YYAA3LRJMLDBIURUL2/events.json","paper":"https://pith.science/paper/WH76AKF4"},"agent_actions":{"view_html":"https://pith.science/pith/WH76AKF4YYAA3LRJMLDBIURUL2","download_json":"https://pith.science/pith/WH76AKF4YYAA3LRJMLDBIURUL2.json","view_paper":"https://pith.science/paper/WH76AKF4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18749&json=true","fetch_graph":"https://pith.science/api/pith-number/WH76AKF4YYAA3LRJMLDBIURUL2/graph.json","fetch_events":"https://pith.science/api/pith-number/WH76AKF4YYAA3LRJMLDBIURUL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WH76AKF4YYAA3LRJMLDBIURUL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WH76AKF4YYAA3LRJMLDBIURUL2/action/storage_attestation","attest_author":"https://pith.science/pith/WH76AKF4YYAA3LRJMLDBIURUL2/action/author_attestation","sign_citation":"https://pith.science/pith/WH76AKF4YYAA3LRJMLDBIURUL2/action/citation_signature","submit_replication":"https://pith.science/pith/WH76AKF4YYAA3LRJMLDBIURUL2/action/replication_record"}},"created_at":"2026-05-20T00:06:19.382933+00:00","updated_at":"2026-05-20T00:06:19.382933+00:00"}