{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H66XVZHKEB2HP4PXTNUYIWC3TF","short_pith_number":"pith:H66XVZHK","schema_version":"1.0","canonical_sha256":"3fbd7ae4ea207477f1f79b6984585b994efe582af43c883788418e1ee9749941","source":{"kind":"arxiv","id":"2410.22448","version":1},"attestation_state":"computed","paper":{"title":"A Closer Look at Neural Codec Resynthesis: Bridging the Gap between Codec and Waveform Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander H. Liu, James Glass, Qirui Wang, Yuan Gong","submitted_at":"2024-10-29T18:29:39Z","abstract_excerpt":"Neural Audio Codecs, initially designed as a compression technique, have gained more attention recently for speech generation. Codec models represent each audio frame as a sequence of tokens, i.e., discrete embeddings. The discrete and low-frequency nature of neural codecs introduced a new way to generate speech with token-based models. As these tokens encode information at various levels of granularity, from coarse to fine, most existing works focus on how to better generate the coarse tokens. In this paper, we focus on an equally important but often overlooked question: How can we better res"},"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":"2410.22448","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-29T18:29:39Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"c82dfb17b12387a465e927e4522f920063ff604eedd214b678dc7cd343936537","abstract_canon_sha256":"bc10fd6180a97c96a7f4668b14a4976301a5f98b967175b1f493c5ae2a1c1bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:16.651960Z","signature_b64":"VzdZ6PEd31r/wHeuxtbRMw83zZe1u7IraQH4iAvP5IlEQ7bXllDJoe8Kv09p+sbVi4z6uuP8GKPRwLyFAnbgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fbd7ae4ea207477f1f79b6984585b994efe582af43c883788418e1ee9749941","last_reissued_at":"2026-07-05T09:28:16.651486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:16.651486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Closer Look at Neural Codec Resynthesis: Bridging the Gap between Codec and Waveform Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Alexander H. Liu, James Glass, Qirui Wang, Yuan Gong","submitted_at":"2024-10-29T18:29:39Z","abstract_excerpt":"Neural Audio Codecs, initially designed as a compression technique, have gained more attention recently for speech generation. Codec models represent each audio frame as a sequence of tokens, i.e., discrete embeddings. The discrete and low-frequency nature of neural codecs introduced a new way to generate speech with token-based models. As these tokens encode information at various levels of granularity, from coarse to fine, most existing works focus on how to better generate the coarse tokens. In this paper, we focus on an equally important but often overlooked question: How can we better res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22448","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/2410.22448/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":"2410.22448","created_at":"2026-07-05T09:28:16.651543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22448v1","created_at":"2026-07-05T09:28:16.651543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22448","created_at":"2026-07-05T09:28:16.651543+00:00"},{"alias_kind":"pith_short_12","alias_value":"H66XVZHKEB2H","created_at":"2026-07-05T09:28:16.651543+00:00"},{"alias_kind":"pith_short_16","alias_value":"H66XVZHKEB2HP4PX","created_at":"2026-07-05T09:28:16.651543+00:00"},{"alias_kind":"pith_short_8","alias_value":"H66XVZHK","created_at":"2026-07-05T09:28:16.651543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08787","citing_title":"Beyond Reconstruction: Full-Context Generative DiT for Music Generation","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF","json":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF.json","graph_json":"https://pith.science/api/pith-number/H66XVZHKEB2HP4PXTNUYIWC3TF/graph.json","events_json":"https://pith.science/api/pith-number/H66XVZHKEB2HP4PXTNUYIWC3TF/events.json","paper":"https://pith.science/paper/H66XVZHK"},"agent_actions":{"view_html":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF","download_json":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF.json","view_paper":"https://pith.science/paper/H66XVZHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22448&json=true","fetch_graph":"https://pith.science/api/pith-number/H66XVZHKEB2HP4PXTNUYIWC3TF/graph.json","fetch_events":"https://pith.science/api/pith-number/H66XVZHKEB2HP4PXTNUYIWC3TF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF/action/storage_attestation","attest_author":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF/action/author_attestation","sign_citation":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF/action/citation_signature","submit_replication":"https://pith.science/pith/H66XVZHKEB2HP4PXTNUYIWC3TF/action/replication_record"}},"created_at":"2026-07-05T09:28:16.651543+00:00","updated_at":"2026-07-05T09:28:16.651543+00:00"}