{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S7LKC6L7QIO6YYOLTUVG6X7F2B","short_pith_number":"pith:S7LKC6L7","schema_version":"1.0","canonical_sha256":"97d6a1797f821dec61cb9d2a6f5fe5d04ed714e35dc7fab7531fd8e30ddb27d2","source":{"kind":"arxiv","id":"2405.04752","version":2},"attestation_state":"computed","paper":{"title":"HILCodec: High-Fidelity and Lightweight Neural Audio Codec","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Beom Jun Woo, Chanyeong Moon, Min Hyun Han, Nam Soo Kim, Sunghwan Ahn","submitted_at":"2024-05-08T01:40:13Z","abstract_excerpt":"The recent advancement of end-to-end neural audio codecs enables compressing audio at very low bitrates while reconstructing the output audio with high fidelity. Nonetheless, such improvements often come at the cost of increased model complexity. In this paper, we identify and address the problems of existing neural audio codecs. We show that the performance of the SEANet-based codec does not increase consistently as the network depth increases. We analyze the root cause of such a phenomenon and suggest a variance-constrained design. Also, we reveal various distortions in previous waveform dom"},"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":"2405.04752","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-05-08T01:40:13Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d75d370a34fd384d4687ce958e279d382ce604a64d3909365d303cd392dc4aae","abstract_canon_sha256":"8c77b6aa3cd007328f483801ff98ebce6ad14c5617d3280a86470f6af4eeda64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:47.119008Z","signature_b64":"/fY8d+Ve+lfk9BK0GbfS/PGw6Ma1U240glZ03R4mFD5YScoK0+7WRu9v0h5Vc4fDXiDShk47Z8gf7i96jQ8IDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97d6a1797f821dec61cb9d2a6f5fe5d04ed714e35dc7fab7531fd8e30ddb27d2","last_reissued_at":"2026-07-05T09:10:47.118495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:47.118495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HILCodec: High-Fidelity and Lightweight Neural Audio Codec","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Beom Jun Woo, Chanyeong Moon, Min Hyun Han, Nam Soo Kim, Sunghwan Ahn","submitted_at":"2024-05-08T01:40:13Z","abstract_excerpt":"The recent advancement of end-to-end neural audio codecs enables compressing audio at very low bitrates while reconstructing the output audio with high fidelity. Nonetheless, such improvements often come at the cost of increased model complexity. In this paper, we identify and address the problems of existing neural audio codecs. We show that the performance of the SEANet-based codec does not increase consistently as the network depth increases. We analyze the root cause of such a phenomenon and suggest a variance-constrained design. Also, we reveal various distortions in previous waveform dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04752","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/2405.04752/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":"2405.04752","created_at":"2026-07-05T09:10:47.118580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04752v2","created_at":"2026-07-05T09:10:47.118580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04752","created_at":"2026-07-05T09:10:47.118580+00:00"},{"alias_kind":"pith_short_12","alias_value":"S7LKC6L7QIO6","created_at":"2026-07-05T09:10:47.118580+00:00"},{"alias_kind":"pith_short_16","alias_value":"S7LKC6L7QIO6YYOL","created_at":"2026-07-05T09:10:47.118580+00:00"},{"alias_kind":"pith_short_8","alias_value":"S7LKC6L7","created_at":"2026-07-05T09:10:47.118580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B","json":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B.json","graph_json":"https://pith.science/api/pith-number/S7LKC6L7QIO6YYOLTUVG6X7F2B/graph.json","events_json":"https://pith.science/api/pith-number/S7LKC6L7QIO6YYOLTUVG6X7F2B/events.json","paper":"https://pith.science/paper/S7LKC6L7"},"agent_actions":{"view_html":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B","download_json":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B.json","view_paper":"https://pith.science/paper/S7LKC6L7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04752&json=true","fetch_graph":"https://pith.science/api/pith-number/S7LKC6L7QIO6YYOLTUVG6X7F2B/graph.json","fetch_events":"https://pith.science/api/pith-number/S7LKC6L7QIO6YYOLTUVG6X7F2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B/action/storage_attestation","attest_author":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B/action/author_attestation","sign_citation":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B/action/citation_signature","submit_replication":"https://pith.science/pith/S7LKC6L7QIO6YYOLTUVG6X7F2B/action/replication_record"}},"created_at":"2026-07-05T09:10:47.118580+00:00","updated_at":"2026-07-05T09:10:47.118580+00:00"}