{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A4IOET5P7PLLIJBMNQVOP5T5YX","short_pith_number":"pith:A4IOET5P","schema_version":"1.0","canonical_sha256":"0710e24faffbd6b4242c6c2ae7f67dc5c87818ec357d08bd35a88c361965f607","source":{"kind":"arxiv","id":"2509.02349","version":2},"attestation_state":"computed","paper":{"title":"AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SD","authors_text":"Chengfeng Zhang, Hao Chen, Haodi Zhang, Hao Zhou, Lu Wang, Siyu Wu, Ting Wang, Zhiyue Wu","submitted_at":"2025-09-02T14:15:22Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have been widely applied in speech and music. This tendency has led to a focus on audio tokenization for Large Models (LMs). Unlike semantic-only text tokens, audio tokens must both capture global semantic content and preserve fine-grained acoustic details. Moreover, they provide a discrete method for speech and music that can be effectively integrated into MLLMs. However, existing research is unsuitable in the definitions of semantic tokens and acoustic tokens. In addition, the evaluation of different codecs typically concentrates on specific domains o"},"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":"2509.02349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-09-02T14:15:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c568ded7e0b3d41057cccc68f5034565c45d2eb11ca427459512012356470870","abstract_canon_sha256":"e4a3821335991af454f8d12cc1b308fb96ff5ff0a98ff1dec7378c06809659ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:41.125938Z","signature_b64":"ogxyVNrS/bz2fKZGfsaqXsgBWuGfRWJJyfk7dzz+3y4rlrJzxqOOh/dsAqeYrG0bvi0lFQVLaH1UCFQZmWvsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0710e24faffbd6b4242c6c2ae7f67dc5c87818ec357d08bd35a88c361965f607","last_reissued_at":"2026-07-05T12:04:41.125444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:41.125444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SD","authors_text":"Chengfeng Zhang, Hao Chen, Haodi Zhang, Hao Zhou, Lu Wang, Siyu Wu, Ting Wang, Zhiyue Wu","submitted_at":"2025-09-02T14:15:22Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have been widely applied in speech and music. This tendency has led to a focus on audio tokenization for Large Models (LMs). Unlike semantic-only text tokens, audio tokens must both capture global semantic content and preserve fine-grained acoustic details. Moreover, they provide a discrete method for speech and music that can be effectively integrated into MLLMs. However, existing research is unsuitable in the definitions of semantic tokens and acoustic tokens. In addition, the evaluation of different codecs typically concentrates on specific domains o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02349","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/2509.02349/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":"2509.02349","created_at":"2026-07-05T12:04:41.125503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02349v2","created_at":"2026-07-05T12:04:41.125503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02349","created_at":"2026-07-05T12:04:41.125503+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4IOET5P7PLL","created_at":"2026-07-05T12:04:41.125503+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4IOET5P7PLLIJBM","created_at":"2026-07-05T12:04:41.125503+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4IOET5P","created_at":"2026-07-05T12:04:41.125503+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/A4IOET5P7PLLIJBMNQVOP5T5YX","json":"https://pith.science/pith/A4IOET5P7PLLIJBMNQVOP5T5YX.json","graph_json":"https://pith.science/api/pith-number/A4IOET5P7PLLIJBMNQVOP5T5YX/graph.json","events_json":"https://pith.science/api/pith-number/A4IOET5P7PLLIJBMNQVOP5T5YX/events.json","paper":"https://pith.science/paper/A4IOET5P"},"agent_actions":{"view_html":"https://pith.science/pith/A4IOET5P7PLLIJBMNQVOP5T5YX","download_json":"https://pith.science/pith/A4IOET5P7PLLIJBMNQVOP5T5YX.json","view_paper":"https://pith.science/paper/A4IOET5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02349&json=true","fetch_graph":"https://pith.science/api/pith-number/A4IOET5P7PLLIJBMNQVOP5T5YX/graph.json","fetch_events":"https://pith.science/api/pith-number/A4IOET5P7PLLIJBMNQVOP5T5YX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4IOET5P7PLLIJBMNQVOP5T5YX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4IOET5P7PLLIJBMNQVOP5T5YX/action/storage_attestation","attest_author":"https://pith.science/pith/A4IOET5P7PLLIJBMNQVOP5T5YX/action/author_attestation","sign_citation":"https://pith.science/pith/A4IOET5P7PLLIJBMNQVOP5T5YX/action/citation_signature","submit_replication":"https://pith.science/pith/A4IOET5P7PLLIJBMNQVOP5T5YX/action/replication_record"}},"created_at":"2026-07-05T12:04:41.125503+00:00","updated_at":"2026-07-05T12:04:41.125503+00:00"}