{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E4QN3KYCINBWTGOA7LJDZ3DNK5","short_pith_number":"pith:E4QN3KYC","schema_version":"1.0","canonical_sha256":"2720ddab0243436999c0fad23cec6d5760b0412e0da0a19f0b0515b2fbeda54b","source":{"kind":"arxiv","id":"2608.04479","version":1},"attestation_state":"computed","paper":{"title":"AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Jinting Wang, Li Liu, Shan Yang, Shengyu Li, Xiaoda Yang, Yan Rong, Yuguang Yang","submitted_at":"2026-08-05T06:06:54Z","abstract_excerpt":"Text-to-audio (TTA) generation has recently achieved remarkable progress in synthesizing realistic audio from natural language descriptions. However, determining whether generated audio faithfully satisfies complex textual instructions remains challenging. Existing benchmarks mainly rely on global similarity metrics, providing limited insight into fine-grained semantic failures. To address this limitation, we introduce \\textbf{AudioScape-TTA}, a structured and complexity-aware benchmark for fine-grained TTA evaluation. AudioScape-TTA represents realistic soundscapes through modality-aware sema"},"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":"2608.04479","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-05T06:06:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b9563e7a9a434f2c6302c7cd114be1de76067613076180db6fc62062b2abdefb","abstract_canon_sha256":"158fce5ab37a0c0adb7fd26af7451db116eb60b12c5ba28fd6f95405612a465f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:35:41.054828Z","signature_b64":"wd5nleeJVRttORKl2cU+2daqpldSxORLv7b1hkkTzV1l+bH4FXm28/avSry0iaqyCOuc/zn2qSdGxvs3fKeVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2720ddab0243436999c0fad23cec6d5760b0412e0da0a19f0b0515b2fbeda54b","last_reissued_at":"2026-08-06T01:35:41.053134Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:35:41.053134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Jinting Wang, Li Liu, Shan Yang, Shengyu Li, Xiaoda Yang, Yan Rong, Yuguang Yang","submitted_at":"2026-08-05T06:06:54Z","abstract_excerpt":"Text-to-audio (TTA) generation has recently achieved remarkable progress in synthesizing realistic audio from natural language descriptions. However, determining whether generated audio faithfully satisfies complex textual instructions remains challenging. Existing benchmarks mainly rely on global similarity metrics, providing limited insight into fine-grained semantic failures. To address this limitation, we introduce \\textbf{AudioScape-TTA}, a structured and complexity-aware benchmark for fine-grained TTA evaluation. AudioScape-TTA represents realistic soundscapes through modality-aware sema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04479","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/2608.04479/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":"2608.04479","created_at":"2026-08-06T01:35:41.055143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04479v1","created_at":"2026-08-06T01:35:41.055143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04479","created_at":"2026-08-06T01:35:41.055143+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4QN3KYCINBW","created_at":"2026-08-06T01:35:41.055143+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4QN3KYCINBWTGOA","created_at":"2026-08-06T01:35:41.055143+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4QN3KYC","created_at":"2026-08-06T01:35:41.055143+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/E4QN3KYCINBWTGOA7LJDZ3DNK5","json":"https://pith.science/pith/E4QN3KYCINBWTGOA7LJDZ3DNK5.json","graph_json":"https://pith.science/api/pith-number/E4QN3KYCINBWTGOA7LJDZ3DNK5/graph.json","events_json":"https://pith.science/api/pith-number/E4QN3KYCINBWTGOA7LJDZ3DNK5/events.json","paper":"https://pith.science/paper/E4QN3KYC"},"agent_actions":{"view_html":"https://pith.science/pith/E4QN3KYCINBWTGOA7LJDZ3DNK5","download_json":"https://pith.science/pith/E4QN3KYCINBWTGOA7LJDZ3DNK5.json","view_paper":"https://pith.science/paper/E4QN3KYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04479&json=true","fetch_graph":"https://pith.science/api/pith-number/E4QN3KYCINBWTGOA7LJDZ3DNK5/graph.json","fetch_events":"https://pith.science/api/pith-number/E4QN3KYCINBWTGOA7LJDZ3DNK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4QN3KYCINBWTGOA7LJDZ3DNK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4QN3KYCINBWTGOA7LJDZ3DNK5/action/storage_attestation","attest_author":"https://pith.science/pith/E4QN3KYCINBWTGOA7LJDZ3DNK5/action/author_attestation","sign_citation":"https://pith.science/pith/E4QN3KYCINBWTGOA7LJDZ3DNK5/action/citation_signature","submit_replication":"https://pith.science/pith/E4QN3KYCINBWTGOA7LJDZ3DNK5/action/replication_record"}},"created_at":"2026-08-06T01:35:41.055143+00:00","updated_at":"2026-08-06T01:35:41.055143+00:00"}