{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KC6IGOLCBU5A43WQWPEPK5AU3T","short_pith_number":"pith:KC6IGOLC","schema_version":"1.0","canonical_sha256":"50bc8339620d3a0e6ed0b3c8f57414dcebe041e0c6b94475dfd195151675a81b","source":{"kind":"arxiv","id":"2606.17404","version":1},"attestation_state":"computed","paper":{"title":"ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daichi Yashima, Kanon Amemiya, Kento Tokura, Komei Sugiura, Shinnosuke Takamichi, Shuntaro Suzuki","submitted_at":"2026-06-16T01:38:38Z","abstract_excerpt":"Text-to-audio (TTA) generation, synthesizing audio from natural language, has been widely studied for its ability to capture precise user intent. To effectively advance TTA models, it is essential to reliably evaluate generated audio without relying on costly human subjective ratings, motivating the development of automatic evaluation metrics that correlate well with human judgments. While recent CLAP-based metrics provide practical reference-free solutions, their coarse-grained text-audio similarity matching often correlates poorly with human ratings. To address this, we propose ELSA, a refer"},"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":"2606.17404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-16T01:38:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"bb97bea91e9dfac03cac85bf81d2a7ac342ac3e0ed28218464fab1dbe6db2f28","abstract_canon_sha256":"274de66b063ec83a65ecdc677388b07accb1b9436917ed72eaaf20778d2707ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:11.985586Z","signature_b64":"OTbqgC2KEk8tlMed94XR5uuT7f2AS30Pygiy19aOipHR9/20jV3vrFOnl55OJYxCCOPtKEXk+dtKBdSRxGNWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50bc8339620d3a0e6ed0b3c8f57414dcebe041e0c6b94475dfd195151675a81b","last_reissued_at":"2026-06-19T16:10:11.985212Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:11.985212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daichi Yashima, Kanon Amemiya, Kento Tokura, Komei Sugiura, Shinnosuke Takamichi, Shuntaro Suzuki","submitted_at":"2026-06-16T01:38:38Z","abstract_excerpt":"Text-to-audio (TTA) generation, synthesizing audio from natural language, has been widely studied for its ability to capture precise user intent. To effectively advance TTA models, it is essential to reliably evaluate generated audio without relying on costly human subjective ratings, motivating the development of automatic evaluation metrics that correlate well with human judgments. While recent CLAP-based metrics provide practical reference-free solutions, their coarse-grained text-audio similarity matching often correlates poorly with human ratings. To address this, we propose ELSA, a refer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17404","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/2606.17404/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":"2606.17404","created_at":"2026-06-19T16:10:11.985272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17404v1","created_at":"2026-06-19T16:10:11.985272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17404","created_at":"2026-06-19T16:10:11.985272+00:00"},{"alias_kind":"pith_short_12","alias_value":"KC6IGOLCBU5A","created_at":"2026-06-19T16:10:11.985272+00:00"},{"alias_kind":"pith_short_16","alias_value":"KC6IGOLCBU5A43WQ","created_at":"2026-06-19T16:10:11.985272+00:00"},{"alias_kind":"pith_short_8","alias_value":"KC6IGOLC","created_at":"2026-06-19T16:10:11.985272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.17404","citing_title":"ELSA: Acoustic Event-Level Semantic Alignment for Fine-Grained Reference-Free Text-to-Audio Evaluation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T","json":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T.json","graph_json":"https://pith.science/api/pith-number/KC6IGOLCBU5A43WQWPEPK5AU3T/graph.json","events_json":"https://pith.science/api/pith-number/KC6IGOLCBU5A43WQWPEPK5AU3T/events.json","paper":"https://pith.science/paper/KC6IGOLC"},"agent_actions":{"view_html":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T","download_json":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T.json","view_paper":"https://pith.science/paper/KC6IGOLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17404&json=true","fetch_graph":"https://pith.science/api/pith-number/KC6IGOLCBU5A43WQWPEPK5AU3T/graph.json","fetch_events":"https://pith.science/api/pith-number/KC6IGOLCBU5A43WQWPEPK5AU3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T/action/storage_attestation","attest_author":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T/action/author_attestation","sign_citation":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T/action/citation_signature","submit_replication":"https://pith.science/pith/KC6IGOLCBU5A43WQWPEPK5AU3T/action/replication_record"}},"created_at":"2026-06-19T16:10:11.985272+00:00","updated_at":"2026-06-19T16:10:11.985272+00:00"}