{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OBDBYYKEJ5454SV4RFPTYXRQSN","short_pith_number":"pith:OBDBYYKE","schema_version":"1.0","canonical_sha256":"70461c61444f79de4abc895f3c5e309369a9b443dcf4390ec4efa5fa5b018bf7","source":{"kind":"arxiv","id":"2506.04376","version":1},"attestation_state":"computed","paper":{"title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Emiliano Acevedo, Magdalena Fuentes, Mart\\'in Rocamora","submitted_at":"2025-06-04T18:45:51Z","abstract_excerpt":"Audio-text models are widely used in zero-shot environmental sound classification as they alleviate the need for annotated data. However, we show that their performance severely drops in the presence of background sound sources. Our analysis reveals that this degradation is primarily driven by SNR levels of background soundscapes, and independent of background type. To address this, we propose a novel method that quantifies and integrates the contribution of background sources into the classification process, improving performance without requiring model retraining. Our domain adaptation techn"},"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":"2506.04376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-04T18:45:51Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"2b330f09add6b874d954f81d8eb4b7c9d84aabb9fc04549f99dd92206135f27f","abstract_canon_sha256":"b105d89ead5336f1d52ebd1658f779dde8c4a1e5dd22081976dba6e31fc54dce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:36.468526Z","signature_b64":"zSvpGy0hgjRkcY9xnLmhNRSRP8HsNmUx3MYlWMOkK+3m8v9fdnRjajI3uI15zD9hVn54+xD6ogqqzlq6Ne0nAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70461c61444f79de4abc895f3c5e309369a9b443dcf4390ec4efa5fa5b018bf7","last_reissued_at":"2026-07-05T11:16:36.468004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:36.468004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Emiliano Acevedo, Magdalena Fuentes, Mart\\'in Rocamora","submitted_at":"2025-06-04T18:45:51Z","abstract_excerpt":"Audio-text models are widely used in zero-shot environmental sound classification as they alleviate the need for annotated data. However, we show that their performance severely drops in the presence of background sound sources. Our analysis reveals that this degradation is primarily driven by SNR levels of background soundscapes, and independent of background type. To address this, we propose a novel method that quantifies and integrates the contribution of background sources into the classification process, improving performance without requiring model retraining. Our domain adaptation techn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04376","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/2506.04376/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":"2506.04376","created_at":"2026-07-05T11:16:36.468064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04376v1","created_at":"2026-07-05T11:16:36.468064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04376","created_at":"2026-07-05T11:16:36.468064+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBDBYYKEJ545","created_at":"2026-07-05T11:16:36.468064+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBDBYYKEJ5454SV4","created_at":"2026-07-05T11:16:36.468064+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBDBYYKE","created_at":"2026-07-05T11:16:36.468064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04844","citing_title":"Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN","json":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN.json","graph_json":"https://pith.science/api/pith-number/OBDBYYKEJ5454SV4RFPTYXRQSN/graph.json","events_json":"https://pith.science/api/pith-number/OBDBYYKEJ5454SV4RFPTYXRQSN/events.json","paper":"https://pith.science/paper/OBDBYYKE"},"agent_actions":{"view_html":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN","download_json":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN.json","view_paper":"https://pith.science/paper/OBDBYYKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04376&json=true","fetch_graph":"https://pith.science/api/pith-number/OBDBYYKEJ5454SV4RFPTYXRQSN/graph.json","fetch_events":"https://pith.science/api/pith-number/OBDBYYKEJ5454SV4RFPTYXRQSN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN/action/storage_attestation","attest_author":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN/action/author_attestation","sign_citation":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN/action/citation_signature","submit_replication":"https://pith.science/pith/OBDBYYKEJ5454SV4RFPTYXRQSN/action/replication_record"}},"created_at":"2026-07-05T11:16:36.468064+00:00","updated_at":"2026-07-05T11:16:36.468064+00:00"}