{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q3PL7XSWRLYNJXGHPNMD2A45J3","short_pith_number":"pith:Q3PL7XSW","schema_version":"1.0","canonical_sha256":"86debfde568af0d4dcc77b583d039d4edea6efddceb172f19a1ad05a513e7a3e","source":{"kind":"arxiv","id":"2306.12300","version":2},"attestation_state":"computed","paper":{"title":"A Multimodal Prototypical Approach for Unsupervised Sound Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Magdalena Fuentes, Saksham Singh Kushwaha","submitted_at":"2023-06-21T14:29:22Z","abstract_excerpt":"In the context of environmental sound classification, the adaptability of systems is key: which sound classes are interesting depends on the context and the user's needs. Recent advances in text-to-audio retrieval allow for zero-shot audio classification, but performance compared to supervised models remains limited. This work proposes a multimodal prototypical approach that exploits local audio-text embeddings to provide more relevant answers to audio queries, augmenting the adaptability of sound detection in the wild. We do this by first using text to query a nearby community of audio embedd"},"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":"2306.12300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-21T14:29:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3e1b25f6fb981d4f22ccb74897833c3e9229f1867dfb4eed40be68d953e275e8","abstract_canon_sha256":"5f0fedb81cc578f9795ed338edc6508d2c4cfebce25c67633b033ebb01a99438"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:22.967478Z","signature_b64":"Q9AkXxbYVzYTMcSn12Kt7wmqDgZ6uEuNa+oPs/4p5yUr/OapMft2u+xghNPzCUPkL4c18nedO1LqafiqitHPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86debfde568af0d4dcc77b583d039d4edea6efddceb172f19a1ad05a513e7a3e","last_reissued_at":"2026-07-05T06:42:22.966980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:22.966980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multimodal Prototypical Approach for Unsupervised Sound Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Magdalena Fuentes, Saksham Singh Kushwaha","submitted_at":"2023-06-21T14:29:22Z","abstract_excerpt":"In the context of environmental sound classification, the adaptability of systems is key: which sound classes are interesting depends on the context and the user's needs. Recent advances in text-to-audio retrieval allow for zero-shot audio classification, but performance compared to supervised models remains limited. This work proposes a multimodal prototypical approach that exploits local audio-text embeddings to provide more relevant answers to audio queries, augmenting the adaptability of sound detection in the wild. We do this by first using text to query a nearby community of audio embedd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12300","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/2306.12300/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":"2306.12300","created_at":"2026-07-05T06:42:22.967039+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12300v2","created_at":"2026-07-05T06:42:22.967039+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12300","created_at":"2026-07-05T06:42:22.967039+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3PL7XSWRLYN","created_at":"2026-07-05T06:42:22.967039+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3PL7XSWRLYNJXGH","created_at":"2026-07-05T06:42:22.967039+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3PL7XSW","created_at":"2026-07-05T06:42:22.967039+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04376","citing_title":"Domain Adaptation Method and Modality Gap Impact in Audio-Text Models for Prototypical Sound Classification","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3","json":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3.json","graph_json":"https://pith.science/api/pith-number/Q3PL7XSWRLYNJXGHPNMD2A45J3/graph.json","events_json":"https://pith.science/api/pith-number/Q3PL7XSWRLYNJXGHPNMD2A45J3/events.json","paper":"https://pith.science/paper/Q3PL7XSW"},"agent_actions":{"view_html":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3","download_json":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3.json","view_paper":"https://pith.science/paper/Q3PL7XSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12300&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3PL7XSWRLYNJXGHPNMD2A45J3/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3PL7XSWRLYNJXGHPNMD2A45J3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3/action/storage_attestation","attest_author":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3/action/author_attestation","sign_citation":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3/action/citation_signature","submit_replication":"https://pith.science/pith/Q3PL7XSWRLYNJXGHPNMD2A45J3/action/replication_record"}},"created_at":"2026-07-05T06:42:22.967039+00:00","updated_at":"2026-07-05T06:42:22.967039+00:00"}