{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q3PL7XSWRLYNJXGHPNMD2A45J3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5f0fedb81cc578f9795ed338edc6508d2c4cfebce25c67633b033ebb01a99438","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-21T14:29:22Z","title_canon_sha256":"3e1b25f6fb981d4f22ccb74897833c3e9229f1867dfb4eed40be68d953e275e8"},"schema_version":"1.0","source":{"id":"2306.12300","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.12300","created_at":"2026-07-05T06:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"2306.12300v2","created_at":"2026-07-05T06:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12300","created_at":"2026-07-05T06:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"Q3PL7XSWRLYN","created_at":"2026-07-05T06:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"Q3PL7XSWRLYNJXGH","created_at":"2026-07-05T06:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"Q3PL7XSW","created_at":"2026-07-05T06:42:22Z"}],"graph_snapshots":[{"event_id":"sha256:89d873985b2ebee248ce64398cf099b42d5f5e89189b5b9bddd7ced2b5590ef4","target":"graph","created_at":"2026-07-05T06:42:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.12300/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Magdalena Fuentes, Saksham Singh Kushwaha","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-21T14:29:22Z","title":"A Multimodal Prototypical Approach for Unsupervised Sound Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12300","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eb469a2979541c042149f120f8a3246c4509c4cfb9cedaa16f481e402f3e47bb","target":"record","created_at":"2026-07-05T06:42:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5f0fedb81cc578f9795ed338edc6508d2c4cfebce25c67633b033ebb01a99438","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-21T14:29:22Z","title_canon_sha256":"3e1b25f6fb981d4f22ccb74897833c3e9229f1867dfb4eed40be68d953e275e8"},"schema_version":"1.0","source":{"id":"2306.12300","kind":"arxiv","version":2}},"canonical_sha256":"86debfde568af0d4dcc77b583d039d4edea6efddceb172f19a1ad05a513e7a3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86debfde568af0d4dcc77b583d039d4edea6efddceb172f19a1ad05a513e7a3e","first_computed_at":"2026-07-05T06:42:22.966980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:22.966980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q9AkXxbYVzYTMcSn12Kt7wmqDgZ6uEuNa+oPs/4p5yUr/OapMft2u+xghNPzCUPkL4c18nedO1LqafiqitHPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:22.967478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.12300","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb469a2979541c042149f120f8a3246c4509c4cfb9cedaa16f481e402f3e47bb","sha256:89d873985b2ebee248ce64398cf099b42d5f5e89189b5b9bddd7ced2b5590ef4"],"state_sha256":"1d059a317e2980333057729b52a74fe74643663c816de58022ceac8122d2bc61"}