{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VN5LX323P3RKMKCUCEE6BEYSHA","short_pith_number":"pith:VN5LX323","schema_version":"1.0","canonical_sha256":"ab7abbef5b7ee2a628541109e09312381d84404dfce0275f0a509fff917fc2db","source":{"kind":"arxiv","id":"2308.04258","version":1},"attestation_state":"computed","paper":{"title":"Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Gerhard Widmer, Khaled Koutini, Paul Primus","submitted_at":"2023-08-08T13:46:55Z","abstract_excerpt":"This work presents a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers. Our method projects recordings and textual descriptions into a shared audio-caption space in which related examples from different modalities are close. Through a systematic analysis, we examine how each component of the system influences retrieval performance. As a result, we identify two key components that play a crucial role in driving performance: the self-attention-based audio encoder for audio embedding and the utilization of additional human-generated and synthetic data sets duri"},"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":"2308.04258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-08-08T13:46:55Z","cross_cats_sorted":["cs.IR","cs.LG","cs.SD"],"title_canon_sha256":"2fdfbc95f0bc4ee17073b76416d62dd1d01a348aec8d02eb326872ec989d973c","abstract_canon_sha256":"8f290de49e34aefa770599ba3c0203594adb1d2717d3e66f8711c909734d8794"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:24.716203Z","signature_b64":"AcowAhdY9njOIvmOlWcI1GMQCQ1Se3hMoov6pKAXZWVBnoLoG3kg45SR+SD1YKjJs7aSm8y4+X8f0Xva+RRTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab7abbef5b7ee2a628541109e09312381d84404dfce0275f0a509fff917fc2db","last_reissued_at":"2026-07-05T06:39:24.715738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:24.715738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Gerhard Widmer, Khaled Koutini, Paul Primus","submitted_at":"2023-08-08T13:46:55Z","abstract_excerpt":"This work presents a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers. Our method projects recordings and textual descriptions into a shared audio-caption space in which related examples from different modalities are close. Through a systematic analysis, we examine how each component of the system influences retrieval performance. As a result, we identify two key components that play a crucial role in driving performance: the self-attention-based audio encoder for audio embedding and the utilization of additional human-generated and synthetic data sets duri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04258","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/2308.04258/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":"2308.04258","created_at":"2026-07-05T06:39:24.715796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04258v1","created_at":"2026-07-05T06:39:24.715796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04258","created_at":"2026-07-05T06:39:24.715796+00:00"},{"alias_kind":"pith_short_12","alias_value":"VN5LX323P3RK","created_at":"2026-07-05T06:39:24.715796+00:00"},{"alias_kind":"pith_short_16","alias_value":"VN5LX323P3RKMKCU","created_at":"2026-07-05T06:39:24.715796+00:00"},{"alias_kind":"pith_short_8","alias_value":"VN5LX323","created_at":"2026-07-05T06:39:24.715796+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/VN5LX323P3RKMKCUCEE6BEYSHA","json":"https://pith.science/pith/VN5LX323P3RKMKCUCEE6BEYSHA.json","graph_json":"https://pith.science/api/pith-number/VN5LX323P3RKMKCUCEE6BEYSHA/graph.json","events_json":"https://pith.science/api/pith-number/VN5LX323P3RKMKCUCEE6BEYSHA/events.json","paper":"https://pith.science/paper/VN5LX323"},"agent_actions":{"view_html":"https://pith.science/pith/VN5LX323P3RKMKCUCEE6BEYSHA","download_json":"https://pith.science/pith/VN5LX323P3RKMKCUCEE6BEYSHA.json","view_paper":"https://pith.science/paper/VN5LX323","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04258&json=true","fetch_graph":"https://pith.science/api/pith-number/VN5LX323P3RKMKCUCEE6BEYSHA/graph.json","fetch_events":"https://pith.science/api/pith-number/VN5LX323P3RKMKCUCEE6BEYSHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VN5LX323P3RKMKCUCEE6BEYSHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VN5LX323P3RKMKCUCEE6BEYSHA/action/storage_attestation","attest_author":"https://pith.science/pith/VN5LX323P3RKMKCUCEE6BEYSHA/action/author_attestation","sign_citation":"https://pith.science/pith/VN5LX323P3RKMKCUCEE6BEYSHA/action/citation_signature","submit_replication":"https://pith.science/pith/VN5LX323P3RKMKCUCEE6BEYSHA/action/replication_record"}},"created_at":"2026-07-05T06:39:24.715796+00:00","updated_at":"2026-07-05T06:39:24.715796+00:00"}