{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZHIMQQXXABGEJOV5SEJD4SQK2B","short_pith_number":"pith:ZHIMQQXX","schema_version":"1.0","canonical_sha256":"c9d0c842f7004c44babd91123e4a0ad0465f510f2bfbecf169bbb3d83231578d","source":{"kind":"arxiv","id":"2408.11641","version":1},"attestation_state":"computed","paper":{"title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Florian Schmid, Gerhard Widmer, Paul Primus","submitted_at":"2024-08-21T14:10:58Z","abstract_excerpt":"Dual-encoder-based audio retrieval systems are commonly optimized with contrastive learning on a set of matching and mismatching audio-caption pairs. This leads to a shared embedding space in which corresponding items from the two modalities end up close together. Since audio-caption datasets typically only contain matching pairs of recordings and descriptions, it has become common practice to create mismatching pairs by pairing the audio with a caption randomly drawn from the dataset. This is not ideal because the randomly sampled caption could, just by chance, partly or entirely describe the"},"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":"2408.11641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:10:58Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"89411ad80b856581a1ba6775340a118c5165ff163b49f23ea7ac8be7a33ab9ac","abstract_canon_sha256":"510d40b90f6e85712fedff07a4b62546c32adfdfb8341283b857b02567e76574"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:46.555113Z","signature_b64":"TAIPCCuecaZTRz0/UPKQ5rYzlSWBmQamGd2p9TwaBSLs9/FGEY7xV65W2EfJeF+0B31rjQfqeLwgvwMvuPcwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9d0c842f7004c44babd91123e4a0ad0465f510f2bfbecf169bbb3d83231578d","last_reissued_at":"2026-07-05T08:57:46.554605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:46.554605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Florian Schmid, Gerhard Widmer, Paul Primus","submitted_at":"2024-08-21T14:10:58Z","abstract_excerpt":"Dual-encoder-based audio retrieval systems are commonly optimized with contrastive learning on a set of matching and mismatching audio-caption pairs. This leads to a shared embedding space in which corresponding items from the two modalities end up close together. Since audio-caption datasets typically only contain matching pairs of recordings and descriptions, it has become common practice to create mismatching pairs by pairing the audio with a caption randomly drawn from the dataset. This is not ideal because the randomly sampled caption could, just by chance, partly or entirely describe the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11641","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/2408.11641/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":"2408.11641","created_at":"2026-07-05T08:57:46.554658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11641v1","created_at":"2026-07-05T08:57:46.554658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11641","created_at":"2026-07-05T08:57:46.554658+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHIMQQXXABGE","created_at":"2026-07-05T08:57:46.554658+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHIMQQXXABGEJOV5","created_at":"2026-07-05T08:57:46.554658+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHIMQQXX","created_at":"2026-07-05T08:57:46.554658+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/ZHIMQQXXABGEJOV5SEJD4SQK2B","json":"https://pith.science/pith/ZHIMQQXXABGEJOV5SEJD4SQK2B.json","graph_json":"https://pith.science/api/pith-number/ZHIMQQXXABGEJOV5SEJD4SQK2B/graph.json","events_json":"https://pith.science/api/pith-number/ZHIMQQXXABGEJOV5SEJD4SQK2B/events.json","paper":"https://pith.science/paper/ZHIMQQXX"},"agent_actions":{"view_html":"https://pith.science/pith/ZHIMQQXXABGEJOV5SEJD4SQK2B","download_json":"https://pith.science/pith/ZHIMQQXXABGEJOV5SEJD4SQK2B.json","view_paper":"https://pith.science/paper/ZHIMQQXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11641&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHIMQQXXABGEJOV5SEJD4SQK2B/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHIMQQXXABGEJOV5SEJD4SQK2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHIMQQXXABGEJOV5SEJD4SQK2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHIMQQXXABGEJOV5SEJD4SQK2B/action/storage_attestation","attest_author":"https://pith.science/pith/ZHIMQQXXABGEJOV5SEJD4SQK2B/action/author_attestation","sign_citation":"https://pith.science/pith/ZHIMQQXXABGEJOV5SEJD4SQK2B/action/citation_signature","submit_replication":"https://pith.science/pith/ZHIMQQXXABGEJOV5SEJD4SQK2B/action/replication_record"}},"created_at":"2026-07-05T08:57:46.554658+00:00","updated_at":"2026-07-05T08:57:46.554658+00:00"}