{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZHIMQQXXABGEJOV5SEJD4SQK2B","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":"510d40b90f6e85712fedff07a4b62546c32adfdfb8341283b857b02567e76574","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:10:58Z","title_canon_sha256":"89411ad80b856581a1ba6775340a118c5165ff163b49f23ea7ac8be7a33ab9ac"},"schema_version":"1.0","source":{"id":"2408.11641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11641","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11641v1","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11641","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_12","alias_value":"ZHIMQQXXABGE","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_16","alias_value":"ZHIMQQXXABGEJOV5","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_8","alias_value":"ZHIMQQXX","created_at":"2026-07-05T08:57:46Z"}],"graph_snapshots":[{"event_id":"sha256:86ed80153c76d2518752c7b10f3eec54d006cec80d5dc905f4f416f30892159c","target":"graph","created_at":"2026-07-05T08:57:46Z","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/2408.11641/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Florian Schmid, Gerhard Widmer, Paul Primus","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:10:58Z","title":"Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11641","kind":"arxiv","version":1},"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":"sha256:86f3bf2751e7900236d797bde70df78c0129fa14a2a459b8034cf3ccd22aa685","target":"record","created_at":"2026-07-05T08:57:46Z","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":"510d40b90f6e85712fedff07a4b62546c32adfdfb8341283b857b02567e76574","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:10:58Z","title_canon_sha256":"89411ad80b856581a1ba6775340a118c5165ff163b49f23ea7ac8be7a33ab9ac"},"schema_version":"1.0","source":{"id":"2408.11641","kind":"arxiv","version":1}},"canonical_sha256":"c9d0c842f7004c44babd91123e4a0ad0465f510f2bfbecf169bbb3d83231578d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9d0c842f7004c44babd91123e4a0ad0465f510f2bfbecf169bbb3d83231578d","first_computed_at":"2026-07-05T08:57:46.554605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:46.554605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TAIPCCuecaZTRz0/UPKQ5rYzlSWBmQamGd2p9TwaBSLs9/FGEY7xV65W2EfJeF+0B31rjQfqeLwgvwMvuPcwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:46.555113Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86f3bf2751e7900236d797bde70df78c0129fa14a2a459b8034cf3ccd22aa685","sha256:86ed80153c76d2518752c7b10f3eec54d006cec80d5dc905f4f416f30892159c"],"state_sha256":"9ef81ff1005b198f19179d7ca80bc9a9170735b126aa9f5bab50e964e41be515"}