{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OXZ6ESC3XQ52PEWTDJFMTZKBTX","short_pith_number":"pith:OXZ6ESC3","canonical_record":{"source":{"id":"2408.11638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:07:06Z","cross_cats_sorted":[],"title_canon_sha256":"24d17f362aec2202d32687f0c0751b3b693085b9660263baf11fe1b9668f8c05","abstract_canon_sha256":"06d0598739c795b54854a3151aa3a80a65e6787a04ad27fe920600f21e6606b0"},"schema_version":"1.0"},"canonical_sha256":"75f3e2485bbc3ba792d31a4ac9e5419dfe205a627918cd8fde6d60504c519410","source":{"kind":"arxiv","id":"2408.11638","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11638","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11638v1","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11638","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_12","alias_value":"OXZ6ESC3XQ52","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_16","alias_value":"OXZ6ESC3XQ52PEWT","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_8","alias_value":"OXZ6ESC3","created_at":"2026-07-05T08:57:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OXZ6ESC3XQ52PEWTDJFMTZKBTX","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11638","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:07:06Z","cross_cats_sorted":[],"title_canon_sha256":"24d17f362aec2202d32687f0c0751b3b693085b9660263baf11fe1b9668f8c05","abstract_canon_sha256":"06d0598739c795b54854a3151aa3a80a65e6787a04ad27fe920600f21e6606b0"},"schema_version":"1.0"},"canonical_sha256":"75f3e2485bbc3ba792d31a4ac9e5419dfe205a627918cd8fde6d60504c519410","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:46.502543Z","signature_b64":"1NTbZWW1vL9X39+FbNHY+CP9xNoz+DKurzBybVwaZv1tSl7+5AYiGtBnl07trf78q0JKKJM4cIYimE6jSKd9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75f3e2485bbc3ba792d31a4ac9e5419dfe205a627918cd8fde6d60504c519410","last_reissued_at":"2026-07-05T08:57:46.502056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:46.502056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11638","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+dAJ7ClPfOsYXHwIQ21/z3K8vdDHeq1rxHNGfcy7081C0X8n0v3WslcX+m0AFKswDdKKf7P/evm6uackVlxfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:11:51.542537Z"},"content_sha256":"c8b22a6b3482cc9ad2e09c98957686b6a69013b0fd69460ba01e241829a53fe8","schema_version":"1.0","event_id":"sha256:c8b22a6b3482cc9ad2e09c98957686b6a69013b0fd69460ba01e241829a53fe8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OXZ6ESC3XQ52PEWTDJFMTZKBTX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Florian Schmid, Gerhard Widmer, Jonathan Greif, Paul Primus","submitted_at":"2024-08-21T14:07:06Z","abstract_excerpt":"Query-by-Vocal Imitation (QBV) is about searching audio files within databases using vocal imitations created by the user's voice. Since most humans can effectively communicate sound concepts through voice, QBV offers the more intuitive and convenient approach compared to text-based search. To fully leverage QBV, developing robust audio feature representations for both the vocal imitation and the original sound is crucial. In this paper, we present a new system for QBV that utilizes the feature extraction capabilities of Convolutional Neural Networks pre-trained with large-scale general-purpos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11638","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/2408.11638/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WhM2ie9fbQgwI9tvJ0zrLA7h0Qx17qRlAI6nt6QSxjfJyQLGQXGz7fnuF3jbWrPMYCA58udtRSosePdEVL0zBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:11:51.543032Z"},"content_sha256":"ed14937c8a5dab85fca206c03383c327241577c313efb0c25000d61423586dd8","schema_version":"1.0","event_id":"sha256:ed14937c8a5dab85fca206c03383c327241577c313efb0c25000d61423586dd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXZ6ESC3XQ52PEWTDJFMTZKBTX/bundle.json","state_url":"https://pith.science/pith/OXZ6ESC3XQ52PEWTDJFMTZKBTX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXZ6ESC3XQ52PEWTDJFMTZKBTX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T16:11:51Z","links":{"resolver":"https://pith.science/pith/OXZ6ESC3XQ52PEWTDJFMTZKBTX","bundle":"https://pith.science/pith/OXZ6ESC3XQ52PEWTDJFMTZKBTX/bundle.json","state":"https://pith.science/pith/OXZ6ESC3XQ52PEWTDJFMTZKBTX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXZ6ESC3XQ52PEWTDJFMTZKBTX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OXZ6ESC3XQ52PEWTDJFMTZKBTX","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":"06d0598739c795b54854a3151aa3a80a65e6787a04ad27fe920600f21e6606b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:07:06Z","title_canon_sha256":"24d17f362aec2202d32687f0c0751b3b693085b9660263baf11fe1b9668f8c05"},"schema_version":"1.0","source":{"id":"2408.11638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11638","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11638v1","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11638","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_12","alias_value":"OXZ6ESC3XQ52","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_16","alias_value":"OXZ6ESC3XQ52PEWT","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_8","alias_value":"OXZ6ESC3","created_at":"2026-07-05T08:57:46Z"}],"graph_snapshots":[{"event_id":"sha256:ed14937c8a5dab85fca206c03383c327241577c313efb0c25000d61423586dd8","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/2408.11638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Query-by-Vocal Imitation (QBV) is about searching audio files within databases using vocal imitations created by the user's voice. Since most humans can effectively communicate sound concepts through voice, QBV offers the more intuitive and convenient approach compared to text-based search. To fully leverage QBV, developing robust audio feature representations for both the vocal imitation and the original sound is crucial. In this paper, we present a new system for QBV that utilizes the feature extraction capabilities of Convolutional Neural Networks pre-trained with large-scale general-purpos","authors_text":"Florian Schmid, Gerhard Widmer, Jonathan Greif, Paul Primus","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:07:06Z","title":"Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11638","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:c8b22a6b3482cc9ad2e09c98957686b6a69013b0fd69460ba01e241829a53fe8","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":"06d0598739c795b54854a3151aa3a80a65e6787a04ad27fe920600f21e6606b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-21T14:07:06Z","title_canon_sha256":"24d17f362aec2202d32687f0c0751b3b693085b9660263baf11fe1b9668f8c05"},"schema_version":"1.0","source":{"id":"2408.11638","kind":"arxiv","version":1}},"canonical_sha256":"75f3e2485bbc3ba792d31a4ac9e5419dfe205a627918cd8fde6d60504c519410","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75f3e2485bbc3ba792d31a4ac9e5419dfe205a627918cd8fde6d60504c519410","first_computed_at":"2026-07-05T08:57:46.502056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:46.502056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1NTbZWW1vL9X39+FbNHY+CP9xNoz+DKurzBybVwaZv1tSl7+5AYiGtBnl07trf78q0JKKJM4cIYimE6jSKd9Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:46.502543Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8b22a6b3482cc9ad2e09c98957686b6a69013b0fd69460ba01e241829a53fe8","sha256:ed14937c8a5dab85fca206c03383c327241577c313efb0c25000d61423586dd8"],"state_sha256":"2106ea490957c43684026afd60518c1edb095237d7255a0701deaff58e251a89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YA3IwK0TOmpZqLQ68aMkp+x6Bzgx0mElzg3CcexWSrl9ZrOHoj+4vLs/WbPP0OxoPywj0gCjjj1YMNj3fHFqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:11:51.546791Z","bundle_sha256":"d8286fa8e18e05fa641cfa1919679bc24679d24875ff8e4f64d5f92ee499e9f5"}}