{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JKRKHFZUNONOCCGQFWICNEZGPK","short_pith_number":"pith:JKRKHFZU","canonical_record":{"source":{"id":"1912.04761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-12-10T15:25:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"76ebff2ef99701afa418ce478b22f7bdfa19fc71fa98215e28470b2ee9463b78","abstract_canon_sha256":"32cbcffce909d6bdf04db983dcf7611f270403c2a87f8804e4239811a7f75e6e"},"schema_version":"1.0"},"canonical_sha256":"4aa2a397346b9ae108d02d902693267aa0ce6b85b71481583e5ba490ddfa6f62","source":{"kind":"arxiv","id":"1912.04761","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.04761","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"1912.04761v2","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04761","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"JKRKHFZUNONO","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"JKRKHFZUNONOCCGQ","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"JKRKHFZU","created_at":"2026-07-05T01:29:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JKRKHFZUNONOCCGQFWICNEZGPK","target":"record","payload":{"canonical_record":{"source":{"id":"1912.04761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-12-10T15:25:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"76ebff2ef99701afa418ce478b22f7bdfa19fc71fa98215e28470b2ee9463b78","abstract_canon_sha256":"32cbcffce909d6bdf04db983dcf7611f270403c2a87f8804e4239811a7f75e6e"},"schema_version":"1.0"},"canonical_sha256":"4aa2a397346b9ae108d02d902693267aa0ce6b85b71481583e5ba490ddfa6f62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:01.725526Z","signature_b64":"6vWIMFb/SKtlhcl3N4AD/jmnAjek/So6MuOvyphlLg5+A3yV4+mC/C1MflF4i4OSqMYvPMbFAOEDNIcSEK/FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aa2a397346b9ae108d02d902693267aa0ce6b85b71481583e5ba490ddfa6f62","last_reissued_at":"2026-07-05T01:29:01.724909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:01.724909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.04761","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f2wfXYcoLnK0WxzfO1q0v3ZWgOizfb5p67AmMKax4VpXZWNlIus0XKxqji6qaiCrwJIiXVJ/PFczCIxLCaQGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:03:14.360487Z"},"content_sha256":"2f1031cfe8b92cb782b905980b3da9b899759677678a04a0ea3675337a32bacd","schema_version":"1.0","event_id":"sha256:2f1031cfe8b92cb782b905980b3da9b899759677678a04a0ea3675337a32bacd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JKRKHFZUNONOCCGQFWICNEZGPK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Mark D. Plumbley, Qiuqiang Kong, Wenwu Wang, Yong Xu","submitted_at":"2019-12-10T15:25:37Z","abstract_excerpt":"Sound event detection (SED) is a task to detect sound events in an audio recording. One challenge of the SED task is that many datasets such as the Detection and Classification of Acoustic Scenes and Events (DCASE) datasets are weakly labelled. That is, there are only audio tags for each audio clip without the onset and offset times of sound events. \\qk{We compare segment-wise and clip-wise training for SED that is lacking in previous works. We propose a convolutional neural network transformer (CNN-Transfomer) for audio tagging and SED, and show that CNN-Transformer performs similarly to a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04761","kind":"arxiv","version":2},"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/1912.04761/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":"2026-07-05T01:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZtYUO+asHQFWHjkyCP0FTgSwytdCnTdoEFTuDdA29FFJdTWkaBstq07TA151KfxFIvYbc6Kdq4lAru3sG6iBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:03:14.361228Z"},"content_sha256":"310dcb19c098942890f09fbec970becb6bb1c9325cdedfcff2c6c36653b9c379","schema_version":"1.0","event_id":"sha256:310dcb19c098942890f09fbec970becb6bb1c9325cdedfcff2c6c36653b9c379"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JKRKHFZUNONOCCGQFWICNEZGPK/bundle.json","state_url":"https://pith.science/pith/JKRKHFZUNONOCCGQFWICNEZGPK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JKRKHFZUNONOCCGQFWICNEZGPK/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":"2026-08-15T03:03:14Z","links":{"resolver":"https://pith.science/pith/JKRKHFZUNONOCCGQFWICNEZGPK","bundle":"https://pith.science/pith/JKRKHFZUNONOCCGQFWICNEZGPK/bundle.json","state":"https://pith.science/pith/JKRKHFZUNONOCCGQFWICNEZGPK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JKRKHFZUNONOCCGQFWICNEZGPK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JKRKHFZUNONOCCGQFWICNEZGPK","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":"32cbcffce909d6bdf04db983dcf7611f270403c2a87f8804e4239811a7f75e6e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-12-10T15:25:37Z","title_canon_sha256":"76ebff2ef99701afa418ce478b22f7bdfa19fc71fa98215e28470b2ee9463b78"},"schema_version":"1.0","source":{"id":"1912.04761","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.04761","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"1912.04761v2","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04761","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"JKRKHFZUNONO","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"JKRKHFZUNONOCCGQ","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"JKRKHFZU","created_at":"2026-07-05T01:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:310dcb19c098942890f09fbec970becb6bb1c9325cdedfcff2c6c36653b9c379","target":"graph","created_at":"2026-07-05T01:29:01Z","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/1912.04761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sound event detection (SED) is a task to detect sound events in an audio recording. One challenge of the SED task is that many datasets such as the Detection and Classification of Acoustic Scenes and Events (DCASE) datasets are weakly labelled. That is, there are only audio tags for each audio clip without the onset and offset times of sound events. \\qk{We compare segment-wise and clip-wise training for SED that is lacking in previous works. We propose a convolutional neural network transformer (CNN-Transfomer) for audio tagging and SED, and show that CNN-Transformer performs similarly to a co","authors_text":"Mark D. Plumbley, Qiuqiang Kong, Wenwu Wang, Yong Xu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-12-10T15:25:37Z","title":"Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04761","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":"sha256:2f1031cfe8b92cb782b905980b3da9b899759677678a04a0ea3675337a32bacd","target":"record","created_at":"2026-07-05T01:29:01Z","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":"32cbcffce909d6bdf04db983dcf7611f270403c2a87f8804e4239811a7f75e6e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-12-10T15:25:37Z","title_canon_sha256":"76ebff2ef99701afa418ce478b22f7bdfa19fc71fa98215e28470b2ee9463b78"},"schema_version":"1.0","source":{"id":"1912.04761","kind":"arxiv","version":2}},"canonical_sha256":"4aa2a397346b9ae108d02d902693267aa0ce6b85b71481583e5ba490ddfa6f62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aa2a397346b9ae108d02d902693267aa0ce6b85b71481583e5ba490ddfa6f62","first_computed_at":"2026-07-05T01:29:01.724909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:29:01.724909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6vWIMFb/SKtlhcl3N4AD/jmnAjek/So6MuOvyphlLg5+A3yV4+mC/C1MflF4i4OSqMYvPMbFAOEDNIcSEK/FAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:29:01.725526Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.04761","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f1031cfe8b92cb782b905980b3da9b899759677678a04a0ea3675337a32bacd","sha256:310dcb19c098942890f09fbec970becb6bb1c9325cdedfcff2c6c36653b9c379"],"state_sha256":"a7e4a33f353adc00901971c4e8037e459305db1822e3b8fc5545df4205709dad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRxpu1KuSnpacD8w0b9RTicb26gMp4tf/GnfjDlGPnP/IX6U4moH9Xq8V41iV1lqSwTzlcYnv9Qqg3T6g0cEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T03:03:14.367353Z","bundle_sha256":"ac87cd51111eb510f1468ff602912f3ef5041264e1ec38623e4d390b1899aa6a"}}