{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DHGYFDPQGZZUULYGFPSGSCQ4JK","short_pith_number":"pith:DHGYFDPQ","schema_version":"1.0","canonical_sha256":"19cd828df036734a2f062be4690a1c4a9e534520c2561dbb4a2b161fa4e44fb2","source":{"kind":"arxiv","id":"1712.09680","version":2},"attestation_state":"computed","paper":{"title":"A Light-Weight Multimodal Framework for Improved Environmental Audio Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Metze, Joseph Szurley, Juncheng Li, Samarjit Das, Yun Wang","submitted_at":"2017-12-27T20:52:21Z","abstract_excerpt":"The lack of strong labels has severely limited the state-of-the-art fully supervised audio tagging systems to be scaled to larger dataset. Meanwhile, audio-visual learning models based on unlabeled videos have been successfully applied to audio tagging, but they are inevitably resource hungry and require a long time to train. In this work, we propose a light-weight, multimodal framework for environmental audio tagging. The audio branch of the framework is a convolutional and recurrent neural network (CRNN) based on multiple instance learning (MIL). It is trained with the audio tracks of a larg"},"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":"1712.09680","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-12-27T20:52:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"02ae9e42a04ee878182f36204160355b2456efba2d6036f2c2054b4acf3593e6","abstract_canon_sha256":"baf9d2235948da22918e9b1fb2542eae59b4755b8e5d8d073daf8f77d1ef36e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:11.902651Z","signature_b64":"2VI8GRUo5bvB6PKDWyzlj8LnziDAhs8HQALfHwuTZnuiv5V54fxPk3T2BqirX5MLtE6dK9ABmS9gNXTLJ2qeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19cd828df036734a2f062be4690a1c4a9e534520c2561dbb4a2b161fa4e44fb2","last_reissued_at":"2026-05-18T00:22:11.902060Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:11.902060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Light-Weight Multimodal Framework for Improved Environmental Audio Tagging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Metze, Joseph Szurley, Juncheng Li, Samarjit Das, Yun Wang","submitted_at":"2017-12-27T20:52:21Z","abstract_excerpt":"The lack of strong labels has severely limited the state-of-the-art fully supervised audio tagging systems to be scaled to larger dataset. Meanwhile, audio-visual learning models based on unlabeled videos have been successfully applied to audio tagging, but they are inevitably resource hungry and require a long time to train. In this work, we propose a light-weight, multimodal framework for environmental audio tagging. The audio branch of the framework is a convolutional and recurrent neural network (CRNN) based on multiple instance learning (MIL). It is trained with the audio tracks of a larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09680","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":""},"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":"1712.09680","created_at":"2026-05-18T00:22:11.902149+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09680v2","created_at":"2026-05-18T00:22:11.902149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09680","created_at":"2026-05-18T00:22:11.902149+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHGYFDPQGZZU","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHGYFDPQGZZUULYG","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHGYFDPQ","created_at":"2026-05-18T12:31:10.602751+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/DHGYFDPQGZZUULYGFPSGSCQ4JK","json":"https://pith.science/pith/DHGYFDPQGZZUULYGFPSGSCQ4JK.json","graph_json":"https://pith.science/api/pith-number/DHGYFDPQGZZUULYGFPSGSCQ4JK/graph.json","events_json":"https://pith.science/api/pith-number/DHGYFDPQGZZUULYGFPSGSCQ4JK/events.json","paper":"https://pith.science/paper/DHGYFDPQ"},"agent_actions":{"view_html":"https://pith.science/pith/DHGYFDPQGZZUULYGFPSGSCQ4JK","download_json":"https://pith.science/pith/DHGYFDPQGZZUULYGFPSGSCQ4JK.json","view_paper":"https://pith.science/paper/DHGYFDPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09680&json=true","fetch_graph":"https://pith.science/api/pith-number/DHGYFDPQGZZUULYGFPSGSCQ4JK/graph.json","fetch_events":"https://pith.science/api/pith-number/DHGYFDPQGZZUULYGFPSGSCQ4JK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHGYFDPQGZZUULYGFPSGSCQ4JK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHGYFDPQGZZUULYGFPSGSCQ4JK/action/storage_attestation","attest_author":"https://pith.science/pith/DHGYFDPQGZZUULYGFPSGSCQ4JK/action/author_attestation","sign_citation":"https://pith.science/pith/DHGYFDPQGZZUULYGFPSGSCQ4JK/action/citation_signature","submit_replication":"https://pith.science/pith/DHGYFDPQGZZUULYGFPSGSCQ4JK/action/replication_record"}},"created_at":"2026-05-18T00:22:11.902149+00:00","updated_at":"2026-05-18T00:22:11.902149+00:00"}