{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:X7WYCUROIX5DMFPN4GMXAERI7A","short_pith_number":"pith:X7WYCURO","schema_version":"1.0","canonical_sha256":"bfed81522e45fa3615ede199701228f83551defbffbf5243c12e8b212effb7c1","source":{"kind":"arxiv","id":"1711.00927","version":2},"attestation_state":"computed","paper":{"title":"Audio Set classification with attention model: A probabilistic perspective","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":"2017-11-02T20:40:29Z","abstract_excerpt":"This paper investigates the classification of the Audio Set dataset. Audio Set is a large scale weakly labelled dataset of sound clips. Previous work used multiple instance learning (MIL) to classify weakly labelled data. In MIL, a bag consists of several instances, and a bag is labelled positive if at least one instances in the audio clip is positive. A bag is labelled negative if all the instances in the bag are negative. We propose an attention model to tackle the MIL problem and explain this attention model from a novel probabilistic perspective. We define a probability space on each bag, "},"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":"1711.00927","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-11-02T20:40:29Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d63f4241ef1e8ef58e910eb79a006a9e1559e094c817f252ae16853725980a41","abstract_canon_sha256":"a0187e8c27f25727105c6eb728ad51be3144acb22b1302b2caec676b05f63d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:34.456340Z","signature_b64":"so92iTrArqT+lppxXNhPMV8eIn76OsVm0c4gEKE7mTzjLvhnnoaRZnOkqkKEjgTnPwTOx8/pHu44cKQLEXUjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfed81522e45fa3615ede199701228f83551defbffbf5243c12e8b212effb7c1","last_reissued_at":"2026-07-05T00:24:34.455984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:34.455984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Set classification with attention model: A probabilistic perspective","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":"2017-11-02T20:40:29Z","abstract_excerpt":"This paper investigates the classification of the Audio Set dataset. Audio Set is a large scale weakly labelled dataset of sound clips. Previous work used multiple instance learning (MIL) to classify weakly labelled data. In MIL, a bag consists of several instances, and a bag is labelled positive if at least one instances in the audio clip is positive. A bag is labelled negative if all the instances in the bag are negative. We propose an attention model to tackle the MIL problem and explain this attention model from a novel probabilistic perspective. We define a probability space on each bag, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00927","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/1711.00927/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":"1711.00927","created_at":"2026-07-05T00:24:34.456040+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00927v2","created_at":"2026-07-05T00:24:34.456040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00927","created_at":"2026-07-05T00:24:34.456040+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7WYCUROIX5D","created_at":"2026-07-05T00:24:34.456040+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7WYCUROIX5DMFPN","created_at":"2026-07-05T00:24:34.456040+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7WYCURO","created_at":"2026-07-05T00:24:34.456040+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.02876","citing_title":"Self-supervised Attention Model for Weakly Labeled Audio Event Classification","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A","json":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A.json","graph_json":"https://pith.science/api/pith-number/X7WYCUROIX5DMFPN4GMXAERI7A/graph.json","events_json":"https://pith.science/api/pith-number/X7WYCUROIX5DMFPN4GMXAERI7A/events.json","paper":"https://pith.science/paper/X7WYCURO"},"agent_actions":{"view_html":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A","download_json":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A.json","view_paper":"https://pith.science/paper/X7WYCURO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00927&json=true","fetch_graph":"https://pith.science/api/pith-number/X7WYCUROIX5DMFPN4GMXAERI7A/graph.json","fetch_events":"https://pith.science/api/pith-number/X7WYCUROIX5DMFPN4GMXAERI7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A/action/storage_attestation","attest_author":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A/action/author_attestation","sign_citation":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A/action/citation_signature","submit_replication":"https://pith.science/pith/X7WYCUROIX5DMFPN4GMXAERI7A/action/replication_record"}},"created_at":"2026-07-05T00:24:34.456040+00:00","updated_at":"2026-07-05T00:24:34.456040+00:00"}