{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4U5Y4LI6EXWZVUU55VA2LKLC6S","short_pith_number":"pith:4U5Y4LI6","schema_version":"1.0","canonical_sha256":"e53b8e2d1e25ed9ad29ded41a5a962f49259dad5e1993f29ced34d81a6e0ca60","source":{"kind":"arxiv","id":"1810.09050","version":3},"attestation_state":"computed","paper":{"title":"A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Metze, Juncheng Li, Yun Wang","submitted_at":"2018-10-22T01:34:29Z","abstract_excerpt":"Sound event detection (SED) entails two subtasks: recognizing what types of sound events are present in an audio stream (audio tagging), and pinpointing their onset and offset times (localization). In the popular multiple instance learning (MIL) framework for SED with weak labeling, an important component is the pooling function. This paper compares five types of pooling functions both theoretically and experimentally, with special focus on their performance of localization. Although the attention pooling function is currently receiving the most attention, we find the linear softmax pooling fu"},"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":"1810.09050","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-10-22T01:34:29Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9e1f6f2a7308ff7d03039b299f6ae2f7b4c39488990433b611c2c61d7bc7ca4c","abstract_canon_sha256":"e48ad4ad828153138227f0c7fa61c1f1a33bdfceb1ca18065d364403c352e73a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:41.767419Z","signature_b64":"bWNgJ0dAGWR5OoN59SIS+xm7qY5Y7z16om9jYK7whntCfTwPswvwBLLhLzjiq/xhVggRX7ebbg0JaTV6wo3gCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e53b8e2d1e25ed9ad29ded41a5a962f49259dad5e1993f29ced34d81a6e0ca60","last_reissued_at":"2026-05-17T23:53:41.766772Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:41.766772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparison of Five Multiple Instance Learning Pooling Functions for Sound Event Detection with Weak Labeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Florian Metze, Juncheng Li, Yun Wang","submitted_at":"2018-10-22T01:34:29Z","abstract_excerpt":"Sound event detection (SED) entails two subtasks: recognizing what types of sound events are present in an audio stream (audio tagging), and pinpointing their onset and offset times (localization). In the popular multiple instance learning (MIL) framework for SED with weak labeling, an important component is the pooling function. This paper compares five types of pooling functions both theoretically and experimentally, with special focus on their performance of localization. Although the attention pooling function is currently receiving the most attention, we find the linear softmax pooling fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09050","kind":"arxiv","version":3},"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":"1810.09050","created_at":"2026-05-17T23:53:41.766866+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.09050v3","created_at":"2026-05-17T23:53:41.766866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09050","created_at":"2026-05-17T23:53:41.766866+00:00"},{"alias_kind":"pith_short_12","alias_value":"4U5Y4LI6EXWZ","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4U5Y4LI6EXWZVUU5","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4U5Y4LI6","created_at":"2026-05-18T12:32:05.422762+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/4U5Y4LI6EXWZVUU55VA2LKLC6S","json":"https://pith.science/pith/4U5Y4LI6EXWZVUU55VA2LKLC6S.json","graph_json":"https://pith.science/api/pith-number/4U5Y4LI6EXWZVUU55VA2LKLC6S/graph.json","events_json":"https://pith.science/api/pith-number/4U5Y4LI6EXWZVUU55VA2LKLC6S/events.json","paper":"https://pith.science/paper/4U5Y4LI6"},"agent_actions":{"view_html":"https://pith.science/pith/4U5Y4LI6EXWZVUU55VA2LKLC6S","download_json":"https://pith.science/pith/4U5Y4LI6EXWZVUU55VA2LKLC6S.json","view_paper":"https://pith.science/paper/4U5Y4LI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.09050&json=true","fetch_graph":"https://pith.science/api/pith-number/4U5Y4LI6EXWZVUU55VA2LKLC6S/graph.json","fetch_events":"https://pith.science/api/pith-number/4U5Y4LI6EXWZVUU55VA2LKLC6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4U5Y4LI6EXWZVUU55VA2LKLC6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4U5Y4LI6EXWZVUU55VA2LKLC6S/action/storage_attestation","attest_author":"https://pith.science/pith/4U5Y4LI6EXWZVUU55VA2LKLC6S/action/author_attestation","sign_citation":"https://pith.science/pith/4U5Y4LI6EXWZVUU55VA2LKLC6S/action/citation_signature","submit_replication":"https://pith.science/pith/4U5Y4LI6EXWZVUU55VA2LKLC6S/action/replication_record"}},"created_at":"2026-05-17T23:53:41.766866+00:00","updated_at":"2026-05-17T23:53:41.766866+00:00"}