{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7UQFLTHEGH4SQFY66D2K3XC3OQ","short_pith_number":"pith:7UQFLTHE","canonical_record":{"source":{"id":"1712.09673","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-12-27T20:30:45Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0122200b87a980f9f93955fa1b6a3f30ce1dd0cf1762ee80f64aaba4cea70015","abstract_canon_sha256":"6ec4d38911c940c5846cee65536f3223950144b0e6a3dd9ab4a7e9a0f89b8644"},"schema_version":"1.0"},"canonical_sha256":"fd2055cce431f928171ef0f4addc5b743e4c1107aa2bccc007a2d0fb7a990c70","source":{"kind":"arxiv","id":"1712.09673","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09673","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09673v2","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09673","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"7UQFLTHEGH4S","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7UQFLTHEGH4SQFY6","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7UQFLTHE","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7UQFLTHEGH4SQFY66D2K3XC3OQ","target":"record","payload":{"canonical_record":{"source":{"id":"1712.09673","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-12-27T20:30:45Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0122200b87a980f9f93955fa1b6a3f30ce1dd0cf1762ee80f64aaba4cea70015","abstract_canon_sha256":"6ec4d38911c940c5846cee65536f3223950144b0e6a3dd9ab4a7e9a0f89b8644"},"schema_version":"1.0"},"canonical_sha256":"fd2055cce431f928171ef0f4addc5b743e4c1107aa2bccc007a2d0fb7a990c70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:16.250373Z","signature_b64":"hdjkuX4GKW0u84mVS1GTNmp4tk7FHfpoeIFFlw6/m8mKXn4WFD1brP3+7Db84DkM2yeCG5JS3ae5pHKQ0/acBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd2055cce431f928171ef0f4addc5b743e4c1107aa2bccc007a2d0fb7a990c70","last_reissued_at":"2026-05-18T00:20:16.249750Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:16.249750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.09673","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":"2026-05-18T00:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cfHNyZwOVY+C9lRxQ7/982z+z5LzL+bd4AuEHzT3gxzDfTsYKSiZXtC6b9MdIdnpyQ+5EJQaYwj41XAuXfdvAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:52:49.580819Z"},"content_sha256":"458b8482cd18e0f463d4c60b278f24daa87455a42b1c1f1f9f91866c3f6eab48","schema_version":"1.0","event_id":"sha256:458b8482cd18e0f463d4c60b278f24daa87455a42b1c1f1f9f91866c3f6eab48"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7UQFLTHEGH4SQFY66D2K3XC3OQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection","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, Shao-Yen Tseng, Yun Wang","submitted_at":"2017-12-27T20:30:45Z","abstract_excerpt":"State-of-the-art audio event detection (AED) systems rely on supervised learning using strongly labeled data. However, this dependence severely limits scalability to large-scale datasets where fine resolution annotations are too expensive to obtain. In this paper, we propose a small-footprint multiple instance learning (MIL) framework for multi-class AED using weakly annotated labels. The proposed MIL framework uses audio embeddings extracted from a pre-trained convolutional neural network as input features. We show that by using audio embeddings the MIL framework can be implemented using a si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09673","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:20:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8uToDdUAJ2H8gfnIm4hRcNOsTbBAK4jMFrTov2txrYxVlOqat8woFVSyKEeV6A9ZpcE3SdHIUV8d3iLOuiLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T06:52:49.581619Z"},"content_sha256":"9dfe9dd4e51e1bf2670c09f926a49e86969af24c1e280b6389a2e75d80007e1b","schema_version":"1.0","event_id":"sha256:9dfe9dd4e51e1bf2670c09f926a49e86969af24c1e280b6389a2e75d80007e1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/bundle.json","state_url":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/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":"2026-06-10T06:52:49Z","links":{"resolver":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ","bundle":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/bundle.json","state":"https://pith.science/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UQFLTHEGH4SQFY66D2K3XC3OQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7UQFLTHEGH4SQFY66D2K3XC3OQ","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":"6ec4d38911c940c5846cee65536f3223950144b0e6a3dd9ab4a7e9a0f89b8644","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-12-27T20:30:45Z","title_canon_sha256":"0122200b87a980f9f93955fa1b6a3f30ce1dd0cf1762ee80f64aaba4cea70015"},"schema_version":"1.0","source":{"id":"1712.09673","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09673","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09673v2","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09673","created_at":"2026-05-18T00:20:16Z"},{"alias_kind":"pith_short_12","alias_value":"7UQFLTHEGH4S","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7UQFLTHEGH4SQFY6","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7UQFLTHE","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:9dfe9dd4e51e1bf2670c09f926a49e86969af24c1e280b6389a2e75d80007e1b","target":"graph","created_at":"2026-05-18T00:20:16Z","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"},"paper":{"abstract_excerpt":"State-of-the-art audio event detection (AED) systems rely on supervised learning using strongly labeled data. However, this dependence severely limits scalability to large-scale datasets where fine resolution annotations are too expensive to obtain. In this paper, we propose a small-footprint multiple instance learning (MIL) framework for multi-class AED using weakly annotated labels. The proposed MIL framework uses audio embeddings extracted from a pre-trained convolutional neural network as input features. We show that by using audio embeddings the MIL framework can be implemented using a si","authors_text":"Florian Metze, Joseph Szurley, Juncheng Li, Samarjit Das, Shao-Yen Tseng, Yun Wang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-12-27T20:30:45Z","title":"Multiple Instance Deep Learning for Weakly Supervised Small-Footprint Audio Event Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09673","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":"sha256:458b8482cd18e0f463d4c60b278f24daa87455a42b1c1f1f9f91866c3f6eab48","target":"record","created_at":"2026-05-18T00:20:16Z","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":"6ec4d38911c940c5846cee65536f3223950144b0e6a3dd9ab4a7e9a0f89b8644","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-12-27T20:30:45Z","title_canon_sha256":"0122200b87a980f9f93955fa1b6a3f30ce1dd0cf1762ee80f64aaba4cea70015"},"schema_version":"1.0","source":{"id":"1712.09673","kind":"arxiv","version":2}},"canonical_sha256":"fd2055cce431f928171ef0f4addc5b743e4c1107aa2bccc007a2d0fb7a990c70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd2055cce431f928171ef0f4addc5b743e4c1107aa2bccc007a2d0fb7a990c70","first_computed_at":"2026-05-18T00:20:16.249750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:16.249750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hdjkuX4GKW0u84mVS1GTNmp4tk7FHfpoeIFFlw6/m8mKXn4WFD1brP3+7Db84DkM2yeCG5JS3ae5pHKQ0/acBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:16.250373Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.09673","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:458b8482cd18e0f463d4c60b278f24daa87455a42b1c1f1f9f91866c3f6eab48","sha256:9dfe9dd4e51e1bf2670c09f926a49e86969af24c1e280b6389a2e75d80007e1b"],"state_sha256":"a396dd28b8978f5ac1274960ee6f24a831f548be4d75cc6143a845ea54b5ee3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7BDMVyb2+/YREDrVgR/HIQkGzXGFeNmnKP0zmvZlj0WZiCe7z8NGloo13sszbja4gxv9AlSNcrC+uHvgxuxEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T06:52:49.585678Z","bundle_sha256":"a1b9bc0c8e596d449dba29da8205e848ab968d3b310e169c86e928e9542d4549"}}