{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:K47RJUHHYEA5QZOUOOSQ6CMJN6","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":"646c840b01be3be872346345e9da0720d723e15d2396a39bf33edc9fe8d79ffd","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2017-01-03T07:35:54Z","title_canon_sha256":"b2f23b36c229ebe8d9782cb364080745bf2db6ca1851288ca28d28ca0bf81d9b"},"schema_version":"1.0","source":{"id":"1701.00599","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.00599","created_at":"2026-05-18T00:53:23Z"},{"alias_kind":"arxiv_version","alias_value":"1701.00599v2","created_at":"2026-05-18T00:53:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00599","created_at":"2026-05-18T00:53:23Z"},{"alias_kind":"pith_short_12","alias_value":"K47RJUHHYEA5","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K47RJUHHYEA5QZOU","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K47RJUHH","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:257a58f25d93b7dccd8a6efc0b3535eb67563bffe3be083ba7a2944e04cbc022","target":"graph","created_at":"2026-05-18T00:53:23Z","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":"We propose a new deep network for audio event recognition, called AENet. In contrast to speech, sounds coming from audio events may be produced by a wide variety of sources. Furthermore, distinguishing them often requires analyzing an extended time period due to the lack of clear sub-word units that are present in speech. In order to incorporate this long-time frequency structure of audio events, we introduce a convolutional neural network (CNN) operating on a large temporal input. In contrast to previous works this allows us to train an audio event detection system end-to-end. The combination","authors_text":"Luc Van Gool, Michael Gygli, Naoya Takahashi","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2017-01-03T07:35:54Z","title":"AENet: Learning Deep Audio Features for Video Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00599","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":"sha256:690f368199144ff0de9d9bb2f9b1c0f3114d520e26dc3ff5ae8649b3aefc95e8","target":"record","created_at":"2026-05-18T00:53:23Z","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":"646c840b01be3be872346345e9da0720d723e15d2396a39bf33edc9fe8d79ffd","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2017-01-03T07:35:54Z","title_canon_sha256":"b2f23b36c229ebe8d9782cb364080745bf2db6ca1851288ca28d28ca0bf81d9b"},"schema_version":"1.0","source":{"id":"1701.00599","kind":"arxiv","version":2}},"canonical_sha256":"573f14d0e7c101d865d473a50f09896fb5082fbf51d26bdcc5bc87963a4fab98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"573f14d0e7c101d865d473a50f09896fb5082fbf51d26bdcc5bc87963a4fab98","first_computed_at":"2026-05-18T00:53:23.861809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:23.861809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SwHlIp8ustq0wOKNKpkvGWSrWH2Ck6IOjQSoRpQjUYjXtx5eka9lvz5axHDAZcfNelyLxys70XsXtJSo/tkHAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:23.862446Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.00599","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:690f368199144ff0de9d9bb2f9b1c0f3114d520e26dc3ff5ae8649b3aefc95e8","sha256:257a58f25d93b7dccd8a6efc0b3535eb67563bffe3be083ba7a2944e04cbc022"],"state_sha256":"08cb881afebcd988da98d020d4430d7c374c7f5c30205162f1c526fc6bfdaccf"}