{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:K47RJUHHYEA5QZOUOOSQ6CMJN6","short_pith_number":"pith:K47RJUHH","canonical_record":{"source":{"id":"1701.00599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2017-01-03T07:35:54Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"b2f23b36c229ebe8d9782cb364080745bf2db6ca1851288ca28d28ca0bf81d9b","abstract_canon_sha256":"646c840b01be3be872346345e9da0720d723e15d2396a39bf33edc9fe8d79ffd"},"schema_version":"1.0"},"canonical_sha256":"573f14d0e7c101d865d473a50f09896fb5082fbf51d26bdcc5bc87963a4fab98","source":{"kind":"arxiv","id":"1701.00599","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:K47RJUHHYEA5QZOUOOSQ6CMJN6","target":"record","payload":{"canonical_record":{"source":{"id":"1701.00599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2017-01-03T07:35:54Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"b2f23b36c229ebe8d9782cb364080745bf2db6ca1851288ca28d28ca0bf81d9b","abstract_canon_sha256":"646c840b01be3be872346345e9da0720d723e15d2396a39bf33edc9fe8d79ffd"},"schema_version":"1.0"},"canonical_sha256":"573f14d0e7c101d865d473a50f09896fb5082fbf51d26bdcc5bc87963a4fab98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:23.862446Z","signature_b64":"SwHlIp8ustq0wOKNKpkvGWSrWH2Ck6IOjQSoRpQjUYjXtx5eka9lvz5axHDAZcfNelyLxys70XsXtJSo/tkHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"573f14d0e7c101d865d473a50f09896fb5082fbf51d26bdcc5bc87963a4fab98","last_reissued_at":"2026-05-18T00:53:23.861809Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:23.861809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.00599","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":"2026-05-18T00:53:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rXRjWZedqc61Q0+3XBata7GAiYCSQyc2B1+96gcHJ3Gg1HhaH9wSEqMs6lX03R1rFPsctT/Lb2vwsWeOIKxGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T07:50:45.737991Z"},"content_sha256":"690f368199144ff0de9d9bb2f9b1c0f3114d520e26dc3ff5ae8649b3aefc95e8","schema_version":"1.0","event_id":"sha256:690f368199144ff0de9d9bb2f9b1c0f3114d520e26dc3ff5ae8649b3aefc95e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:K47RJUHHYEA5QZOUOOSQ6CMJN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AENet: Learning Deep Audio Features for Video Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"cs.MM","authors_text":"Luc Van Gool, Michael Gygli, Naoya Takahashi","submitted_at":"2017-01-03T07:35:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00599","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":"2026-05-18T00:53:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MHdiUVlAj05XkbbNYjfTIDakFA48Xa+IPDYtYtp31kJHoFQC3lNFb2ZwPc/Y7V/XNrjUzG+AI7WkkYwJ0VePDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T07:50:45.738771Z"},"content_sha256":"257a58f25d93b7dccd8a6efc0b3535eb67563bffe3be083ba7a2944e04cbc022","schema_version":"1.0","event_id":"sha256:257a58f25d93b7dccd8a6efc0b3535eb67563bffe3be083ba7a2944e04cbc022"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/bundle.json","state_url":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/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":"2026-06-09T07:50:45Z","links":{"resolver":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6","bundle":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/bundle.json","state":"https://pith.science/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K47RJUHHYEA5QZOUOOSQ6CMJN6/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AnkatttDUvlUBexjedswI9tKqc+p9u5LK4CilbliZwS5dehvfhTGIIETFbsBc2wZtzxjWf3A99CdvBnoZAvuDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T07:50:45.742934Z","bundle_sha256":"76272d0a258b23308daa5c59f3335fa6ce29df44797f267be5804259468b2d36"}}