{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UBLLLQWCZURN5DNAEE3H65N3YR","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":"f5bcd44733a4b24d1fe35bf880e9b9376f9609da15c9fac60263452f298755eb","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-14T22:00:47Z","title_canon_sha256":"bc1e32801952cfc3c7e156b658e585fb9c24322306fd5260e48c6aac7700ad84"},"schema_version":"1.0","source":{"id":"2409.09546","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09546","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09546v2","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09546","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_12","alias_value":"UBLLLQWCZURN","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_16","alias_value":"UBLLLQWCZURN5DNA","created_at":"2026-07-05T09:41:41Z"},{"alias_kind":"pith_short_8","alias_value":"UBLLLQWC","created_at":"2026-07-05T09:41:41Z"}],"graph_snapshots":[{"event_id":"sha256:656b3b2b22a5c46e89218e3c976c9a1125f42306d460635540318684df18a427","target":"graph","created_at":"2026-07-05T09:41:41Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.09546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a pre-training pipeline for audio spectrogram transformers for frame-level sound event detection tasks. On top of common pre-training steps, we add a meticulously designed training routine on AudioSet frame-level annotations. This includes a balanced sampler, aggressive data augmentation, and ensemble knowledge distillation. For five transformers, we obtain a substantial performance improvement over previously available checkpoints both on AudioSet frame-level predictions and on frame-level sound event detection downstream tasks, confirming our pipeline's effectiveness. We publish t","authors_text":"Florian Schmid, Francesco Foscarin, Gerhard Widmer, Jan Schl\\\"uter, Paul Primus, Tobias Morocutti","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-14T22:00:47Z","title":"Effective Pre-Training of Audio Transformers for Sound Event Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09546","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":"sha256:02c1233072c3d27eb1c3ab53a8c17f4c1fde833122ac9c0ee50db055d570055e","target":"record","created_at":"2026-07-05T09:41:41Z","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":"f5bcd44733a4b24d1fe35bf880e9b9376f9609da15c9fac60263452f298755eb","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-14T22:00:47Z","title_canon_sha256":"bc1e32801952cfc3c7e156b658e585fb9c24322306fd5260e48c6aac7700ad84"},"schema_version":"1.0","source":{"id":"2409.09546","kind":"arxiv","version":2}},"canonical_sha256":"a056b5c2c2cd22de8da021367f75bbc4480e53031d534d8923eeeaec237d9660","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a056b5c2c2cd22de8da021367f75bbc4480e53031d534d8923eeeaec237d9660","first_computed_at":"2026-07-05T09:41:41.747153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:41.747153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MpBZbi3N13n09R+WtLL7E+DWRvi4M56b0QCYHs9fPalU/2Y7bUWlWqHGLmlTVDqqgtUPDMm/8ABPrfEjsCP5Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:41.747689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09546","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02c1233072c3d27eb1c3ab53a8c17f4c1fde833122ac9c0ee50db055d570055e","sha256:656b3b2b22a5c46e89218e3c976c9a1125f42306d460635540318684df18a427"],"state_sha256":"b481332f3c5ddd2572113475b27448acceffce884670b1c701b874f955d748b5"}