{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UBLLLQWCZURN5DNAEE3H65N3YR","short_pith_number":"pith:UBLLLQWC","schema_version":"1.0","canonical_sha256":"a056b5c2c2cd22de8da021367f75bbc4480e53031d534d8923eeeaec237d9660","source":{"kind":"arxiv","id":"2409.09546","version":2},"attestation_state":"computed","paper":{"title":"Effective Pre-Training of Audio Transformers for Sound Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Florian Schmid, Francesco Foscarin, Gerhard Widmer, Jan Schl\\\"uter, Paul Primus, Tobias Morocutti","submitted_at":"2024-09-14T22:00:47Z","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"},"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":"2409.09546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-14T22:00:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"bc1e32801952cfc3c7e156b658e585fb9c24322306fd5260e48c6aac7700ad84","abstract_canon_sha256":"f5bcd44733a4b24d1fe35bf880e9b9376f9609da15c9fac60263452f298755eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:41.747689Z","signature_b64":"MpBZbi3N13n09R+WtLL7E+DWRvi4M56b0QCYHs9fPalU/2Y7bUWlWqHGLmlTVDqqgtUPDMm/8ABPrfEjsCP5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a056b5c2c2cd22de8da021367f75bbc4480e53031d534d8923eeeaec237d9660","last_reissued_at":"2026-07-05T09:41:41.747153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:41.747153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective Pre-Training of Audio Transformers for Sound Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Florian Schmid, Francesco Foscarin, Gerhard Widmer, Jan Schl\\\"uter, Paul Primus, Tobias Morocutti","submitted_at":"2024-09-14T22:00:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09546","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.09546/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2409.09546","created_at":"2026-07-05T09:41:41.747214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09546v2","created_at":"2026-07-05T09:41:41.747214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09546","created_at":"2026-07-05T09:41:41.747214+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBLLLQWCZURN","created_at":"2026-07-05T09:41:41.747214+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBLLLQWCZURN5DNA","created_at":"2026-07-05T09:41:41.747214+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBLLLQWC","created_at":"2026-07-05T09:41:41.747214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01802","citing_title":"MOSS-Audio Technical Report","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR","json":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR.json","graph_json":"https://pith.science/api/pith-number/UBLLLQWCZURN5DNAEE3H65N3YR/graph.json","events_json":"https://pith.science/api/pith-number/UBLLLQWCZURN5DNAEE3H65N3YR/events.json","paper":"https://pith.science/paper/UBLLLQWC"},"agent_actions":{"view_html":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR","download_json":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR.json","view_paper":"https://pith.science/paper/UBLLLQWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09546&json=true","fetch_graph":"https://pith.science/api/pith-number/UBLLLQWCZURN5DNAEE3H65N3YR/graph.json","fetch_events":"https://pith.science/api/pith-number/UBLLLQWCZURN5DNAEE3H65N3YR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR/action/storage_attestation","attest_author":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR/action/author_attestation","sign_citation":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR/action/citation_signature","submit_replication":"https://pith.science/pith/UBLLLQWCZURN5DNAEE3H65N3YR/action/replication_record"}},"created_at":"2026-07-05T09:41:41.747214+00:00","updated_at":"2026-07-05T09:41:41.747214+00:00"}