{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7FFZEWYXZXBJSAV7C5BCJBXBK5","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":"606484f94830ca13ecad75b35dcb2d44b886b8b494f878fef0c374f762e03699","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T20:36:46Z","title_canon_sha256":"56bfdbf5102cc67e1ae8496f169e865bc11a9adf37631bac94ffa3a998a721ef"},"schema_version":"1.0","source":{"id":"2408.00791","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00791","created_at":"2026-07-05T08:51:21Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00791v1","created_at":"2026-07-05T08:51:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00791","created_at":"2026-07-05T08:51:21Z"},{"alias_kind":"pith_short_12","alias_value":"7FFZEWYXZXBJ","created_at":"2026-07-05T08:51:21Z"},{"alias_kind":"pith_short_16","alias_value":"7FFZEWYXZXBJSAV7","created_at":"2026-07-05T08:51:21Z"},{"alias_kind":"pith_short_8","alias_value":"7FFZEWYX","created_at":"2026-07-05T08:51:21Z"}],"graph_snapshots":[{"event_id":"sha256:f10539cc2aefe959b8f9ec18f5ea5add4ae15da95e676005baf25b670d31ea0b","target":"graph","created_at":"2026-07-05T08:51:21Z","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/2408.00791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This technical report describes the CP-JKU team's submission for Task 4 Sound Event Detection with Heterogeneous Training Datasets and Potentially Missing Labels of the DCASE 24 Challenge. We fine-tune three large Audio Spectrogram Transformers, PaSST, BEATs, and ATST, on the joint DESED and MAESTRO datasets in a two-stage training procedure. The first stage closely matches the baseline system setup and trains a CRNN model while keeping the large pre-trained transformer model frozen. In the second stage, both CRNN and transformer are fine-tuned using heavily weighted self-supervised losses. Af","authors_text":"Florian Schmid, Gerhard Widmer, Jonathan Greif, Paul Primus, Tobias Morocutti","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T20:36:46Z","title":"Improving Audio Spectrogram Transformers for Sound Event Detection Through Multi-Stage Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00791","kind":"arxiv","version":1},"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:fc151d420492036fe3ae274ac28801ee704f186745dc35360627e034c46a3903","target":"record","created_at":"2026-07-05T08:51:21Z","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":"606484f94830ca13ecad75b35dcb2d44b886b8b494f878fef0c374f762e03699","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T20:36:46Z","title_canon_sha256":"56bfdbf5102cc67e1ae8496f169e865bc11a9adf37631bac94ffa3a998a721ef"},"schema_version":"1.0","source":{"id":"2408.00791","kind":"arxiv","version":1}},"canonical_sha256":"f94b925b17cdc29902bf17422486e1575b88699297a567a40134d1da6593710f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f94b925b17cdc29902bf17422486e1575b88699297a567a40134d1da6593710f","first_computed_at":"2026-07-05T08:51:21.917564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:21.917564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/k8M8Dum873EUHFw38J3XyaAVhdivIdG4bFyb0N3S8B2mQL3pqCsLOMZMqVCZMQWRrtCHNQy9Vyj+w1SDscfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:21.918026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.00791","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc151d420492036fe3ae274ac28801ee704f186745dc35360627e034c46a3903","sha256:f10539cc2aefe959b8f9ec18f5ea5add4ae15da95e676005baf25b670d31ea0b"],"state_sha256":"5686a68771c44e22a0e85ee0c4740353d695e887e6f3e398ec840d1dd49e89c1"}