{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HWXB2CYPCUEALBFNKFINZJ7CGO","short_pith_number":"pith:HWXB2CYP","schema_version":"1.0","canonical_sha256":"3dae1d0b0f15080584ad5150dca7e2339e6f993b661e3134e55631006244a219","source":{"kind":"arxiv","id":"2407.12997","version":1},"attestation_state":"computed","paper":{"title":"Multi-Iteration Multi-Stage Fine-Tuning of Transformers for Sound Event Detection with Heterogeneous Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Florian Schmid, Gerhard Widmer, Jonathan Greif, Paul Primus, Tobias Morocutti","submitted_at":"2024-07-17T20:32:58Z","abstract_excerpt":"A central problem in building effective sound event detection systems is the lack of high-quality, strongly annotated sound event datasets. For this reason, Task 4 of the DCASE 2024 challenge proposes learning from two heterogeneous datasets, including audio clips labeled with varying annotation granularity and with different sets of possible events. We propose a multi-iteration, multi-stage procedure for fine-tuning Audio Spectrogram Transformers on the joint DESED and MAESTRO Real datasets. The first stage closely matches the baseline system setup and trains a CRNN model while keeping the pr"},"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":"2407.12997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T20:32:58Z","cross_cats_sorted":[],"title_canon_sha256":"85e1b7dbf7b0005d9850a8ad8373a36c8bd293d2dbdb9d49bb617d60abe1cdb5","abstract_canon_sha256":"6e019b65d5b96f8efeb6d1188606f2f113973b724dc4fb0b9e14d82c1c9dc06f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:14.446183Z","signature_b64":"BIB/kZ0D6WLLgFtOY/zC+gdc6eaU/SrvrPt68SCdVlhr3b3/3YJyZYQrXxlc87FeT3z2w5kEwrTV+Moy4F78DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dae1d0b0f15080584ad5150dca7e2339e6f993b661e3134e55631006244a219","last_reissued_at":"2026-07-05T08:45:14.445753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:14.445753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Iteration Multi-Stage Fine-Tuning of Transformers for Sound Event Detection with Heterogeneous Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Florian Schmid, Gerhard Widmer, Jonathan Greif, Paul Primus, Tobias Morocutti","submitted_at":"2024-07-17T20:32:58Z","abstract_excerpt":"A central problem in building effective sound event detection systems is the lack of high-quality, strongly annotated sound event datasets. For this reason, Task 4 of the DCASE 2024 challenge proposes learning from two heterogeneous datasets, including audio clips labeled with varying annotation granularity and with different sets of possible events. We propose a multi-iteration, multi-stage procedure for fine-tuning Audio Spectrogram Transformers on the joint DESED and MAESTRO Real datasets. The first stage closely matches the baseline system setup and trains a CRNN model while keeping the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12997","kind":"arxiv","version":1},"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/2407.12997/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":"2407.12997","created_at":"2026-07-05T08:45:14.445808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12997v1","created_at":"2026-07-05T08:45:14.445808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12997","created_at":"2026-07-05T08:45:14.445808+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWXB2CYPCUEA","created_at":"2026-07-05T08:45:14.445808+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWXB2CYPCUEALBFN","created_at":"2026-07-05T08:45:14.445808+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWXB2CYP","created_at":"2026-07-05T08:45:14.445808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO","json":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO.json","graph_json":"https://pith.science/api/pith-number/HWXB2CYPCUEALBFNKFINZJ7CGO/graph.json","events_json":"https://pith.science/api/pith-number/HWXB2CYPCUEALBFNKFINZJ7CGO/events.json","paper":"https://pith.science/paper/HWXB2CYP"},"agent_actions":{"view_html":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO","download_json":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO.json","view_paper":"https://pith.science/paper/HWXB2CYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12997&json=true","fetch_graph":"https://pith.science/api/pith-number/HWXB2CYPCUEALBFNKFINZJ7CGO/graph.json","fetch_events":"https://pith.science/api/pith-number/HWXB2CYPCUEALBFNKFINZJ7CGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO/action/storage_attestation","attest_author":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO/action/author_attestation","sign_citation":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO/action/citation_signature","submit_replication":"https://pith.science/pith/HWXB2CYPCUEALBFNKFINZJ7CGO/action/replication_record"}},"created_at":"2026-07-05T08:45:14.445808+00:00","updated_at":"2026-07-05T08:45:14.445808+00:00"}