{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VM7GKXHQSBT3EPH7JFIOXKRDPC","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":"2bfc4433ea36e739ba90e2b80ba89f8773aa623c01fd259575e0bb7199ac9a2b","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-17T07:54:31Z","title_canon_sha256":"77be2f0b55576fd49efc949099a0f03404b24fbe995a6c20c999be7112fa38c9"},"schema_version":"1.0","source":{"id":"2505.11889","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11889","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11889v2","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11889","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"VM7GKXHQSBT3","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"pith_short_16","alias_value":"VM7GKXHQSBT3EPH7","created_at":"2026-07-05T11:59:14Z"},{"alias_kind":"pith_short_8","alias_value":"VM7GKXHQ","created_at":"2026-07-05T11:59:14Z"}],"graph_snapshots":[{"event_id":"sha256:4a9ae8ef66ddd95167746c2dbfd1d07ff1960d79f79177e3e9a2e06b15dd1cb5","target":"graph","created_at":"2026-07-05T11:59:14Z","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/2505.11889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning (SSL) models offer powerful representations for sound event detection (SED), yet their synergistic potential remains underexplored. This study systematically evaluates state-of-the-art SSL models to guide optimal model selection and integration for SED. We propose a framework that combines heterogeneous SSL representations (e.g., BEATs, HuBERT, WavLM) through three fusion strategies: individual SSL embedding integration, dual-modal fusion, and full aggregation. Experiments on the DCASE 2023 Task 4 Challenge reveal that dual-modal fusion (e.g., CRNN+BEATs+WavLM) achieve","authors_text":"Dongxing Xu, Hanfang Cui, Li Li, Longfei Song, Yanhua Long","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-17T07:54:31Z","title":"Revisiting SSL for sound event detection: complementary fusion and adaptive post-processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11889","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":"sha256:19f5141cf4e89fde01a5db7879749bab8e193fbab0c8a38313777b6d085cf261","target":"record","created_at":"2026-07-05T11:59:14Z","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":"2bfc4433ea36e739ba90e2b80ba89f8773aa623c01fd259575e0bb7199ac9a2b","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-17T07:54:31Z","title_canon_sha256":"77be2f0b55576fd49efc949099a0f03404b24fbe995a6c20c999be7112fa38c9"},"schema_version":"1.0","source":{"id":"2505.11889","kind":"arxiv","version":2}},"canonical_sha256":"ab3e655cf09067b23cff4950ebaa2378a0d02c33e7e8153b94bb75e10a0f86db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab3e655cf09067b23cff4950ebaa2378a0d02c33e7e8153b94bb75e10a0f86db","first_computed_at":"2026-07-05T11:59:14.597446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:14.597446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"87x5mdwpycwLnl0qib0kiTpcwr5kzlCfz64pdk5UyAMv5PIaYsBPziAemnphznSNYZaV0yPHIz/OWksFKm2KAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:14.597897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11889","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19f5141cf4e89fde01a5db7879749bab8e193fbab0c8a38313777b6d085cf261","sha256:4a9ae8ef66ddd95167746c2dbfd1d07ff1960d79f79177e3e9a2e06b15dd1cb5"],"state_sha256":"471fc36808cb1609786382f2cc102b3a61dde012d225118c35415f7e31dec065"}