{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K2EENXT56Z5P75E5353D7RPQJ3","short_pith_number":"pith:K2EENXT5","canonical_record":{"source":{"id":"2507.22322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T01:51:38Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c0e3f557b95dba5053eb3b5af7cdcd95a81297871859aa98b52051af17aaf14d","abstract_canon_sha256":"c38ec428d9ab5a152c8d3244d07ead61a8048cc689385b2ad9cc8f8ae0d381f9"},"schema_version":"1.0"},"canonical_sha256":"568846de7df67afff49ddf763fc5f04ec2f82c1f20c67d57db34b5057700225d","source":{"kind":"arxiv","id":"2507.22322","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22322","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22322v1","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22322","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"K2EENXT56Z5P","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"pith_short_16","alias_value":"K2EENXT56Z5P75E5","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"pith_short_8","alias_value":"K2EENXT5","created_at":"2026-07-05T11:45:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K2EENXT56Z5P75E5353D7RPQJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2507.22322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T01:51:38Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c0e3f557b95dba5053eb3b5af7cdcd95a81297871859aa98b52051af17aaf14d","abstract_canon_sha256":"c38ec428d9ab5a152c8d3244d07ead61a8048cc689385b2ad9cc8f8ae0d381f9"},"schema_version":"1.0"},"canonical_sha256":"568846de7df67afff49ddf763fc5f04ec2f82c1f20c67d57db34b5057700225d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:20.147445Z","signature_b64":"HrnUnUnPvmTt5grChZ9N1FNmZoaQ6TipC+wc/l66wN3eT/6OiF+XQ1vcHtnMtbZtVqwJEficjS+ds+m3Do1eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"568846de7df67afff49ddf763fc5f04ec2f82c1f20c67d57db34b5057700225d","last_reissued_at":"2026-07-05T11:45:20.147045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:20.147045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.22322","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nNEZ4ZwpMRn9rynEBMaMpd+0iXw3YIHOdPYP9hr425+6GRUYpIhSaEr38Fbdnp/w2cGPIXD9id42vO14HojVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:08:03.828130Z"},"content_sha256":"926f64842b70d717f0a74ef53f0b82843976bacad70833a7d79aef7b7e7ca8ab","schema_version":"1.0","event_id":"sha256:926f64842b70d717f0a74ef53f0b82843976bacad70833a7d79aef7b7e7ca8ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K2EENXT56Z5P75E5353D7RPQJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Two-Step Learning Framework for Enhancing Sound Event Localization and Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hogeon Yu","submitted_at":"2025-07-30T01:51:38Z","abstract_excerpt":"Sound Event Localization and Detection (SELD) is crucial in spatial audio processing, enabling systems to detect sound events and estimate their 3D directions. Existing SELD methods use single- or dual-branch architectures: single-branch models share SED and DoA representations, causing optimization conflicts, while dual-branch models separate tasks but limit information exchange. To address this, we propose a two-step learning framework. First, we introduce a tracwise reordering format to maintain temporal consistency, preventing event reassignments across tracks. Next, we train SED and DoA n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22322","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/2507.22322/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:45:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oOzOt7prQFCrBBqmq1QdvXLoioOpaEfdwmJ+RR1De4d6YpM2kCQ27k/Lxfj0Rr1f9JOpQgVK/UXtPqkAgkKdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:08:03.828638Z"},"content_sha256":"4893a5b5238da4e7f3d981d352f0df306082008b821aac18c81d431b36df6e07","schema_version":"1.0","event_id":"sha256:4893a5b5238da4e7f3d981d352f0df306082008b821aac18c81d431b36df6e07"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K2EENXT56Z5P75E5353D7RPQJ3/bundle.json","state_url":"https://pith.science/pith/K2EENXT56Z5P75E5353D7RPQJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K2EENXT56Z5P75E5353D7RPQJ3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T18:08:03Z","links":{"resolver":"https://pith.science/pith/K2EENXT56Z5P75E5353D7RPQJ3","bundle":"https://pith.science/pith/K2EENXT56Z5P75E5353D7RPQJ3/bundle.json","state":"https://pith.science/pith/K2EENXT56Z5P75E5353D7RPQJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K2EENXT56Z5P75E5353D7RPQJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K2EENXT56Z5P75E5353D7RPQJ3","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":"c38ec428d9ab5a152c8d3244d07ead61a8048cc689385b2ad9cc8f8ae0d381f9","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T01:51:38Z","title_canon_sha256":"c0e3f557b95dba5053eb3b5af7cdcd95a81297871859aa98b52051af17aaf14d"},"schema_version":"1.0","source":{"id":"2507.22322","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.22322","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"2507.22322v1","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22322","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"K2EENXT56Z5P","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"pith_short_16","alias_value":"K2EENXT56Z5P75E5","created_at":"2026-07-05T11:45:20Z"},{"alias_kind":"pith_short_8","alias_value":"K2EENXT5","created_at":"2026-07-05T11:45:20Z"}],"graph_snapshots":[{"event_id":"sha256:4893a5b5238da4e7f3d981d352f0df306082008b821aac18c81d431b36df6e07","target":"graph","created_at":"2026-07-05T11:45:20Z","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/2507.22322/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sound Event Localization and Detection (SELD) is crucial in spatial audio processing, enabling systems to detect sound events and estimate their 3D directions. Existing SELD methods use single- or dual-branch architectures: single-branch models share SED and DoA representations, causing optimization conflicts, while dual-branch models separate tasks but limit information exchange. To address this, we propose a two-step learning framework. First, we introduce a tracwise reordering format to maintain temporal consistency, preventing event reassignments across tracks. Next, we train SED and DoA n","authors_text":"Hogeon Yu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T01:51:38Z","title":"A Two-Step Learning Framework for Enhancing Sound Event Localization and Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22322","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":"sha256:926f64842b70d717f0a74ef53f0b82843976bacad70833a7d79aef7b7e7ca8ab","target":"record","created_at":"2026-07-05T11:45:20Z","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":"c38ec428d9ab5a152c8d3244d07ead61a8048cc689385b2ad9cc8f8ae0d381f9","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-30T01:51:38Z","title_canon_sha256":"c0e3f557b95dba5053eb3b5af7cdcd95a81297871859aa98b52051af17aaf14d"},"schema_version":"1.0","source":{"id":"2507.22322","kind":"arxiv","version":1}},"canonical_sha256":"568846de7df67afff49ddf763fc5f04ec2f82c1f20c67d57db34b5057700225d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"568846de7df67afff49ddf763fc5f04ec2f82c1f20c67d57db34b5057700225d","first_computed_at":"2026-07-05T11:45:20.147045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:20.147045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HrnUnUnPvmTt5grChZ9N1FNmZoaQ6TipC+wc/l66wN3eT/6OiF+XQ1vcHtnMtbZtVqwJEficjS+ds+m3Do1eCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:20.147445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.22322","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:926f64842b70d717f0a74ef53f0b82843976bacad70833a7d79aef7b7e7ca8ab","sha256:4893a5b5238da4e7f3d981d352f0df306082008b821aac18c81d431b36df6e07"],"state_sha256":"f684309f1873ae824bf2f2bd18cc6ea0df978d8c92da0da72f581cac94681381"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"seHJOoqwzg/Gw8nZ94lbnh7efBL7c/2F4N1iSb0I61NjiXAGlGHHwnWWJpFV/xh/aNgf8irec09JTyJFSD/XCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:08:03.833578Z","bundle_sha256":"a2ad5c3caf59236639c9bc6fb3646e7b642d29287c3797dd145a3a349ff3ceb2"}}