{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HJJK3ZKOOLN6IHI5CLV57MWRLO","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":"8a388a7a932bfdafd11efd6fa3335cc265236472d4a972f2650c4ea7386188c3","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-23T07:58:28Z","title_canon_sha256":"d310b0e540c6429c2993fa64c76778ddc7b2c8181813957491ae4b33216498dc"},"schema_version":"1.0","source":{"id":"2507.17297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17297","created_at":"2026-07-05T11:42:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17297v1","created_at":"2026-07-05T11:42:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17297","created_at":"2026-07-05T11:42:05Z"},{"alias_kind":"pith_short_12","alias_value":"HJJK3ZKOOLN6","created_at":"2026-07-05T11:42:05Z"},{"alias_kind":"pith_short_16","alias_value":"HJJK3ZKOOLN6IHI5","created_at":"2026-07-05T11:42:05Z"},{"alias_kind":"pith_short_8","alias_value":"HJJK3ZKO","created_at":"2026-07-05T11:42:05Z"}],"graph_snapshots":[{"event_id":"sha256:3ca61d01d2e5e667ce2621c8d0cac2569f8cc1a06c85e2fec9245fb7517ebc38","target":"graph","created_at":"2026-07-05T11:42:05Z","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/2507.17297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial semantic segmentation of sound scenes (S5) involves the accurate identification of active sound classes and the precise separation of their sources from complex acoustic mixtures. Conventional systems rely on a two-stage pipeline - audio tagging followed by label-conditioned source separation - but are often constrained by the absence of fine-grained temporal information critical for effective separation. In this work, we address this limitation by introducing a novel approach for S5 that enhances the synergy between the event detection and source separation stages. Our key contributio","authors_text":"Florian Schmid, Gerhard Widmer, Jonathan Greif, Paul Primus, Tobias Morocutti","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-23T07:58:28Z","title":"On Temporal Guidance and Iterative Refinement in Audio Source Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17297","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:a840d5e1fd27588c2466e517813e4754f207947e75c52b415cbb69141029cbc8","target":"record","created_at":"2026-07-05T11:42:05Z","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":"8a388a7a932bfdafd11efd6fa3335cc265236472d4a972f2650c4ea7386188c3","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-23T07:58:28Z","title_canon_sha256":"d310b0e540c6429c2993fa64c76778ddc7b2c8181813957491ae4b33216498dc"},"schema_version":"1.0","source":{"id":"2507.17297","kind":"arxiv","version":1}},"canonical_sha256":"3a52ade54e72dbe41d1d12ebdfb2d15b923cb9d384881a25bda9184244d5cc0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a52ade54e72dbe41d1d12ebdfb2d15b923cb9d384881a25bda9184244d5cc0d","first_computed_at":"2026-07-05T11:42:05.426559Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:05.426559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W9Ya+AUrnBM0cTFEWmkDyayo9wPD9h9+CFWmp9gZ04e3dy+iO7b2f6mvoSx/JplnZeZJxnvu5HxdYC6zeFzHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:05.427058Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a840d5e1fd27588c2466e517813e4754f207947e75c52b415cbb69141029cbc8","sha256:3ca61d01d2e5e667ce2621c8d0cac2569f8cc1a06c85e2fec9245fb7517ebc38"],"state_sha256":"e9cfb376f3741e5de5bfb4a8f4ed18417eeaadc2bca7041d74798e05a67388a9"}