{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HJKSASIDOJWMFMWMCUK73WTVXN","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":"07398c13a44527f247428dfa54538cbacf1d927b22922300a3e8a34cfffb4a4a","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-28T16:52:17Z","title_canon_sha256":"2c767355da1ff3cd5e708ba9e61643ed6a13eb667954f5fa9852c5d31421bbb5"},"schema_version":"1.0","source":{"id":"2606.29497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.29497","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"arxiv_version","alias_value":"2606.29497v1","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29497","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_12","alias_value":"HJKSASIDOJWM","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_16","alias_value":"HJKSASIDOJWMFMWM","created_at":"2026-06-30T01:18:09Z"},{"alias_kind":"pith_short_8","alias_value":"HJKSASID","created_at":"2026-06-30T01:18:09Z"}],"graph_snapshots":[{"event_id":"sha256:e623981ac300a079b13557f7a65c9a389f0ef2dba167743e5c13fa4418d013c9","target":"graph","created_at":"2026-06-30T01:18:09Z","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/2606.29497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In long-form multi-party conversations, highly imbalanced speaker activity and frequent overlap make it difficult to identify \"who spoke when and what\". Sliding-window continuous speech separation (CSS) mitigates sparse supervision, but often suffers from cross-window speaker inconsistency and residual crosstalk, which in practice requires diarization for reliable speaker attribution. Motivated by the stability of speakers' directions of arrival (DOAs) in meetings, we propose PATSE, a multi-channel Position-Aware Target Speaker Extraction front-end that uses DOA as a spatial prior to directly ","authors_text":"Junzhe Chen, Tatsuya Kawahara, Wangjin Zhou, Yichi Wang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-28T16:52:17Z","title":"Position-Aware Target Speaker Extraction for Long-Form Multi-Party Conversations: A Diarization-Free Framework for ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29497","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:b3506b69dfeeec2c3780a47b1e37940ff9f0ede9f79518f93d34287e8f7a3664","target":"record","created_at":"2026-06-30T01:18:09Z","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":"07398c13a44527f247428dfa54538cbacf1d927b22922300a3e8a34cfffb4a4a","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-28T16:52:17Z","title_canon_sha256":"2c767355da1ff3cd5e708ba9e61643ed6a13eb667954f5fa9852c5d31421bbb5"},"schema_version":"1.0","source":{"id":"2606.29497","kind":"arxiv","version":1}},"canonical_sha256":"3a55204903726cc2b2cc1515fdda75bb566e2860d2d4d21c85f7cdaf193023a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a55204903726cc2b2cc1515fdda75bb566e2860d2d4d21c85f7cdaf193023a6","first_computed_at":"2026-06-30T01:18:09.182694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:09.182694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0I/dZBEXbgAczulHIqNUtB6cCwDzPkaZwT1IDaHoC7z7nNy2d5yQlpiro4eDxoZtVbe2wRdVTFoG+9yA2lwoBw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:09.183405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.29497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3506b69dfeeec2c3780a47b1e37940ff9f0ede9f79518f93d34287e8f7a3664","sha256:e623981ac300a079b13557f7a65c9a389f0ef2dba167743e5c13fa4418d013c9"],"state_sha256":"0008effdc7a4636c6c386893380f3713bff152d0ed542331ea735eb6442dda47"}