{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5O2TA6S6XSES4YJZ4JQ5LMZ4DQ","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":"0cd55faef2c0245469449410a28244ae6ede415ad613bd3b19c37bd356c0e576","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-27T02:21:38Z","title_canon_sha256":"f2eb4fc4459ff787ae72d8220d8395ec1477b1f5785f12cd5c324e1d5015707e"},"schema_version":"1.0","source":{"id":"2505.20635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20635","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20635v1","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20635","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"5O2TA6S6XSES","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"5O2TA6S6XSES4YJZ","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"5O2TA6S6","created_at":"2026-07-05T11:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:e07b7b22f533dceeb716095f05c08137826c34eef1fcd33dd2d7ff282e5a4d11","target":"graph","created_at":"2026-07-05T11:10:15Z","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/2505.20635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speaker extraction isolates a target speaker's speech from a mixture speech signal conditioned on a visual cue, typically using the target speaker's face recording. However, in real-world scenarios, other co-occurring faces are often present on-screen, providing valuable speaker activity cues in the scene. In this work, we introduce a plug-and-play inter-speaker attention module to process these flexible numbers of co-occurring faces, allowing for more accurate speaker extraction in complex multi-person environments. We integrate our module into two prominent models: the AV-DPRNN ","authors_text":"Bin Ma, Chong Zhang, Kun Zhou, Shengkui Zhao, Tingting Wang, Yukun Ma, Zexu Pan","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-27T02:21:38Z","title":"Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20635","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":"sha256:7c99871f775bc96a394d91df7fdd0b7034b09a035dd61fb254e2faf175bbe755","target":"record","created_at":"2026-07-05T11:10:15Z","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":"0cd55faef2c0245469449410a28244ae6ede415ad613bd3b19c37bd356c0e576","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-27T02:21:38Z","title_canon_sha256":"f2eb4fc4459ff787ae72d8220d8395ec1477b1f5785f12cd5c324e1d5015707e"},"schema_version":"1.0","source":{"id":"2505.20635","kind":"arxiv","version":1}},"canonical_sha256":"ebb5307a5ebc892e6139e261d5b33c1c3077d78503e93fa3b6e5d6a4b8b384ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebb5307a5ebc892e6139e261d5b33c1c3077d78503e93fa3b6e5d6a4b8b384ee","first_computed_at":"2026-07-05T11:10:15.791267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:15.791267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XRQzU1YTLAZtAG64OQWNmt/3xLLhveCJDOfnvuksha2Es9AA93Bcnf5yUuiea2NAlvvnWnDMDUqvLjkd1zfYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:15.791767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c99871f775bc96a394d91df7fdd0b7034b09a035dd61fb254e2faf175bbe755","sha256:e07b7b22f533dceeb716095f05c08137826c34eef1fcd33dd2d7ff282e5a4d11"],"state_sha256":"fb6a974861bed4d80c64a3be9bf029ed6da932b1abf2e949e4afc036ad5f30d9"}