{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V3U2RLTZL4QIFNFXS3QBAJNKJJ","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":"19dfc96addfb422261fa483d52664294a8b2efc6029c3ae2e3f651fb60abecaa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-06T09:47:34Z","title_canon_sha256":"25c0ca48aefa38474e019d864ddd67c0314033566a01d533db2a5a565d1c1798"},"schema_version":"1.0","source":{"id":"2608.05816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05816","created_at":"2026-08-07T00:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05816v1","created_at":"2026-08-07T00:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05816","created_at":"2026-08-07T00:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"V3U2RLTZL4QI","created_at":"2026-08-07T00:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"V3U2RLTZL4QIFNFX","created_at":"2026-08-07T00:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"V3U2RLTZ","created_at":"2026-08-07T00:52:49Z"}],"graph_snapshots":[{"event_id":"sha256:1eb709c39aa54e4e0bbe3970d00526fd00dd220db1a1bf90de72b27064a3779d","target":"graph","created_at":"2026-08-07T00:52:49Z","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/2608.05816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Localising multiple sound sources in visual scenes remains a fundamental challenge in multimodal perception due to an inherent circular dependency: separating mixed audio requires knowing source locations, while identifying sound-producing regions requires separated audio signals. In this paper, we focus on the dual-source setting and discover a selective convergence in self-supervised audio-visual learning: when presented with multiple sound sources, contrastive models naturally converge to the most salient audio-visual correspondence rather than attempting to represent all sources equally. T","authors_text":"Dongheng Lin, Han Hu, Haotian Li, Hyung Jin Chang, Jianbo Jiao, Yuqi Hou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-06T09:47:34Z","title":"Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05816","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":"sha256:977b09aa86f90ff2503b286068dd2f9e5d472e1a6b214874277f789510eb36b2","target":"record","created_at":"2026-08-07T00:52:49Z","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":"19dfc96addfb422261fa483d52664294a8b2efc6029c3ae2e3f651fb60abecaa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-06T09:47:34Z","title_canon_sha256":"25c0ca48aefa38474e019d864ddd67c0314033566a01d533db2a5a565d1c1798"},"schema_version":"1.0","source":{"id":"2608.05816","kind":"arxiv","version":1}},"canonical_sha256":"aee9a8ae795f2082b4b796e01025aa4a4d0f525a2c015d5aadcc648616afab60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aee9a8ae795f2082b4b796e01025aa4a4d0f525a2c015d5aadcc648616afab60","first_computed_at":"2026-08-07T00:52:49.192829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:52:49.192829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wbx8hW/Jl7ezyEIjQp/DAX1v28hA9B3Ybk3lQsHN3podq24edkzx7O7GLONADGFwSYKB7PsvY7R2bMY6QhWwCA==","signature_status":"signed_v1","signed_at":"2026-08-07T00:52:49.194276Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:977b09aa86f90ff2503b286068dd2f9e5d472e1a6b214874277f789510eb36b2","sha256:1eb709c39aa54e4e0bbe3970d00526fd00dd220db1a1bf90de72b27064a3779d"],"state_sha256":"e3daeb2d65fea28db88b30e8bdfdf86377bc1c2c8cf57350aa9dda1dc9ddef9c"}