{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V3U2RLTZL4QIFNFXS3QBAJNKJJ","short_pith_number":"pith:V3U2RLTZ","schema_version":"1.0","canonical_sha256":"aee9a8ae795f2082b4b796e01025aa4a4d0f525a2c015d5aadcc648616afab60","source":{"kind":"arxiv","id":"2608.05816","version":1},"attestation_state":"computed","paper":{"title":"Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Dongheng Lin, Han Hu, Haotian Li, Hyung Jin Chang, Jianbo Jiao, Yuqi Hou","submitted_at":"2026-08-06T09:47:34Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.05816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2026-08-06T09:47:34Z","cross_cats_sorted":[],"title_canon_sha256":"25c0ca48aefa38474e019d864ddd67c0314033566a01d533db2a5a565d1c1798","abstract_canon_sha256":"19dfc96addfb422261fa483d52664294a8b2efc6029c3ae2e3f651fb60abecaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:52:49.194276Z","signature_b64":"wbx8hW/Jl7ezyEIjQp/DAX1v28hA9B3Ybk3lQsHN3podq24edkzx7O7GLONADGFwSYKB7PsvY7R2bMY6QhWwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aee9a8ae795f2082b4b796e01025aa4a4d0f525a2c015d5aadcc648616afab60","last_reissued_at":"2026-08-07T00:52:49.192829Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:52:49.192829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Dongheng Lin, Han Hu, Haotian Li, Hyung Jin Chang, Jianbo Jiao, Yuqi Hou","submitted_at":"2026-08-06T09:47:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05816","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/2608.05816/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.05816","created_at":"2026-08-07T00:52:49.194390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05816v1","created_at":"2026-08-07T00:52:49.194390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05816","created_at":"2026-08-07T00:52:49.194390+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3U2RLTZL4QI","created_at":"2026-08-07T00:52:49.194390+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3U2RLTZL4QIFNFX","created_at":"2026-08-07T00:52:49.194390+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3U2RLTZ","created_at":"2026-08-07T00:52:49.194390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ","json":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ.json","graph_json":"https://pith.science/api/pith-number/V3U2RLTZL4QIFNFXS3QBAJNKJJ/graph.json","events_json":"https://pith.science/api/pith-number/V3U2RLTZL4QIFNFXS3QBAJNKJJ/events.json","paper":"https://pith.science/paper/V3U2RLTZ"},"agent_actions":{"view_html":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ","download_json":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ.json","view_paper":"https://pith.science/paper/V3U2RLTZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05816&json=true","fetch_graph":"https://pith.science/api/pith-number/V3U2RLTZL4QIFNFXS3QBAJNKJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/V3U2RLTZL4QIFNFXS3QBAJNKJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ/action/storage_attestation","attest_author":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ/action/author_attestation","sign_citation":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ/action/citation_signature","submit_replication":"https://pith.science/pith/V3U2RLTZL4QIFNFXS3QBAJNKJJ/action/replication_record"}},"created_at":"2026-08-07T00:52:49.194390+00:00","updated_at":"2026-08-07T00:52:49.194390+00:00"}