{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4C2UA5M3B2COLCRL3GNKWY6TH3","short_pith_number":"pith:4C2UA5M3","schema_version":"1.0","canonical_sha256":"e0b540759b0e84e58a2bd99aab63d33edaf8a69a106d2bc2c5c2e5e2bba160c8","source":{"kind":"arxiv","id":"2507.07384","version":2},"attestation_state":"computed","paper":{"title":"AV-SSAN: Audio-Visual Selective DoA Estimation through Explicit Multi-Band Semantic-Spatial Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongxu Zhu, Jiadong Wang, Kainan Chen, Xinyuan Qian, Yu Chen","submitted_at":"2025-07-10T02:49:56Z","abstract_excerpt":"Audio-visual sound source localization (AV-SSL) estimates the position of sound sources by fusing auditory and visual cues. Current AV-SSL methodologies typically require spatially-paired audio-visual data and cannot selectively localize specific target sources. To address these limitations, we introduce Cross-Instance Audio-Visual Localization (CI-AVL), a novel task that localizes target sound sources using visual prompts from different instances of the same semantic class. CI-AVL enables selective localization without spatially paired data. To solve this task, we propose AV-SSAN, a semantic-"},"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":"2507.07384","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-10T02:49:56Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5428531b5bf4c8e26d6df34580b8da693effd2a9a2c445e11c49e9f8d0fd11c0","abstract_canon_sha256":"f8ef5f80b2c358fe5620448705200793e5f05b342146d237feb19de52fdc1044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:11.320399Z","signature_b64":"MHVL7TEe1TBCOIK/sFY4uGaO0j5HDTe6Lfs1r+Aggb7dtMUGrdTPeIc+yCstmnDg6B6lF/ldMxatCO29sDXsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0b540759b0e84e58a2bd99aab63d33edaf8a69a106d2bc2c5c2e5e2bba160c8","last_reissued_at":"2026-07-05T11:49:11.319917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:11.319917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AV-SSAN: Audio-Visual Selective DoA Estimation through Explicit Multi-Band Semantic-Spatial Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hongxu Zhu, Jiadong Wang, Kainan Chen, Xinyuan Qian, Yu Chen","submitted_at":"2025-07-10T02:49:56Z","abstract_excerpt":"Audio-visual sound source localization (AV-SSL) estimates the position of sound sources by fusing auditory and visual cues. Current AV-SSL methodologies typically require spatially-paired audio-visual data and cannot selectively localize specific target sources. To address these limitations, we introduce Cross-Instance Audio-Visual Localization (CI-AVL), a novel task that localizes target sound sources using visual prompts from different instances of the same semantic class. CI-AVL enables selective localization without spatially paired data. To solve this task, we propose AV-SSAN, a semantic-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07384","kind":"arxiv","version":2},"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/2507.07384/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":"2507.07384","created_at":"2026-07-05T11:49:11.319974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07384v2","created_at":"2026-07-05T11:49:11.319974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07384","created_at":"2026-07-05T11:49:11.319974+00:00"},{"alias_kind":"pith_short_12","alias_value":"4C2UA5M3B2CO","created_at":"2026-07-05T11:49:11.319974+00:00"},{"alias_kind":"pith_short_16","alias_value":"4C2UA5M3B2COLCRL","created_at":"2026-07-05T11:49:11.319974+00:00"},{"alias_kind":"pith_short_8","alias_value":"4C2UA5M3","created_at":"2026-07-05T11:49:11.319974+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/4C2UA5M3B2COLCRL3GNKWY6TH3","json":"https://pith.science/pith/4C2UA5M3B2COLCRL3GNKWY6TH3.json","graph_json":"https://pith.science/api/pith-number/4C2UA5M3B2COLCRL3GNKWY6TH3/graph.json","events_json":"https://pith.science/api/pith-number/4C2UA5M3B2COLCRL3GNKWY6TH3/events.json","paper":"https://pith.science/paper/4C2UA5M3"},"agent_actions":{"view_html":"https://pith.science/pith/4C2UA5M3B2COLCRL3GNKWY6TH3","download_json":"https://pith.science/pith/4C2UA5M3B2COLCRL3GNKWY6TH3.json","view_paper":"https://pith.science/paper/4C2UA5M3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07384&json=true","fetch_graph":"https://pith.science/api/pith-number/4C2UA5M3B2COLCRL3GNKWY6TH3/graph.json","fetch_events":"https://pith.science/api/pith-number/4C2UA5M3B2COLCRL3GNKWY6TH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4C2UA5M3B2COLCRL3GNKWY6TH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4C2UA5M3B2COLCRL3GNKWY6TH3/action/storage_attestation","attest_author":"https://pith.science/pith/4C2UA5M3B2COLCRL3GNKWY6TH3/action/author_attestation","sign_citation":"https://pith.science/pith/4C2UA5M3B2COLCRL3GNKWY6TH3/action/citation_signature","submit_replication":"https://pith.science/pith/4C2UA5M3B2COLCRL3GNKWY6TH3/action/replication_record"}},"created_at":"2026-07-05T11:49:11.319974+00:00","updated_at":"2026-07-05T11:49:11.319974+00:00"}