{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V4X6N2DNP2VMXCZTY4JSCCEDJU","short_pith_number":"pith:V4X6N2DN","schema_version":"1.0","canonical_sha256":"af2fe6e86d7eaacb8b33c7132108834d21b2b9e57482446f4466c412998c28fa","source":{"kind":"arxiv","id":"2507.04667","version":2},"attestation_state":"computed","paper":{"title":"What's Making That Sound Right Now? Video-centric Audio-Visual Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Hahyeon Choi, Junhoo Lee, Nojun Kwak","submitted_at":"2025-07-07T05:12:34Z","abstract_excerpt":"Audio-Visual Localization (AVL) aims to identify sound-emitting sources within a visual scene. However, existing studies focus on image-level audio-visual associations, failing to capture temporal dynamics. Moreover, they assume simplified scenarios where sound sources are always visible and involve only a single object. To address these limitations, we propose AVATAR, a video-centric AVL benchmark that incorporates high-resolution temporal information. AVATAR introduces four distinct scenarios -- Single-sound, Mixed-sound, Multi-entity, and Off-screen -- enabling a more comprehensive evaluati"},"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":"2507.04667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T05:12:34Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"7e740b874583f643998e6ea5be3feb2ebfcc53621f5d24b3b337e93d0dccde32","abstract_canon_sha256":"83f961b0265f6fbf68a8cf1ca33e3a91d4fcc583c529d044ef6fa570c944bb10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:26.706513Z","signature_b64":"lOtutr7lIytK7s3ZnDL9f/9dK/xSGHwocxxR9EdBGDfddeTiZduL1KpPH8yJR+rHhatHARAtSsBg+rptbrD9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af2fe6e86d7eaacb8b33c7132108834d21b2b9e57482446f4466c412998c28fa","last_reissued_at":"2026-07-05T11:33:26.705945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:26.705945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What's Making That Sound Right Now? Video-centric Audio-Visual Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Hahyeon Choi, Junhoo Lee, Nojun Kwak","submitted_at":"2025-07-07T05:12:34Z","abstract_excerpt":"Audio-Visual Localization (AVL) aims to identify sound-emitting sources within a visual scene. However, existing studies focus on image-level audio-visual associations, failing to capture temporal dynamics. Moreover, they assume simplified scenarios where sound sources are always visible and involve only a single object. To address these limitations, we propose AVATAR, a video-centric AVL benchmark that incorporates high-resolution temporal information. AVATAR introduces four distinct scenarios -- Single-sound, Mixed-sound, Multi-entity, and Off-screen -- enabling a more comprehensive evaluati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04667","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/2507.04667/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":"2507.04667","created_at":"2026-07-05T11:33:26.706014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04667v2","created_at":"2026-07-05T11:33:26.706014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04667","created_at":"2026-07-05T11:33:26.706014+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4X6N2DNP2VM","created_at":"2026-07-05T11:33:26.706014+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4X6N2DNP2VMXCZT","created_at":"2026-07-05T11:33:26.706014+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4X6N2DN","created_at":"2026-07-05T11:33:26.706014+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/V4X6N2DNP2VMXCZTY4JSCCEDJU","json":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU.json","graph_json":"https://pith.science/api/pith-number/V4X6N2DNP2VMXCZTY4JSCCEDJU/graph.json","events_json":"https://pith.science/api/pith-number/V4X6N2DNP2VMXCZTY4JSCCEDJU/events.json","paper":"https://pith.science/paper/V4X6N2DN"},"agent_actions":{"view_html":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU","download_json":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU.json","view_paper":"https://pith.science/paper/V4X6N2DN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04667&json=true","fetch_graph":"https://pith.science/api/pith-number/V4X6N2DNP2VMXCZTY4JSCCEDJU/graph.json","fetch_events":"https://pith.science/api/pith-number/V4X6N2DNP2VMXCZTY4JSCCEDJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/action/storage_attestation","attest_author":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/action/author_attestation","sign_citation":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/action/citation_signature","submit_replication":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/action/replication_record"}},"created_at":"2026-07-05T11:33:26.706014+00:00","updated_at":"2026-07-05T11:33:26.706014+00:00"}