{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V4X6N2DNP2VMXCZTY4JSCCEDJU","short_pith_number":"pith:V4X6N2DN","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"},"canonical_sha256":"af2fe6e86d7eaacb8b33c7132108834d21b2b9e57482446f4466c412998c28fa","source":{"kind":"arxiv","id":"2507.04667","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04667","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04667v2","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04667","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_12","alias_value":"V4X6N2DNP2VM","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_16","alias_value":"V4X6N2DNP2VMXCZT","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_8","alias_value":"V4X6N2DN","created_at":"2026-07-05T11:33:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V4X6N2DNP2VMXCZTY4JSCCEDJU","target":"record","payload":{"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"},"canonical_sha256":"af2fe6e86d7eaacb8b33c7132108834d21b2b9e57482446f4466c412998c28fa","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"},"source_kind":"arxiv","source_id":"2507.04667","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9hWMSodWr9fkheJffFKGD/YBLCUQw8vFl95LwgjSoCY2WuH3tzsOMvRSCLadYMmzkYcB8efoxudmP2YVGQJlAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:30:40.155072Z"},"content_sha256":"ab2aa4a0abe3fc403b804d9ac9bf31fecbee8d2fe9a9d7c2bf7084159e870155","schema_version":"1.0","event_id":"sha256:ab2aa4a0abe3fc403b804d9ac9bf31fecbee8d2fe9a9d7c2bf7084159e870155"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V4X6N2DNP2VMXCZTY4JSCCEDJU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vs+hlmI1qgE+PEnDmbffDFE6+zWYNSygWgoVuqUG2UQgkxgD8qHPw0QyI6VhwEx2zNjAGnZnuJopq8UOwwyxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:30:40.155948Z"},"content_sha256":"a6bb5edec1c81f797257919dfa32117a08874029226ef141aefb8c04e7289409","schema_version":"1.0","event_id":"sha256:a6bb5edec1c81f797257919dfa32117a08874029226ef141aefb8c04e7289409"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/bundle.json","state_url":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T07:30:40Z","links":{"resolver":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU","bundle":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/bundle.json","state":"https://pith.science/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4X6N2DNP2VMXCZTY4JSCCEDJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V4X6N2DNP2VMXCZTY4JSCCEDJU","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":"83f961b0265f6fbf68a8cf1ca33e3a91d4fcc583c529d044ef6fa570c944bb10","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T05:12:34Z","title_canon_sha256":"7e740b874583f643998e6ea5be3feb2ebfcc53621f5d24b3b337e93d0dccde32"},"schema_version":"1.0","source":{"id":"2507.04667","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04667","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04667v2","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04667","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_12","alias_value":"V4X6N2DNP2VM","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_16","alias_value":"V4X6N2DNP2VMXCZT","created_at":"2026-07-05T11:33:26Z"},{"alias_kind":"pith_short_8","alias_value":"V4X6N2DN","created_at":"2026-07-05T11:33:26Z"}],"graph_snapshots":[{"event_id":"sha256:a6bb5edec1c81f797257919dfa32117a08874029226ef141aefb8c04e7289409","target":"graph","created_at":"2026-07-05T11:33:26Z","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/2507.04667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hahyeon Choi, Junhoo Lee, Nojun Kwak","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T05:12:34Z","title":"What's Making That Sound Right Now? Video-centric Audio-Visual Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04667","kind":"arxiv","version":2},"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:ab2aa4a0abe3fc403b804d9ac9bf31fecbee8d2fe9a9d7c2bf7084159e870155","target":"record","created_at":"2026-07-05T11:33:26Z","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":"83f961b0265f6fbf68a8cf1ca33e3a91d4fcc583c529d044ef6fa570c944bb10","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T05:12:34Z","title_canon_sha256":"7e740b874583f643998e6ea5be3feb2ebfcc53621f5d24b3b337e93d0dccde32"},"schema_version":"1.0","source":{"id":"2507.04667","kind":"arxiv","version":2}},"canonical_sha256":"af2fe6e86d7eaacb8b33c7132108834d21b2b9e57482446f4466c412998c28fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af2fe6e86d7eaacb8b33c7132108834d21b2b9e57482446f4466c412998c28fa","first_computed_at":"2026-07-05T11:33:26.705945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:26.705945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lOtutr7lIytK7s3ZnDL9f/9dK/xSGHwocxxR9EdBGDfddeTiZduL1KpPH8yJR+rHhatHARAtSsBg+rptbrD9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:26.706513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04667","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab2aa4a0abe3fc403b804d9ac9bf31fecbee8d2fe9a9d7c2bf7084159e870155","sha256:a6bb5edec1c81f797257919dfa32117a08874029226ef141aefb8c04e7289409"],"state_sha256":"ef6733fa95d0f8b9c4e2ddff957074f03e9359980d83278f0287f20725076dc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56Gt3MCY/lnRjWJxrFQ2PjFLXYTInlrUvq4Sb1NwmfMOgFGMSoYyKYLsRfbHBbos9dsjUAOwbP0X1b94CWeCAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:30:40.164729Z","bundle_sha256":"d47cba4982f7a9c72223272da6347496370b0ddf4f07e6c152e334b834eaf9d7"}}