{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DBVQIHCVALCDBKFYNHA6IITYJJ","short_pith_number":"pith:DBVQIHCV","schema_version":"1.0","canonical_sha256":"186b041c5502c430a8b869c1e422784a4c990b3489371e1fb1cb5abf55320ab5","source":{"kind":"arxiv","id":"2204.05156","version":1},"attestation_state":"computed","paper":{"title":"How to Listen? Rethinking Visual Sound Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ho-Hsiang Wu, Juan Pablo Bello, Magdalena Fuentes, Prem Seetharaman","submitted_at":"2022-04-11T14:41:35Z","abstract_excerpt":"Localizing visual sounds consists on locating the position of objects that emit sound within an image. It is a growing research area with potential applications in monitoring natural and urban environments, such as wildlife migration and urban traffic. Previous works are usually evaluated with datasets having mostly a single dominant visible object, and proposed models usually require the introduction of localization modules during training or dedicated sampling strategies, but it remains unclear how these design choices play a role in the adaptability of these methods in more challenging scen"},"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":"2204.05156","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-11T14:41:35Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"6639431185fb876f7c6818adbed1b54739fe227e624c643fbc84125e70641f44","abstract_canon_sha256":"26e0d59e1ed57752db3b38bb4495d8100211e9226204935ebe7b9ea56ecc1214"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:17.966394Z","signature_b64":"rdp3GWo48CXsBsqtpTCC8VJmTEfXq/TUhMpr3RCwQTsmRoFeSdQc+s9D/L0pkiHFp297srBfGFWPjwewLggRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"186b041c5502c430a8b869c1e422784a4c990b3489371e1fb1cb5abf55320ab5","last_reissued_at":"2026-07-05T04:13:17.965897Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:17.965897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Listen? Rethinking Visual Sound Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ho-Hsiang Wu, Juan Pablo Bello, Magdalena Fuentes, Prem Seetharaman","submitted_at":"2022-04-11T14:41:35Z","abstract_excerpt":"Localizing visual sounds consists on locating the position of objects that emit sound within an image. It is a growing research area with potential applications in monitoring natural and urban environments, such as wildlife migration and urban traffic. Previous works are usually evaluated with datasets having mostly a single dominant visible object, and proposed models usually require the introduction of localization modules during training or dedicated sampling strategies, but it remains unclear how these design choices play a role in the adaptability of these methods in more challenging scen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05156","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/2204.05156/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":"2204.05156","created_at":"2026-07-05T04:13:17.965959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05156v1","created_at":"2026-07-05T04:13:17.965959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05156","created_at":"2026-07-05T04:13:17.965959+00:00"},{"alias_kind":"pith_short_12","alias_value":"DBVQIHCVALCD","created_at":"2026-07-05T04:13:17.965959+00:00"},{"alias_kind":"pith_short_16","alias_value":"DBVQIHCVALCDBKFY","created_at":"2026-07-05T04:13:17.965959+00:00"},{"alias_kind":"pith_short_8","alias_value":"DBVQIHCV","created_at":"2026-07-05T04:13:17.965959+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/DBVQIHCVALCDBKFYNHA6IITYJJ","json":"https://pith.science/pith/DBVQIHCVALCDBKFYNHA6IITYJJ.json","graph_json":"https://pith.science/api/pith-number/DBVQIHCVALCDBKFYNHA6IITYJJ/graph.json","events_json":"https://pith.science/api/pith-number/DBVQIHCVALCDBKFYNHA6IITYJJ/events.json","paper":"https://pith.science/paper/DBVQIHCV"},"agent_actions":{"view_html":"https://pith.science/pith/DBVQIHCVALCDBKFYNHA6IITYJJ","download_json":"https://pith.science/pith/DBVQIHCVALCDBKFYNHA6IITYJJ.json","view_paper":"https://pith.science/paper/DBVQIHCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05156&json=true","fetch_graph":"https://pith.science/api/pith-number/DBVQIHCVALCDBKFYNHA6IITYJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DBVQIHCVALCDBKFYNHA6IITYJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DBVQIHCVALCDBKFYNHA6IITYJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DBVQIHCVALCDBKFYNHA6IITYJJ/action/storage_attestation","attest_author":"https://pith.science/pith/DBVQIHCVALCDBKFYNHA6IITYJJ/action/author_attestation","sign_citation":"https://pith.science/pith/DBVQIHCVALCDBKFYNHA6IITYJJ/action/citation_signature","submit_replication":"https://pith.science/pith/DBVQIHCVALCDBKFYNHA6IITYJJ/action/replication_record"}},"created_at":"2026-07-05T04:13:17.965959+00:00","updated_at":"2026-07-05T04:13:17.965959+00:00"}