{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3NAUCEXQHM3O6DNQT52AKHNAIZ","short_pith_number":"pith:3NAUCEXQ","schema_version":"1.0","canonical_sha256":"db414112f03b36ef0db09f74051da04667910f38eaae59483d20ea3bea8d081a","source":{"kind":"arxiv","id":"2410.01020","version":3},"attestation_state":"computed","paper":{"title":"A Critical Assessment of Visual Sound Source Localization Models Including Negative Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Gloria Haro, Magdalena Fuentes, Xavier Juanola","submitted_at":"2024-10-01T19:28:45Z","abstract_excerpt":"The task of Visual Sound Source Localization (VSSL) involves identifying the location of sound sources in visual scenes, integrating audio-visual data for enhanced scene understanding. Despite advancements in state-of-the-art (SOTA) models, we observe three critical flaws: i) The evaluation of the models is mainly focused in sounds produced by objects that are visible in the image, ii) The evaluation often assumes a prior knowledge of the size of the sounding object, and iii) No universal threshold for localization in real-world scenarios is established, as previous approaches only consider po"},"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":"2410.01020","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:28:45Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"91ed1966aa2eb1263b35b48d9e4659bdc42dec1677fcb9f695580dba7c9ecd2d","abstract_canon_sha256":"5c685fe721dae3ccb2fac16b1ccb9c142b770bdbbb65427c3ec9bdde5f85125e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:53.181838Z","signature_b64":"tOcn1laqOKQ5onYp2fvMLXa8pAPXu09YzxElCp1W/8VpJpa6FrW5vwSaBrk+4ck3ifsDCFZjGtES9gP79wRHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db414112f03b36ef0db09f74051da04667910f38eaae59483d20ea3bea8d081a","last_reissued_at":"2026-07-05T09:59:53.181411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:53.181411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Critical Assessment of Visual Sound Source Localization Models Including Negative Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Gloria Haro, Magdalena Fuentes, Xavier Juanola","submitted_at":"2024-10-01T19:28:45Z","abstract_excerpt":"The task of Visual Sound Source Localization (VSSL) involves identifying the location of sound sources in visual scenes, integrating audio-visual data for enhanced scene understanding. Despite advancements in state-of-the-art (SOTA) models, we observe three critical flaws: i) The evaluation of the models is mainly focused in sounds produced by objects that are visible in the image, ii) The evaluation often assumes a prior knowledge of the size of the sounding object, and iii) No universal threshold for localization in real-world scenarios is established, as previous approaches only consider po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01020","kind":"arxiv","version":3},"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/2410.01020/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":"2410.01020","created_at":"2026-07-05T09:59:53.181461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01020v3","created_at":"2026-07-05T09:59:53.181461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01020","created_at":"2026-07-05T09:59:53.181461+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NAUCEXQHM3O","created_at":"2026-07-05T09:59:53.181461+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NAUCEXQHM3O6DNQ","created_at":"2026-07-05T09:59:53.181461+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NAUCEXQ","created_at":"2026-07-05T09:59:53.181461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00358","citing_title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ","json":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ.json","graph_json":"https://pith.science/api/pith-number/3NAUCEXQHM3O6DNQT52AKHNAIZ/graph.json","events_json":"https://pith.science/api/pith-number/3NAUCEXQHM3O6DNQT52AKHNAIZ/events.json","paper":"https://pith.science/paper/3NAUCEXQ"},"agent_actions":{"view_html":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ","download_json":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ.json","view_paper":"https://pith.science/paper/3NAUCEXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01020&json=true","fetch_graph":"https://pith.science/api/pith-number/3NAUCEXQHM3O6DNQT52AKHNAIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3NAUCEXQHM3O6DNQT52AKHNAIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ/action/storage_attestation","attest_author":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ/action/author_attestation","sign_citation":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ/action/citation_signature","submit_replication":"https://pith.science/pith/3NAUCEXQHM3O6DNQT52AKHNAIZ/action/replication_record"}},"created_at":"2026-07-05T09:59:53.181461+00:00","updated_at":"2026-07-05T09:59:53.181461+00:00"}