{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3NAUCEXQHM3O6DNQT52AKHNAIZ","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":"5c685fe721dae3ccb2fac16b1ccb9c142b770bdbbb65427c3ec9bdde5f85125e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:28:45Z","title_canon_sha256":"91ed1966aa2eb1263b35b48d9e4659bdc42dec1677fcb9f695580dba7c9ecd2d"},"schema_version":"1.0","source":{"id":"2410.01020","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01020","created_at":"2026-07-05T09:59:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01020v3","created_at":"2026-07-05T09:59:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01020","created_at":"2026-07-05T09:59:53Z"},{"alias_kind":"pith_short_12","alias_value":"3NAUCEXQHM3O","created_at":"2026-07-05T09:59:53Z"},{"alias_kind":"pith_short_16","alias_value":"3NAUCEXQHM3O6DNQ","created_at":"2026-07-05T09:59:53Z"},{"alias_kind":"pith_short_8","alias_value":"3NAUCEXQ","created_at":"2026-07-05T09:59:53Z"}],"graph_snapshots":[{"event_id":"sha256:4990c12e7f4e953553d4b7890f9ff259f4feca45482a670b8b39065dc4e9fadc","target":"graph","created_at":"2026-07-05T09:59:53Z","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/2410.01020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gloria Haro, Magdalena Fuentes, Xavier Juanola","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:28:45Z","title":"A Critical Assessment of Visual Sound Source Localization Models Including Negative Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01020","kind":"arxiv","version":3},"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:f199703da627fd4a35c2ec9daac0a2aa104ec1f0bcffd144079d123e3e0bcd3d","target":"record","created_at":"2026-07-05T09:59:53Z","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":"5c685fe721dae3ccb2fac16b1ccb9c142b770bdbbb65427c3ec9bdde5f85125e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-01T19:28:45Z","title_canon_sha256":"91ed1966aa2eb1263b35b48d9e4659bdc42dec1677fcb9f695580dba7c9ecd2d"},"schema_version":"1.0","source":{"id":"2410.01020","kind":"arxiv","version":3}},"canonical_sha256":"db414112f03b36ef0db09f74051da04667910f38eaae59483d20ea3bea8d081a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db414112f03b36ef0db09f74051da04667910f38eaae59483d20ea3bea8d081a","first_computed_at":"2026-07-05T09:59:53.181411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:53.181411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tOcn1laqOKQ5onYp2fvMLXa8pAPXu09YzxElCp1W/8VpJpa6FrW5vwSaBrk+4ck3ifsDCFZjGtES9gP79wRHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:53.181838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01020","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f199703da627fd4a35c2ec9daac0a2aa104ec1f0bcffd144079d123e3e0bcd3d","sha256:4990c12e7f4e953553d4b7890f9ff259f4feca45482a670b8b39065dc4e9fadc"],"state_sha256":"b29d3c115d2e75a4c0f0bb5d28845acab6ff3cd4998ad6d8c803c3f4086c9cf0"}