{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XVQ4CON7CVXEVNFZI77UCVM72J","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":"b3f5cf4f27c3fa47c4e4e02d4ea81e429a7275a984a168f60797785a7f06859a","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T16:36:16Z","title_canon_sha256":"0c2cf42ff19e8296fdb183d16ea666eeeb7d3f876cea7e1b1399fe3c27f3ec26"},"schema_version":"1.0","source":{"id":"2508.21761","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21761","created_at":"2026-07-05T12:01:49Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21761v1","created_at":"2026-07-05T12:01:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21761","created_at":"2026-07-05T12:01:49Z"},{"alias_kind":"pith_short_12","alias_value":"XVQ4CON7CVXE","created_at":"2026-07-05T12:01:49Z"},{"alias_kind":"pith_short_16","alias_value":"XVQ4CON7CVXEVNFZ","created_at":"2026-07-05T12:01:49Z"},{"alias_kind":"pith_short_8","alias_value":"XVQ4CON7","created_at":"2026-07-05T12:01:49Z"}],"graph_snapshots":[{"event_id":"sha256:9e742d353f03cba0c0ebe28be477d0befa88547b54f69513e1b4119de1f1b08f","target":"graph","created_at":"2026-07-05T12:01:49Z","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/2508.21761/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual sound source localization is a fundamental perception task that aims to detect the location of sounding sources in a video given its audio. Despite recent progress, we identify two shortcomings in current methods: 1) most approaches perform poorly in cases with low audio-visual semantic correspondence such as silence, noise, and offscreen sounds, i.e. in the presence of negative audio; and 2) most prior evaluations are limited to positive cases, where both datasets and metrics convey scenarios with a single visible sound source in the scene. To address this, we introduce three key contr","authors_text":"Giovana Morais, Gloria Haro, Magdalena Fuentes, Xavier Juanola","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T16:36:16Z","title":"Learning from Silence and Noise for Visual Sound Source Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21761","kind":"arxiv","version":1},"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":"sha256:53e805320ffb86d8f7fe586bce2c9dc52bce807d19776ffef22c484061c07f65","target":"record","created_at":"2026-07-05T12:01:49Z","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":"b3f5cf4f27c3fa47c4e4e02d4ea81e429a7275a984a168f60797785a7f06859a","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T16:36:16Z","title_canon_sha256":"0c2cf42ff19e8296fdb183d16ea666eeeb7d3f876cea7e1b1399fe3c27f3ec26"},"schema_version":"1.0","source":{"id":"2508.21761","kind":"arxiv","version":1}},"canonical_sha256":"bd61c139bf156e4ab4b947ff41559fd257471fe92655ce76f78205070673dddf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd61c139bf156e4ab4b947ff41559fd257471fe92655ce76f78205070673dddf","first_computed_at":"2026-07-05T12:01:49.231204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:49.231204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aM557mpZOwXXimCkzH4rYXD7yhTvcHXHWYR6zkGFtK2lEXpeygiXOVuw2aOqvmpIJR6gvVzvOc96vFhLiLZ9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:49.231700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21761","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53e805320ffb86d8f7fe586bce2c9dc52bce807d19776ffef22c484061c07f65","sha256:9e742d353f03cba0c0ebe28be477d0befa88547b54f69513e1b4119de1f1b08f"],"state_sha256":"4b77bd316ff23fe90593eba4cfa28d214ef7af1f562b19671e97de8be9476072"}