{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4XMZ5LFRQ2R226DGAPRO7KPPWB","short_pith_number":"pith:4XMZ5LFR","schema_version":"1.0","canonical_sha256":"e5d99eacb186a3ad786603e2efa9efb07ef936077069fa416ad13417f336ec13","source":{"kind":"arxiv","id":"2209.09634","version":1},"attestation_state":"computed","paper":{"title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.SD","authors_text":"Pedro Morgado, Shentong Mo","submitted_at":"2022-08-30T14:17:46Z","abstract_excerpt":"Audio-visual source localization is a challenging task that aims to predict the location of visual sound sources in a video. Since collecting ground-truth annotations of sounding objects can be costly, a plethora of weakly-supervised localization methods that can learn from datasets with no bounding-box annotations have been proposed in recent years, by leveraging the natural co-occurrence of audio and visual signals. Despite significant interest, popular evaluation protocols have two major flaws. First, they allow for the use of a fully annotated dataset to perform early stopping, thus signif"},"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":"2209.09634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-30T14:17:46Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"title_canon_sha256":"3dd1987ea39b3ce23f1cdb3a08a135027c8db5139d4a03c33f8665caa0f9ed29","abstract_canon_sha256":"cd6e8f9ab28d8fa91bae27b1bb868a885fba0ec48e266a3cd7ff7dfbaf03bc8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:59:02.552747Z","signature_b64":"0wJ1lrH/iN1gCzWpcSiqmxFPkDWKF9Zs5V1pcTtqT7r1qVA0YDSJ2pjVdsTTXUZ5+ikAH71ZqL58Pi5eX5P0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5d99eacb186a3ad786603e2efa9efb07ef936077069fa416ad13417f336ec13","last_reissued_at":"2026-07-05T04:59:02.552268Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:59:02.552268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM"],"primary_cat":"cs.SD","authors_text":"Pedro Morgado, Shentong Mo","submitted_at":"2022-08-30T14:17:46Z","abstract_excerpt":"Audio-visual source localization is a challenging task that aims to predict the location of visual sound sources in a video. Since collecting ground-truth annotations of sounding objects can be costly, a plethora of weakly-supervised localization methods that can learn from datasets with no bounding-box annotations have been proposed in recent years, by leveraging the natural co-occurrence of audio and visual signals. Despite significant interest, popular evaluation protocols have two major flaws. First, they allow for the use of a fully annotated dataset to perform early stopping, thus signif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09634","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/2209.09634/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":"2209.09634","created_at":"2026-07-05T04:59:02.552339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.09634v1","created_at":"2026-07-05T04:59:02.552339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09634","created_at":"2026-07-05T04:59:02.552339+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XMZ5LFRQ2R2","created_at":"2026-07-05T04:59:02.552339+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XMZ5LFRQ2R226DG","created_at":"2026-07-05T04:59:02.552339+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XMZ5LFR","created_at":"2026-07-05T04:59:02.552339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.01015","citing_title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB","json":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB.json","graph_json":"https://pith.science/api/pith-number/4XMZ5LFRQ2R226DGAPRO7KPPWB/graph.json","events_json":"https://pith.science/api/pith-number/4XMZ5LFRQ2R226DGAPRO7KPPWB/events.json","paper":"https://pith.science/paper/4XMZ5LFR"},"agent_actions":{"view_html":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB","download_json":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB.json","view_paper":"https://pith.science/paper/4XMZ5LFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.09634&json=true","fetch_graph":"https://pith.science/api/pith-number/4XMZ5LFRQ2R226DGAPRO7KPPWB/graph.json","fetch_events":"https://pith.science/api/pith-number/4XMZ5LFRQ2R226DGAPRO7KPPWB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/action/storage_attestation","attest_author":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/action/author_attestation","sign_citation":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/action/citation_signature","submit_replication":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/action/replication_record"}},"created_at":"2026-07-05T04:59:02.552339+00:00","updated_at":"2026-07-05T04:59:02.552339+00:00"}