{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4XMZ5LFRQ2R226DGAPRO7KPPWB","short_pith_number":"pith:4XMZ5LFR","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"},"canonical_sha256":"e5d99eacb186a3ad786603e2efa9efb07ef936077069fa416ad13417f336ec13","source":{"kind":"arxiv","id":"2209.09634","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.09634","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"2209.09634v1","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09634","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"4XMZ5LFRQ2R2","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"pith_short_16","alias_value":"4XMZ5LFRQ2R226DG","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"pith_short_8","alias_value":"4XMZ5LFR","created_at":"2026-07-05T04:59:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4XMZ5LFRQ2R226DGAPRO7KPPWB","target":"record","payload":{"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"},"canonical_sha256":"e5d99eacb186a3ad786603e2efa9efb07ef936077069fa416ad13417f336ec13","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"},"source_kind":"arxiv","source_id":"2209.09634","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IwOitxRkV84/dGC34qb6o/OWdcEjwJwOq6BjCyfJ3XxhL5ueNLJm/K6oPjEoDOdfJMs9QA0r5v++1LuLHPfzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:53:32.262222Z"},"content_sha256":"a77aec0bf89da3efd6ab30d3a9e6419403e3c68cb0886072b44b7e95813923cf","schema_version":"1.0","event_id":"sha256:a77aec0bf89da3efd6ab30d3a9e6419403e3c68cb0886072b44b7e95813923cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4XMZ5LFRQ2R226DGAPRO7KPPWB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7cJJqLzQttqxNWOVzAXZ1wyXBB+LXIkSF9AI1m7+sp8ssf1UNdS2rAp7ju7Y7PCKWBS7wC7JQfkOUVwoliBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:53:32.262756Z"},"content_sha256":"d0bfc0fc97cdcc36defe42b95f61d0c4a09c3aee80882d4d22608fe47e7a60dc","schema_version":"1.0","event_id":"sha256:d0bfc0fc97cdcc36defe42b95f61d0c4a09c3aee80882d4d22608fe47e7a60dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/bundle.json","state_url":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T20:53:32Z","links":{"resolver":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB","bundle":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/bundle.json","state":"https://pith.science/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4XMZ5LFRQ2R226DGAPRO7KPPWB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4XMZ5LFRQ2R226DGAPRO7KPPWB","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":"cd6e8f9ab28d8fa91bae27b1bb868a885fba0ec48e266a3cd7ff7dfbaf03bc8a","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-30T14:17:46Z","title_canon_sha256":"3dd1987ea39b3ce23f1cdb3a08a135027c8db5139d4a03c33f8665caa0f9ed29"},"schema_version":"1.0","source":{"id":"2209.09634","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.09634","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"2209.09634v1","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09634","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"4XMZ5LFRQ2R2","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"pith_short_16","alias_value":"4XMZ5LFRQ2R226DG","created_at":"2026-07-05T04:59:02Z"},{"alias_kind":"pith_short_8","alias_value":"4XMZ5LFR","created_at":"2026-07-05T04:59:02Z"}],"graph_snapshots":[{"event_id":"sha256:d0bfc0fc97cdcc36defe42b95f61d0c4a09c3aee80882d4d22608fe47e7a60dc","target":"graph","created_at":"2026-07-05T04:59:02Z","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/2209.09634/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Pedro Morgado, Shentong Mo","cross_cats":["cs.CV","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-30T14:17:46Z","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09634","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:a77aec0bf89da3efd6ab30d3a9e6419403e3c68cb0886072b44b7e95813923cf","target":"record","created_at":"2026-07-05T04:59:02Z","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":"cd6e8f9ab28d8fa91bae27b1bb868a885fba0ec48e266a3cd7ff7dfbaf03bc8a","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-08-30T14:17:46Z","title_canon_sha256":"3dd1987ea39b3ce23f1cdb3a08a135027c8db5139d4a03c33f8665caa0f9ed29"},"schema_version":"1.0","source":{"id":"2209.09634","kind":"arxiv","version":1}},"canonical_sha256":"e5d99eacb186a3ad786603e2efa9efb07ef936077069fa416ad13417f336ec13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5d99eacb186a3ad786603e2efa9efb07ef936077069fa416ad13417f336ec13","first_computed_at":"2026-07-05T04:59:02.552268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:59:02.552268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0wJ1lrH/iN1gCzWpcSiqmxFPkDWKF9Zs5V1pcTtqT7r1qVA0YDSJ2pjVdsTTXUZ5+ikAH71ZqL58Pi5eX5P0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:59:02.552747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.09634","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a77aec0bf89da3efd6ab30d3a9e6419403e3c68cb0886072b44b7e95813923cf","sha256:d0bfc0fc97cdcc36defe42b95f61d0c4a09c3aee80882d4d22608fe47e7a60dc"],"state_sha256":"bf0beda796e219852ee0046a13a55573a1a5dbcb34c1fe158e6a7aa64609ef6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d4To97rUJ5S8/7u+HZ9Xjdy1IO8F27C5X8yCSVdE6OwLCDf6sxvWk9Yr9DJrTAzcJIVbu6x9DQS29cHiJKYXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:53:32.268162Z","bundle_sha256":"1cd315a78ffa55a1915f6b5b0e8df57e4aa062cb27cd6121c2e9a059483e6c8f"}}