{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4L3ESVZT5CR3BNQBJZERXYFNHT","short_pith_number":"pith:4L3ESVZT","canonical_record":{"source":{"id":"2403.03145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T17:35:46Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"0c25d8f2bb3a76215047a2a24e6e847a93cee52bdffff4f51ce2062e6a1e8e96","abstract_canon_sha256":"cf7b71b0ec46b33c66dd2eaf7cdc53520a9ddfb7ab17b1738a8a35ed91d2ceb3"},"schema_version":"1.0"},"canonical_sha256":"e2f6495733e8a3b0b6014e491be0ad3cec43ef3db0a4abf352baac0bb60aaa44","source":{"kind":"arxiv","id":"2403.03145","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03145","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03145v1","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03145","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_12","alias_value":"4L3ESVZT5CR3","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_16","alias_value":"4L3ESVZT5CR3BNQB","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_8","alias_value":"4L3ESVZT","created_at":"2026-07-05T07:52:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4L3ESVZT5CR3BNQBJZERXYFNHT","target":"record","payload":{"canonical_record":{"source":{"id":"2403.03145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T17:35:46Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"0c25d8f2bb3a76215047a2a24e6e847a93cee52bdffff4f51ce2062e6a1e8e96","abstract_canon_sha256":"cf7b71b0ec46b33c66dd2eaf7cdc53520a9ddfb7ab17b1738a8a35ed91d2ceb3"},"schema_version":"1.0"},"canonical_sha256":"e2f6495733e8a3b0b6014e491be0ad3cec43ef3db0a4abf352baac0bb60aaa44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:36.649741Z","signature_b64":"cc+LRQBQf+O3I4ES4S0JJd7SFVJ9izgisfEkWqWg1Z87kQMXj+ctbmeRQsxRRQEw+lGf1iEAJNfZL9Ldkq7lCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2f6495733e8a3b0b6014e491be0ad3cec43ef3db0a4abf352baac0bb60aaa44","last_reissued_at":"2026-07-05T07:52:36.649306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:36.649306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.03145","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":"2026-07-05T07:52:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQwD8YrLiAE2AtILyKHWe7RaGEMgD6q2r17db8szaX/bnOs9jdMGOxgoy9671gtG7+QfH/yKOqdZPNM89SzTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:22:44.823532Z"},"content_sha256":"d6520227121cfea246ad61e505cedcf3e409ca6e6b8f90ef050e48d110e50259","schema_version":"1.0","event_id":"sha256:d6520227121cfea246ad61e505cedcf3e409ca6e6b8f90ef050e48d110e50259"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4L3ESVZT5CR3BNQBJZERXYFNHT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Hu Su, Shijie Ma, Siyang Sun, Wei Zou, Yuhao Zhao, Yun Zheng, Yuxin Guo, Zhiqing Wang","submitted_at":"2024-03-05T17:35:46Z","abstract_excerpt":"Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without any bounding-box annotations, they struggle to achieve precise localization, especially for small objects, and suffer from blurry boundaries and false positives. Moreover, the naive semi-supervised method is poor in fully leveraging the information of abundant unlabeled data. In this paper, we propose a novel semi-supervised learning framework for AVSL, namely"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03145","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/2403.03145/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":"2026-07-05T07:52:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aaodf4u0Pyv0MBP6hORUWuo5jtML+p7SGl/hGnFGUlsih0jfoPd4ezNJctoc+umcT26ET5Bc1fdhEiFF/zIoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:22:44.824050Z"},"content_sha256":"9f8a7727c4c428b668217c50a36856ca47e2d9ede1161fb02f968b44bea1a751","schema_version":"1.0","event_id":"sha256:9f8a7727c4c428b668217c50a36856ca47e2d9ede1161fb02f968b44bea1a751"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4L3ESVZT5CR3BNQBJZERXYFNHT/bundle.json","state_url":"https://pith.science/pith/4L3ESVZT5CR3BNQBJZERXYFNHT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4L3ESVZT5CR3BNQBJZERXYFNHT/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":"2026-08-22T13:22:44Z","links":{"resolver":"https://pith.science/pith/4L3ESVZT5CR3BNQBJZERXYFNHT","bundle":"https://pith.science/pith/4L3ESVZT5CR3BNQBJZERXYFNHT/bundle.json","state":"https://pith.science/pith/4L3ESVZT5CR3BNQBJZERXYFNHT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4L3ESVZT5CR3BNQBJZERXYFNHT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4L3ESVZT5CR3BNQBJZERXYFNHT","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":"cf7b71b0ec46b33c66dd2eaf7cdc53520a9ddfb7ab17b1738a8a35ed91d2ceb3","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T17:35:46Z","title_canon_sha256":"0c25d8f2bb3a76215047a2a24e6e847a93cee52bdffff4f51ce2062e6a1e8e96"},"schema_version":"1.0","source":{"id":"2403.03145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03145","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03145v1","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03145","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_12","alias_value":"4L3ESVZT5CR3","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_16","alias_value":"4L3ESVZT5CR3BNQB","created_at":"2026-07-05T07:52:36Z"},{"alias_kind":"pith_short_8","alias_value":"4L3ESVZT","created_at":"2026-07-05T07:52:36Z"}],"graph_snapshots":[{"event_id":"sha256:9f8a7727c4c428b668217c50a36856ca47e2d9ede1161fb02f968b44bea1a751","target":"graph","created_at":"2026-07-05T07:52:36Z","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/2403.03145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without any bounding-box annotations, they struggle to achieve precise localization, especially for small objects, and suffer from blurry boundaries and false positives. Moreover, the naive semi-supervised method is poor in fully leveraging the information of abundant unlabeled data. In this paper, we propose a novel semi-supervised learning framework for AVSL, namely","authors_text":"Hu Su, Shijie Ma, Siyang Sun, Wei Zou, Yuhao Zhao, Yun Zheng, Yuxin Guo, Zhiqing Wang","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T17:35:46Z","title":"Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03145","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:d6520227121cfea246ad61e505cedcf3e409ca6e6b8f90ef050e48d110e50259","target":"record","created_at":"2026-07-05T07:52:36Z","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":"cf7b71b0ec46b33c66dd2eaf7cdc53520a9ddfb7ab17b1738a8a35ed91d2ceb3","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-05T17:35:46Z","title_canon_sha256":"0c25d8f2bb3a76215047a2a24e6e847a93cee52bdffff4f51ce2062e6a1e8e96"},"schema_version":"1.0","source":{"id":"2403.03145","kind":"arxiv","version":1}},"canonical_sha256":"e2f6495733e8a3b0b6014e491be0ad3cec43ef3db0a4abf352baac0bb60aaa44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2f6495733e8a3b0b6014e491be0ad3cec43ef3db0a4abf352baac0bb60aaa44","first_computed_at":"2026-07-05T07:52:36.649306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:36.649306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cc+LRQBQf+O3I4ES4S0JJd7SFVJ9izgisfEkWqWg1Z87kQMXj+ctbmeRQsxRRQEw+lGf1iEAJNfZL9Ldkq7lCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:36.649741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03145","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6520227121cfea246ad61e505cedcf3e409ca6e6b8f90ef050e48d110e50259","sha256:9f8a7727c4c428b668217c50a36856ca47e2d9ede1161fb02f968b44bea1a751"],"state_sha256":"97ad3ee9997b846c0bbbc3897b2977acc20b8805f69fcb06fadb7e1db0623df5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QlhV4unGLrYAkEM/ySy5G3EROqRS5hX1OlreFB/ufdvzESmSTHxlGOFqT7b+0aHccyjNBz4R5WI11rIfN8nOBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T13:22:44.828959Z","bundle_sha256":"8292d6480cb15fbd70c69879a11ab03d61ef856928c6523ac38e710ea91ab8cc"}}