{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K4O2O5FHWTZGQVMZKEIFBHBZ4S","short_pith_number":"pith:K4O2O5FH","canonical_record":{"source":{"id":"2412.00049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-11-24T03:26:34Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"9baee5809a53e86d27efc24af480c77505a853cd9b4da936642781db86c7117e","abstract_canon_sha256":"87e3e2332c5f1f50114b78db0e98fa3cb9f1bdf4872d9099e3c89611c303366d"},"schema_version":"1.0"},"canonical_sha256":"571da774a7b4f26855995110509c39e4831a7d3094de4c4fb4291d3a87e6d1bc","source":{"kind":"arxiv","id":"2412.00049","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00049","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00049v1","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00049","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"pith_short_12","alias_value":"K4O2O5FHWTZG","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"pith_short_16","alias_value":"K4O2O5FHWTZGQVMZ","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"pith_short_8","alias_value":"K4O2O5FH","created_at":"2026-07-05T09:42:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K4O2O5FHWTZGQVMZKEIFBHBZ4S","target":"record","payload":{"canonical_record":{"source":{"id":"2412.00049","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-11-24T03:26:34Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"9baee5809a53e86d27efc24af480c77505a853cd9b4da936642781db86c7117e","abstract_canon_sha256":"87e3e2332c5f1f50114b78db0e98fa3cb9f1bdf4872d9099e3c89611c303366d"},"schema_version":"1.0"},"canonical_sha256":"571da774a7b4f26855995110509c39e4831a7d3094de4c4fb4291d3a87e6d1bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:35.235307Z","signature_b64":"tNxW7dzssnHUBI8gAAvvwL0l2odBz1BjlQBTmyBiocRB+KaCDTEisz1Bie3q9laR3GMdyDhTvwfTIPxm2Dj/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"571da774a7b4f26855995110509c39e4831a7d3094de4c4fb4291d3a87e6d1bc","last_reissued_at":"2026-07-05T09:42:35.234812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:35.234812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.00049","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":"2026-07-05T09:42:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o74vNmi0NIAPr/jWUl9ouqS5iTUbvyrPt4RbHTwPAXtSIDjOoJ5aed/kIpXyrIym7ulJQZ0/tO9363k0e1tBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:56:49.997381Z"},"content_sha256":"085238e16285892de0448f85bd5fc3482e750aa79cc7bdd0fb4b682cee4f5231","schema_version":"1.0","event_id":"sha256:085238e16285892de0448f85bd5fc3482e750aa79cc7bdd0fb4b682cee4f5231"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K4O2O5FHWTZGQVMZKEIFBHBZ4S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Luis Vilaca, Paula Vinan, Yi Yu","submitted_at":"2024-11-24T03:26:34Z","abstract_excerpt":"Audio-visual correlation learning aims to capture and understand natural phenomena between audio and visual data. The rapid growth of Deep Learning propelled the development of proposals that process audio-visual data and can be observed in the number of proposals in the past years. Thus encouraging the development of a comprehensive survey. Besides analyzing the models used in this context, we also discuss some tasks of definition and paradigm applied in AI multimedia. In addition, we investigate objective functions frequently used and discuss how audio-visual data is exploited in the optimiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00049","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/2412.00049/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":"2026-07-05T09:42:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QxYk9jfcbpQD3sCvMfgPO2q0s2VGpfprlHmh7zo5sXhZ1+9G6oSDJCGmW3LIcgP36xYFt2+CuO0lF+rThrCxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:56:49.998199Z"},"content_sha256":"9d43a2b975c33664e7ac7e795b93cbaf8981391975dbd3cbf89c219886974f60","schema_version":"1.0","event_id":"sha256:9d43a2b975c33664e7ac7e795b93cbaf8981391975dbd3cbf89c219886974f60"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4O2O5FHWTZGQVMZKEIFBHBZ4S/bundle.json","state_url":"https://pith.science/pith/K4O2O5FHWTZGQVMZKEIFBHBZ4S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4O2O5FHWTZGQVMZKEIFBHBZ4S/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":"2026-08-12T20:56:50Z","links":{"resolver":"https://pith.science/pith/K4O2O5FHWTZGQVMZKEIFBHBZ4S","bundle":"https://pith.science/pith/K4O2O5FHWTZGQVMZKEIFBHBZ4S/bundle.json","state":"https://pith.science/pith/K4O2O5FHWTZGQVMZKEIFBHBZ4S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4O2O5FHWTZGQVMZKEIFBHBZ4S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K4O2O5FHWTZGQVMZKEIFBHBZ4S","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":"87e3e2332c5f1f50114b78db0e98fa3cb9f1bdf4872d9099e3c89611c303366d","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-11-24T03:26:34Z","title_canon_sha256":"9baee5809a53e86d27efc24af480c77505a853cd9b4da936642781db86c7117e"},"schema_version":"1.0","source":{"id":"2412.00049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00049","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00049v1","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00049","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"pith_short_12","alias_value":"K4O2O5FHWTZG","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"pith_short_16","alias_value":"K4O2O5FHWTZGQVMZ","created_at":"2026-07-05T09:42:35Z"},{"alias_kind":"pith_short_8","alias_value":"K4O2O5FH","created_at":"2026-07-05T09:42:35Z"}],"graph_snapshots":[{"event_id":"sha256:9d43a2b975c33664e7ac7e795b93cbaf8981391975dbd3cbf89c219886974f60","target":"graph","created_at":"2026-07-05T09:42:35Z","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/2412.00049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual correlation learning aims to capture and understand natural phenomena between audio and visual data. The rapid growth of Deep Learning propelled the development of proposals that process audio-visual data and can be observed in the number of proposals in the past years. Thus encouraging the development of a comprehensive survey. Besides analyzing the models used in this context, we also discuss some tasks of definition and paradigm applied in AI multimedia. In addition, we investigate objective functions frequently used and discuss how audio-visual data is exploited in the optimiz","authors_text":"Luis Vilaca, Paula Vinan, Yi Yu","cross_cats":["cs.AI","cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-11-24T03:26:34Z","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00049","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":"sha256:085238e16285892de0448f85bd5fc3482e750aa79cc7bdd0fb4b682cee4f5231","target":"record","created_at":"2026-07-05T09:42:35Z","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":"87e3e2332c5f1f50114b78db0e98fa3cb9f1bdf4872d9099e3c89611c303366d","cross_cats_sorted":["cs.AI","cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-11-24T03:26:34Z","title_canon_sha256":"9baee5809a53e86d27efc24af480c77505a853cd9b4da936642781db86c7117e"},"schema_version":"1.0","source":{"id":"2412.00049","kind":"arxiv","version":1}},"canonical_sha256":"571da774a7b4f26855995110509c39e4831a7d3094de4c4fb4291d3a87e6d1bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"571da774a7b4f26855995110509c39e4831a7d3094de4c4fb4291d3a87e6d1bc","first_computed_at":"2026-07-05T09:42:35.234812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:35.234812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tNxW7dzssnHUBI8gAAvvwL0l2odBz1BjlQBTmyBiocRB+KaCDTEisz1Bie3q9laR3GMdyDhTvwfTIPxm2Dj/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:35.235307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:085238e16285892de0448f85bd5fc3482e750aa79cc7bdd0fb4b682cee4f5231","sha256:9d43a2b975c33664e7ac7e795b93cbaf8981391975dbd3cbf89c219886974f60"],"state_sha256":"fed8770f0440e1ca28bd0368c17771d551221a448bb3b631035534abcd74ab30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K7NJF/K43w0bTGxu97UVhHuDYd54fCkQ4UZryOuh9XlQORr3SqYtsjq6layeC3+K1W4NWaCSFzv5pdOo6oOHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T20:56:50.003233Z","bundle_sha256":"d86bccf293400f4d70425b154afdbada178b1331b58e57028fb36875a01e0981"}}