{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UYQ3SVH534RZ2HE2BYO2LKPQIO","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":"7692635ef8f691612c2bd0008109d605651faeaec0ac88b4e94a57e8b4b899e4","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-02T12:59:58Z","title_canon_sha256":"58a3c2af159306ad79cf0e9d57c73e401c7f312082479210b309ff33e3d16a6d"},"schema_version":"1.0","source":{"id":"2505.01237","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01237","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01237v2","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01237","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_12","alias_value":"UYQ3SVH534RZ","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_16","alias_value":"UYQ3SVH534RZ2HE2","created_at":"2026-07-05T11:06:31Z"},{"alias_kind":"pith_short_8","alias_value":"UYQ3SVH5","created_at":"2026-07-05T11:06:31Z"}],"graph_snapshots":[{"event_id":"sha256:7b804a7906c370ac43426c5fa0091b4a2d32e1cc5df1be0607f91ff340d7a655","target":"graph","created_at":"2026-07-05T11:06:31Z","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/2505.01237/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in audio-visual learning have shown promising results in learning representations across modalities. However, most approaches rely on global audio representations that fail to capture fine-grained temporal correspondences with visual frames. Additionally, existing methods often struggle with conflicting optimization objectives when trying to jointly learn reconstruction and cross-modal alignment. In this work, we propose CAV-MAE Sync as a simple yet effective extension of the original CAV-MAE framework for self-supervised audio-visual learning. We address three key challenges: ","authors_text":"Andrew Rouditchenko, Brian Kingsbury, Edson Araujo, Hilde Kuehne, James R. Glass, Leonid Karlinsky, Rogerio Feris, Samuel Thomas, Saurabhchand Bhati, Yuan Gong","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-02T12:59:58Z","title":"CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01237","kind":"arxiv","version":2},"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:c33b9944dbb5294ef2881db356cc3279f9a60b5c08c13911873ca010c94a5c08","target":"record","created_at":"2026-07-05T11:06:31Z","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":"7692635ef8f691612c2bd0008109d605651faeaec0ac88b4e94a57e8b4b899e4","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-02T12:59:58Z","title_canon_sha256":"58a3c2af159306ad79cf0e9d57c73e401c7f312082479210b309ff33e3d16a6d"},"schema_version":"1.0","source":{"id":"2505.01237","kind":"arxiv","version":2}},"canonical_sha256":"a621b954fddf239d1c9a0e1da5a9f0439cea1f1bf61fb08815dd710cbdf00c5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a621b954fddf239d1c9a0e1da5a9f0439cea1f1bf61fb08815dd710cbdf00c5e","first_computed_at":"2026-07-05T11:06:31.350330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:31.350330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kuzAYMSBwOdkpSrpCY3tb41PJwzw27H/m8G3NBM2ssLjHZ5uG9CP4E4widwJwrrj0SBaHFtIidG6PMR06lm9DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:31.350832Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01237","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c33b9944dbb5294ef2881db356cc3279f9a60b5c08c13911873ca010c94a5c08","sha256:7b804a7906c370ac43426c5fa0091b4a2d32e1cc5df1be0607f91ff340d7a655"],"state_sha256":"b0f3fe9fecc0de33df9314afe54e94445fa4c9dca4b40d9a8a1e0e32a5c13496"}