{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UYQ3SVH534RZ2HE2BYO2LKPQIO","short_pith_number":"pith:UYQ3SVH5","schema_version":"1.0","canonical_sha256":"a621b954fddf239d1c9a0e1da5a9f0439cea1f1bf61fb08815dd710cbdf00c5e","source":{"kind":"arxiv","id":"2505.01237","version":2},"attestation_state":"computed","paper":{"title":"CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Andrew Rouditchenko, Brian Kingsbury, Edson Araujo, Hilde Kuehne, James R. Glass, Leonid Karlinsky, Rogerio Feris, Samuel Thomas, Saurabhchand Bhati, Yuan Gong","submitted_at":"2025-05-02T12:59:58Z","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: "},"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":"2505.01237","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-02T12:59:58Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"58a3c2af159306ad79cf0e9d57c73e401c7f312082479210b309ff33e3d16a6d","abstract_canon_sha256":"7692635ef8f691612c2bd0008109d605651faeaec0ac88b4e94a57e8b4b899e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:31.350832Z","signature_b64":"kuzAYMSBwOdkpSrpCY3tb41PJwzw27H/m8G3NBM2ssLjHZ5uG9CP4E4widwJwrrj0SBaHFtIidG6PMR06lm9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a621b954fddf239d1c9a0e1da5a9f0439cea1f1bf61fb08815dd710cbdf00c5e","last_reissued_at":"2026-07-05T11:06:31.350330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:31.350330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Andrew Rouditchenko, Brian Kingsbury, Edson Araujo, Hilde Kuehne, James R. Glass, Leonid Karlinsky, Rogerio Feris, Samuel Thomas, Saurabhchand Bhati, Yuan Gong","submitted_at":"2025-05-02T12:59:58Z","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: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01237","kind":"arxiv","version":2},"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/2505.01237/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":"2505.01237","created_at":"2026-07-05T11:06:31.350391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01237v2","created_at":"2026-07-05T11:06:31.350391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01237","created_at":"2026-07-05T11:06:31.350391+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYQ3SVH534RZ","created_at":"2026-07-05T11:06:31.350391+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYQ3SVH534RZ2HE2","created_at":"2026-07-05T11:06:31.350391+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYQ3SVH5","created_at":"2026-07-05T11:06:31.350391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO","json":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO.json","graph_json":"https://pith.science/api/pith-number/UYQ3SVH534RZ2HE2BYO2LKPQIO/graph.json","events_json":"https://pith.science/api/pith-number/UYQ3SVH534RZ2HE2BYO2LKPQIO/events.json","paper":"https://pith.science/paper/UYQ3SVH5"},"agent_actions":{"view_html":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO","download_json":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO.json","view_paper":"https://pith.science/paper/UYQ3SVH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01237&json=true","fetch_graph":"https://pith.science/api/pith-number/UYQ3SVH534RZ2HE2BYO2LKPQIO/graph.json","fetch_events":"https://pith.science/api/pith-number/UYQ3SVH534RZ2HE2BYO2LKPQIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO/action/storage_attestation","attest_author":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO/action/author_attestation","sign_citation":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO/action/citation_signature","submit_replication":"https://pith.science/pith/UYQ3SVH534RZ2HE2BYO2LKPQIO/action/replication_record"}},"created_at":"2026-07-05T11:06:31.350391+00:00","updated_at":"2026-07-05T11:06:31.350391+00:00"}