{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FTPAGX2HIPX7P22DLP2O77EFZN","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":"22d88ce6a757b468cca30d5454130ff9677f0d85e8e9e8af0c077ca5e6ae89a6","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2022-10-02T07:29:57Z","title_canon_sha256":"a3db38c1b76bd13e0e44e9ff96a234d460650e73996b22cc34135083c92bf2ec"},"schema_version":"1.0","source":{"id":"2210.07839","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07839","created_at":"2026-07-05T06:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07839v4","created_at":"2026-07-05T06:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07839","created_at":"2026-07-05T06:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"FTPAGX2HIPX7","created_at":"2026-07-05T06:00:13Z"},{"alias_kind":"pith_short_16","alias_value":"FTPAGX2HIPX7P22D","created_at":"2026-07-05T06:00:13Z"},{"alias_kind":"pith_short_8","alias_value":"FTPAGX2H","created_at":"2026-07-05T06:00:13Z"}],"graph_snapshots":[{"event_id":"sha256:3e22c586e3d5933220a29d9fb8bdc5c4c23e1468841162f4bc40bac9a6216231","target":"graph","created_at":"2026-07-05T06:00:13Z","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/2210.07839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we first extend the recent Masked Auto-Encoder (MAE) model from a single modality to audio-visual multi-modalities. Subsequently, we propose the Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) by combining contrastive learning and masked data modeling, two major self-supervised learning frameworks, to learn a joint and coordinated audio-visual representation. Our experiments show that the contrastive audio-visual correspondence learning objective not only enables the model to perform audio-visual retrieval tasks, but also helps the model learn a better joint representatio","authors_text":"Alexander H. Liu, Andrew Rouditchenko, David Harwath, Hilde Kuehne, James Glass, Leonid Karlinsky, 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":"2022-10-02T07:29:57Z","title":"Contrastive Audio-Visual Masked Autoencoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07839","kind":"arxiv","version":4},"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":"sha256:4fddec5e56b0171083ee19d09e577b5fc7a706004ba9dcb1a4ce375d1a872d19","target":"record","created_at":"2026-07-05T06:00:13Z","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":"22d88ce6a757b468cca30d5454130ff9677f0d85e8e9e8af0c077ca5e6ae89a6","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2022-10-02T07:29:57Z","title_canon_sha256":"a3db38c1b76bd13e0e44e9ff96a234d460650e73996b22cc34135083c92bf2ec"},"schema_version":"1.0","source":{"id":"2210.07839","kind":"arxiv","version":4}},"canonical_sha256":"2cde035f4743eff7eb435bf4effc85cb45413dbaa1af0e26f8b9d066005c65f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cde035f4743eff7eb435bf4effc85cb45413dbaa1af0e26f8b9d066005c65f5","first_computed_at":"2026-07-05T06:00:13.830470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:00:13.830470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4YnVLfqsyxTvEFCH0AHPaMg8HkyORAPVwjDDeFOsqgj1WTvmlPWmloDEj6BQObsrIPfSJBL56xoF+gWjAxpzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:00:13.831002Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07839","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fddec5e56b0171083ee19d09e577b5fc7a706004ba9dcb1a4ce375d1a872d19","sha256:3e22c586e3d5933220a29d9fb8bdc5c4c23e1468841162f4bc40bac9a6216231"],"state_sha256":"659bf2e3f6c5767bffdd6f017f1a752f8162ad6836313980dd285a67c081af7e"}