{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HDYA5TUJCWWKYN3YUTAHUTK2ZX","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":"e64a00e1ee15ed4390d5908e5e224fe29d738e92e41428eed467b9a3c2d39653","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T18:59:59Z","title_canon_sha256":"c79a4ed74effac5351e14d9506727ae800f30fcbd43cbdebd8ea1ae9424bfce5"},"schema_version":"1.0","source":{"id":"2212.08071","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08071","created_at":"2026-07-05T06:31:07Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08071v2","created_at":"2026-07-05T06:31:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08071","created_at":"2026-07-05T06:31:07Z"},{"alias_kind":"pith_short_12","alias_value":"HDYA5TUJCWWK","created_at":"2026-07-05T06:31:07Z"},{"alias_kind":"pith_short_16","alias_value":"HDYA5TUJCWWKYN3Y","created_at":"2026-07-05T06:31:07Z"},{"alias_kind":"pith_short_8","alias_value":"HDYA5TUJ","created_at":"2026-07-05T06:31:07Z"}],"graph_snapshots":[{"event_id":"sha256:b407bd6761e8d9ddeaca49ab6b763e1c5933248101c5ae0c54e542d5cdee2f7a","target":"graph","created_at":"2026-07-05T06:31:07Z","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/2212.08071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and inter-modal contrastive learning with masking, and (3) self-training by reconstructing joint audio-video contextualized features learned from the first two objectives. Pre-training with MAViL not only enables the model to perform well in audio-visual classification and retrieval tasks but also improves representations of each modality in isolation, without using infor","authors_text":"Chaitanya Ryali, Christoph Feichtenhofer, Gargi Ghosh, Haoqi Fan, Hu Xu, Jitendra Malik, Po-Yao Huang, Shang-Wen Li, Vasu Sharma, Yanghao Li","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T18:59:59Z","title":"MAViL: Masked Audio-Video Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08071","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":"sha256:26b6afe9d83f606e0f84dd9e1d6c869861745d105aa66c7770dc3c9f61d160ae","target":"record","created_at":"2026-07-05T06:31:07Z","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":"e64a00e1ee15ed4390d5908e5e224fe29d738e92e41428eed467b9a3c2d39653","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T18:59:59Z","title_canon_sha256":"c79a4ed74effac5351e14d9506727ae800f30fcbd43cbdebd8ea1ae9424bfce5"},"schema_version":"1.0","source":{"id":"2212.08071","kind":"arxiv","version":2}},"canonical_sha256":"38f00ece8915acac3778a4c07a4d5acdc0e5f616b0a479387ba97c83940a53cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38f00ece8915acac3778a4c07a4d5acdc0e5f616b0a479387ba97c83940a53cb","first_computed_at":"2026-07-05T06:31:07.586257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:31:07.586257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5kEqSaNmgv7JDuHAwimeUMNi8uGDLuzY1aCbmBC2QBEvAZpt393Cxa0OANo8N+17pV+Yh10liTAkT2YPnXqZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:31:07.586766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08071","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26b6afe9d83f606e0f84dd9e1d6c869861745d105aa66c7770dc3c9f61d160ae","sha256:b407bd6761e8d9ddeaca49ab6b763e1c5933248101c5ae0c54e542d5cdee2f7a"],"state_sha256":"ab54b5d34ab213fbeffeeb115ec0a3b231251778dd72d99d31cac122cd49375a"}