{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TKC4FNG4WWT35LZO67USCVCHKE","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":"4070609f4d20f3b37aea52e493e1380a5de9adf37b5979d9f8a38a4f73c09c9e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T22:48:42Z","title_canon_sha256":"9c364044168bd1a135341ce87966421bfd237b74b401e16b2da362f2c95978b2"},"schema_version":"1.0","source":{"id":"2606.25225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25225","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25225v1","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25225","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"TKC4FNG4WWT3","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_16","alias_value":"TKC4FNG4WWT35LZO","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_8","alias_value":"TKC4FNG4","created_at":"2026-06-25T00:18:21Z"}],"graph_snapshots":[{"event_id":"sha256:c1808ea8769d65c9577873ca832f55d949247eb06581479493e0af75ea2038cf","target":"graph","created_at":"2026-06-25T00:18:21Z","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/2606.25225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning from large-scale video data has emerged as a dominant paradigm for visual representation learning. Since audio and visual streams naturally co-occur in video data, extending this success to jointly learn from both modalities is a natural next step, yet it remains challenging. Existing audio-visual self-supervised methods rely on modality-specific encoders and complex combinations of contrastive or reconstruction objectives, limiting cross-modal synergy and scalability. Joint Embedding Predictive Architectures (JEPAs) offer a simple, modality-agnostic alternative, but h","authors_text":"Adrien Bardes, Matthew J. Muckley, Michael Rabbat, Nicolas Ballas, Revant Teotia, Sumit Chopra","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T22:48:42Z","title":"MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25225","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":"sha256:2b982aa0de776d6f17d1967a37692af7ab63f929ca50d210cf6dbb0b4c76424d","target":"record","created_at":"2026-06-25T00:18:21Z","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":"4070609f4d20f3b37aea52e493e1380a5de9adf37b5979d9f8a38a4f73c09c9e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-23T22:48:42Z","title_canon_sha256":"9c364044168bd1a135341ce87966421bfd237b74b401e16b2da362f2c95978b2"},"schema_version":"1.0","source":{"id":"2606.25225","kind":"arxiv","version":1}},"canonical_sha256":"9a85c2b4dcb5a7beaf2ef7e921544751068b1355f2bfc71ad2160917c4ac9b58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a85c2b4dcb5a7beaf2ef7e921544751068b1355f2bfc71ad2160917c4ac9b58","first_computed_at":"2026-06-25T00:18:21.430826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:18:21.430826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PT+D/yyPGcuJrZjKNPD9QmdUyhbvCFw2sgbfOzah0BwSBQZkK3T2hiOrvgEVaT/UFJ5TJShyyTbD07z5YxEbBQ==","signature_status":"signed_v1","signed_at":"2026-06-25T00:18:21.431240Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b982aa0de776d6f17d1967a37692af7ab63f929ca50d210cf6dbb0b4c76424d","sha256:c1808ea8769d65c9577873ca832f55d949247eb06581479493e0af75ea2038cf"],"state_sha256":"c69ecf695aa8ef30fb5f46c6662ca4fb46e52dbd6aebc1ee5f6e3da9a9314ae4"}